Mercurial > repos > jjohnson > mothur_toolsuite
changeset 2:e076d95dbdb5
Migrated tool version 1.19.0 from old tool shed archive to new tool shed repository
line wrap: on
line diff
--- a/mothur/README Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/README Tue Jun 07 17:05:08 2011 -0400 @@ -1,9 +1,10 @@ Provides galaxy tools for the Mothur metagenomics package - http://www.mothur.org/wiki/Main_Page -Install mothur v.1.16.0 on your galaxy system so galaxy can execute the mothur command +Install mothur v.1.19.0 on your galaxy system so galaxy can execute the mothur command + ( This version of wrappers is designed for Mothur version 1.19 - it may work on later versions ) http://www.mothur.org/wiki/Download_mothur http://www.mothur.org/wiki/Installation - ( This Galaxy iMothur wrapper will invoke Mothur in command line mode: http://www.mothur.org/wiki/Command_line_mode ) + ( This Galaxy Mothur wrapper will invoke Mothur in command line mode: http://www.mothur.org/wiki/Command_line_mode ) TreeVector is also packaged with this Mothur package to view phylogenetic trees: TreeVector is a utility to create and integrate phylogenetic trees as Scalable Vector Graphics (SVG) files. @@ -102,11 +103,13 @@ <datatype extension="shared" type="galaxy.datatypes.metagenomics:SharedRabund" display_in_upload="true"/> <datatype extension="relabund" type="galaxy.datatypes.metagenomics:RelAbund" display_in_upload="true"/> <datatype extension="names" type="galaxy.datatypes.metagenomics:Names" display_in_upload="true"/> + <datatype extension="design" type="galaxy.datatypes.metagenomics:Design" display_in_upload="true"/> <datatype extension="summary" type="galaxy.datatypes.metagenomics:Summary" display_in_upload="true"/> <datatype extension="groups" type="galaxy.datatypes.metagenomics:Group" display_in_upload="true"/> <datatype extension="oligos" type="galaxy.datatypes.metagenomics:Oligos" display_in_upload="true"/> <datatype extension="align" type="galaxy.datatypes.metagenomics:SequenceAlignment" display_in_upload="true"/> <datatype extension="accnos" type="galaxy.datatypes.metagenomics:AccNos" display_in_upload="true"/> + <datatype extension="map" type="galaxy.datatypes.metagenomics:SecondaryStructureMap" display_in_upload="true"/> <datatype extension="align.check" type="galaxy.datatypes.metagenomics:AlignCheck" display_in_upload="true"/> <datatype extension="align.report" type="galaxy.datatypes.metagenomics:AlignReport" display_in_upload="true"/> <datatype extension="filter" type="galaxy.datatypes.metagenomics:LaneMask" display_in_upload="true"/> @@ -114,7 +117,8 @@ <datatype extension="pair.dist" type="galaxy.datatypes.metagenomics:PairwiseDistanceMatrix" display_in_upload="true"/> <datatype extension="square.dist" type="galaxy.datatypes.metagenomics:SquareDistanceMatrix" display_in_upload="true"/> <datatype extension="lower.dist" type="galaxy.datatypes.metagenomics:LowerTriangleDistanceMatrix" display_in_upload="true"/> - <datatype extension="taxonomy" type="galaxy.datatypes.metagenomics:SequenceTaxonomy" display_in_upload="true"/> + <datatype extension="seq.taxonomy" type="galaxy.datatypes.metagenomics:SequenceTaxonomy" display_in_upload="true"/> + <datatype extension="rdp.taxonomy" type="galaxy.datatypes.metagenomics:RDPSequenceTaxonomy" display_in_upload="true"/> <datatype extension="cons.taxonomy" type="galaxy.datatypes.metagenomics:ConsensusTaxonomy" display_in_upload="true"/> <datatype extension="tax.summary" type="galaxy.datatypes.metagenomics:TaxonomySummary" display_in_upload="true"/> <datatype extension="freq" type="galaxy.datatypes.metagenomics:Frequency" display_in_upload="true"/> @@ -122,6 +126,7 @@ <datatype extension="filtered.quan" type="galaxy.datatypes.metagenomics:FilteredQuantile" display_in_upload="true"/> <datatype extension="masked.quan" type="galaxy.datatypes.metagenomics:MaskedQuantile" display_in_upload="true"/> <datatype extension="filtered.masked.quan" type="galaxy.datatypes.metagenomics:FilteredMaskedQuantile" display_in_upload="true"/> + <datatype extension="axes" type="galaxy.datatypes.metagenomics:Axes" display_in_upload="true"/> <datatype extension="tre" type="galaxy.datatypes.data:Newick" display_in_upload="true"/> <!-- End Mothur Datatypes --> @@ -137,6 +142,7 @@ <tool file="mothur/sub.sample.xml"/> <label text="Mothur Sequence Analysis" id="mothur_sequence_analysis"/> <tool file="mothur/sffinfo.xml"/> + <tool file="mothur/make.fastq.xml"/> <tool file="mothur/fastq.info.xml"/> <tool file="mothur/summary.seqs.xml"/> <tool file="mothur/reverse.seqs.xml"/> @@ -162,7 +168,7 @@ <tool file="mothur/nmds.xml"/> <tool file="mothur/corr.axes.xml"/> <tool file="mothur/classify.seqs.xml"/> - <label text="Mothur Sequence Chimera Detection" id="mothur_sequence_chimera"/> + <label text="Mothur Sequence Chimera Detection" id="mothur_sequence_chimera"/> <tool file="mothur/chimera.bellerophon.xml"/> <tool file="mothur/chimera.ccode.xml"/> <tool file="mothur/chimera.check.xml"/> @@ -176,15 +182,22 @@ <tool file="mothur/cluster.classic.xml"/> <tool file="mothur/cluster.split.xml"/> <tool file="mothur/metastats.xml"/> - <tool file="mothur/read.otu.xml"/> + <tool file="mothur/sens.spec.xml"/> <tool file="mothur/classify.otu.xml"/> <tool file="mothur/parse.list.xml"/> <tool file="mothur/get.otus.xml"/> <tool file="mothur/remove.otus.xml"/> <tool file="mothur/remove.rare.xml"/> + <tool file="mothur/get.otulist.xml"/> <tool file="mothur/get.oturep.xml"/> + <tool file="mothur/otu.hierarchy.xml"/> + <tool file="mothur/get.rabund.xml"/> + <tool file="mothur/get.sabund.xml"/> <tool file="mothur/get.relabund.xml"/> + <tool file="mothur/make.shared.xml"/> <tool file="mothur/get.group.xml"/> + <tool file="mothur/bin.seqs.xml"/> + <tool file="mothur/get.sharedseqs.xml"/> <label text="Mothur Single Sample Analysis" id="mothur_single_sample_analysis"/> <tool file="mothur/collect.single.xml"/> <tool file="mothur/rarefaction.single.xml"/> @@ -205,6 +218,10 @@ <tool file="mothur/unifrac.weighted.xml"/> <tool file="mothur/unifrac.unweighted.xml"/> <tool file="mothur/libshuff.xml"/> + <tool file="mothur/amova.xml"/> + <tool file="mothur/homova.xml"/> + <tool file="mothur/mantel.xml"/> + <tool file="mothur/anosim.xml"/> <label text="Mothur Phylotype Analysis" id="mothur_phylotype_analysis"/> <tool file="mothur/get.lineage.xml"/> <tool file="mothur/remove.lineage.xml"/> @@ -212,7 +229,6 @@ <tool file="mothur/phylo.diversity.xml"/> <tool file="mothur/clearcut.xml"/> <tool file="mothur/indicator.xml"/> - <tool file="mothur/bootstrap.shared.xml"/> <tool file="mothur/TreeVector.xml"/> </section> <!-- metagenomics_mothur -->
--- a/mothur/lib/galaxy/datatypes/metagenomics.py Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/lib/galaxy/datatypes/metagenomics.py Tue Jun 07 17:05:08 2011 -0400 @@ -712,12 +712,91 @@ return False class SequenceTaxonomy(Tabular): - file_ext = 'taxonomy' + file_ext = 'seq.taxonomy' + """ + A table with 2 columns: + - SequenceName + - Taxonomy (semicolon-separated taxonomy in descending order) + Example: + X56533.1 Eukaryota;Alveolata;Ciliophora;Intramacronucleata;Oligohymenophorea;Hymenostomatida;Tetrahymenina;Glaucomidae;Glaucoma; + X97975.1 Eukaryota;Parabasalidea;Trichomonada;Trichomonadida;unclassified_Trichomonadida; + AF052717.1 Eukaryota;Parabasalidea; + """ def __init__(self, **kwd): - """A list of names""" Tabular.__init__( self, **kwd ) self.column_names = ['name','taxonomy'] + def sniff( self, filename ): + """ + Determines whether the file is a SequenceTaxonomy + """ + try: + pat = '^([^ \t\n\r\f\v;]+([(]\d+[)])?[;])+$' + fh = open( filename ) + count = 0 + while True: + line = fh.readline() + if not line: + break #EOF + line = line.strip() + if line: + fields = line.split('\t') + if len(fields) != 2: + return False + if not re.match(pat,fields[1]): + return False + count += 1 + if count > 10: + break + if count > 0: + return True + except: + pass + finally: + fh.close() + return False + +class RDPSequenceTaxonomy(SequenceTaxonomy): + file_ext = 'rdp.taxonomy' + """ + A table with 2 columns: + - SequenceName + - Taxonomy (semicolon-separated taxonomy in descending order, RDP requires exactly 6 levels deep) + Example: + AB001518.1 Bacteria;Bacteroidetes;Sphingobacteria;Sphingobacteriales;unclassified_Sphingobacteriales; + AB001724.1 Bacteria;Cyanobacteria;Cyanobacteria;Family_II;GpIIa; + AB001774.1 Bacteria;Chlamydiae;Chlamydiae;Chlamydiales;Chlamydiaceae;Chlamydophila; + """ + def sniff( self, filename ): + """ + Determines whether the file is a SequenceTaxonomy + """ + try: + pat = '^([^ \t\n\r\f\v;]+([(]\d+[)])?[;]){6}$' + fh = open( filename ) + count = 0 + while True: + line = fh.readline() + if not line: + break #EOF + line = line.strip() + if line: + fields = line.split('\t') + if len(fields) != 2: + return False + if not re.match(pat,fields[1]): + return False + count += 1 + if count > 10: + break + if count > 0: + return True + except: + pass + finally: + fh.close() + return False + class ConsensusTaxonomy(Tabular): file_ext = 'cons.taxonomy' def __init__(self, **kwd): @@ -845,9 +924,9 @@ ## Qiime Classes -class MetadataMapping(Tabular): +class QiimeMetadataMapping(Tabular): MetadataElement( name="column_names", default=[], desc="Column Names", readonly=False, visible=True, no_value=[] ) - file_ext = 'mapping' + file_ext = 'qiimemapping' def __init__(self, **kwd): """ @@ -887,6 +966,144 @@ Tabular.set_meta(self, dataset, overwrite, skip, max_data_lines) self.set_column_names(dataset) +class QiimeOTU(Tabular): + """ + Associates OTUs with sequence IDs + Example: + 0 FLP3FBN01C2MYD FLP3FBN01B2ALM + 1 FLP3FBN01DF6NE FLP3FBN01CKW1J FLP3FBN01CHVM4 + 2 FLP3FBN01AXQ2Z + """ + file_ext = 'qiimeotu' + +class QiimeOTUTable(Tabular): + """ + #Full OTU Counts + #OTU ID PC.354 PC.355 PC.356 Consensus Lineage + 0 0 1 0 Root;Bacteria;Firmicutes;"Clostridia";Clostridiales + 1 1 3 1 Root;Bacteria + 2 0 2 2 Root;Bacteria;Bacteroidetes + """ + MetadataElement( name="column_names", default=[], desc="Column Names", readonly=False, visible=True, no_value=[] ) + file_ext = 'qiimeotutable' + def init_meta( self, dataset, copy_from=None ): + tabular.Tabular.init_meta( self, dataset, copy_from=copy_from ) + def set_meta( self, dataset, overwrite = True, skip = None, **kwd ): + self.set_column_names(dataset) + def set_column_names(self, dataset): + if dataset.has_data(): + dataset_fh = open( dataset.file_name ) + line = dataset_fh.readline() + line = dataset_fh.readline() + if line.startswith('#OTU ID'): + dataset.metadata.column_names = line.strip().split('\t'); + dataset_fh.close() + dataset.metadata.comment_lines = 2 + +class QiimeDistanceMatrix(Tabular): + """ + PC.354 PC.355 PC.356 + PC.354 0.0 3.177 1.955 + PC.355 3.177 0.0 3.444 + PC.356 1.955 3.444 0.0 + """ + file_ext = 'qiimedistmat' + def init_meta( self, dataset, copy_from=None ): + tabular.Tabular.init_meta( self, dataset, copy_from=copy_from ) + def set_meta( self, dataset, overwrite = True, skip = None, **kwd ): + self.set_column_names(dataset) + def set_column_names(self, dataset): + if dataset.has_data(): + dataset_fh = open( dataset.file_name ) + line = dataset_fh.readline() + # first line contains the names + dataset.metadata.column_names = line.strip().split('\t'); + dataset_fh.close() + dataset.metadata.comment_lines = 1 + +class QiimePCA(Tabular): + """ + Principal Coordinate Analysis Data + The principal coordinate (PC) axes (columns) for each sample (rows). + Pairs of PCs can then be graphed to view the relationships between samples. + The bottom of the output file contains the eigenvalues and % variation explained for each PC. + Example: + pc vector number 1 2 3 + PC.354 -0.309063936588 0.0398252112257 0.0744672231759 + PC.355 -0.106593922619 0.141125998277 0.0780204374172 + PC.356 -0.219869362955 0.00917241121781 0.0357281314115 + + + eigvals 0.480220500471 0.163567082874 0.125594470811 + % variation explained 51.6955484555 17.6079322939 + """ + file_ext = 'qiimepca' + +class QiimeParams(Tabular): + """ +###pick_otus_through_otu_table.py parameters### + +# OTU picker parameters +pick_otus:otu_picking_method uclust +pick_otus:clustering_algorithm furthest + +# Representative set picker parameters +pick_rep_set:rep_set_picking_method first +pick_rep_set:sort_by otu + """ + file_ext = 'qiimeparams' + +class QiimePrefs(data.Text): + """ + A text file, containing coloring preferences to be used by make_distance_histograms.py, make_2d_plots.py and make_3d_plots.py. + Example: +{ +'background_color':'black', + +'sample_coloring': + { + 'Treatment': + { + 'column':'Treatment', + 'colors':(('red',(0,100,100)),('blue',(240,100,100))) + }, + 'DOB': + { + 'column':'DOB', + 'colors':(('red',(0,100,100)),('blue',(240,100,100))) + } + }, +'MONTE_CARLO_GROUP_DISTANCES': + { + 'Treatment': 10, + 'DOB': 10 + } +} + """ + file_ext = 'qiimeprefs' + +class QiimeTaxaSummary(Tabular): + """ + Taxon PC.354 PC.355 PC.356 + Root;Bacteria;Actinobacteria 0.0 0.177 0.955 + Root;Bacteria;Firmicutes 0.177 0.0 0.444 + Root;Bacteria;Proteobacteria 0.955 0.444 0.0 + """ + MetadataElement( name="column_names", default=[], desc="Column Names", readonly=False, visible=True, no_value=[] ) + file_ext = 'qiimetaxsummary' + + def set_column_names(self, dataset): + if dataset.has_data(): + dataset_fh = open( dataset.file_name ) + line = dataset_fh.readline() + if line.startswith('Taxon'): + dataset.metadata.column_names = line.strip().split('\t'); + dataset_fh.close() + + def set_meta( self, dataset, overwrite = True, skip = None, max_data_lines = None, **kwd ): + Tabular.set_meta(self, dataset, overwrite, skip, max_data_lines) + self.set_column_names(dataset) + if __name__ == '__main__': import doctest, sys doctest.testmod(sys.modules[__name__])
--- a/mothur/suite_config.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/suite_config.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,240 +1,270 @@ -<suite id="Mothur_toolsuite" name="Mothur Metagenomics" version="1.16.0"> +<suite id="Mothur_toolsuite" name="Mothur Metagenomics" version="1.19.0"> <description>Mothur metagenomics commands as Galaxy tools</description> - <tool id="mothur_align_check" name="Align.check" version="1.16.0"> + <tool id="mothur_align_check" name="Align.check" version="1.19.0"> <description>Calculate the number of potentially misaligned bases</description> </tool> - <tool id="mothur_align_seqs" name="Align.seqs" version="1.16.0"> + <tool id="mothur_align_seqs" name="Align.seqs" version="1.19.0"> <description>Align sequences to a template alignment</description> </tool> - <tool id="mothur_bin_seqs" name="Bin.seqs" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_amova" name="Amova" version="1.19.0"> + <description>Analysis of molecular variance</description> + </tool> + <tool id="mothur_anosim" name="Anosim" version="1.19.0"> + <description>Non-parametric multivariate analysis of changes in community structure</description> + </tool> + <tool id="mothur_bin_seqs" name="Bin.seqs" version="1.19.0"> <description>Order Sequences by OTU</description> </tool> - <tool id="mothur_bootstrap_shared" name="Bootstrap.shared" version="1.16.0" force_history_refresh="True"> - <description>Generate a newick trees for dissimilarity among groups</description> - </tool> - <tool id="mothur_chimera_bellerophon" name="Chimera.bellerophon" version="1.16.0"> + <tool id="mothur_chimera_bellerophon" name="Chimera.bellerophon" version="1.19.0"> <description>Find putative chimeras using bellerophon</description> </tool> - <tool id="mothur_chimera_ccode" name="Chimera.ccode" version="1.16.0"> + <tool id="mothur_chimera_ccode" name="Chimera.ccode" version="1.19.0"> <description>Find putative chimeras using ccode</description> </tool> - <tool id="mothur_chimera_check" name="Chimera.check" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_chimera_check" name="Chimera.check" version="1.19.0"> <description>Find putative chimeras using chimeraCheck</description> </tool> - <tool id="mothur_chimera_pintail" name="Chimera.pintail" version="1.16.0"> + <tool id="mothur_chimera_pintail" name="Chimera.pintail" version="1.19.0"> <description>Find putative chimeras using pintail</description> </tool> - <tool id="mothur_chimera_slayer" name="Chimera.slayer" version="1.16.0"> + <tool id="mothur_chimera_slayer" name="Chimera.slayer" version="1.19.0"> <description>Find putative chimeras using slayer</description> </tool> - <tool id="mothur_chop_seqs" name="Chop.seqs" version="1.16.0"> + <tool id="mothur_chop_seqs" name="Chop.seqs" version="1.19.0"> <description>Trim sequences to a specified length</description> </tool> - <tool id="mothur_classify_otu" name="Classify.otu" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_classify_otu" name="Classify.otu" version="1.19.0"> <description>Assign sequences to taxonomy</description> </tool> - <tool id="mothur_classify_seqs" name="Classify.seqs" version="1.16.0"> + <tool id="mothur_classify_seqs" name="Classify.seqs" version="1.19.0"> <description>Assign sequences to taxonomy</description> </tool> - <tool id="mothur_clearcut" name="Clearcut" version="1.16.0"> + <tool id="mothur_clearcut" name="Clearcut" version="1.19.0"> <description>Generate a tree using relaxed neighbor joining</description> </tool> - <tool id="mothur_cluster_classic" name="Cluster.classic" version="1.16.0"> + <tool id="mothur_cluster_classic" name="Cluster.classic" version="1.19.0"> <description>Assign sequences to OTUs (Dotur implementation)</description> </tool> - <tool id="mothur_cluster_fragments" name="Cluster.fragments" version="1.16.0"> + <tool id="mothur_cluster_fragments" name="Cluster.fragments" version="1.19.0"> <description> Group sequences that are part of a larger sequence</description> </tool> - <tool id="mothur_cluster_split" name="Cluster.split" version="1.16.0"> + <tool id="mothur_cluster_split" name="Cluster.split" version="1.19.0"> <description>Assign sequences to OTUs (Operational Taxonomic Unit) splits large matrices</description> </tool> - <tool id="mothur_cluster" name="Cluster" version="1.16.0"> + <tool id="mothur_cluster" name="Cluster" version="1.19.0"> <description>Assign sequences to OTUs (Operational Taxonomic Unit)</description> </tool> - <tool id="mothur_collect_shared" name="Collect.shared" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_collect_shared" name="Collect.shared" version="1.19.0"> <description>Generate collector's curves for calculators on OTUs</description> </tool> - <tool id="mothur_collect_single" name="Collect.single" version="1.16.0" force_history_refresh="True"> - <description>Summary of calculator values for OTUs</description> + <tool id="mothur_collect_single" name="Collect.single" version="1.19.0"> + <description>Generate collector's curves for OTUs</description> </tool> - <tool id="mothur_consensus_seqs" name="Consensus.seqs" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_consensus_seqs" name="Consensus.seqs" version="1.19.0"> <description>Find a consensus sequence for each OTU or phylotype</description> </tool> - <tool id="mothur_corr_axes" name="Corr.axes" version="1.16.0"> + <tool id="mothur_corr_axes" name="Corr.axes" version="1.19.0"> <description>correlation of data to axes</description> </tool> - <tool id="mothur_degap_seqs" name="Degap.seqs" version="1.16.0"> + <tool id="mothur_degap_seqs" name="Degap.seqs" version="1.19.0"> <description>Remove gap characters from sequences</description> </tool> - <tool id="mothur_deunique_seqs" name="Deunique.seqs" version="1.16.0"> + <tool id="mothur_deunique_seqs" name="Deunique.seqs" version="1.19.0"> <description>Return all sequences</description> </tool> - <tool id="mothur_dist_seqs" name="Dist.seqs" version="1.16.0"> + <tool id="mothur_dist_seqs" name="Dist.seqs" version="1.19.0"> <description>calculate uncorrected pairwise distances between aligned sequences</description> </tool> - <tool id="mothur_dist_shared" name="Dist.shared" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_dist_shared" name="Dist.shared" version="1.19.0"> <description>Generate a phylip-formatted dissimilarity distance matrix among multiple groups</description> </tool> - <tool id="mothur_fastq_info" name="Fastq.info" version="1.16.0"> + <tool id="mothur_fastq_info" name="Fastq.info" version="1.19.0"> <description>Convert fastq to fasta and quality</description> </tool> - <tool id="mothur_filter_seqs" name="Filter.seqs" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_filter_seqs" name="Filter.seqs" version="1.19.0"> <description>removes columns from alignments</description> </tool> - <tool id="mothur_get_groups" name="Get.groups" version="1.16.0"> + <tool id="mothur_get_groups" name="Get.groups" version="1.19.0"> <description>Select groups</description> </tool> - <tool id="mothur_get_group" name="Get.group" version="1.16.0"> + <tool id="mothur_get_group" name="Get.group" version="1.19.0"> <description>group names from shared or from list and group</description> </tool> - <tool id="mothur_get_lineage" name="Get.lineage" version="1.16.0"> + <tool id="mothur_get_lineage" name="Get.lineage" version="1.19.0"> <description>Picks by taxon</description> </tool> - <tool id="mothur_get_oturep" name="Get.oturep" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_get_otulist" name="Get.otulist" version="1.19.0"> + <description>Get otus for each distance in a otu list</description> + </tool> + <tool id="mothur_get_oturep" name="Get.oturep" version="1.19.0"> <description>Generate a fasta with a representative sequence for each OTU</description> </tool> - <tool id="mothur_get_otus" name="Get.otus" version="1.16.0"> + <tool id="mothur_get_otus" name="Get.otus" version="1.19.0"> <description>Get otus containing sequences from specified groups</description> </tool> - <tool id="mothur_get_relabund" name="Get.relabund" version="1.16.0"> + <tool id="mothur_get_rabund" name="Get.rabund" version="1.19.0"> + <description>Get rabund from a otu list or sabund</description> + </tool> + <tool id="mothur_get_relabund" name="Get.relabund" version="1.19.0"> <description>Calculate the relative abundance of each otu</description> </tool> - <tool id="mothur_get_seqs" name="Get.seqs" version="1.16.0"> + <tool id="mothur_get_sabund" name="Get.sabund" version="1.19.0"> + <description>Get sabund from a otu list or rabund</description> + </tool> + <tool id="mothur_get_seqs" name="Get.seqs" version="1.19.0"> <description>Picks sequences by name</description> </tool> - <tool id="mothur_hcluster" name="Hcluster" version="1.16.0"> + <tool id="mothur_get_sharedseqs" name="Get.sharedseqs" version="1.19.0"> + <description>Get shared sequences at each distance from list and group</description> + </tool> + <tool id="mothur_hcluster" name="Hcluster" version="1.19.0"> <description>Assign sequences to OTUs (Operational Taxonomic Unit)</description> </tool> - <tool id="mothur_heatmap_bin" name="Heatmap.bin" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_heatmap_bin" name="Heatmap.bin" version="1.19.0"> <description>Generate a heatmap for OTUs</description> </tool> - <tool id="mothur_heatmap_sim" name="Heatmap.sim" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_heatmap_sim" name="Heatmap.sim" version="1.19.0"> <description>Generate a heatmap for pariwise similarity</description> </tool> - <tool id="mothur_indicator" name="Indicator" version="1.16.0"> + <tool id="mothur_homova" name="Homova" version="1.19.0"> + <description>Homogeneity of molecular variance</description> + </tool> + <tool id="mothur_indicator" name="Indicator" version="1.19.0"> <description>Identify indicator "species" for nodes on a tree</description> </tool> - <tool id="mothur_libshuff" name="Libshuff" version="1.16.0"> + <tool id="mothur_libshuff" name="Libshuff" version="1.19.0"> <description>Cramer-von Mises tests communities for the same structure</description> </tool> - <tool id="mothur_list_seqs" name="List.seqs" version="1.16.0"> - <description>Lists the names of the sequences</description> + <tool id="mothur_list_seqs" name="List.seqs" version="1.19.0"> + <description>Lists the names (accnos) of the sequences</description> </tool> - <tool id="mothur_make_design" name="Make Design" version="1.16.0" > + <tool id="mothur_make_design" name="Make Design" version="1.19.0" > <description>Assign groups to Sets</description> </tool> - <tool id="mothur_make_files" name="Make.group" version="1.16.0"> + <tool id="mothur_make_fastq" name="Make.fastq" version="1.19.0"> + <description>Convert fasta and quality to fastq</description> + </tool> + <tool id="mothur_make_files" name="Make.group" version="1.19.0"> <description>Make a group file</description> </tool> - <tool id="mothur_merge_files" name="Merge.files" version="1.16.0"> + <tool id="mothur_make_shared" name="Make.shared" version="1.19.0"> + <description>Make a shared file from a list and a group</description> + </tool> + <tool id="mothur_mantel" name="Mantel" version="1.19.0"> + <description>Mantel correlation coefficient between two matrices.</description> + </tool> + <tool id="mothur_merge_files" name="Merge.files" version="1.19.0"> <description>Merge data</description> </tool> - <tool id="mothur_merge_groups" name="Merge.groups" version="1.16.0" > + <tool id="mothur_merge_groups" name="Merge.groups" version="1.19.0" > <description>Merge groups in a shared file</description> </tool> - <tool id="mothur_metastats" name="Metastats" version="1.16.0"> + <tool id="mothur_metastats" name="Metastats" version="1.19.0" > <description>generate principle components plot data</description> </tool> - <tool id="mothur_nmds" name="Nmds" version="1.16.0"> + <tool id="mothur_nmds" name="Nmds" version="1.19.0"> <description>generate non-metric multidimensional scaling data</description> </tool> - <tool id="mothur_normalize_shared" name="Normalize.shared" version="1.16.0"> + <tool id="mothur_normalize_shared" name="Normalize.shared" version="1.19.0"> <description>Normalize the number of sequences per group to a specified level</description> </tool> - <tool id="mothur_pairwise_seqs" name="Pairwise.seqs" version="1.16.0"> + <tool id="mothur_otu_hierarchy" name="Otu.hierarchy" version="1.19.0"> + <description>Relate OTUs at different distances</description> + </tool> + <tool id="mothur_pairwise_seqs" name="Pairwise.seqs" version="1.19.0"> <description>calculate uncorrected pairwise distances between sequences</description> </tool> - <tool id="mothur_parse_list" name="Parse.list" version="1.16.0" force_history_refresh="True"> - <description>Order Sequences by OTU</description> + <tool id="mothur_parse_list" name="Parse.list" version="1.19.0"> + <description>Generate a List file for each group</description> </tool> - <tool id="mothur_parsimony" name="Parsimony" version="1.16.0"> + <tool id="mothur_parsimony" name="Parsimony" version="1.19.0"> <description>Describes whether two or more communities have the same structure</description> </tool> - <tool id="mothur_pca" name="Pca" version="1.16.0"> - <description>generate principle components plot data</description> + <tool id="mothur_pca" name="Pca" version="1.19.0"> + <description>Principal Coordinate Analysis for a shared file</description> </tool> - <tool id="mothur_pcoa" name="Pcoa" version="1.16.0" > - <description>Principal Coordinate Analysis</description> + <tool id="mothur_pcoa" name="Pcoa" version="1.19.0" > + <description>Principal Coordinate Analysis for a distance matrix</description> </tool> - <tool id="mothur_phylo_diversity" name="Phylo.diversity" version="1.16.0"> - <description>Alpha Diversity calculate unique branch length</description> + <tool id="mothur_phylo_diversity" name="Phylo.diversity" version="1.19.0"> + <description>Alpha Diversity calculates unique branch length</description> </tool> - <tool id="mothur_phylotype" name="Phylotype" version="1.16.0"> + <tool id="mothur_phylotype" name="Phylotype" version="1.19.0"> <description>Assign sequences to OTUs based on taxonomy</description> </tool> - <tool id="mothur_pre_cluster" name="Pre.cluster" version="1.16.0"> + <tool id="mothur_pre_cluster" name="Pre.cluster" version="1.19.0"> <description>Remove sequences due to pyrosequencing errors</description> </tool> - <tool id="mothur_rarefaction_shared" name="Rarefaction.shared" version="1.16.0"> + <tool id="mothur_rarefaction_shared" name="Rarefaction.shared" version="1.19.0"> <description>Generate inter-sample rarefaction curves for OTUs</description> </tool> - <tool id="mothur_rarefaction_single" name="Rarefaction.single" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_rarefaction_single" name="Rarefaction.single" version="1.19.0"> <description>Generate intra-sample rarefaction curves for OTUs</description> </tool> - <tool id="mothur_read_otu" name="Read.otu" version="1.16.0" force_history_refresh="True"> - <description>Read OTU list and group to create a shared file</description> + <tool id="mothur_remove_groups" name="Remove.groups" version="1.19.0"> + <description>Remove groups from groups,fasta,names,list,taxonomy</description> </tool> - <tool id="mothur_remove_groups" name="Remove.groups" version="1.16.0"> - <description>Remove groups</description> - </tool> - <tool id="mothur_remove_lineage" name="Remove.lineage" version="1.16.0"> + <tool id="mothur_remove_lineage" name="Remove.lineage" version="1.19.0"> <description>Picks by taxon</description> </tool> - <tool id="mothur_remove_otus" name="Remove.otus" version="1.16.0"> + <tool id="mothur_remove_otus" name="Remove.otus" version="1.19.0"> <description>Remove otus containing sequences from specified groups</description> </tool> - <tool id="mothur_remove_rare" name="Remove.rare" version="1.16.0"> + <tool id="mothur_remove_rare" name="Remove.rare" version="1.19.0"> <description>Remove rare OTUs</description> </tool> - <tool id="mothur_remove_seqs" name="Remove.seqs" version="1.16.0"> + <tool id="mothur_remove_seqs" name="Remove.seqs" version="1.19.0"> <description>Remove sequences by name</description> </tool> - <tool id="mothur_reverse_seqs" name="Reverse.seqs" version="1.16.0"> + <tool id="mothur_reverse_seqs" name="Reverse.seqs" version="1.19.0"> <description>Reverse complement the sequences</description> </tool> - <tool id="mothur_screen_seqs" name="Screen.seqs" version="1.16.0"> + <tool id="mothur_screen_seqs" name="Screen.seqs" version="1.19.0"> <description>Screen sequences</description> </tool> - <tool id="mothur_sffinfo" name="Sffinfo" version="1.16.0"> + <tool id="mothur_sens_spec" name="Sens.spec" version="1.19.0" > + <description>Determine the quality of OTU assignment</description> + </tool> + <tool id="mothur_sffinfo" name="Sffinfo" version="1.19.0"> <description>Summarize the quality of sequences</description> </tool> - <tool id="mothur_split_abund" name="Split.abund" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_split_abund" name="Split.abund" version="1.19.0"> <description>Separate sequences into rare and abundant groups</description> </tool> - <tool id="mothur_split_groups" name="Split.groups" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_split_groups" name="Split.groups" version="1.19.0"> <description>Generates a fasta file for each group</description> </tool> - <tool id="mothur_sub_sample" name="Sub.sample" version="1.16.0"> + <tool id="mothur_sub_sample" name="Sub.sample" version="1.19.0"> <description>Create a sub sample</description> </tool> - <tool id="mothur_summary_seqs" name="Summary.seqs" version="1.16.0"> + <tool id="mothur_summary_seqs" name="Summary.seqs" version="1.19.0"> <description>Summarize the quality of sequences</description> </tool> - <tool id="mothur_summary_shared" name="Summary.shared" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_summary_shared" name="Summary.shared" version="1.19.0"> <description>Summary of calculator values for OTUs</description> </tool> - <tool id="mothur_summary_single" name="Summary.single" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_summary_single" name="Summary.single" version="1.19.0"> <description>Summary of calculator values for OTUs</description> </tool> - <tool id="mothur_tree_shared" name="Tree.shared" version="1.16.0" force_history_refresh="True"> + <tool id="mothur_tree_shared" name="Tree.shared" version="1.19.0"> <description>Generate a newick tree for dissimilarity among groups</description> </tool> <tool id="tree_vector" name="TreeVector" version="1.0"> <description>Draw a Phylogenic Tree</description> </tool> - <tool id="mothur_trim_seqs" name="Trim.seqs" version="1.16.0"> + <tool id="mothur_trim_seqs" name="Trim.seqs" version="1.19.0"> <description>Trim sequences - primers, barcodes, quality</description> </tool> - <tool id="mothur_unifrac_unweighted" name="unifrac.unweighted" version="1.16.0"> + <tool id="mothur_unifrac_unweighted" name="unifrac.unweighted" version="1.19.0"> <description>Describes whether two or more communities have the same structure</description> </tool> - <tool id="mothur_unifrac_weighted" name="unifrac.weighted" version="1.16.0"> + <tool id="mothur_unifrac_weighted" name="unifrac.weighted" version="1.19.0"> <description>Describes whether two or more communities have the same structure</description> </tool> - <tool id="mothur_unique_seqs" name="Unique.seqs" version="1.16.0"> + <tool id="mothur_unique_seqs" name="Unique.seqs" version="1.19.0"> <description>Return unique sequences</description> </tool> - <tool id="mothur_venn" name="Venn" version="1.16.0" force_history_refresh="True"> - <description>Generate Venn diagrams gor groups </description> + <tool id="mothur_venn" name="Venn" version="1.19.0"> + <description>Generate Venn diagrams for groups </description> </tool> </suite>
--- a/mothur/tool-data/mothur_calculators.loc Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tool-data/mothur_calculators.loc Tue Jun 07 17:05:08 2011 -0400 @@ -26,16 +26,20 @@ chao single sing Community richness the Chao1 estimator jack single sing Community richness the jackknife estimator sobs single sing Community richness the observed richness +##Community evenness +simpsoneven single sing Community evenness a Simpson index-based measure of evenness +shannoneven single sing Community evenness a Shannon index-based measure of evenness +heip single sing Community evenness Heip's metric of community evenness +smithwilson single sing Community evenness Smith and Wilson's metric of community evenness ##Community diversity bergerparker single xxxx Community diversity the Berger-Parker index -coverage single sing Community diversity the sampling coverage coverage +coverage single sing Community diversity the sampling coverage +goodscoverage single sing Community diversity the Good's estimate of sampling coverage invsimpson single sing Community diversity the Simpson index npshannon single sing Community diversity the non-parametric Shannon index qstat single xxxx Community diversity the Q statistic shannon single sing Community diversity the Shannon index simpson single sing Community diversity the Simpson index -simpsoneven single sing Community diversity the Simpson index -smithwilson single sing Smith and Wilson's metric of community evenness ##Estimates of number of additional OTUs observed with extra sampling boneh single xxxx Estimator Boneh's estimator efron single xxxx Estimator Efron's estimator @@ -55,6 +59,7 @@ jest shared shar Community Membership Similarity the Jaccard similarity coefficient based on the Chao1 estimated richnesses kulczynski shared xxxx Community Membership Similarity the Kulczynski similarity coefficient kulczynskicody shared xxxx Community Membership Similarity the Kulczynski-Cody similarity coefficient +kstest shared xxxx Kolmogorov-Smirnov test lennon shared xxxx Community Membership Similarity the Lennon similarity coefficient ochiai shared xxxx Community Membership Similarity the Ochiai similarity coefficient sorclass shared shar Community Membership Similarity the Sorenson similarity coefficient based on the observed richness
--- a/mothur/tools/mothur/align.check.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/align.check.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_align_check" name="Align.check" version="1.16.0"> +<tool id="mothur_align_check" name="Align.check" version="1.19.0"> <description>Calculate the number of potentially misaligned bases</description> <command interpreter="python"> mothur_wrapper.py @@ -6,16 +6,27 @@ --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.align\.check$:'$out_file --outputdir='$logfile.extra_files_path' --fasta=$fasta - --map=$map + --map=$ss.map </command> <inputs> - <param name="fasta" type="data" format="align" label="fasta - Sequences"/> - <param name="map" type="select" label="map - Select a secondary structure map" help="Contact Galaxy team for additions"> - <options from_file="mothur_map.loc"> - <column name="name" index="0" /> - <column name="value" index="1" /> - </options> - </param> + <param name="fasta" type="data" format="align" label="fasta - Aligned Sequences"/> + <conditional name="ss"> + <param name="source" label="Select Secondary Structure Map from" type="select"> + <option value="cached">Cached Secondary Structure Maps</option> + <option value="history">Your History</option> + </param> + <when value="cached"> + <param name="map" type="select" label="map - Select a secondary structure map" help="Contact Galaxy team for additions"> + <options from_file="mothur_map.loc"> + <column name="name" index="0" /> + <column name="value" index="1" /> + </options> + </param> + </when> + <when value="history"> + <param name="map" format="map" type="data" label="Secondary Structure Map" /> + </when> + </conditional> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -37,8 +48,9 @@ **Command Documenation** -The align.check_ command allows you to calculate the number of potentially misaligned bases in a 16S rRNA gene sequence alignment. +The align.check_ command allows you to calculate the number of potentially misaligned bases in a 16S rRNA gene sequence alignment using a secondary_structure_map_. If you are familiar with the editor window in ARB, this is the same as counting the number of ~, #, -, and = signs. +.. _secondary_structure_map: http://www.mothur.org/wiki/Secondary_structure_map .. _align.check: http://www.mothur.org/wiki/Align.check </help>
--- a/mothur/tools/mothur/align.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/align.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,12 +1,12 @@ -<tool id="mothur_align_seqs" name="Align.seqs" version="1.16.0"> +<tool id="mothur_align_seqs" name="Align.seqs" version="1.19.0"> <description>Align sequences to a template alignment</description> <command interpreter="python"> mothur_wrapper.py --cmd='align.seqs' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.align$:'$out_file,'^\S+\.align\.report$:'$report --outputdir='$logfile.extra_files_path' - --candidate=$candidate - --template=$alignment.template + --fasta=$candidate + --reference=$alignment.template #if $search.method == 'kmer': --ksize=$search.ksize #else: @@ -26,22 +26,22 @@ --processors=2 </command> <inputs> - <param name="candidate" type="data" format="fasta" label="candidate - Candiate Sequences"/> + <param name="candidate" type="data" format="fasta" label="fasta - Candiate Sequences"/> <conditional name="alignment"> - <param name="source" type="select" label="Select Template from" help=""> - <option value="hist">History</option> + <param name="source" type="select" label="Select Reference Template from" help=""> <option value="ref">Cached Reference</option> + <option value="history">Your History</option> </param> <when value="ref"> - <param name="template" type="select" label="template - Select an alignment database " help=""> + <param name="template" type="select" label="reference - Select an alignment database " help=""> <options from_file="mothur_aligndb.loc"> <column name="name" index="0" /> <column name="value" index="1" /> </options> </param> </when> - <when value="hist"> - <param name="template" type="data" format="fasta" label="template - Template to align with" help=""/> + <when value="history"> + <param name="template" type="data" format="fasta" label="reference - Reference to align with" help=""/> </when> </conditional> <conditional name="search"> @@ -111,8 +111,16 @@ **Command Documenation** -The align.seqs_ command aligns a user-supplied fasta-formatted candidate sequence file to a user-supplied fasta-formatted template alignment. +The align.seqs_ command aligns a user-supplied fasta-formatted candidate sequence file to a user-supplied fasta-formatted template_alignment_. +The general approach is to + i) find the closest template for each candidate using kmer searching, blastn, or suffix tree searching; + ii) to make a pairwise alignment between the candidate and de-gapped template sequences using the Needleman-Wunsch, Gotoh, or blastn algorithms; and + iii) to re-insert gaps to the candidate and template pairwise alignments using the NAST algorithm so that the candidate sequence alignment is compatible with the original template alignment. + +In general the alignment is very fast - we are able to align over 186,000 full-length sequences to the SILVA alignment in less than 3 hrs with a quality as good as the SINA aligner. Furthermore, this rate can be accelerated using multiple processors. While the aligner doesn't explicitly take into account the secondary structure of the 16S rRNA gene, if the template database is based on the secondary structure, then the resulting alignment will at least be implicitly based on the secondary structure. + +.. _template_alignment: http://www.mothur.org/wiki/Alignment_database .. _align.seqs: http://www.mothur.org/wiki/Align.seqs
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/amova.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,63 @@ +<tool id="mothur_amova" name="Amova" version="1.19.0"> + <description>Analysis of molecular variance</description> + <command interpreter="python"> + mothur_wrapper.py + --cmd='amova' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.amova$:'$amova + --outputdir='$logfile.extra_files_path' + --phylip=$dist + --design=$design + #if int($iters.__str__) > 0: + --iters=$iters + #end if + #if float($alpha.__str__) > 0.0: + --alpha=$alpha + #end if + </command> + <inputs> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="design" type="data" format="tabular" label="design - assign groups to new grouping" + help="design has 2 TAB-separated columns: group and grouping (Tool: Make_Design) "/> + <param name="alpha" type="float" optional="true" value="0.05" label="alpha - acceptable stopping precision (default 0.05)"/> + <param name="iters" type="integer" value="1000" label="iters - Number of random configuration to try (default 1000)"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="tabular" name="amova" label="${tool.name} on ${on_string}: amova"/> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The amova_ command calculates the analysis of molecular variance from a phylip_distance_matrix_, a nonparametric analog of traditional analysis of variance. This method is widely used in population genetics to test the hypothesis that genetic diversity within two populations is not significantly different from that which would result from pooling the two populations. + +A design file partitions a list of names into groups. It is a tab-delimited file with 2 columns: name and group, e.g. : + ======= ======= + duck bird + cow mammal + pig mammal + goose bird + cobra reptile + ======= ======= + +The Make_Design tool can construct a design file from a Mothur dataset that contains group names. + + +.. _phylip_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _amova: http://www.mothur.org/wiki/Amova + + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/anosim.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,63 @@ +<tool id="mothur_anosim" name="Anosim" version="1.19.0"> + <description>Non-parametric multivariate analysis of changes in community structure</description> + <command interpreter="python"> + mothur_wrapper.py + --cmd='anosim' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.anosim$:'$anosim + --outputdir='$logfile.extra_files_path' + --phylip=$dist + --design=$design + #if int($iters.__str__) > 0: + --iters=$iters + #end if + #if float($alpha.__str__) > 0.0: + --alpha=$alpha + #end if + </command> + <inputs> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="design" type="data" format="tabular" label="design - assign groups to new grouping" + help="design has 2 columns: group(col 1) and grouping(col 2) (separated by a TAB character)"/> + <param name="alpha" type="float" optional="true" value="0.05" label="alpha - acceptable stopping precision (default 0.05)"/> + <param name="iters" type="integer" value="1000" label="iters - Number of random configuration to try (default 1000)"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="tabular" name="anosim" label="${tool.name} on ${on_string}: anosim"/> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The anosim_ command uses a phylip_distance_matrix_ and a design file to calculate the non-parametric multivariate analysis of changes in community structure. + +A design file partitions a list of names into groups. It is a tab-delimited file with 2 columns: name and group, e.g. : + ======= ======= + duck bird + cow mammal + pig mammal + goose bird + cobra reptile + ======= ======= + +The Make_Design tool can construct a design file from a Mothur dataset that contains group names. + + +.. _phylip_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _anosim: http://www.mothur.org/wiki/Anosim + + + </help> +</tool>
--- a/mothur/tools/mothur/bin.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/bin.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_bin_seqs" name="Bin.seqs" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_bin_seqs" name="Bin.seqs" version="1.19.0" force_history_refresh="True"> <description>Order Sequences by OTU</description> <command interpreter="python"> mothur_wrapper.py @@ -8,18 +8,20 @@ --datasetid='$logfile.id' --new_file_path='$__new_file_path__' --new_datasets='^\S+?\.(unique|[0-9.]*)\.fasta$:fasta' --fasta=$fasta - --READ_cmd='read.otu' - --READ_list=$otu + --list=$otu #if $name.__str__ != "None" and len($name.__str__) > 0: --name=$name #end if #if $label.__str__ != "None" and len($label.__str__) > 0: --label='$label' #end if + #if $group.__str__ != "None" and len($group.__str__) > 0: + --group='$group' + #end if </command> <inputs> <param name="fasta" type="data" format="fasta" label="fasta - Sequences to Bin"/> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> + <param name="otu" type="data" format="list" label="list - OTU List"/> <param name="name" type="data" format="names" optional="true" label="name - Sequences Name reference"/> <param name="label" type="select" label="label - OTU Labels" multiple="true"> <options from_dataset="otu"> @@ -27,6 +29,7 @@ <column name="value" index="0"/> </options> </param> + <param name="group" type="data" format="group" optional="true" label="group - Sequences Name reference"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -47,8 +50,9 @@ **Command Documenation** -The bin.seqs_ command prints out a fasta-formatted file where sequences are ordered according to the OTU that they belong to. Such an output may be helpful for generating primers specific to an OTU or for classification of sequences. +The bin.seqs_ command generates fasta-formatted files where sequences are ordered according to the OTU from the list_file_ that they belong to. Such an output may be helpful for generating primers specific to an OTU or for classification of sequences. +.. _list_file: http://www.mothur.org/wiki/List_file .. _bin.seqs: http://www.mothur.org/wiki/Bin.seqs </help>
--- a/mothur/tools/mothur/chimera.bellerophon.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/chimera.bellerophon.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_chimera_bellerophon" name="Chimera.bellerophon" version="1.16.0"> +<tool id="mothur_chimera_bellerophon" name="Chimera.bellerophon" version="1.19.0"> <description>Find putative chimeras using bellerophon</description> <command interpreter="python"> mothur_wrapper.py @@ -46,8 +46,25 @@ **Command Documenation** -The chimera.bellerophon_ command identifies putative chimeras using the bellerophon approach. +The chimera.bellerophon_ command identifies putative chimeras using the bellerophon_ approach. + +Advantages of Bellerophon: + + 1) You can process all sequences from a PCR-clone library in a single analysis and don't have to inspect outputs for every sequence in the dataset. + 2) The approximate putative breakpoint is calculated using a sliding window (see above) and will help verification of the chimera manually. + 3) A chimeric sequence is not only tested against two (putative) parent sequences but rather is assessed by how well it fits into the complete phylogenetic environment of a multiple sequence alignment. Hence sequences do not become invisible to the program as is the case with CHIMERA_CHECK (see Ref 1 below). + 4) The calculations Bellerophon uses to detect chimeric sequences are computationally relatively cheap and results are quickly calculated for datasets with up 50 sequences (~1 min). Larger datasets take longer - 100 sequences ~30 min, 300 sequences ~8 hours. +Tips for using Bellerophon: + + 1) Bellerophon works most efficiently if the parent sequences or non-chimeric sequences closely related to the parent sequences are present in the dataset analyzed. Therefore, as many sequences as possible from the one PCR-clone library should be included in the analysis since the parent sequences of any chimera are most likely to be in that dataset. Addition of non-chimeric outgroup sequences (e.g. from isolates) may help refine an analysis by providing reference points (and a broader phylogenetic context) in the analysis, but be aware of increasing analysis time with bigger datasets. + 2) Bellerophon is compromised by using sequences of different lengths as this can produce artificial skews in distance matrices of fragments of the alignment. Datasets containing sequences of the same length and covering the same portion of the gene should be used (usually not an issue with sequences from a PCR-clone library). The filter will automatically remove sequences too short for the window size, i.e. less than 600 bp for a window size of 300. + 3) If possible multiple window sizes should be used as the number of identified chimeras can vary with the choice of the window size. + 4) Re-running the dataset without the first reported chimeras may identify additional putative chimeras by reducing noise in the analysis. Ideally, the dataset should continue to be re-run removing previously reported chimeras until no chimeras are identified. + 5) Bellerophon should be used in concert with other detection methods such as CHIMERA_CHECK and putatively identified chimeras should always be confirmed by manual inspection of the sequences for signature shifts. + + +.. _bellerophon: http://comp-bio.anu.edu.au/Bellerophon/doc/doc.html .. _chimera.bellerophon: http://www.mothur.org/wiki/Chimera.bellerophon
--- a/mothur/tools/mothur/chimera.ccode.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/chimera.ccode.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_chimera_ccode" name="Chimera.ccode" version="1.16.0"> +<tool id="mothur_chimera_ccode" name="Chimera.ccode" version="1.19.0"> <description>Find putative chimeras using ccode</description> <command interpreter="python"> mothur_wrapper.py @@ -6,7 +6,7 @@ --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.ccode\.chimeras$:'$out_file,'^\S+\.ccode\.accnos$:'$out_accnos --outputdir='$logfile.extra_files_path' --fasta=$fasta - --template=$alignment.template + --reference=$alignment.template $filter #if $mask.source == 'default': --mask=default @@ -22,14 +22,14 @@ --processors=2 </command> <inputs> - <param name="fasta" type="data" format="fasta" label="fasta - Candiate Sequences"/> + <param name="fasta" type="data" format="align" label="fasta - Candiate Aligned Sequences"/> <conditional name="alignment"> - <param name="source" type="select" label="Select Template from" help=""> + <param name="source" type="select" label="Select Reference Template from" help=""> <option value="hist">History</option> <option value="ref">Cached Reference</option> </param> <when value="ref"> - <param name="template" type="select" label="template - Select an alignment database " help=""> + <param name="template" type="select" label="reference - Select an alignment database " help=""> <options from_file="mothur_aligndb.loc"> <column name="name" index="0" /> <column name="value" index="1" /> @@ -37,7 +37,7 @@ </param> </when> <when value="hist"> - <param name="template" type="data" format="fasta" label="template - Template to align with" help=""/> + <param name="template" type="data" format="fasta" label="reference - Reference to align with" help=""/> </when> </conditional> <param name="filter" type="boolean" falsevalue="" truevalue="--filter=true" checked="false" label="filter - Apply a 50% soft vertical filter"/> @@ -46,12 +46,12 @@ <param name="source" type="select" label="Mask option"> <option value="">None</option> <option value="default">default ecoli mask</option> - <option value="history">From your history</option> + <option value="history">From Your History</option> </param> <when value=""/> <when value="default"/> <when value="history"> - <param name="input" type="data" format="filter" label="Mask for the template file" help=""/> + <param name="input" type="data" format="filter" label="Mask for the reference file" help=""/> </when> </conditional> <param name="window" type="integer" value="0" label="window - Length of sequence you want in each window analyzed (default if < 1)" @@ -79,8 +79,14 @@ **Command Documenation** -The chimera.ccode_ command identifies putative chimeras using the ccode approach. +The chimera.ccode_ command identifies putative chimeras using the ccode approach (Chimera and Cross-Over Detection and Evaluation). Ccode_ compares differences in distances, for each word, between query sequence and reference sequences, and reference sequences and themselves. + +This method was written using the algorithms described in the paper_ "Evaluating putative chimeric sequences from PCR-amplified products" by Juan M. Gonzalez, Johannes Zimmerman and Cesareo Saiz-Jimenez. +The program can analyze sequences for any required word length. Generally, values of 5-20% of sequence length appear to deliver accurate results, for example, working on 16S rDNA sequences with a full-length of #1500 nt. It should be noted that the use of fragments either too long or too short might result in a reduction of sensitivity. + +.. _Ccode: http://www.microextreme.net/downloads.html +.. _paper: http://bioinformatics.oxfordjournals.org/content/21/3/333.full.pdf .. _chimera.ccode: http://www.mothur.org/wiki/Chimera.ccode
--- a/mothur/tools/mothur/chimera.check.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/chimera.check.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_chimera_check" name="Chimera.check" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_chimera_check" name="Chimera.check" version="1.19.0" force_history_refresh="True"> <description>Find putative chimeras using chimeraCheck</description> <command interpreter="python"> mothur_wrapper.py @@ -6,7 +6,7 @@ --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.chimeracheck\.chimeras$:'$out_file --outputdir='$logfile.extra_files_path' --fasta=$fasta - --template=$alignment.template + --reference=$alignment.template #if int($ksize.__str__) > 0: --ksize=$ksize #end if @@ -15,23 +15,25 @@ #end if #if $svg.gen == 'yes': --svg=true - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^(\S+)\.chimeracheck\.svg$:svg' - #if $name.__str__ != "None" and len($name.__str__) > 0: - --name='$name' + #if $svg.name.__str__ != "None" and len($svg.name.__str__) > 0: + --name='$svg.name' + #end if + #if $svg.as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^(\S+)\.chimeracheck\.svg$:svg' #end if #end if --processors=2 </command> <inputs> - <param name="fasta" type="data" format="fasta" label="fasta - Candiate Sequences"/> + <param name="fasta" type="data" format="align" label="fasta - Candiate Aligned Sequences"/> <conditional name="alignment"> - <param name="source" type="select" label="Select Template from" help=""> + <param name="source" type="select" label="Select Reference Template from" help=""> <option value="hist">History</option> <option value="ref">Cached Reference</option> </param> <when value="ref"> - <param name="template" type="select" label="template - Select an alignment database " help=""> + <param name="template" type="select" label="reference - Select an alignment database " help=""> <options from_file="mothur_aligndb.loc"> <column name="name" index="0" /> <column name="value" index="1" /> @@ -39,7 +41,7 @@ </param> </when> <when value="hist"> - <param name="template" type="data" format="fasta" label="template - Template to align with" help=""/> + <param name="template" type="data" format="fasta" label="reference - Reference to align with" help=""/> </when> </conditional> <param name="ksize" type="integer" value="7" label="ksize - kmer length to determine differences between sequence fragments (uses default if < 1)"/> @@ -53,6 +55,7 @@ <when value="no"/> <when value="yes"> <param name="name" type="data" format="names" optional="true" label="name - Names of queries for which to generate SVG plot"/> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Create a new history dataset for each image"/> </when> </conditional> </inputs> @@ -76,7 +79,9 @@ **Command Documenation** -The chimera.check_ command identifies putative chimeras using the chimeraCheck approach. Note: following the RDP model this method does not determine whether or not a sequence is chimeric, but allows you to determine that based on the IS values produced. +The chimera.check_ command identifies putative chimeras using the chimeraCheck approach. It looks at distance of left side of query to it's closest match + distance of right side of query to it's closest match - distance of whole query and its closest match over several windows. + +Note: following the RDP model this method does not determine whether or not a sequence is chimeric, but allows you to determine that based on the IS values produced. .. _chimera.check: http://www.mothur.org/wiki/Chimera.check
--- a/mothur/tools/mothur/chimera.pintail.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/chimera.pintail.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_chimera_pintail" name="Chimera.pintail" version="1.16.0"> +<tool id="mothur_chimera_pintail" name="Chimera.pintail" version="1.19.0"> <description>Find putative chimeras using pintail</description> <command interpreter="python"> mothur_wrapper.py @@ -9,7 +9,7 @@ #set results = $results + ["'^\S+\.pintail\.accnos$:'" + $out_accnos.__str__] --outputdir='$logfile.extra_files_path' --fasta=$fasta - --template=$alignment.template + --reference=$alignment.template $filter #if $mask.source == 'default': --mask=default @@ -38,12 +38,12 @@ <inputs> <param name="fasta" type="data" format="fasta" label="fasta - Candiate Sequences"/> <conditional name="alignment"> - <param name="source" type="select" label="Select Template from" help=""> + <param name="source" type="select" label="Select Reference Template from" help=""> <option value="hist">History</option> <option value="ref">Cached Reference</option> </param> <when value="ref"> - <param name="template" type="select" label="template - Select an alignment database " help=""> + <param name="template" type="select" label="reference - Select an alignment database " help=""> <options from_file="mothur_aligndb.loc"> <column name="name" index="0" /> <column name="value" index="1" /> @@ -51,7 +51,7 @@ </param> </when> <when value="hist"> - <param name="template" type="data" format="fasta" label="template - Template to align with" help=""/> + <param name="template" type="data" format="fasta" label="reference - Reference to align with" help=""/> </when> </conditional> <param name="filter" type="boolean" falsevalue="" truevalue="--filter=true" checked="false" label="filter - Apply a 50% soft vertical filter"/> @@ -137,8 +137,26 @@ **Command Documenation** -The chimera.pintail_ command identifies putative chimeras using the pintail approach. +The chimera.pintail_ command identifies putative chimeras using the pintail approach. It looks at the variation between the expected differences and the observed differences in the query sequence over several windows. + +This method was written using the algorithms described in the paper_ "At Least 1 in 20 16S rRNA Sequence Records Currently Held in the Public Repositories is Estimated To Contain Substantial Anomalies" by Kevin E. Ashelford 1, Nadia A. Chuzhanova 3, John C. Fry 1, Antonia J. Jones 2 and Andrew J. Weightman 1. + + +From www.bioinformatics-toolkit.org_ + +The Pintail algorithm is a technique for determining whether a 16S rDNA sequence is anomalous. It is based on the idea that the extent of local base differences between two aligned 16S rDNA sequences should be roughly the same along the length of the alignment (having allowed for the underlying pattern of hypervariable and conserved regions known to exist within the 16S rRNA gene). In other words, evolutionary distance between two reliable sequences should be constant along the length of the gene. +In contrast, if an error-free sequence is compared with an anomalous sequence, evolutionary distance along the alignment is unlikely to be constant, especially if the anomaly in question is a chimera and formed from phylogenetically different parental sequences. + +The Pintail algorithm is designed to detect and quantify such local variations and in doing so generates the Deviation from Expectation (DE) statistic. The higher the DE value, the greater the likelihood that the query is anomalous. + +The algorithm works as follows + +The sequence to be checked (the query) is first globally aligned with a phylogenetically similar sequence known to be error-free (the subject). At regular intervals along the resulting alignment, the local evolutionary distance between query and subject is estimated by recording percentage base mismatches within a sampling window of fixed length. The resulting array of percentages (observed percentage differences) reflects variations in evolutionary distance between the query and subject along the length of the 16S rRNA gene. Subtracting observed percentage differences from an equivalent array of expected percentage differences (predicted values for error-free sequences), we obtain a set of deviations, the standard deviation of which (Deviation from Expectation, DE) summarises the variation between observed and expected datasets. The greater the DE value, the greater the disparity there is between observed and expected percentage differences, and the more likely it is that the query sequence is anomalous. + + +.. _paper: http://www.ncbi.nlm.nih.gov/pubmed/16332745 +.. _www.bioinformatics-toolkit.org: http://www.bioinformatics-toolkit.org/Help/Topics/pintailAlgorithm.html .. _chimera.pintail: http://www.mothur.org/wiki/Chimera.pintail
--- a/mothur/tools/mothur/chimera.slayer.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/chimera.slayer.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_chimera_slayer" name="Chimera.slayer" version="1.16.0"> +<tool id="mothur_chimera_slayer" name="Chimera.slayer" version="1.19.0"> <description>Find putative chimeras using slayer</description> <command interpreter="python"> mothur_wrapper.py @@ -8,12 +8,12 @@ --tmpdir='${logfile.extra_files_path}/input' --fasta=$fasta #if $alignment.source == 'self': - --template='self' + --reference='self' #if $alignment.name.__str__ != "None" and len($alignment.name.__str__) > 0: --name=$alignment.name #end if #else: - --template=$alignment.template + --reference=$alignment.template #end if #if $options.setby == 'user': --search=$options.search @@ -30,19 +30,20 @@ --minsnp=$options.minsnp --divergence=$options.divergence $options.trim + $options.split #end if --processors=2 </command> <inputs> <param name="fasta" type="data" format="fasta" label="fasta - Candiate Sequences"/> <conditional name="alignment"> - <param name="source" type="select" label="Select Template from" help=""> + <param name="source" type="select" label="Select Reference Template from" help=""> <option value="hist">History</option> <option value="ref">Cached Reference</option> <option value="self">Self - Use abundant sequences from the input Candiate Sequences fasta </option> </param> <when value="ref"> - <param name="template" type="select" label="template - Select an alignment database " help=""> + <param name="template" type="select" label="reference - Select an alignment database " help=""> <options from_file="mothur_aligndb.loc"> <column name="name" index="0" /> <column name="value" index="1" /> @@ -50,7 +51,7 @@ </param> </when> <when value="hist"> - <param name="template" type="data" format="fasta" label="template - Template to align with" help=""/> + <param name="template" type="data" format="fasta" label="reference - Reference to align with" help=""/> </when> <when value="self"> <param name="name" type="data" format="names" optional="true" label="names - Sequences Names"/> @@ -75,12 +76,13 @@ <param name="numwanted" type="integer" value="15" label="numwanted - Number of potential parents to to compare with query sequence (default 15)"/> <param name="parents" type="integer" value="3" label="parents - Number of potential parents to investigate from the numwanted best matches"/> <param name="minsim" type="integer" value="90" label="minsim - Minimum similarity % between the query and parent (default 90)"/> - <param name="mincov" type="integer" value="70" label="mincov - Minimum coverage % of closest matches in template and the query (default 70)"/> + <param name="mincov" type="integer" value="70" label="mincov - Minimum coverage % of closest matches in reference and the query (default 70)"/> <param name="iters" type="integer" value="100" label="iters - Number of bootstrap iterations to try (default 100)"/> <param name="minbs" type="integer" value="90" label="minbs - Minimum bootstrap support % for calling a sequence chimeric (default 90)"/> <param name="minsnp" type="integer" value="100" label="minsnp - Percent of SNPs to sample on each side of breakpoint for computing bootstrap support (default 100)"/> <param name="divergence" type="float" value="1.007" label="divergence - Divergence cutoff for chimera determination (default 1.007)"/> <param name="trim" type="boolean" truevalue="--trim=True" falsevalue="" checked="false" label="trim - include chimeric sequences trimmed to their longest peice" /> + <param name="split" type="boolean" truevalue="--split=True" falsevalue="" checked="false" label="split - detect tri- and quadmeras" help="if a sequence comes back as non-chimeric, mothur will test the two sides to see if they are chimeric."/> </when> </conditional> </inputs> @@ -107,6 +109,20 @@ The chimera.slayer_ command identifies putative chimeras using the slayer approach. +ChimeraSlayer_ is a chimeric sequence detection utility, compatible with near-full length Sanger sequences and shorter 454-FLX sequences (~500 bp). + +Chimera Slayer involves the following series of steps that operate to flag chimeric 16S rRNA sequences: + + (A) the ends of a query sequence are searched against an included database of reference chimera-free 16S sequences to identify potential parents of a chimera; + (B) candidate parents of a chimera are selected as those that form a branched best scoring alignment to the NAST-formatted query sequence; + (C) the NAST alignment of the query sequence is improved in a `chimera-aware' profile-based NAST realignment to the selected reference parent sequences; and + (D) an evolutionary framework is used to flag query sequences found to exhibit greater sequence homology to an in silico chimera formed between any two of the selected reference parent sequences. + +Note: +It is not recommended to blindly discard all sequences flagged as chimeras. Some may represent naturally formed chimeras that do not represent PCR artifacts. Sequences flagged may warrant further investigation. + + +.. _ChimeraSlayer: http://microbiomeutil.sourceforge.net/ .. _chimera.slayer: http://www.mothur.org/wiki/Chimera.slayer
--- a/mothur/tools/mothur/chop.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/chop.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_chop_seqs" name="Chop.seqs" version="1.16.0"> +<tool id="mothur_chop_seqs" name="Chop.seqs" version="1.19.0"> <description>Trim sequences to a specified length</description> <command interpreter="python"> mothur_wrapper.py @@ -12,7 +12,7 @@ $short </command> <inputs> - <param name="fasta" type="data" format="fasta" label="fasta - Dataset"/> + <param name="fasta" type="data" format="fasta,align" label="fasta - Sequences to be chopped"/> <param name="numbases" type="integer" value="10" label="numbases - Number of bases to keep"/> <param name="keep" type="select" label="keep - Part of the sequence to keep"> <option value="front">front</option> @@ -23,7 +23,7 @@ </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="fasta" name="out_fasta" label="${tool.name} on ${on_string}: chop.fasta" /> + <data format_source="fasta" name="out_fasta" label="${tool.name} on ${on_string}: chop.fasta" /> </outputs> <requirements> <requirement type="binary">mothur</requirement> @@ -41,7 +41,7 @@ **Command Documenation** -The chop.seqs_ command reads a fasta file and outputs a .chop.fasta containing the trimmed sequences. It works on both aligned and unaligned sequences. +The chop.seqs_ command reads a fasta file of sequences and outputs a .chop.fasta file containing the trimmed sequences. It works on both aligned and unaligned sequences. .. _chop.seqs: http://www.mothur.org/wiki/Chop.seqs
--- a/mothur/tools/mothur/classify.otu.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/classify.otu.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_classify_otu" name="Classify.otu" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_classify_otu" name="Classify.otu" version="1.19.0" force_history_refresh="True"> <description>Assign sequences to taxonomy</description> <command interpreter="python"> mothur_wrapper.py @@ -6,7 +6,7 @@ --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?\.(unique|[0-9.]*\.cons\.taxonomy)$:cons.taxonomy' + --new_datasets='^\S+?\.(unique|[0-9.]*\.cons\.taxonomy)$:cons.taxonomy','^\S+?\.(unique|[0-9.]*\.cons\.tax\.summary)$:tax.summary' --list=$otu --taxonomy=$tax.taxonomy #if $reftax.source != 'none' and len($reftax.taxonomy.__str__) > 0: @@ -18,6 +18,10 @@ #if $label.__str__ != "None" and len($label.__str__) > 0: --label='$label' #end if + #if $group.__str__ != "None" and len($group.__str__) > 0: + --group='$group' + #end if + --basis=$basis $probs </command> <inputs> @@ -28,7 +32,7 @@ <option value="ref">Cached Reference</option> </param> <when value="ref"> - <param name="taxonomy" type="select" format="taxonomy" label="taxonomy - Taxonomy Reference"> + <param name="taxonomy" type="select" format="seq.taxonomy" label="taxonomy - Taxonomy Reference"> <options from_file="mothur_taxonomy.loc"> <column name="name" index="0" /> <column name="value" index="1" /> @@ -36,7 +40,7 @@ </param> </when> <when value="hist"> - <param name="taxonomy" type="data" format="taxonomy" label="taxonomy - Taxonomy Reference"/> + <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy Reference"/> </when> </conditional> <conditional name="reftax"> @@ -47,7 +51,7 @@ </param> <when value="none"/> <when value="ref"> - <param name="taxonomy" type="select" format="taxonomy" label="reftaxonomy - Taxonomy Reference used when sequences were classified"> + <param name="taxonomy" type="select" format="seq.taxonomy" label="reftaxonomy - Taxonomy Reference used when sequences were classified"> <options from_file="mothur_taxonomy.loc"> <column name="name" index="0" /> <column name="value" index="1" /> @@ -55,7 +59,7 @@ </param> </when> <when value="hist"> - <param name="taxonomy" type="data" format="taxonomy" label="reftaxonomy - Taxonomy Reference used when sequences were classified"/> + <param name="taxonomy" type="data" format="seq.taxonomy" label="reftaxonomy - Taxonomy Reference used when sequences were classified"/> </when> </conditional> <param name="label" type="select" label="label - OTU Labels" multiple="true"> @@ -68,6 +72,11 @@ <validator type="in_range" message="Confindence percentage cutoff must be between 0 and 100" min="0" max="100"/> </param> <param name="probs" type="boolean" falsevalue="--probs=false" truevalue="" checked="true" label="probs - Show probabilities"/> + <param name="basis" type="select" label="basis - Summary file gives numbers of" help=""> + <option value="otu">OTU</option> + <option value="sequence">sequence</option> + </param> + <param name="group" type="data" format="groups" optional="true" label="group - Groups for summary file"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -90,6 +99,8 @@ The classify.otu_ command assigns sequences to chosen taxonomy outline. +The basis parameter allows you indicate what you want the summary file to represent, options are otu and sequence. Default is otu. For example consider the following basis=sequence could give Clostridiales 3 105 16 43 46, where 105 is the total number of sequences whose otu classified to Clostridiales. 16 is the number of sequences in the otus from groupA, 43 is the number of sequences in the otus from groupB, and 46 is the number of sequences in the otus from groupC. Now for basis=otu could give Clostridiales 3 7 6 1 2, where 7 is the number of otus that classified to Clostridiales. 6 is the number of otus containing sequences from groupA, 1 is the number of otus containing sequences from groupB, and 2 is the number of otus containing sequences from groupC. + .. _classify.otu: http://www.mothur.org/wiki/Classify.otu
--- a/mothur/tools/mothur/classify.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/classify.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_classify_seqs" name="Classify.seqs" version="1.16.0"> +<tool id="mothur_classify_seqs" name="Classify.seqs" version="1.19.0"> <description>Assign sequences to taxonomy</description> <command interpreter="python"> mothur_wrapper.py @@ -6,7 +6,7 @@ --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.taxonomy$:'$taxonomy_out,'^\S+\.tax\.summary$:'$tax_summary --outputdir='$logfile.extra_files_path' --fasta=$fasta - --template=$alignment.template + --reference=$alignment.template --taxonomy=$tax.taxonomy #if $classify.method == 'bayesian': --method=$classify.method @@ -43,12 +43,12 @@ <inputs> <param name="fasta" type="data" format="fasta" label="fasta - Candiate Sequences"/> <conditional name="alignment"> - <param name="source" type="select" label="Select Template from" help=""> + <param name="source" type="select" label="Select Reference Template from" help=""> <option value="hist">History</option> <option value="ref">Cached Reference</option> </param> <when value="ref"> - <param name="template" type="select" label="template - Select an alignment database " help=""> + <param name="template" type="select" label="reference - Select an alignment database " help=""> <options from_file="mothur_aligndb.loc"> <column name="name" index="0" /> <column name="value" index="1" /> @@ -56,7 +56,7 @@ </param> </when> <when value="hist"> - <param name="template" type="data" format="fasta" label="template - Template to align with" help=""/> + <param name="template" type="data" format="fasta" label="reference - Reference to align with" help=""/> </when> </conditional> <conditional name="tax"> @@ -65,7 +65,7 @@ <option value="hist">History</option> </param> <when value="ref"> - <param name="taxonomy" type="select" format="taxonomy" label="taxonomy - Taxonomy reference"> + <param name="taxonomy" type="select" format="seq.taxonomy" label="taxonomy - Taxonomy reference"> <options from_file="mothur_taxonomy.loc"> <column name="name" index="0" /> <column name="value" index="1" /> @@ -73,7 +73,7 @@ </param> </when> <when value="hist"> - <param name="taxonomy" type="data" format="taxonomy" label="taxonomy - Taxonomy reference"/> + <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy reference"/> </when> </conditional> <conditional name="classify"> @@ -115,7 +115,7 @@ </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: taxonomy" /> + <data format="seq.taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: taxonomy" /> <data format="tax.summary" name="tax_summary" label="${tool.name} on ${on_string}: tax.summary" /> </outputs> <requirements>
--- a/mothur/tools/mothur/clearcut.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/clearcut.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_clearcut" name="Clearcut" version="1.16.0"> +<tool id="mothur_clearcut" name="Clearcut" version="1.19.0"> <description>Generate a tree using relaxed neighbor joining</description> <command interpreter="python"> mothur_wrapper.py @@ -81,6 +81,13 @@ The clearcut_ command runs clearcut +The clearcut command allows mothur users to run the clearcut_program_ from within mothur. The clearcut program written by Initiative for Bioinformatics and Evolutionary Studies (IBEST) at the University of Idaho. For more information about clearcut please refer to http://bioinformatics.hungry.com/clearcut/ + +Clearcut is a stand-alone reference implementation of relaxed neighbor joining (RNJ). + +Clearcut is capable of taking either a distance matrix or a multiple sequence alignment (MSA) as input. If necessary, Clearcut will compute corrected distances based on a configurable distance correction model (Jukes-Cantor or Kimura). Clearcut outputs a phylogenetic tree in Newick format and an optional corrected distance matrix. + +.. _clearcut_program: http://bioinformatics.hungry.com/clearcut/ .. _clearcut: http://www.mothur.org/wiki/Clearcut </help>
--- a/mothur/tools/mothur/cluster.classic.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/cluster.classic.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,57 +1,39 @@ -<tool id="mothur_cluster_classic" name="Cluster.classic" version="1.16.0"> +<tool id="mothur_cluster_classic" name="Cluster.classic" version="1.19.0"> <description>Assign sequences to OTUs (Dotur implementation)</description> <command interpreter="python"> mothur_wrapper.py --cmd='cluster.classic' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.[fna]n\.sabund$:'$sabund,'^\S+\.[fna]n\.rabund$:'$rabund,'^\S+\.[fna]n\.list$:'$otulist --outputdir='$logfile.extra_files_path' - --READ_cmd='read.dist' - #if $matrix.format == "column": - --READ_column=$matrix.dist - --READ_name=$matrix.name - #elif $matrix.format == "phylip": - --READ_phylip=$matrix.dist - #if $matrix.name.__str__ != "None" and len($matrix.name.__str__) > 0: - --READ_name=$matrix.name - #end if - #end if - $sim - #if float($cutoff.__str__) > 0.0: - --READ_cutoff=$cutoff - #end if - $hard - #if len($precision.__str__) > 0: - --READ_precision=$precision + --phylip=$dist + #if $name.__str__ != "None" and len($name.__str__) > 0: + --name=$name #end if #if len($method.__str__) > 0: --method=$method #end if + #if float($cutoff.__str__) > 0.0: + --cutoff=$cutoff + #end if + $hard + #if len($precision.__str__) > 0: + --precision=$precision + #end if + $sim </command> <inputs> - <conditional name="matrix"> - <param name="format" type="select" label="Select a Distance Matrix Format" help=""> - <option value="column">Pairwise Column Matrix</option> - <option value="phylip">Phylip Distance Matrix</option> - </param> - <when value="column"> - <param name="dist" type="data" format="pair.dist" label="read.dist(column=) - Distance Matrix"/> - <param name="name" type="data" format="names" label="read.dist(name=) - Sequences Name reference"/> - </when> - <when value="phylip"> - <param name="dist" type="data" format="lower.dist,square.dist" label="read.dist(phylip=) - Distance Matrix"/> - <param name="name" type="data" format="names" optional="true" label="read.dist(name=) - Sequences Name reference"/> - </when> - </conditional> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="name" type="data" format="names" optional="true" label="name - Sequences Name reference"/> <!-- ? conditional - to hide complexity --> <param name="method" type="select" label="method - Select a Clustering Method" help=""> - <option value="furthest" selected="true">Furthest neighbor</option> + <option value="furthest">Furthest neighbor</option> <option value="nearest">Nearest neighbor</option> - <option value="average">Average neighbor</option> + <option value="average" selected="true">Average neighbor</option> <option value="weighted">Weighted</option> </param> <param name="cutoff" type="float" value="0.0" label="cutoff - Distance Cutoff threshold - ignored if not > 0" help="Ignore pairwise distances larger than this, a common value would be 0.10"/> - <param name="hard" type="boolean" checked="false" truevalue="--hard=true" falsevalue="" label="hard - Use hard cutoff instead of rounding" + <param name="hard" type="boolean" checked="true" truevalue="--hard=true" falsevalue="--hard=false" label="hard - Use hard cutoff instead of rounding" help=""/> <param name="precision" type="select" optional="true" label="precision - Precision for rounding distance values" help="Set higher precision for longer genome scale sequence lengths"> @@ -62,9 +44,8 @@ <option value="100000">.00001</option> <option value="1000000">.000001</option> </param> - <param name="sim" type="boolean" checked="false" truevalue="--READ_sim=true" falsevalue="" label="sim - Matrix values are Similary instead of Distance" + <param name="sim" type="boolean" checked="false" truevalue="--sim=true" falsevalue="" label="sim - Matrix values are Similary instead of Distance" help=""/> - </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" />
--- a/mothur/tools/mothur/cluster.fragments.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/cluster.fragments.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_cluster_fragments" name="Cluster.fragments" version="1.16.0"> +<tool id="mothur_cluster_fragments" name="Cluster.fragments" version="1.19.0"> <description> Group sequences that are part of a larger sequence</description> <command interpreter="python"> mothur_wrapper.py
--- a/mothur/tools/mothur/cluster.split.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/cluster.split.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,9 +1,9 @@ -<tool id="mothur_cluster_split" name="Cluster.split" version="1.16.0"> +<tool id="mothur_cluster_split" name="Cluster.split" version="1.19.0"> <description>Assign sequences to OTUs (Operational Taxonomic Unit) splits large matrices</description> <command interpreter="python"> mothur_wrapper.py --cmd='cluster.split' - --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.sabund$:'$sabund,'^\S+\.rabund$:'$rabund,'^\S+\.list$:'$otulist + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.sabund$:'$sabund,'^\S+\.rabund$:'$rabund,'^\S+\.list$:'$otulist,'^\S+\.dist$:'$dist_out --outputdir='$logfile.extra_files_path' #if $splitby.splitmethod == "distance": #if $splitby.matrix.format == "column": @@ -72,26 +72,26 @@ <when value="classify"> <param name="dist" type="data" format="pair.dist" label="column - Distance Matrix"/> <param name="name" type="data" format="names" label="name - Sequences Name reference"/> - <param name="taxonomy" type="data" format="taxonomy" label="taxonomy - Taxonomy (from Classify.seqs)"/> + <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy (from Classify.seqs)"/> <param name="taxlevel" type="integer" value="1" label="taxlevel - taxonomy level for split (default=1)" help="taxonomy level you want to use to split the distance file, default=1, meaning use the first taxon in each list"/> </when> <when value="fasta"> <param name="fasta" type="data" format="fasta" label="fasta - Sequences"/> <param name="name" type="data" format="names" label="name - Sequences Name reference"/> - <param name="taxonomy" type="data" format="taxonomy" label="taxonomy - Taxonomy (from Classify.seqs)"/> + <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy (from Classify.seqs)"/> <param name="taxlevel" type="integer" value="1" label="taxlevel - taxonomy level for split (default=1)" help="taxonomy level you want to use to split the distance file, default=1, meaning use the first taxon in each list"/> </when> </conditional> <!-- splitby --> <param name="method" type="select" label="method - Select a Clustering Method" help=""> - <option value="furthest" selected="true">Furthest neighbor</option> + <option value="furthest">Furthest neighbor</option> <option value="nearest">Nearest neighbor</option> - <option value="average">Average neighbor</option> + <option value="average" selected="true">Average neighbor</option> </param> <param name="cutoff" type="float" value="0.0" label="cutoff - Distance Cutoff threshold - ignored if not > 0" help="Ignore pairwise distances larger than this, a common value would be 0.10"/> - <param name="hard" type="boolean" checked="false" truevalue="--hard=true" falsevalue="" label="hard - Use hard cutoff instead of rounding" + <param name="hard" type="boolean" checked="true" truevalue="--hard=true" falsevalue="--hard=true" label="hard - Use hard cutoff instead of rounding" help=""/> <param name="precision" type="select" optional="true" label="precision - Precision for rounding distance values" help="Set higher precision for longer genome scale sequence lengths"> @@ -110,6 +110,9 @@ <data format="rabund" name="rabund" label="${tool.name} on ${on_string}: rabund (Rank Abundance)"/> <data format="sabund" name="sabund" label="${tool.name} on ${on_string}: sabund (Species Abundance)"/> <data format="list" name="otulist" label="${tool.name} on ${on_string}: list (OTU List)"/> + <data format="pair.dist" name="dist_out" label="${tool.name} on ${on_string}: Column dist"> + <filter>splitby.splitmethod == 'fasta' </filter> + </data> </outputs> <requirements> <requirement type="binary">mothur</requirement>
--- a/mothur/tools/mothur/cluster.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/cluster.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,27 +1,26 @@ -<tool id="mothur_cluster" name="Cluster" version="1.16.0"> +<tool id="mothur_cluster" name="Cluster" version="1.19.0"> <description>Assign sequences to OTUs (Operational Taxonomic Unit)</description> <command interpreter="python"> mothur_wrapper.py --cmd='cluster' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.[fna]n\.sabund$:'$sabund,'^\S+\.[fna]n\.rabund$:'$rabund,'^\S+\.[fna]n\.list$:'$otulist --outputdir='$logfile.extra_files_path' - --READ_cmd='read.dist' #if $matrix.format == "column": - --READ_column=$matrix.dist - --READ_name=$matrix.name + --column=$matrix.dist + --name=$matrix.name #elif $matrix.format == "phylip": - --READ_phylip=$matrix.dist + --phylip=$matrix.dist #if $matrix.name.__str__ != "None" and len($matrix.name.__str__) > 0: - --READ_name=$matrix.name + --name=$matrix.name #end if #end if $sim #if float($cutoff.__str__) > 0.0: - --READ_cutoff=$cutoff + --cutoff=$cutoff #end if $hard #if len($precision.__str__) > 0: - --READ_precision=$precision + --precision=$precision #end if #if len($method.__str__) > 0: --method=$method @@ -34,24 +33,24 @@ <option value="phylip">Phylip Distance Matrix</option> </param> <when value="column"> - <param name="dist" type="data" format="pair.dist" label="read.dist(column=) - Distance Matrix"/> - <param name="name" type="data" format="names" label="read.dist(name=) - Sequences Name reference"/> + <param name="dist" type="data" format="pair.dist" label="column - Distance Matrix"/> + <param name="name" type="data" format="names" label="name - Sequences Name reference"/> </when> <when value="phylip"> - <param name="dist" type="data" format="lower.dist,square.dist" label="read.dist(phylip=) - Distance Matrix"/> - <param name="name" type="data" format="names" optional="true" label="read.dist(name=) - Sequences Name reference"/> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="name" type="data" format="names" optional="true" label="name - Sequences Name reference"/> </when> </conditional> <!-- ? conditional - to hide complexity --> <param name="method" type="select" label="method - Select a Clustering Method" help=""> - <option value="furthest" selected="true">Furthest neighbor</option> + <option value="furthest">Furthest neighbor</option> <option value="nearest">Nearest neighbor</option> - <option value="average">Average neighbor</option> + <option value="average" selected="true">Average neighbor</option> <option value="weighted">Weighted</option> </param> <param name="cutoff" type="float" value="0.0" label="cutoff - Distance Cutoff threshold - ignored if not > 0" help="Ignore pairwise distances larger than this, a common value would be 0.10"/> - <param name="hard" type="boolean" checked="false" truevalue="--hard=true" falsevalue="" label="hard - Use hard cutoff instead of rounding" + <param name="hard" type="boolean" checked="true" truevalue="--hard=true" falsevalue="--hard=false" label="hard - Use hard cutoff instead of rounding" help=""/> <param name="precision" type="select" optional="true" label="precision - Precision for rounding distance values" help="Set higher precision for longer genome scale sequence lengths"> @@ -62,7 +61,7 @@ <option value="100000">.00001</option> <option value="1000000">.000001</option> </param> - <param name="sim" type="boolean" checked="false" truevalue="--READ_sim=true" falsevalue="" label="sim - Matrix values are Similary instead of Distance" + <param name="sim" type="boolean" checked="false" truevalue="--sim=true" falsevalue="" label="sim - Matrix values are Similary instead of Distance" help=""/> </inputs> @@ -88,8 +87,14 @@ **Command Documenation** -The cluster_ command assign sequences to OTUs (Operational Taxonomy Unit). +The cluster_ command assign sequences to OTUs (Operational Taxonomy Unit). The assignment is based on a phylip-formatted_distance_matrix_ or a column-formatted_distance_matrix_ and name_ file. It generates a list_, a sabund_ (Species Abundance), and a rabund_ (Relative Abundance) file. +.. _phylip-formatted_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _column-formatted_distance_matrix: http://www.mothur.org/wiki/Column-formatted_distance_matrix +.. _name: http://www.mothur.org/wiki/Name_file +.. _list: http://www.mothur.org/wiki/List_file +.. _rabund: http://www.mothur.org/wiki/Rabund_file +.. _sabund: http://www.mothur.org/wiki/Sabund_file .. _cluster: http://www.mothur.org/wiki/Cluster
--- a/mothur/tools/mothur/collect.shared.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/collect.shared.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_collect_shared" name="Collect.shared" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_collect_shared" name="Collect.shared" version="1.19.0" force_history_refresh="True"> <description>Generate collector's curves for calculators on OTUs</description> <command interpreter="python"> mothur_wrapper.py @@ -7,74 +7,40 @@ --outputdir='$logfile.extra_files_path' --datasetid='$logfile.id' --new_file_path='$__new_file_path__' --new_datasets='^\S+?\.(anderberg|braycurtis|jabund|jclass|jest|kstest|kulczynski|kulczynskicody|lennon|morisitahorn|ochiai|shared\.ace|shared\.chao|shared\.nseqs|shared\.sobs|sorabund|sorclass|sorest|thetan|thetayc|whittaker)$:tabular' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if + --shared=$otu + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' #end if #if $calc.__str__ != "None" and len($calc.__str__) > 0: - --calc='$calc' + --calc='$calc' #end if $all #if float($freq.__str__) > 0: --freq=$freq #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups=$groups #end if </command> <inputs> - <conditional name="input"> - <param name="source" type="select" label="Generate Collector Curvers for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to condider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> - <param name="calc" type="select" label="calc - Calculators (Uses defaults if none selected)" multiple="true"> + <param name="otu" type="data" format="shared" label="shared - OTU Shared"/> + <param name="label" type="select" label="label - OTU Label filter" multiple="true"> + <help>To filter: select labels to include</help> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + <param name="groups" type="select" label="groups - Groups filter (uses all groups if none are selected)" multiple="true"> + <help>To filter: select select at least 2 groups</help> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + <param name="calc" type="select" label="calc - Calculators (Uses defaults if none are selected)" multiple="true"> <options from_file="mothur_calculators.loc"> <column name="mult" index="1"/> <column name="name" index="0"/> @@ -105,8 +71,9 @@ **Command Documenation** -The collect.shared_ command generates collector's curves for calculators, which describe the similarity between communities or their shared richness. Collector's curves describe how richness or diversity change as you sample additional individuals. If a collector's curve becomes parallel to the x-axis, you can be reasonably confident that you have done a good job of sampling and can trust the last value in the curve. +The collect.shared_ command generates collector's curves for calculators_, which describe the similarity between communities or their shared richness. Collector's curves describe how richness or diversity change as you sample additional individuals. If a collector's curve becomes parallel to the x-axis, you can be reasonably confident that you have done a good job of sampling and can trust the last value in the curve. For calc parameter choices see: http://www.mothur.org/wiki/Calculators +.. _calculators: http://www.mothur.org/wiki/Calculators .. _collect.shared: http://www.mothur.org/wiki/Collect.shared </help>
--- a/mothur/tools/mothur/collect.single.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/collect.single.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,16 +1,20 @@ -<tool id="mothur_collect_single" name="Collect.single" version="1.16.0" force_history_refresh="True"> - <description>Summary of calculator values for OTUs</description> +<tool id="mothur_collect_single" name="Collect.single" version="1.19.0" force_history_refresh="True"> + <description>Generate collector's curves for OTUs</description> <command interpreter="python"> mothur_wrapper.py --cmd='collect.single' --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+\.(\S+)$:tabular' - --READ_cmd='read.otu' - --READ_list=$otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' + --new_datasets='^\S+?\.(\S+)$:tabular' + #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__): + --shared=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('rabund').__class__): + --rabund=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sabund').__class__): + --sabund=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('list').__class__): + --list=$otu #end if #if $label.__str__ != "None" and len($label.__str__) > 0: --label='$label' @@ -24,13 +28,12 @@ #if int($size.__str__) > 0: --size=$size #end if - </command> #if float($freq.__str__) > 0: --freq=$freq #end if + </command> <inputs> - <param name="otu" type="data" format="list,shared" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" optional="true" label="read.otu(group=) - Group file for the OTU List"/> + <param name="otu" type="data" format="list,rabund,sabund,shared" label="list,rabund,sabund,shared - OTU List"/> <param name="label" type="select" label="label - OTU Labels" multiple="true"> <options from_dataset="otu"> <column name="name" index="0"/> @@ -46,9 +49,11 @@ <filter type="static_value" name="mult" column="1" value="single" /> </options> </param> - <param name="abund" type="integer" value="10" label="abund - ACE Estimator threshold for abundant versus rare OTUs"/> - <param name="size" type="integer" value="0" label="size - "/> - <param name="freq" type="float" value="0.0" label="freq - "/> + <param name="abund" type="integer" value="10" label="abund - ACE Estimator threshold for abundant versus rare OTUs (default 10)"/> + <param name="size" type="integer" value="0" label="size - sample size for OTU prediction (ignored if < 1)" + help="By default these calculators will base the prediction on a sample that is the same size as the initial sampling"/> + <param name="freq" type="float" value="0.0" label="freq - frequency for output (default is every 100 sequences)" + help="Use a decimal between 0 and 1 to set the frequency as a percentage of the number of sequences"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -69,8 +74,9 @@ **Command Documenation** -The collect.single_ command generates collector's curves using calculators, that describe the richness, diversity, and other features of individual samples. Collector's curves describe how richness or diversity change as you sample additional individuals. If a collector's curve becomes parallel to the x-axis, you can be reasonably confident that you have done a good job of sampling and can trust the last value in the curve. Otherwise, you need to keep sampling. +The collect.single_ command generates collector's curves using calculators_, that describe the richness, diversity, and other features of individual samples. Collector's curves describe how richness or diversity change as you sample additional individuals. If a collector's curve becomes parallel to the x-axis, you can be reasonably confident that you have done a good job of sampling and can trust the last value in the curve. Otherwise, you need to keep sampling. For calc parameter choices see: http://www.mothur.org/wiki/Calculators +.. _calculators: http://www.mothur.org/wiki/Calculators .. _collect.single: http://www.mothur.org/wiki/Collect.single </help>
--- a/mothur/tools/mothur/consensus.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/consensus.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_consensus_seqs" name="Consensus.seqs" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_consensus_seqs" name="Consensus.seqs" version="1.19.0" force_history_refresh="True"> <description>Find a consensus sequence for each OTU or phylotype</description> <command interpreter="python"> mothur_wrapper.py
--- a/mothur/tools/mothur/corr.axes.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/corr.axes.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_corr_axes" name="Corr.axes" version="1.16.0"> +<tool id="mothur_corr_axes" name="Corr.axes" version="1.19.0"> <description>correlation of data to axes</description> <command interpreter="python"> mothur_wrapper.py
--- a/mothur/tools/mothur/degap.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/degap.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_degap_seqs" name="Degap.seqs" version="1.16.0"> +<tool id="mothur_degap_seqs" name="Degap.seqs" version="1.19.0"> <description>Remove gap characters from sequences</description> <command interpreter="python"> mothur_wrapper.py
--- a/mothur/tools/mothur/deunique.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/deunique.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_deunique_seqs" name="Deunique.seqs" version="1.16.0"> +<tool id="mothur_deunique_seqs" name="Deunique.seqs" version="1.19.0"> <description>Return all sequences</description> <command interpreter="python"> mothur_wrapper.py @@ -10,7 +10,7 @@ </command> <inputs> <param name="fasta" type="data" format="fasta" label="fasta - Sequences to filter"/> - <param name="names" type="data" format="names" optional="true" label="names - Sequences Name reference"/> + <param name="names" type="data" format="names" label="names - Sequences Name reference"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -32,8 +32,9 @@ **Command Documenation** -The deunique.seqs_ command is the reverse of the unique.seqs command, and creates a fasta file from a fasta and name file. +The deunique.seqs_ command is the reverse of the unique.seqs command, and creates a fasta file from a fasta and name_ file. +.. _name: http://www.mothur.org/wiki/Name_file .. _deunique.seqs: http://www.mothur.org/wiki/Deunique.seqs
--- a/mothur/tools/mothur/dist.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/dist.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_dist_seqs" name="Dist.seqs" version="1.16.0"> +<tool id="mothur_dist_seqs" name="Dist.seqs" version="1.19.0"> <description>calculate uncorrected pairwise distances between aligned sequences</description> <command interpreter="python"> mothur_wrapper.py @@ -64,8 +64,10 @@ **Command Documenation** -The dist.seqs_ command will calculate uncorrected pairwise distances between aligned sequences. +The dist.seqs_ command will calculate uncorrected pairwise distances between aligned sequences. The command will generate a column-formatted_distance_matrix_ that is compatible with the column option in the read.dist command. The command is also able to generate a phylip-formatted_distance_matrix_. There are several options for how to handle gap comparisons and terminal gaps. +.. _column-formatted_distance_matrix: http://www.mothur.org/wiki/Column-formatted_distance_matrix +.. _phylip-formatted_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix .. _dist.seqs: http://www.mothur.org/wiki/Dist.seqs
--- a/mothur/tools/mothur/dist.shared.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/dist.shared.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,37 +1,28 @@ -<tool id="mothur_dist_shared" name="Dist.shared" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_dist_shared" name="Dist.shared" version="1.19.0" force_history_refresh="True"> <description>Generate a phylip-formatted dissimilarity distance matrix among multiple groups</description> <command interpreter="python"> mothur_wrapper.py --cmd='dist.shared' --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - #if len($output.__str__) > 0: - #if $output.__str__ == 'square': - --new_datasets='^\S+?\.([a-z]+\.(unique|[0-9.]*)\.(square|lt))\.dist$:square.dist' - #elif $output.__str__ == 'lt': + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + #if len($output.__str__) > 0: + #if $output.__str__ == 'square': + --new_datasets='^\S+?\.([a-z]+\.(unique|[0-9.]*)\.(square|lt))\.dist$:square.dist' + #elif $output.__str__ == 'lt': + --new_datasets='^\S+?\.([a-z]+\.(unique|[0-9.]*)\.(square|lt))\.dist$:lower.dist' + #end if + #else: --new_datasets='^\S+?\.([a-z]+\.(unique|[0-9.]*)\.(square|lt))\.dist$:lower.dist' #end if - #else: - --new_datasets='^\S+?\.([a-z]+\.(unique|[0-9.]*)\.(square|lt))\.dist$:lower.dist' #end if - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if + --shared=$otu + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups=$groups #end if #if $calc.__str__ != "None" and len($calc.__str__) > 0: --calc=$calc @@ -42,47 +33,21 @@ </command> <inputs> <!-- list,group or shared --> - <conditional name="input"> - <param name="source" type="select" label="Generate Collector Curvers for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> + <param name="otu" type="data" format="shared" label="shared - OTU Shared"/> + <param name="label" type="select" label="label - OTU Labels to calculate" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + <param name="groups" type="select" label="groups - Groups to analyze" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> <param name="calc" type="select" label="calc - Calculators (Uses defaults if none selected)" multiple="true"> <options from_file="mothur_calculators.loc"> <column name="mult2" index="2"/> @@ -91,10 +56,11 @@ <filter type="static_value" name="mult2" column="2" value="shar" /> </options> </param> - <param name="output" type="select" label="output - Distance Matrix Output Format" help=""> + <param name="output" type="select" label="output - Distance Matrix Output Format" help="A Distance Matrix will be generated for each calculator label pair"> <option value="lt">Phylip formatted Lower Triangle Matrix</option> <option value="square">Phylip formatted Square Matrix</option> </param> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Create a new history dataset for each distance matrix"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -115,8 +81,10 @@ **Command Documenation** -The dist.shared_ command will generate a phylip-formatted distance matrix that describes the dissimilarity (1-similarity) among multiple groups. +The dist.shared_ command will generate a phylip-formatted_distance_matrix_ that describes the dissimilarity (1-similarity) among multiple groups from a shared_ file. For calc parameter choices see: http://www.mothur.org/wiki/Calculators +.. _phylip-formatted_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _shared: http://www.mothur.org/wiki/Shared_file .. _dist.shared: http://www.mothur.org/wiki/Dist.shared
--- a/mothur/tools/mothur/fastq.info.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/fastq.info.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_fastq_info" name="Fastq.info" version="1.16.0"> +<tool id="mothur_fastq_info" name="Fastq.info" version="1.19.0"> <description>Convert fastq to fasta and quality</description> <command interpreter="python"> mothur_wrapper.py
--- a/mothur/tools/mothur/filter.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/filter.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_filter_seqs" name="Filter.seqs" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_filter_seqs" name="Filter.seqs" version="1.19.0" force_history_refresh="True"> <description>removes columns from alignments</description> <command interpreter="python"> mothur_wrapper.py
--- a/mothur/tools/mothur/get.group.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/get.group.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,54 +1,14 @@ -<tool id="mothur_get_group" name="Get.group" version="1.16.0"> +<tool id="mothur_get_group" name="Get.group" version="1.19.0"> <description>group names from shared or from list and group</description> <command interpreter="python"> mothur_wrapper.py --cmd='get.group' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.bootGroups$:'$bootgroups --outputdir='$logfile.extra_files_path' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --READ_groups='$input.groups' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #end if + --shared=$otu </command> <inputs> - <conditional name="input"> - <param name="source" type="select" label="Generate principle components for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> + <param name="otu" type="data" format="shared" label="shared - OTU Shared"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" />
--- a/mothur/tools/mothur/get.groups.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/get.groups.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_get_groups" name="Get.groups" version="1.16.0"> +<tool id="mothur_get_groups" name="Get.groups" version="1.19.0"> <description>Select groups</description> <command interpreter="python"> mothur_wrapper.py @@ -46,7 +46,7 @@ <param name="fasta_in" type="data" format="fasta" optional="true" label="fasta - Fasta Sequences"/> <param name="name_in" type="data" format="names" optional="true" label="name - Sequences Name reference"/> <param name="list_in" type="data" format="list" optional="true" label="list - OTU List"/> - <param name="taxonomy_in" type="data" format="taxonomy" optional="true" label="taxonomy - Taxonomy"/> + <param name="taxonomy_in" type="data" format="seq.taxonomy" optional="true" label="taxonomy - Taxonomy"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -61,7 +61,7 @@ <data format="list" name="list_out" label="${tool.name} on ${on_string}: pick.list"> <filter>list_in != None</filter> </data> - <data format="taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"> + <data format="seq.taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"> <filter>taxonomy_in != None</filter> </data> </outputs>
--- a/mothur/tools/mothur/get.lineage.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/get.lineage.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_get_lineage" name="Get.lineage" version="1.16.0"> +<tool id="mothur_get_lineage" name="Get.lineage" version="1.19.0"> <description>Picks by taxon</description> <command interpreter="python"> mothur_wrapper.py @@ -20,7 +20,7 @@ #end if #if $alignreport_in.__str__ != "None" and len($alignreport_in.__str__) > 0: --alignreport=$alignreport_in - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($alignreport_in.__str__)) + ":'" + $alignreport_out.__str__] + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.pick.align.report',$os.path.basename($alignreport_in.__str__)) + ":'" + $alignreport_out.__str__] #end if #if $list_in.__str__ != "None" and len($list_in.__str__) > 0: --list=$list_in @@ -34,7 +34,7 @@ --result=#echo ','.join($results) </command> <inputs> - <param name="taxonomy" type="data" format="taxonomy" label="taxonomy - Taxonomy"/> + <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy"/> <param name="taxons" type="select" size="120" label="Browse Taxons from Taxonomy"> <options from_dataset="taxonomy"> <column name="name" index="1"/> @@ -51,9 +51,8 @@ <param name="dups" type="boolean" truevalue="" falsevalue="--dups=false" checked="true" label="dups - Apply to duplicate names"/> </inputs> <outputs> - <!-- fix format --> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"/> + <data format="seq.taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"/> <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: pick.fasta"> <filter>fasta_in != None</filter> </data> @@ -86,8 +85,13 @@ **Command Documenation** -The get.lineage_ command reads a taxonomy file and a taxon and generates a new file that contains only the sequences in the that are from that taxon. You may also include either a fasta, name, group, list, or align.report file to this command and mothur will generate new files for each of those containing only the selected sequences. +The get.lineage_ command reads a taxonomy_ file and a taxon and generates a new file that contains only the sequences in the that are from that taxon. You may also include either a fasta, name_, group_, list_, or align.report_ file to this command and mothur will generate new files for each of those containing only the selected sequences. +.. _taxonomy: http://www.mothur.org/wiki/Taxonomy_outline +.. _name: http://www.mothur.org/wiki/Name_file +.. _group: http://www.mothur.org/wiki/Group_file +.. _list: http://www.mothur.org/wiki/List_file +.. _align.report: http://www.mothur.org/wiki/Align.seqs .. _get.lineage: http://www.mothur.org/wiki/Get.lineage
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/get.otulist.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,63 @@ +<tool id="mothur_get_otulist" name="Get.otulist" force_history_refresh="True" version="1.19.0"> + <description>Get otus for each distance in a otu list</description> + <command interpreter="python"> + mothur_wrapper.py + ## output {group_file_name}.pick.{label}.groups {list_file_name}.pick.{label}.list + #import re, os.path + --cmd='get.otulist' + --result='^mothur.\S+\.logfile$:'$logfile + --outputdir='$logfile.extra_files_path' + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.((unique|[0-9.]*)\.otu)$:tabular' + #end if + --list=$list_in + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label=$label + #end if + #if $sort.__str__ != "None" and len($sort.__str__) > 0: + --sort=$sort + #end if + </command> + <inputs> + <param name="list_in" type="data" format="list" label="list - OTU List"/> + <param name="label" type="select" multiple="true" label="label - select OTU distance labels" help="By default, uses all if none are selected."> + <options from_dataset="list_in"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + <param name="sort" type="select" label="sort - select the output format"> + <help>If otu is selected the output will be otu number followed by the list of names in that otu. + If name is selected the output will be a sequence name followed by its otu number.</help> + <option value="otu" selected="true">otu</option> + <option value="name">name</option> + </param> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Create a new history dataset for each label list"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The get.otulist_ command parses a list file and creates an .otu file for each distance containing 2 columns. The first column is the OTU number the second column is a list of sequences in that OTU. + +.. _get.otulist: http://www.mothur.org/wiki/Get.otulist + + + </help> +</tool>
--- a/mothur/tools/mothur/get.oturep.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/get.oturep.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,12 +1,14 @@ -<tool id="mothur_get_oturep" name="Get.oturep" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_get_oturep" name="Get.oturep" version="1.19.0" force_history_refresh="True"> <description>Generate a fasta with a representative sequence for each OTU</description> <command interpreter="python"> mothur_wrapper.py --cmd='get.oturep' --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?\.((unique|[0-9.]*)(\S+)\.rep\.fasta)$:fasta','^\S+?\.((unique|[0-9.]*)(\S+)\.rep\.names)$:names' + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.((unique|[0-9.]*)(\S+)\.rep\.fasta)$:fasta','^\S+?\.((unique|[0-9.]*)(\S+)\.rep\.names)$:names' + #end if --fasta=$fasta --list=$otu_list #if $input.source == 'column': @@ -21,8 +23,13 @@ #if $label.__str__ != "None" and len($label.__str__) > 0: --label='$label' #end if - #if $groups.__str__ != "None" and len($groups.__str__) > 0: - --groups=$groups + #if $pick.type == 'yes': + #if $pick.group.__str__ != "None" and len($pick.group.__str__) > 0: + --group=$pick.group + #end if + #if $pick.groups.__str__ != "None" and len($pick.groups.__str__) > 0: + --groups=$pick.groups + #end if #end if #if $sorted.__str__ != "None" and len($sorted.__str__) > 0: --sorted=$sorted @@ -34,26 +41,36 @@ <param name="fasta" type="data" format="fasta" label="fasta - Fasta"/> <param name="otu_list" type="data" format="list" label="list - OTU List"/> <conditional name="input"> - <param name="source" type="select" label="Distance Matrix"> + <param name="source" type="select" label="Distance Matrix Format"> <option value="column">Pairwise Column Distance Matrix</option> <option value="phylip">Phylip Distance Matrix</option> </param> <when value="column"> - <param name="dist" type="data" format="pair.dist" label="column - Distance Matrix"/> - <param name="name" type="data" format="names" label="name - Sequences Name reference"/> + <param name="dist" type="data" format="pair.dist" label="column - Distance Matrix"/> + <param name="name" type="data" format="names" label="name - Sequences Name reference"/> </when> <when value="phylip"> - <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> - <param name="name" type="data" format="names" optional="true" label="name - Names"/> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="name" type="data" format="names" optional="true" label="name - Names"/> </when> </conditional> - <param name="group" type="data" format="groups" optional="true" label="group - Group file for the OTU List"/> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - </options> - </param> + <conditional name="pick"> + <param name="type" type="select" label="Parse a group file into abundant and rare groups?" help=""> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> + <when value="no"/> + <when value="yes"> + <param name="group" type="data" format="groups" label="group - Group file for the OTU List"/> + <param name="groups" type="select" label="groups - Group Selection (all used if none are selected)" multiple="true"> + <options from_dataset="group"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + </when> + </conditional> <!-- pick --> <param name="label" type="select" label="label - OTU Labels" multiple="true"> <options from_dataset="otu_list"> <column name="name" index="0"/> @@ -67,8 +84,8 @@ <option value="size">Bin Size</option> <option value="group">Group</option> </param> - <param name="large" type="boolean" checked="false" truevalue="--large=true" falsevalue="" label="large - Distance Matrix is very Large"/> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Create a new history dataset for each label"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" />
--- a/mothur/tools/mothur/get.otus.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/get.otus.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_get_otus" name="Get.otus" version="1.16.0"> +<tool id="mothur_get_otus" name="Get.otus" version="1.19.0"> <description>Get otus containing sequences from specified groups</description> <command interpreter="python"> mothur_wrapper.py @@ -9,15 +9,18 @@ --group=$group_in --list=$list_in --label=$label - #if $groups.__str__ != "None" and len($groups.__str__) > 0: - --groups=$groups - #end if - #if $accnos.__str__ != "None" and len($accnos.__str__) > 0: - --accnos=$accnos + #if $groupnames.source == 'groups': + #if $groupnames.groups.__str__ != "None" and len($groupnames.groups.__str__) > 0: + --groups=$groupnames.groups + #end if + #else + #if $groupnames.accnos.__str__ != "None" and len($groupnames.accnos.__str__) > 0: + --accnos=$groupnames.accnos + #end if #end if #set results = ["'^mothur.\S+\.logfile$:'" + $logfile.__str__] - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.' + $label.__str__ + '.\2',$os.path.basename($group_in.__str__)) + ":'" + $group_out.__str__] - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.'+ $label.__str__ + '.\2',$os.path.basename($list_in.__str__)) + ":'" + $list_out.__str__] + #set results = $results + ["'" + $re.sub(r'^(.*)\.(.*?)',r'\1.pick.' + $label.__str__ + r'.\2',$os.path.basename($group_in.__str__)) + ":'" + $group_out.__str__] + #set results = $results + ["'" + $re.sub(r'^(.*)\.(.*?)',r'\1.pick.'+ $label.__str__ + r'.\2',$os.path.basename($list_in.__str__)) + ":'" + $list_out.__str__] --result=#echo ','.join($results) </command> <inputs> @@ -29,14 +32,25 @@ <column name="value" index="0"/> </options> </param> - <param name="groups" type="select" optional="true" label="groups - Pick groups to include" multiple="true"> - <options from_dataset="group_in"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - <param name="accnos" type="data" format="accnos" optional="true" label="accnos - Group Names from your history"/> + <conditional name="groupnames"> + <param name="source" type="select" label="Select Group Names from"> + <option value="groups">A List of Group Names</option> + <option value="accnos">A History Group Name Accnos Dataset</option> + </param> + <when value="groups"> + <param name="groups" type="select" label="groups - Pick groups to include" multiple="true" force_select="true"> + <help>At least one group must be selected</help> + <options from_dataset="group_in"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + </when> + <when value="accnos"> + <param name="accnos" type="data" format="accnos" optional="true" label="accnos - Group Names from your history"/> + </when> + </conditional> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -59,8 +73,9 @@ **Command Documenation** -The get.otus_ command selects otus containing sequences from a specific group or set of groups. +The get.otus_ command selects otus from a list_ containing sequences from a specific group or set of groups. +.. _list: http://www.mothur.org/wiki/List_file .. _get.otus: http://www.mothur.org/wiki/Get.otus
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/get.rabund.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,58 @@ +<tool id="mothur_get_rabund" name="Get.rabund" version="1.19.0"> + <description>Get rabund from a otu list or sabund</description> + <command interpreter="python"> + mothur_wrapper.py + --cmd='get.rabund' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.rabund$:'$rabund + --outputdir='$logfile.extra_files_path' + #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('list').__class__): + --list=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sabund').__class__): + --sabund=$otu + #end if + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label=$label + #end if + $sorted + </command> + <inputs> + <param name="otu" type="data" format="list,sabund" label="list,sabund - List or Sabund"/> + <param name="label" type="select" multiple="true" label="label - select OTU distance labels" help="(all used if none are selected)"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + <param name="sorted" type="boolean" checked="false" truevalue="--sorted=true" falsevalue="" label="sorted - sort by abundance" + help="By default the data in the rabund file the same order as the OTUs in input, select to sort by abundance."/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="rabund" name="rabund" label="${tool.name} on ${on_string}: rabund (Rank Abundance)"/> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The get.rabund_ command generates an rabund_ file from a list_ or sabund_ file. + +.. _rabund: http://www.mothur.org/wiki/Rabund_file +.. _list: http://www.mothur.org/wiki/List_file +.. _sabund: http://www.mothur.org/wiki/Sabund_file +.. _get.rabund: http://www.mothur.org/wiki/Get.rabund + + + </help> +</tool>
--- a/mothur/tools/mothur/get.relabund.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/get.relabund.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,76 +1,41 @@ -<tool id="mothur_get_relabund" name="Get.relabund" version="1.16.0"> +<tool id="mothur_get_relabund" name="Get.relabund" version="1.19.0"> <description>Calculate the relative abundance of each otu</description> <command interpreter="python"> mothur_wrapper.py --cmd='get.relabund' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.relabund$:'$relabund --outputdir='$logfile.extra_files_path' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if + --shared=$otu + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups=$groups #end if #if $scale.__str__ != "None" and len($scale.__str__) > 0: --scale=$scale #end if </command> <inputs> - <conditional name="input"> - <param name="source" type="select" label="Get Relative abundance for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> + <param name="otu" type="data" format="shared" label="shared - OTU Shared" + help="Use Make.shared to create a shared file from a list and a group file"/> + <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> <param name="scale" type="select" label="scale - Scale by"> <option value="">Use default</option> - <option value="totalgroup">Total Groups</option> + <option value="totalgroup" selected="true">Total Groups</option> <option value="totalotu">Total OTUs</option> <option value="averagegroup">Average Groups</option> <option value="averageotu">Average OTUs</option> @@ -96,8 +61,9 @@ **Command Documenation** -The get.relabund_ command calculates the relative abundance of each otu in a sample. It outputs a .relabund file. +The get.relabund_ command calculates the relative abundance of each otu in a sample from a shared_ file. It outputs a .relabund_ file. +.. _shared: http://www.mothur.org/wiki/Shared_file .. _get.relabund: http://www.mothur.org/wiki/Get.relabund </help>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/get.sabund.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,55 @@ +<tool id="mothur_get_sabund" name="Get.sabund" version="1.19.0"> + <description>Get sabund from a otu list or rabund</description> + <command interpreter="python"> + mothur_wrapper.py + --cmd='get.sabund' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.sabund$:'$sabund + --outputdir='$logfile.extra_files_path' + #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('list').__class__): + --list=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('rabund').__class__): + --rabund=$otu + #end if + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label=$label + #end if + </command> + <inputs> + <param name="otu" type="data" format="list,rabund" label="list,rabund - List or Rabund"/> + <param name="label" type="select" multiple="true" label="label - select OTU distance labels" help="(all used if none are selected)"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="sabund" name="sabund" label="${tool.name} on ${on_string}: sabund (Species Abundance)"/> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The get.sabund_ command generates an sabund_ file from a list_ or rabund_ file. + +.. _sabund: http://www.mothur.org/wiki/Sabund_file +.. _list: http://www.mothur.org/wiki/List_file +.. _rabund: http://www.mothur.org/wiki/Rabund_file +.. _get.sabund: http://www.mothur.org/wiki/Get.sabund + + + </help> +</tool>
--- a/mothur/tools/mothur/get.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/get.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_get_seqs" name="Get.seqs" version="1.16.0"> +<tool id="mothur_get_seqs" name="Get.seqs" version="1.19.0"> <description>Picks sequences by name</description> <command interpreter="python"> mothur_wrapper.py @@ -47,7 +47,7 @@ <param name="group_in" type="data" format="groups" optional="true" label="group - Sequences Groups"/> <param name="alignreport_in" type="data" format="align.report" optional="true" label="alignreport - Align Report"/> <param name="list_in" type="data" format="list" optional="true" label="list - OTU List"/> - <param name="taxonomy_in" type="data" format="taxonomy" optional="true" label="taxonomy - Taxonomy"/> + <param name="taxonomy_in" type="data" format="seq.taxonomy" optional="true" label="taxonomy - Taxonomy"/> <param name="dups" type="boolean" truevalue="" falsevalue="--dups=false" checked="true" label="dups - Apply to duplicates"/> </inputs> <outputs> @@ -72,7 +72,7 @@ <data format="list" name="list_out" label="${tool.name} on ${on_string}: pick.list"> <filter>list_in != None</filter> </data> - <data format="taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"> + <data format="seq.taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"> <filter>taxonomy_in != None</filter> </data> </outputs> @@ -92,8 +92,14 @@ **Command Documenation** -The get.seqs_ command takes a list of sequence names and either a fasta, name, group, list, or align.report file to generate a new file that contains only the sequences in the list. This command may be used in conjunction with the list.seqs command to help screen a sequence collection. +The get.seqs_ command takes a list of sequence names and either a fasta, name_, group_, list_, align.report_ or taxonomy_ file to generate a new file that contains only the sequences in the list. This command may be used in conjunction with the list.seqs_ command to help screen a sequence collection. +.. _name: http://www.mothur.org/wiki/Name_file +.. _group: http://www.mothur.org/wiki/Group_file +.. _list: http://www.mothur.org/wiki/List_file +.. _align.report: http://www.mothur.org/wiki/Align.seqs +.. _taxonomy: http://www.mothur.org/wiki/Taxonomy_outline +.. _list.seqs: http://www.mothur.org/wiki/list.seqs .. _get.seqs: http://www.mothur.org/wiki/Get.seqs
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/get.sharedseqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,106 @@ +<tool id="mothur_get_sharedseqs" name="Get.sharedseqs" version="1.19.0" force_history_refresh="True"> + <description>Get shared sequences at each distance from list and group</description> + <command interpreter="python"> + mothur_wrapper.py + #import re, os.path + --cmd='get.sharedseqs' + --result='^mothur.\S+\.logfile$:'$logfile + --outputdir='$logfile.extra_files_path' + --list=$list + --group=$group + #set datasets = ["'^\S+?\.((unique|[0-9.]*)(\S+)\.shared.seqs)$:tabular'"] + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' + #end if + #if $seqs_from.selection == 'unique': + #if $seqs_from.groups.__str__ != "None" and len($seqs_from.groups.__str__) > 0: + --unique=$seqs_from.groups + #end if + #elif $seqs_from.selection == 'shared': + #if $seqs_from.groups.__str__ != "None" and len($seqs_from.groups.__str__) > 0: + --shared=$seqs_from.groups + #end if + #end if + #if $fasta.__str__ != "None" and len($fasta.__str__) > 0: + --fasta=$fasta + #set datasets = $datasets + ["'^\S+?\.((unique|[0-9.]*)(\S+)\.shared.fasta)$:fasta'"] + #end if + #if $output.__str__ != "None" and len($output.__str__) > 0: + --output=$output + #set datasets = $datasets + ["'^\S+?\.((unique|[0-9.]*)(\S+)\.accnos)$:accnos'"] + #end if + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets=#echo ','.join($datasets) + #end if + </command> + <inputs> + <param name="list" type="data" format="list" label="list - OTU List"/> + <param name="group" type="data" format="groups" label="group - "/> + <param name="label" type="select" optional="true" label="label - Select OTU Labels to include" multiple="true" + help="By default all are included if no selection is made."> + <options from_dataset="list"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + <param name="fasta" type="data" format="fasta" optional="true" label="fasta - Dataset"/> + + <conditional name="seqs_from"> + <param name="selection" type="select" label="Select Groups" help=""> + <option value="all" selected="true">None (use all groups)</option> + <option value="unique">OTUs that contain ONLY sequences from the selected groups</option> + <option value="shared">OTUs that contain sequences from the selected groups</option> + </param> + <when value="all"/> + <when value="unique"> + <param name="groups" type="select" label="unique - Group to analyze" multiple="true"> + <options from_dataset="group"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + </when> + <when value="shared"> + <param name="groups" type="select" label="shared - Groups to analyze" multiple="true"> + <options from_dataset="group"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + </when> + </conditional> <!-- seqs_from --> + + <param name="output" type="select" label="output - select the output format" help="accnos can be used with get.seqs, list.seqs and remove.seqs"> + <option value="" selected="true">default: (name group bin_number)</option> + <option value="accnos">accnos (name)</option> + </param> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Create a new history dataset for each label"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The get.sharedseqs_ command takes a list and group file and outputs a *.shared.seqs file for each distance. This is useful for those cases where you might be interested in identifying sequences that are either unique or shared by specific groups, which you could then classify. + +.. _get.sharedseqs: http://www.mothur.org/wiki/Get.sharedseqs + + </help> +</tool>
--- a/mothur/tools/mothur/hcluster.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/hcluster.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_hcluster" name="Hcluster" version="1.16.0"> +<tool id="mothur_hcluster" name="Hcluster" version="1.19.0"> <description>Assign sequences to OTUs (Operational Taxonomic Unit)</description> <command interpreter="python"> mothur_wrapper.py @@ -18,10 +18,10 @@ --method=$method #end if #if float($cutoff.__str__) > 0.0: - --READ_cutoff=$cutoff + --cutoff=$cutoff #end if #if len($precision.__str__) > 0: - --READ_precision=$precision + --precision=$precision #end if $hard $sorted @@ -58,9 +58,9 @@ </param> <param name="method" type="select" label="method - Select a Clustering Method" help=""> - <option value="furthest" selected="true">Furthest neighbor</option> + <option value="average" selected="true">Average neighbor</option> <option value="nearest">Nearest neighbor</option> - <option value="average">Average neighbor</option> + <option value="furthest">Furthest neighbor</option> <option value="weighted">Weighted</option> </param> <param name="sorted" type="boolean" checked="false" truevalue="--sorted=true" falsevalue="" label="sorted - The input matrix is already sorted" @@ -91,9 +91,15 @@ **Command Documenation** -The cluster_ command assign sequences to OTUs (Operational Taxonomy Unit). +The hcluster_ command assign sequences to OTUs (Operational Taxonomy Unit). The assignment is based on a phylip-formatted_distance_matrix_ or a column-formatted_distance_matrix_ and name_ file. It generates a list_, a sabund_ (Species Abundance), and a rabund_ (Relative Abundance) file. -.. _cluster: http://www.mothur.org/wiki/Cluster +.. _phylip-formatted_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _column-formatted_distance_matrix: http://www.mothur.org/wiki/Column-formatted_distance_matrix +.. _name: http://www.mothur.org/wiki/Name_file +.. _list: http://www.mothur.org/wiki/List_file +.. _rabund: http://www.mothur.org/wiki/Rabund_file +.. _sabund: http://www.mothur.org/wiki/Sabund_file +.. _hcluster: http://www.mothur.org/wiki/Hcluster </help>
--- a/mothur/tools/mothur/heatmap.bin.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/heatmap.bin.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,30 +1,31 @@ -<tool id="mothur_heatmap_bin" name="Heatmap.bin" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_heatmap_bin" name="Heatmap.bin" version="1.19.0" force_history_refresh="True"> <description>Generate a heatmap for OTUs</description> <command interpreter="python"> mothur_wrapper.py --cmd='heatmap.bin' --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?\.((\S+)\.(unique|[0-9.]*)\.heatmap\.bin\.svg)$:svg' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_relabund=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.((\S+)\.(unique|[0-9.]*)\.heatmap\.bin\.svg)$:svg' #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: + #if isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__): + --shared=$input.otu + #elif isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('rabund').__class__): + --rabund=$input.otu + #elif isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sabund').__class__): + --sabund=$input.otu + #elif isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('list').__class__): + --list=$input.otu + #elif isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('relabund').__class__): + --relabund=$input.otu + #end if + #if $input.has_groups != 'no' and $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: --groups=$input.groups #end if + #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: + --label='$input.label' + #end if #if $scale.__str__ != "None" and len($scale.__str__) > 0: --scale='$scale' #end if @@ -39,42 +40,54 @@ #end if </command> <inputs> - <!-- get.relabund relabund type should also work --> - <conditional name="input"> - <param name="source" type="select" label="Generate Heatmap for"> - <option value="similarity">OTU list</option> - <option value="relabund">OTU Relative Abundance</option> + <conditional name="input"> + <param name="has_groups" type="select" label="Generate Heatmap for"> + <option value="default">shared or relabund</option> + <option value="no">list, rabund, sabund</option> + <option value="yes">list, rabund, sabund with groups</option> </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group) - Group file for the OTU List"/> + <when value="default"> + <param name="otu" type="data" format="shared,relabund" label="shared,relabund - OTU List"/> + <param name="groups" type="select" label="groups - Groups to condider" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> <param name="label" type="select" label="label - OTU Labels" multiple="true"> <options from_dataset="otu"> <column name="name" index="0"/> <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> </options> </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> + </when> + <when value="no"> + <param name="otu" type="data" format="list,rabund,sabund" label="list,rabund,sabund - OTU List"/> + <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + </when> + <when value="yes"> + <param name="otu" type="data" format="list,rabund,sabund" label="list,rabund,sabund - OTU List"/> + <param name="otu_group" type="data" format="groups" label="read.otu(group) - Group file for the OTU List"/> + <param name="groups" type="select" label="groups - Groups to include" multiple="true"> <options from_dataset="otu_group"> <column name="name" index="1"/> <column name="value" index="1"/> <filter type="unique_value" name="unq_grp" column="1" /> </options> </param> - </when> - <when value="relabund"> - <param name="otu" type="data" format="relabund" label="read.otu(relabund=) - OTU Relative Abundance"/> <param name="label" type="select" label="label - OTU Labels" multiple="true"> <options from_dataset="otu"> <column name="name" index="0"/> <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> + <filter type="unique_value" name="unq_lbl" column="0" /> </options> </param> </when> @@ -88,11 +101,12 @@ <param name="sorted" type="select" label="sorted - Sort heatmap"> <option value="">By shared</option> <option value="none">Don't sort</option> - <option value="totalotu">By Total OTUs</option> - <option value="totalgroup">By Total Groups</option> + <option value="topotu">By Total OTUs</option> + <option value="topgroup">By Total Groups</option> </param> <param name="numotu" type="integer" value="0" label="numotu - Limit the number of OTUs displayed (ignored if 0)"/> <param name="fontsize" type="integer" value="24" label="fontsize - Fontsize (default is 24)"/> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Create a new history dataset for each image"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -113,8 +127,10 @@ **Command Documenation** -The heatmap.bin_ command generates a heat map from data provided in either a .list or a .shared file. +The heatmap.bin_ command generates a heat map from data provided in either a list_ or a shared_ file. +.. _list: http://www.mothur.org/wiki/List_file +.. _shared: http://www.mothur.org/wiki/Shared_file .. _heatmap.bin: http://www.mothur.org/wiki/Heatmap.bin </help>
--- a/mothur/tools/mothur/heatmap.sim.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/heatmap.sim.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,30 +1,22 @@ -<tool id="mothur_heatmap_sim" name="Heatmap.sim" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_heatmap_sim" name="Heatmap.sim" version="1.19.0" force_history_refresh="True"> <description>Generate a heatmap for pariwise similarity</description> <command interpreter="python"> mothur_wrapper.py --cmd='heatmap.sim' - --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?\.((unique|[0-9.]*)(\S+)\.heatmap\.sim\.svg)$:svg' - #if $input.source == 'similarity': - --READ_cmd='read.otu' - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' + #if $as_datasets.__str__ == "yes": + #if $input.source == 'shared': + --result='^mothur.\S+\.logfile$:'$logfile + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.((unique|[0-9.]*)(\S+)\.heatmap\.sim\.svg)$:svg' + #else: + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.heatmap\.sim\.svg$:'$heatmap #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --label='$input.label' - #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups - #end if - #if $input.calc.__str__ != "None" and len($input.calc.__str__) > 0: - --calc='$input.calc' - #end if - #elif $input.source == 'shared': - --READ_cmd='read.otu' - --READ_shared=$input.otu + #else: + --result='^mothur.\S+\.logfile$:'$logfile + #end if + #if $input.source == 'shared': + --shared=$input.otu #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: --label='$input.label' #end if @@ -39,45 +31,15 @@ --name=$input.name #elif $input.source == 'phylip': --phylip=$input.dist - #if $input.name.__str__ != "None" and len($input.name.__str__) > 0: - --name=$input.name - #end if #end if </command> <inputs> - <!-- get.relabund relabund type should also work --> <conditional name="input"> <param name="source" type="select" label="Generate Heatmap for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - <option value="column">Pairwise Column Distance Matrix</option> - <option value="phylip">Phylip Distance Matrix</option> + <option value="shared">shared - Sample Similarity - OTU Shared</option> + <option value="phylip">phylip - Phylip Distance Matrix</option> + <option value="column">colomn - Pairwise Column Distance Matrix</option> </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to include" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - <param name="calc" type="select" label="calc - Calculators (Uses defaults if none selected)" multiple="true"> - <options from_file="mothur_calculators.loc"> - <column name="mult2" index="2"/> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="static_value" name="mult2" column="2" value="shar" /> - </options> - </param> - </when> <when value="shared"> <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> <param name="label" type="select" label="label - OTU Labels" multiple="true"> @@ -94,6 +56,14 @@ <filter type="unique_value" name="unq_grp" column="1" /> </options> </param> + <param name="calc" type="select" label="calc - Calculators (Uses defaults if none selected)" multiple="true"> + <options from_file="mothur_calculators.loc"> + <column name="mult2" index="2"/> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="static_value" name="mult2" column="2" value="shar" /> + </options> + </param> </when> <when value="column"> <param name="dist" type="data" format="pair.dist" label="column - Distance Matrix"/> @@ -101,12 +71,15 @@ </when> <when value="phylip"> <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> - <param name="name" type="data" format="names" optional="true" label="name - Names"/> </when> </conditional> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Create a new history dataset for each image"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="svg" name="heatmap" label="${tool.name} on ${on_string}: heatmap.sim.svg"> + <filter>as_datasets != 'true' and input['source'] != 'shared'</filter> + </data> </outputs> <requirements> <requirement type="binary">mothur</requirement> @@ -124,8 +97,12 @@ **Command Documenation** -The heatmap.sim_ command generates a heat map from data provided in either a .list or a .shared file. +The heatmap.sim_ command generates a heat map from data provided in either a shared_ file, a phylip_ distance matrix, or a column_ distance matrix and a name_ file. For calc parameter choices see: http://www.mothur.org/wiki/Calculators +.. _shared: http://www.mothur.org/wiki/Shared_file +.. _phylip: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _column: http://www.mothur.org/wiki/Column-formatted_distance_matrix +.. _name: http://www.mothur.org/wiki/Name_file .. _heatmap.sim: http://www.mothur.org/wiki/Heatmap.sim </help>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/homova.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,62 @@ +<tool id="mothur_homova" name="Homova" version="1.19.0"> + <description>Homogeneity of molecular variance</description> + <command interpreter="python"> + mothur_wrapper.py + --cmd='homova' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.homova$:'$homova + --outputdir='$logfile.extra_files_path' + --phylip=$dist + --design=$design + #if int($iters.__str__) > 0: + --iters=$iters + #end if + #if float($alpha.__str__) > 0.0: + --alpha=$alpha + #end if + </command> + <inputs> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="design" type="data" format="tabular" label="design - assign groups to new grouping" + help="design has 2 columns: group(col 1) and grouping(col 2) (separated by a TAB character)"/> + <param name="alpha" type="float" optional="true" value="0.05" label="alpha - acceptable stopping precision (default 0.05)"/> + <param name="iters" type="integer" value="1000" label="iters - Number of random configuration to try (default 1000)"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="tabular" name="homova" label="${tool.name} on ${on_string}: homova"/> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The homova_ command calculates the homogeneity of molecular variance (HOMOVA) from a phylip_distance_matrix_, a nonparametric analog of Bartlett's test for homo- geneity of variance, which has been used in population genetics to test the hypothesis that the genetic diversity within two or more populations is homogeneous. + +A design file partitions a list of names into groups. It is a tab-delimited file with 2 columns: name and group, e.g. : + ======= ======= + duck bird + cow mammal + pig mammal + goose bird + cobra reptile + ======= ======= + +The Make_Design tool can construct a design file from a Mothur dataset that contains group names. + +.. _phylip_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _homova: http://www.mothur.org/wiki/Homova + + + </help> +</tool>
--- a/mothur/tools/mothur/indicator.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/indicator.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_indicator" name="Indicator" version="1.16.0"> +<tool id="mothur_indicator" name="Indicator" version="1.19.0"> <description>Identify indicator "species" for nodes on a tree</description> <command interpreter="python"> mothur_wrapper.py @@ -64,8 +64,9 @@ **Command Documenation** -The indicator_ command reads a shared or relabund file and a tree file, and outputs a .indicator.tre and .indicator.summary file. The new tree contains labels at each internal node. The label is the node number so you can relate the tree to the summary file. The summary file lists the indicator value for each OTU for each node. +The indicator_ command reads a shared_ or relabund file and a tree file, and outputs a .indicator.tre and .indicator.summary file. The new tree contains labels at each internal node. The label is the node number so you can relate the tree to the summary file. The summary file lists the indicator value for each OTU for each node. +.. _shared: http://www.mothur.org/wiki/Shared_file .. _indicator: http://www.mothur.org/wiki/Indicator
--- a/mothur/tools/mothur/libshuff.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/libshuff.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,21 +1,19 @@ -<tool id="mothur_libshuff" name="Libshuff" version="1.16.0"> +<tool id="mothur_libshuff" name="Libshuff" version="1.19.0"> <description>Cramer-von Mises tests communities for the same structure</description> <command interpreter="python"> mothur_wrapper.py --cmd='libshuff' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.libshuff\.summary$:'$summary,'^\S+\.libshuff\.coverage$:'$coverage --outputdir='$logfile.extra_files_path' - --READ_cmd='read.dist' - #if $matrix.format == "column": - --READ_column=$matrix.dist - --READ_name=$matrix.name - #elif $matrix.format == "phylip": - --READ_phylip=$matrix.dist + --phylip=$dist + --group=$group + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups=$groups #end if - --READ_group=$group #if len($iters.__str__) > 0: --iters=$iters #end if + $sim #if $form == "discrete": #if 1.0 >= float($form.step.__str__) > 0.0: --step=$form.step @@ -26,22 +24,17 @@ #end if </command> <inputs> - <conditional name="matrix"> - <param name="format" type="select" label="Select a Distance Matrix Format" help=""> - <option value="column">Pairwise Column Matrix</option> - <option value="phylip">Phylip Distance Matrix</option> - </param> - <when value="column"> - <param name="dist" type="data" format="pair.dist" label="read.dist(column=) - Distance Matrix"/> - <param name="name" type="data" format="names" label="read.dist(name) - Sequences Name reference"/> - </when> - <when value="phylip"> - <param name="dist" type="data" format="lower.dist,square.dist" label="read.dist(phylip=) - Distance Matrix"/> - </when> - </conditional> - <param name="group" type="data" format="groups" label="read.dist(group=) - Groups"/> - <!-- ? conditional - to hide complexity --> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="group" type="data" format="groups" label="group - Groups"/> + <param name="groups" type="select" label="groups - Groups to condider" multiple="true"> + <options from_dataset="group"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> <param name="iters" type="integer" value="10000" label="iters - Number of iterations to try (default 10000)"/> + <param name="sim" type="boolean" checked="false" truevalue="--sim=true" falsevalue="" label="sim - Matrix values are Similary instead of Distance" help=""/> <conditional name="form"> <param name="form" type="select" label="form - Select a Clustering Method" help=""> <option value="integral" selected="true">Integral</option>
--- a/mothur/tools/mothur/list.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/list.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,5 +1,5 @@ -<tool id="mothur_list_seqs" name="List.seqs" version="1.16.0"> - <description>Lists the names of the sequences</description> +<tool id="mothur_list_seqs" name="List.seqs" version="1.19.0"> + <description>Lists the names (accnos) of the sequences</description> <command interpreter="python"> mothur_wrapper.py --cmd='list.seqs' @@ -9,7 +9,7 @@ --fasta=$search.input #elif $search.type == "name": --name=$search.input - #else if search.type == "group": + #else if $search.type == "group": --group=$search.input #elif $search.type == "alignreport": --alignreport=$search.input @@ -45,7 +45,7 @@ <param name="input" type="data" format="list" label="list - OTU List"/> </when> <when value="taxonomy"> - <param name="input" type="data" format="taxonomy" label="taxonomy - Sequence Taxonomy"/> + <param name="input" type="data" format="seq.taxonomy" label="taxonomy - Sequence Taxonomy"/> </when> </conditional> </inputs> @@ -70,8 +70,13 @@ **Command Documenation** -The list.seqs_ command writes out the names of the sequences found within a fasta, name, group, list, or align.report file. +The list.seqs_ command writes out the names of the sequences found within a fasta, name_, group_, list_, align.report_ or taxonomy_ file. +.. _name: http://www.mothur.org/wiki/Name_file +.. _group: http://www.mothur.org/wiki/Group_file +.. _list: http://www.mothur.org/wiki/List_file +.. _align.report: http://www.mothur.org/wiki/Align.seqs +.. _taxonomy: http://www.mothur.org/wiki/Taxonomy_outline .. _list.seqs: http://www.mothur.org/wiki/list.seqs
--- a/mothur/tools/mothur/make.design.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/make.design.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_make_design" name="Make Design" version="1.16.0" > +<tool id="mothur_make_design" name="Make Design" version="1.19.0" > <description>Assign groups to Sets</description> <command> cat $generated_design > $design </command>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/make.fastq.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,41 @@ +<tool id="mothur_make_fastq" name="Make.fastq" version="1.19.0"> + <description>Convert fasta and quality to fastq</description> + <command interpreter="python"> + mothur_wrapper.py + --cmd='fastq.info' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.fastq$:'$fastq + --outputdir='$logfile.extra_files_path' + --fasta=$fasta + --qfile=$qfile + </command> + <inputs> + <param name="fasta" type="data" format="fasta" label="fasta - Fasta Sequence file"/> + <param name="qfile" type="data" format="qual" label="qfile - Sequence Quality file"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="fastq" name="fastq" label="${tool.name} on ${on_string}: fastq"/> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The fastq.info_ command reads a fasta file and quality file and creates a fastq. + + +.. _fastq.info: http://www.mothur.org/wiki/Make.fastq + + </help> +</tool>
--- a/mothur/tools/mothur/make.group.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/make.group.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_make_files" name="Make.group" version="1.16.0"> +<tool id="mothur_make_files" name="Make.group" version="1.19.0"> <description>Make a group file</description> <command interpreter="python"> mothur_wrapper.py @@ -36,8 +36,9 @@ **Command Documenation** -The make.group_ command reads a fasta file or series of fasta files and creates a group file. +The make.group_ command reads a fasta file or series of fasta files and creates a group_ file. +.. _group: http://www.mothur.org/wiki/Group_file .. _make.group: http://www.mothur.org/wiki/Make.group
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/make.shared.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,75 @@ +<tool id="mothur_make_shared" name="Make.shared" version="1.19.0" force_history_refresh="True"> + <description>Make a shared file from a list and a group</description> + <command interpreter="python"> + mothur_wrapper.py + #import re, os.path + --cmd='make.shared' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.shared$:'$shared + --outputdir='$logfile.extra_files_path' + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.((\S+)\.rabund)$:rabund' + #end if + --list=$list + --group=$group + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' + #end if + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --unique=$groups + #end if + #if $ordergroup.__str__ != "None" and len($ordergroup.__str__) > 0: + --ordergroup=$ordergroup + #end if + </command> + <inputs> + <param name="list" type="data" format="list" label="list - OTU List"/> + <param name="group" type="data" format="groups" label="group - "/> + <param name="label" type="select" optional="true" label="label - Select OTU Labels to include" multiple="true" + help="By default all are included if no selection is made."> + <options from_dataset="list"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + <param name="groups" type="select" label="groups - Groups to include" multiple="true"> + <options from_dataset="group"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + <param name="ordergroup" type="data" format="groups" optional="true" label="ordergroup - one column list of group names in desired order"/> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Create a new history dataset for each group rabund"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="shared" name="shared" label="${tool.name} on ${on_string}: shared" /> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The make.shared_ command takes a list_ and a group_ file and outputs a shared_ file, as well as a rabund_ file for each group. + + +.. _list: http://www.mothur.org/wiki/List_file +.. _group: http://www.mothur.org/wiki/Group_file +.. _shared: http://www.mothur.org/wiki/Shared_file +.. _rabund: http://www.mothur.org/wiki/Rabund_file +.. _make.shared: http://www.mothur.org/wiki/Make.shared + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/mantel.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,52 @@ +<tool id="mothur_mantel" name="Mantel" version="1.19.0"> + <description>Mantel correlation coefficient between two matrices.</description> + <command interpreter="python"> + mothur_wrapper.py + --cmd='mantel' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.mantel$:'$mantel + --outputdir='$logfile.extra_files_path' + --phylip=$dist + --phylip2=$dist2 + --method=$method + #if int($iters.__str__) > 0: + --iters=$iters + #end if + </command> + <inputs> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="dist2" type="data" format="lower.dist,square.dist" label="phylip2 - Distance Matrix"/> + <param name="method" type="select" optional="true" label="method - pearson, spearman, or kendall. Default: pearson" > + <option value="pearson" selected="true">pearson</option> + <option value="spearman">spearman</option> + <option value="kendall">kendall</option> + </param> + <param name="iters" type="integer" value="1000" label="iters - Number of random configuration to try (default 1000)"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="tabular" name="mantel" label="${tool.name} on ${on_string}: mantel"/> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The mantel_ command calculates the Mantel correlation coefficient between two matrices_. + +.. _matrices: //www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _mantel: http://www.mothur.org/wiki/Mantel + + + </help> +</tool>
--- a/mothur/tools/mothur/merge.files.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/merge.files.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_merge_files" name="Merge.files" version="1.16.0"> +<tool id="mothur_merge_files" name="Merge.files" version="1.19.0"> <description>Merge data</description> <command interpreter="python"> mothur_wrapper.py
--- a/mothur/tools/mothur/merge.groups.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/merge.groups.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_merge_groups" name="Merge.groups" version="1.16.0" > +<tool id="mothur_merge_groups" name="Merge.groups" version="1.19.0" > <description>Merge groups in a shared file</description> <command interpreter="python"> mothur_wrapper.py @@ -92,8 +92,20 @@ **Command Documenation** -The merge.groups_ command reads a shared file and a design file and merges the groups in the shared file that are in the same grouping in the design file. +The merge.groups_ command reads a shared_ file and a design file and merges the groups in the shared file that are in the same grouping in the design file. +A design file partitions a list of names into groups. It is a tab-delimited file with 2 columns: name and group, e.g. : + ======= ======= + duck bird + cow mammal + pig mammal + goose bird + cobra reptile + ======= ======= + +The Make_Design tool can construct a design file from a Mothur dataset that contains group names. + +.. _shared: http://www.mothur.org/wiki/Shared_file .. _merge.groups: http://www.mothur.org/wiki/Merge.groups </help>
--- a/mothur/tools/mothur/metastats.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/metastats.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,30 +1,21 @@ -<tool id="mothur_metastats" name="Metastats" version="1.16.0"> +<tool id="mothur_metastats" name="Metastats" version="1.19.0" force_history_refresh="True" > <description>generate principle components plot data</description> <command interpreter="python"> mothur_wrapper.py --cmd='metastats' - --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.metastats$:'$metastats + --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --READ_groups='$input.groups' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --READ_groups='$input.groups' - #end if + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.((unique|[0-9.]*)(\..*?)+\.metastats)$:txt' + #end if + --shared=$otu + --design=$design + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' + #end if + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups='$groups' #end if #if int($iters.__str__) > 0: --iters=$iters @@ -32,59 +23,29 @@ #if 1 >= $threshold >= 0: --threshold=$threshold #end if - #if $design.__str__ != "None" and len($design.__str__) > 0: - --design=$design - #if $sets.__str__ != "None" and len($sets.__str__) > 0: - --sets=$sets - #end if + #if $sets.__str__ != "None" and len($sets.__str__) > 0: + --sets=$sets #end if --processors=2 </command> <inputs> - <conditional name="input"> - <param name="source" type="select" label="Generate metastats for OTUs from"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> - <param name="iters" type="integer" value="1000" label="iters - Number of randomizations (default 1000)"/> - <param name="threshold" type="float" value="0.05" label="threshold - significance level to reject null hypotheses (ignored if < 0)"/> + <param name="otu" type="data" format="shared" label="shared - OTU Shared"/> + <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> <param name="design" type="data" format="tabular" label="design - assign groups to new grouping" - help="design has 2 columns: group(col 1) and grouping(col 2) (separated by a TAB character)"/> + help="design has 2 columns: group(col 1) and grouping(col 2) (separated by a TAB character) use make.design"/> <param name="sets" type="select" label="sets - group sets to analyze" multiple="true"> <options from_dataset="design"> <column name="name" index="1"/> @@ -92,10 +53,12 @@ <filter type="unique_value" name="unq_grp" column="1" /> </options> </param> + <param name="iters" type="integer" value="1000" label="iters - Number of randomizations (default 1000)"/> + <param name="threshold" type="float" value="0.05" label="threshold - significance level to reject null hypotheses (ignored if < 0)"/> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Create a new history datasets for each label"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="text" name="metastats" label="${tool.name} on ${on_string}: metastats" /> </outputs> <requirements> <requirement type="binary">mothur</requirement>
--- a/mothur/tools/mothur/mothur_wrapper.py Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/mothur_wrapper.py Tue Jun 07 17:05:08 2011 -0400 @@ -4,7 +4,7 @@ http://www.mothur.org/ Supports mothur version -mothur v.1.15.0 +mothur v.1.17.0 Class encapsulating Mothur galaxy tool. Expect each invocation to include: @@ -46,7 +46,7 @@ debug = False #debug = True -max_processors = 1 +max_processors = 2 def stop_err( msg ): sys.stderr.write( "%s\n" % msg ) @@ -54,6 +54,8 @@ def __main__(): # tranform the logfile into html + # add extra file ouput + # add object tags for svg files def logfile_to_html(logfile_path,htmlfile_path,tmp_input_dir_name,tmp_output_dir_name,title="Mothur Logfile"): if debug: print >> sys.stdout, 'logfile_to_html %s -> %s' % (logfile_path, htmlfile_path) if debug: print >> sys.stdout, 'logfile_to_html input_dir: %s' % tmp_input_dir_name @@ -69,10 +71,18 @@ continue elif line.find('put directory to ') >= 0: continue + elif line.startswith('Mothur\'s directories:') : + continue + elif line.startswith('outputDir=') : + continue elif line.startswith('Type ') : continue elif line.find(tmp_output_dir_name) >= 0: - line = re.sub(out_pat,'<a href="\\1">\\1</a>',line) + # if debug: print >> sys.stdout, 'logfile_to_html #%s#' % line + if line.strip().endswith('.svg'): + line = re.sub(out_pat,' <object id="object" type="image/svg+xml" data="\\1">\\1</object> <br><a href="\\1">\\1</a> <hr/>',line) + else: + line = re.sub(out_pat,'<a href="\\1">\\1</a>',line) elif line.find(tmp_input_dir_name) >= 0: line = re.sub(in_pat,'\\1',line) html.write(line) @@ -165,6 +175,146 @@ The complexity of inputs should be handled by the glaxy tool xml file. """ cmd_dict = dict() + cmd_dict['align.check'] = dict({'required' : ['fasta','map']}) + #cmd_dict['align.seqs'] = dict({'required' : ['candidate','template'], 'optional' : ['search','ksize','align','match','mismatch','gapopen','gapextend','flip','threshold','processors']}) + cmd_dict['align.seqs'] = dict({'required' : ['fasta','reference',], 'optional' : ['search','ksize','align','match','mismatch','gapopen','gapextend','flip','threshold','processors']}) + cmd_dict['amova'] = dict({'required' : ['phylip','design'] , 'optional' : ['alpha','iters']}) + cmd_dict['anosim'] = dict({'required' : ['phylip','design'] , 'optional' : ['alpha','iters']}) + #cmd_dict['bin.seqs'] = dict({'required' : ['fasta'], 'optional' : ['name','label','group']}) + cmd_dict['bin.seqs'] = dict({'required' : ['list','fasta'], 'optional' : ['name','label','group']}) + #cmd_dict['bootstrap.shared'] = dict({'required' : [], 'optional' : ['calc','groups','iters','label']}) + cmd_dict['bootstrap.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','groups','iters','label']}) + #catchall + cmd_dict['chimera.bellerophon'] = dict({'required' : ['fasta'], 'optional' : ['filter','correction','window','increment','processors']}) + #cmd_dict['chimera.ccode'] = dict({'required' : ['fasta','template'], 'optional' : ['filter','mask','window','numwanted','processors']}) + cmd_dict['chimera.ccode'] = dict({'required' : ['fasta','reference'], 'optional' : ['filter','mask','window','numwanted','processors']}) + #cmd_dict['chimera.check'] = dict({'required' : ['fasta','template'], 'optional' : ['ksize','svg','name','increment','processors']}) + cmd_dict['chimera.check'] = dict({'required' : ['fasta','reference'], 'optional' : ['ksize','svg','name','increment','processors']}) + #cmd_dict['chimera.pintail'] = dict({'required' : ['fasta','template'], 'optional' : ['conservation','quantile','filter','mask','window','increment','processors']}) + cmd_dict['chimera.pintail'] = dict({'required' : ['fasta','reference'], 'optional' : ['conservation','quantile','filter','mask','window','increment','processors']}) + #cmd_dict['chimera.slayer'] = dict({'required' : ['fasta','template'], 'optional' : ['name','search','window','increment','match','mismatch','numwanted','parents','minsim','mincov','iters','minbs','minsnp','divergence','realign','split','processors']}) + cmd_dict['chimera.slayer'] = dict({'required' : ['fasta','reference'], 'optional' : ['name','search','window','increment','match','mismatch','numwanted','parents','minsim','mincov','iters','minbs','minsnp','divergence','realign','split','processors']}) + #cmd_dict['chop.seqs'] = dict({'required' : ['fasta','numbases'], 'optional' : ['keep','short']}) + cmd_dict['chop.seqs'] = dict({'required' : ['fasta','numbases'], 'optional' : ['countgaps','keep','short']}) + cmd_dict['classify.otu'] = dict({'required' : ['list','taxonomy'],'optional' : ['name','cutoff','label','group','probs','basis','reftaxonomy']}) + #cmd_dict['classify.seqs'] = dict({'required' : ['fasta','template','taxonomy'],'optional' : ['name','search','ksize','method','match','mismatch','gapopen','gapextend','numwanted','probs','processors']}) + cmd_dict['classify.seqs'] = dict({'required' : ['fasta','reference','taxonomy'],'optional' : ['name','search','ksize','method','match','mismatch','gapopen','gapextend','numwanted','probs','processors']}) + cmd_dict['clearcut'] = dict({'required' : [['phylip','fasta']],'optional' : ['seed','norandom','shuffle','neighbor','expblen','expdist','ntrees','matrixout','kimura','jukes','protein','DNA']}) + #cmd_dict['cluster'] = dict({'required' : [] , 'optional' : ['method','cutoff','hard','precision']}) + cmd_dict['cluster'] = dict({'required' : [['phylip','column']] , 'optional' : ['name','method','cutoff','hard','precision','sim','showabund','timing']}) + #cmd_dict['cluster.classic'] = dict({'required' : ['phylip'] , 'optional' : ['method','cutoff','hard','precision']}) + cmd_dict['cluster.classic'] = dict({'required' : ['phylip'] , 'optional' : ['name','method','cutoff','hard','sim','precision']}) + cmd_dict['cluster.fragments'] = dict({'required' : ['fasta'] , 'optional' : ['name','diffs','percent']}) + cmd_dict['cluster.split'] = dict({'required' : [['fasta','phylip','column']] , 'optional' : ['name','method','splitmethod','taxonomy','taxlevel','showabund','cutoff','hard','large','precision','timing','processors']}) + #cmd_dict['collect.shared'] = dict({'required' : [], 'optional' : ['calc','label','freq','groups','all']}) + cmd_dict['collect.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','freq','groups','all']}) + #cmd_dict['collect.single'] = dict({'required' : [], 'optional' : ['calc','abund','size','label','freq']}) + cmd_dict['collect.single'] = dict({'required' : [['list', 'sabund', 'rabund', 'shared']], 'optional' : ['calc','abund','size','label','freq']}) + cmd_dict['consensus.seqs'] = dict({'required' : ['fasta'], 'optional' : ['list','name','label']}) + cmd_dict['corr.axes'] = dict({'required' : [['shared','relabund','metadata'],'axes'], 'optional' : ['label','groups','method','numaxes']}) + cmd_dict['degap.seqs'] = dict({'required' : ['fasta']}) + cmd_dict['deunique.seqs'] = dict({'required' : ['fasta','name'], 'optional' : []}) + #cmd_dict['dist.seqs'] = dict({'required' : ['fasta'], 'optional' : ['calc','countends','output','cutoff','processors']}) + cmd_dict['dist.seqs'] = dict({'required' : ['fasta'], 'optional' : ['calc','countends','output','cutoff','oldfasta','column','processors']}) + #cmd_dict['dist.shared'] = dict({'required' : [], 'optional' : ['calc','label','groups','output']}) + cmd_dict['dist.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','groups','output']}) + cmd_dict['fastq.info'] = dict({'required' : ['fastq'], 'optional' : []}) + cmd_dict['filter.seqs'] = dict({'required' : ['fasta'], 'optional' : ['vertical','trump','soft','hard','processors']}) + #cmd_dict['get.group'] = dict({'required' : [], 'optional' : []}) + cmd_dict['get.group'] = dict({'required' : ['shared'], 'optional' : []}) + cmd_dict['get.groups'] = dict({'required' : ['group'], 'optional' : ['groups','accnos','fasta','name','list','taxonomy']}) + cmd_dict['get.lineage'] = dict({'required' : ['taxonomy','taxon'],'optional' : ['fasta','name','group','list','alignreport','dups']}) + ##cmd_dict['get.otulist'] = dict({'required' : [], 'optional' : []}) + cmd_dict['get.otulist'] = dict({'required' : ['list'], 'optional' : ['label','sort']}) + #cmd_dict['get.oturep'] = dict({'required' : ['fasta','list'], 'optional' : ['phylip','column','name','label','group','groups','sorted','precision','cutoff','large','weighted']}) + cmd_dict['get.oturep'] = dict({'required' : ['fasta','list',['phylip','column']], 'optional' : ['name','label','group','groups','sorted','precision','cutoff','large','weighted']}) + cmd_dict['get.otus'] = dict({'required' : ['group','list','label'], 'optional' : ['groups','accnos']}) + ##cmd_dict['get.rabund'] = dict({'required' : [],'optional' : []}) + cmd_dict['get.rabund'] = dict({'required' : [['list','sabund']],'optional' : ['sorted','label']}) + #cmd_dict['get.relabund'] = dict({'required' : [],'optional' : ['scale','label','groups']}) + cmd_dict['get.relabund'] = dict({'required' : ['shared'],'optional' : ['scale','label','groups']}) + ##cmd_dict['get.sabund'] = dict({'required' : [],'optional' : []}) + cmd_dict['get.sabund'] = dict({'required' : [['list','rabund']],'optional' : ['label']}) + cmd_dict['get.seqs'] = dict({'required' : ['accnos',['fasta','qfile','name','group','list','alignreport','taxonomy']], 'optional' : ['dups']}) + ##cmd_dict['get.sharedseqs'] = dict({'required' : [], 'optional' : []}) + cmd_dict['get.sharedseqs'] = dict({'required' : ['list','group'], 'optional' : ['label', 'unique', 'shared', 'output', 'fasta']}) + cmd_dict['hcluster'] = dict({'required' : [['column','phylip']] , 'optional' : ['name','method','cutoff','hard','precision','sorted','showabund','timing']}) + #cmd_dict['heatmap.bin'] = dict({'required' : [], 'optional' : ['label','groups','scale','sorted','numotu','fontsize']}) + cmd_dict['heatmap.bin'] = dict({'required' : [['list', 'sabund', 'rabund', 'shared']], 'optional' : ['label','groups','scale','sorted','numotu','fontsize']}) + #cmd_dict['heatmap.sim'] = dict({'required' : [], 'optional' : ['calc','phylip','column','name','label','groups']}) + cmd_dict['heatmap.sim'] = dict({'required' : [['shared','phylip','column']], 'optional' : ['calc','name','label','groups']}) + cmd_dict['homova'] = dict({'required' : ['phylip','design'] , 'optional' : ['alpha','iters']}) + cmd_dict['indicator'] = dict({'required' : ['tree',['shared','relabund']], 'optional' : ['groups','label','design']}) + #cmd_dict['libshuff'] = dict({'required' : [],'optional' : ['iters','form','step','cutoff']}) + cmd_dict['libshuff'] = dict({'required' : ['phylip','group'],'optional' : ['groups','iters','form','sim','step','cutoff']}) + cmd_dict['list.seqs'] = dict({'required' : [['fasta','name','group','list','alignreport','taxonomy']]}) + cmd_dict['make,fastq'] = dict({'required' : ['fasta','qfile'] , 'optional' : []}) + #cmd_dict['make.group'] = dict({'required' : ['fasta','groups'], 'optional' : ['output']}) + cmd_dict['make.group'] = dict({'required' : ['fasta','groups'], 'optional' : []}) + cmd_dict['make.shared'] = dict({'required' : ['list','group'], 'optional' : ['label','groups','ordergroup']}) + cmd_dict['mantel'] = dict({'required' : ['phylip','phylip2'] , 'optional' : ['method','iters']}) + cmd_dict['merge.files'] = dict({'required' : ['input','output']}) + cmd_dict['merge.groups'] = dict({'required' : ['shared','design'], 'optional' : ['groups', 'label']}) + #cmd_dict['metastats'] = dict({'required' : ['design'], 'optional' : ['groups', 'label','iters','threshold','sets','processors']}) + cmd_dict['metastats'] = dict({'required' : ['shared','design'], 'optional' : ['groups', 'label','iters','threshold','sets','processors']}) + cmd_dict['nmds'] = dict({'required' : ['phylip'], 'optional' : ['axes','mindim','maxdim','iters','maxiters','epsilon']}) + #cmd_dict['normalize.shared'] = dict({'required' : [], 'optional' : ['label','method','norm','groups']}) + cmd_dict['normalize.shared'] = dict({'required' : [['shared','relabund']], 'optional' : ['label','method','norm','groups','makerelabund']}) + ##cmd_dict['otu.hierarchy'] = dict({'required' : [], 'optional' : []}) + cmd_dict['otu.hierarchy'] = dict({'required' : ['list','label'], 'optional' : ['output']}) + cmd_dict['pairwise.seqs'] = dict({'required' : ['fasta'], 'optional' : ['align','calc','countends','output','cutoff','match','mismatch','gapopen','gapextend','processors']}) + cmd_dict['parse.list'] = dict({'required' : ['list','group'], 'optional' : ['label']}) + #cmd_dict['parsimony'] = dict({'required' : [], 'optional' : ['groups','iters','random','processors']}) + cmd_dict['parsimony'] = dict({'required' : ['tree'], 'optional' : ['group','groups','name','iters','random','processors']}) + #cmd_dict['pca'] = dict({'required' : [], 'optional' : ['label','groups','metric']}) + cmd_dict['pca'] = dict({'required' : [['shared','relabund']], 'optional' : ['label','groups','metric']}) + #cmd_dict['pcoa'] = dict({'required' : ['phylip'], 'optional' : []}) + cmd_dict['pcoa'] = dict({'required' : ['phylip'], 'optional' : ['metric']}) + #cmd_dict['phylo.diversity'] = dict({'required' : [],'optional' : ['groups','iters','freq','scale','rarefy','collect','summary','processors']}) + cmd_dict['phylo.diversity'] = dict({'required' : ['tree','group'],'optional' : ['name','groups','iters','freq','scale','rarefy','collect','summary','processors']}) + cmd_dict['phylotype'] = dict({'required' : ['taxonomy'],'optional' : ['name','cutoff','label']}) + #cmd_dict['pre.cluster'] = dict({'required' : ['fasta'], 'optional' : ['names','diffs']}) + cmd_dict['pre.cluster'] = dict({'required' : ['fasta'], 'optional' : ['name','diffs']}) + #cmd_dict['rarefaction.shared'] = dict({'required' : [], 'optional' : ['label','iters','groups','jumble']}) + cmd_dict['rarefaction.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','iters','groups','jumble']}) + #cmd_dict['rarefaction.single'] = dict({'required' : [], 'optional' : ['calc','abund','iters','label','freq','processors']}) + cmd_dict['rarefaction.single'] = dict({'required' : [['list', 'sabund', 'rabund', 'shared']], 'optional' : ['calc','abund','iters','label','freq','processors']}) + #cmd_dict['read.dist'] = dict({'required' : [['phylip','column']], 'optional' : ['name','cutoff','hard','precision','sim','group']}) + #cmd_dict['read.otu'] = dict({'required' : [['rabund','sabund','list','shared','relabund']], 'optional' : ['label','group','groups','ordergroup']}) + #cmd_dict['read.tree'] = dict({'required' : ['tree'], 'optional' : ['name','group']}) + cmd_dict['remove.groups'] = dict({'required' : ['group'], 'optional' : ['groups','accnos','fasta','name','list','taxonomy']}) + cmd_dict['remove.lineage'] = dict({'required' : ['taxonomy','taxon'],'optional' : ['fasta','name','group','list','alignreport','dups']}) + cmd_dict['remove.otus'] = dict({'required' : ['group','list','label'], 'optional' : ['groups','accnos']}) + #cmd_dict['remove.rare'] = dict({'required' : [['list','sabund','rabund','shared'],'nseqs'], 'optional' : ['group','groups','label','bygroup']}) + cmd_dict['remove.rare'] = dict({'required' : [['list','sabund','rabund','shared'],'nseqs'], 'optional' : ['group','groups','label','bygroup']}) + cmd_dict['remove.seqs'] = dict({'required' : ['accnos',['fasta','qfile','name','group','list','alignreport','taxonomy']], 'optional' : ['dups']}) + cmd_dict['reverse.seqs'] = dict({'required' : ['fasta']}) + cmd_dict['screen.seqs'] = dict({'required' : ['fasta'], 'optional' : ['start','end','maxambig','maxhomop','minlength','maxlength','criteria','optimize','name','group','alignreport','processors']}) + cmd_dict['sens.spec'] = dict({'required' : ['list',['column','phylip']] , 'optional' : ['label','cutoff','hard','precision']}) + cmd_dict['sffinfo'] = dict({'required' : [['sff','sfftxt']], 'optional' : ['fasta','qfile','trim','sfftxt','flow','accnos']}) + cmd_dict['split.abund'] = dict({'required' : ['fasta',['name','list']], 'optional' : ['cutoff','group','groups','label','accnos']}) + #cmd_dict['split.groups'] = dict({'required' : ['fasta','group'], 'optional' : []}) + cmd_dict['split.groups'] = dict({'required' : ['fasta','group'], 'optional' : ['name','groups']}) + cmd_dict['sub.sample'] = dict({'required' : [['fasta','list','sabund','rabund','shared']], 'optional' : ['name','group','groups','label','size','persample']}) + #cmd_dict['summary.seqs'] = dict({'required' : ['fasta'],'outputs' : ['names']}) + cmd_dict['summary.seqs'] = dict({'required' : ['fasta'], 'optional' : ['name','processors']}) + #cmd_dict['summary.shared'] = dict({'required' : [], 'optional' : ['calc','label','groups','all','distance']}) + cmd_dict['summary.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','groups','all','distance','processors']}) + #cmd_dict['summary.single'] = dict({'required' : [], 'optional' : ['calc','abund','size','label','groupmode']}) + cmd_dict['summary.single'] = dict({'required' : [['list','sabund','rabund','shared']], 'optional' : ['calc','abund','size','label','groupmode']}) + #cmd_dict['tree.shared'] = dict({'required' : [], 'optional' : ['groups','calc','cutoff','precision','label']}) + cmd_dict['tree.shared'] = dict({'required' : [['shared','phylip','column']], 'optional' : ['name','groups','calc','cutoff','precision','label']}) + cmd_dict['trim.seqs'] = dict({'required' : ['fasta'], 'optional' : ['group','oligos','qfile','qaverage','qthreshold','qtrim','flip','maxambig','maxhomop','minlength','maxlength','bdiffs','pdiffs','tdiffs','allfiles','keepfirst','removelast']}) + #cmd_dict['unifrac.unweighted'] = dict({'required' : [], 'optional' : ['groups','iters','distance','random','root','processors']}) + cmd_dict['unifrac.unweighted'] = dict({'required' : ['tree'], 'optional' : ['name','group','groups','iters','distance','random','root','processors']}) + #cmd_dict['unifrac.weighted'] = dict({'required' : [], 'optional' : ['groups','iters','distance','random','root','processors']}) + cmd_dict['unifrac.weighted'] = dict({'required' : ['tree'], 'optional' : ['name','group','groups','iters','distance','random','root','processors']}) + #cmd_dict['unique.seqs'] = dict({'required' : ['fasta'], 'optional' : ['names']}) + cmd_dict['unique.seqs'] = dict({'required' : ['fasta'], 'optional' : ['name']}) + #cmd_dict['venn'] = dict({'required' : [], 'optional' : ['calc','label','groups','abund','nseqs','permute']}) + cmd_dict['venn'] = dict({'required' : [['list','shared']], 'optional' : ['calc','label','groups','abund','nseqs','permute']}) + ## + """ cmd_dict['merge.files'] = dict({'required' : ['input','output']}) cmd_dict['make.group'] = dict({'required' : ['fasta','groups'], 'optional' : ['output']}) cmd_dict['merge.groups'] = dict({'required' : ['shared','design'], 'optional' : ['groups', 'label']}) @@ -192,7 +342,7 @@ cmd_dict['chimera.ccode'] = dict({'required' : ['fasta','template'], 'optional' : ['filter','mask','window','numwanted','processors']}) cmd_dict['chimera.check'] = dict({'required' : ['fasta','template'], 'optional' : ['ksize','svg','name','increment','processors']}) cmd_dict['chimera.pintail'] = dict({'required' : ['fasta','template'], 'optional' : ['conservation','quantile','filter','mask','window','increment','processors']}) - cmd_dict['chimera.slayer'] = dict({'required' : ['fasta','template'], 'optional' : ['name','search','window','increment','match','mismatch','numwanted','parents','minsim','mincov','iters','minbs','minsnp','divergence','realign','processors']}) + cmd_dict['chimera.slayer'] = dict({'required' : ['fasta','template'], 'optional' : ['name','search','window','increment','match','mismatch','numwanted','parents','minsim','mincov','iters','minbs','minsnp','divergence','realign','split','processors']}) cmd_dict['dist.seqs'] = dict({'required' : ['fasta'], 'optional' : ['calc','countends','output','cutoff','processors']}) cmd_dict['pairwise.seqs'] = dict({'required' : ['fasta'], 'optional' : ['align','calc','countends','output','cutoff','match','mismatch','gapopen','gapextend','processors']}) cmd_dict['read.dist'] = dict({'required' : [['phylip','column']], 'optional' : ['name','cutoff','hard','precision','sim','group']}) @@ -203,7 +353,7 @@ cmd_dict['cluster.fragments'] = dict({'required' : ['fasta'] , 'optional' : ['name','diffs','percent']}) cmd_dict['cluster.split'] = dict({'required' : [['fasta','phylip','column']] , 'optional' : ['name','method','splitmethod','taxonomy','taxlevel','showabund','cutoff','hard','large','precision','timing','processors']}) cmd_dict['metastats'] = dict({'required' : ['design'], 'optional' : ['groups', 'label','iters','threshold','sets','processors']}) - cmd_dict['summary.single'] = dict({'required' : [], 'optional' : ['calc','abund','size','label','groupmode','processors']}) + cmd_dict['summary.single'] = dict({'required' : [], 'optional' : ['calc','abund','size','label','groupmode']}) cmd_dict['summary.shared'] = dict({'required' : [], 'optional' : ['calc','label','groups','all','distance']}) cmd_dict['collect.single'] = dict({'required' : [], 'optional' : ['calc','abund','size','label','freq']}) cmd_dict['collect.shared'] = dict({'required' : [], 'optional' : ['calc','label','freq','groups','all']}) @@ -214,21 +364,21 @@ cmd_dict['split.abund'] = dict({'required' : ['fasta',['name','list']], 'optional' : ['cutoff','group','groups','label','accnos']}) cmd_dict['split.groups'] = dict({'required' : ['fasta','group'], 'optional' : []}) cmd_dict['tree.shared'] = dict({'required' : [], 'optional' : ['groups','calc','cutoff','precision','label']}) - cmd_dict['unifrac.unweighted'] = dict({'required' : [], 'optional' : ['groups','iters','distance','random','processors']}) - cmd_dict['unifrac.weighted'] = dict({'required' : [], 'optional' : ['groups','iters','distance','random','processors']}) + cmd_dict['unifrac.unweighted'] = dict({'required' : [], 'optional' : ['groups','iters','distance','random','root','processors']}) + cmd_dict['unifrac.weighted'] = dict({'required' : [], 'optional' : ['groups','iters','distance','random','root','processors']}) cmd_dict['parsimony'] = dict({'required' : [], 'optional' : ['groups','iters','random','processors']}) cmd_dict['sffinfo'] = dict({'required' : ['sff'], 'optional' : ['fasta','qfile','trim','sfftxt','flow','accnos']}) cmd_dict['fastq.info'] = dict({'required' : ['fastq'], 'optional' : []}) cmd_dict['heatmap.bin'] = dict({'required' : [], 'optional' : ['label','groups','scale','sorted','numotu','fontsize']}) cmd_dict['heatmap.sim'] = dict({'required' : [], 'optional' : ['calc','phylip','column','name','label','groups']}) - cmd_dict['venn'] = dict({'required' : [], 'optional' : ['calc','label','groups','nseqs','permute']}) + cmd_dict['venn'] = dict({'required' : [], 'optional' : ['calc','label','groups','abund','nseqs','permute']}) cmd_dict['pcoa'] = dict({'required' : ['phylip'], 'optional' : []}) cmd_dict['pca'] = dict({'required' : [], 'optional' : ['label','groups','metric']}) cmd_dict['nmds'] = dict({'required' : ['phylip'], 'optional' : ['axes','mindim','maxdim','iters','maxiters','epsilon']}) cmd_dict['corr.axes'] = dict({'required' : [['shared','relabund','metadata'],'axes'], 'optional' : ['label','groups','method','numaxes']}) cmd_dict['get.group'] = dict({'required' : [], 'optional' : []}) cmd_dict['phylotype'] = dict({'required' : ['taxonomy'],'optional' : ['name','cutoff','label']}) - cmd_dict['phylo.diversity'] = dict({'required' : [],'optional' : ['groups','iters','freq','processors','scale','rarefy','collect','summary','processors']}) + cmd_dict['phylo.diversity'] = dict({'required' : [],'optional' : ['groups','iters','freq','scale','rarefy','collect','summary','processors']}) cmd_dict['get.oturep'] = dict({'required' : ['fasta','list'], 'optional' : ['phylip','column','name','label','group','groups','sorted','precision','cutoff','large','weighted']}) cmd_dict['get.relabund'] = dict({'required' : [],'optional' : ['scale','label','groups']}) cmd_dict['libshuff'] = dict({'required' : [],'optional' : ['iters','form','step','cutoff']}) @@ -237,10 +387,7 @@ cmd_dict['get.lineage'] = dict({'required' : ['taxonomy','taxon'],'optional' : ['fasta','name','group','list','alignreport','dups']}) cmd_dict['remove.lineage'] = dict({'required' : ['taxonomy','taxon'],'optional' : ['fasta','name','group','list','alignreport','dups']}) cmd_dict['bootstrap.shared'] = dict({'required' : [], 'optional' : ['calc','groups','iters','label']}) - """ - Mothur 1.15 - """ - cmd_dict['cluster.classic'] = dict({'required' : [] , 'optional' : ['method','cutoff','hard','precision']}) + cmd_dict['cluster.classic'] = dict({'required' : ['phylip'] , 'optional' : ['method','cutoff','hard','precision']}) cmd_dict['get.groups'] = dict({'required' : ['group'], 'optional' : ['groups','accnos','fasta','name','list','taxonomy']}) cmd_dict['remove.groups'] = dict({'required' : ['group'], 'optional' : ['groups','accnos','fasta','name','list','taxonomy']}) cmd_dict['get.otus'] = dict({'required' : ['group','list','label'], 'optional' : ['groups','accnos']}) @@ -251,6 +398,14 @@ cmd_dict['sub.sample'] = dict({'required' : [['fasta','list','sabund','rabund','shared']], 'optional' : ['name','group','groups','label','size','persample']}) cmd_dict['consensus.seqs'] = dict({'required' : ['fasta'], 'optional' : ['list','name','label']}) cmd_dict['indicator'] = dict({'required' : ['tree',['shared','relabund']], 'optional' : ['groups','label','design']}) + + cmd_dict['amova'] = dict({'required' : ['phylip','design'] , 'optional' : ['alpha','iters']}) + cmd_dict['homova'] = dict({'required' : ['phylip','design'] , 'optional' : ['alpha','iters']}) + cmd_dict['anosim'] = dict({'required' : ['phylip','design'] , 'optional' : ['alpha','iters']}) + cmd_dict['mantel'] = dict({'required' : ['phylip','phylip2'] , 'optional' : ['method','iters']}) + cmd_dict['make,fastq'] = dict({'required' : ['fasta','qfile'] , 'optional' : []}) + """ + parser = optparse.OptionParser() # Options for managing galaxy interaction parser.add_option( '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stdout' ) @@ -318,6 +473,7 @@ # parser.add_option( '--taxon', dest='taxon', action="callback", callback=remove_confidence_callback, help='A Taxon' ) parser.add_option( '--candidate', dest='candidate', help=' file ' ) parser.add_option( '--template', dest='template', help=' file ' ) + parser.add_option( '--reference', dest='reference', help=' file ' ) parser.add_option( '--dups', dest='dups', help='if True also apply to the aliases from the names files' ) parser.add_option( '--keep', dest='keep', help='Either front or back to specify the which end of the sequence to keep' ) parser.add_option( '--search', dest='search', help='Method for finding the template sequence: kmer, blast, suffix' ) @@ -353,6 +509,7 @@ parser.add_option( '--output', dest='output', help='Format for output' ) parser.add_option( '--method', dest='method', help='Method to use for analysis - cluster' ) parser.add_option( '--splitmethod', dest='splitmethod', help='Method to split a distance file - cluster.split' ) + parser.add_option( '--split', dest='split', help='Chimera split parameter, whether to detect trimeras and quadmeras' ) parser.add_option( '--abund', dest='abund', type='int', help='Threshold for rare to Abundant OTU classification' ) parser.add_option( '--size', dest='size', type='int', help='Size - sample size' ) parser.add_option( '--groupmode', dest='groupmode', help='Collate groups into one result table' ) @@ -373,12 +530,15 @@ parser.add_option( '--percent', dest='percent', type='int', help='(0-100 percent)' ) parser.add_option( '--divergence', dest='divergence', type='float', help='Divergence cutoff for chimera determination' ) parser.add_option( '--sff', dest='sff', help='Sff file' ) + parser.add_option( '--svg', dest='svg', help='SVG' ) parser.add_option( '--sfftxt', dest='sfftxt', help='Generate a sff.txt file' ) parser.add_option( '--flow', dest='flow', help='Generate a flowgram file' ) parser.add_option( '--trim', dest='trim', help='Whether sequences and quality scores are trimmed to the clipQualLeft and clipQualRight values' ) parser.add_option( '--input', dest='input', help='' ) parser.add_option( '--phylip', dest='phylip', help='' ) + parser.add_option( '--phylip2', dest='phylip2', help='' ) parser.add_option( '--column', dest='column', help='' ) + parser.add_option( '--sort', dest='sort', help='specify sort order' ) parser.add_option( '--sorted', dest='sorted', help='Input is presorted' ) parser.add_option( '--showabund', dest='showabund', help='' ) parser.add_option( '--short', dest='short', help='Keep sequences that are too short to chop' ) @@ -387,6 +547,7 @@ parser.add_option( '--numotu', dest='numotu', help='' ) parser.add_option( '--fontsize', dest='fontsize', help='' ) parser.add_option( '--neqs', dest='neqs', help='' ) + parser.add_option( '--random', dest='random', help='' ) parser.add_option( '--permute', dest='permute', help='' ) parser.add_option( '--rarefy', dest='rarefy', help='' ) parser.add_option( '--collect', dest='collect', help='' ) @@ -408,6 +569,8 @@ parser.add_option( '--sets', dest='sets', help='' ) parser.add_option( '--metric', dest='metric', help='' ) parser.add_option( '--epsilon', dest='epsilon', help='' ) + parser.add_option( '--alpha', dest='alpha', help='' ) + parser.add_option( '--root', dest='root', help='' ) parser.add_option( '--axes', dest='axes', help='table of name column followed by columns of axis values' ) parser.add_option( '--numaxes', dest='numaxes', help='the number of axes' ) parser.add_option( '--metadata', dest='metadata', help='data table with columns of floating-point values' ) @@ -446,7 +609,14 @@ os.makedirs(options.tmpdir) tmp_dir = options.tmpdir else: - tmp_dir = tempfile.mkdtemp() + if options.outputdir != None: + if not os.path.isdir(options.outputdir): + os.makedirs(options.outputdir) + tmp_dir = os.path.join(options.outputdir,'tmp') + if not os.path.isdir(tmp_dir): + os.makedirs(tmp_dir) + else: + tmp_dir = tempfile.mkdtemp() if options.inputdir != None: if not os.path.isdir(options.inputdir): os.makedirs(options.inputdir) @@ -478,11 +648,12 @@ # print >> sys.stderr, cmd_opts # print >> sys.stderr, params # so will appear as blurb for file params.append('%s(%s)' % (options.cmd,cmd_opts)) + if debug: params.append('get.current()') try: # Generate the mothur commandline # http://www.mothur.org/wiki/Command_line_mode cmdline = 'mothur "#' + '; '.join(params) + '"' - # print >> sys.stdout, '%s' % cmdline + if debug: print >> sys.stdout, '%s' % cmdline if tmp_dir == None or not os.path.isdir(tmp_dir): tmp_dir = tempfile.mkdtemp() tmp_stderr_name = tempfile.NamedTemporaryFile( dir=tmp_dir,suffix='.err' ).name @@ -492,6 +663,7 @@ proc = subprocess.Popen( args=cmdline, shell=True, cwd=tmp_dir, stderr=tmp_stderr.fileno(), stdout=tmp_stdout.fileno() ) # proc = subprocess.Popen( args=cmdline, shell=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE ) returncode = proc.wait() + if debug: print >> sys.stdout, 'returncode %d' % returncode tmp_stderr.close() # get stderr, allowing for case where it's very large tmp_stderr = open( tmp_stderr_name, 'rb' ) @@ -505,12 +677,26 @@ except OverflowError: pass tmp_stderr.close() + tmp_stdout.close() + if debug: print >> sys.stdout, 'parse %s' % tmp_stdout_name if returncode != 0: + try: + # try to copy stdout to the logfile + for output in options.result.split(','): + # Each item has a regex pattern and a file path to a galaxy dataset + (pattern,path) = output.split(':') + if debug: print >> sys.stdout, '%s -> %s' % (pattern,path) + if pattern.find('\.logfile') > 0: + if path != None and os.path.exists(path): + logfile_to_html(tmp_stdout_name,path,inputdir,outputdir,title="Mothur %s Error Logfile" % options.cmd) + break + except: + pass raise Exception, stderr stdout = '' # Parse stdout to provide info - tmp_stdout.close() tmp_stdout = open( tmp_stdout_name, 'rb' ) + # try to find a "little" something interesting to print as info for the galaxy interface info = '' if options.cmd.startswith('chimera') and not options.cmd.endswith('check'): pattern = '^.*$' @@ -533,19 +719,32 @@ info += "Chimeras: %d" % chimera_count else: found_begin = False + info_chars = 0 for line in tmp_stdout: if line.find(outputdir) >= 0: continue + if line.startswith('**************'): + continue if re.match('^Processing.*',line): continue + if re.match('^Reading .*',line): + continue + if re.match('^Merging .*',line): + continue + if re.match('^DONE.*',line): + continue if re.match('.*\.\.\.\s*$',line): continue if re.match('^\d*\s*$',line): continue + # if re.match('^(unique|[0-9.]*)(\t\d+)+',line): # abundance from cluster commands + if not options.cmd.startswith('unifrac') and re.match('^([0-9.]+)(\t\d+)*',line): # abundance from cluster commands, allow unique line into info + continue if re.match('Output .*',line): break - if found_begin: + if found_begin and info_chars < 200: info += "%s" % line + info_chars += len(line) if re.match('mothur > ' + options.cmd + '\(.*\)', line): found_begin = True tmp_stdout.close() @@ -553,6 +752,15 @@ # Collect output files flist = os.listdir(outputdir) if debug: print >> sys.stdout, '%s' % flist + # chimera.check can generate svg files, but they are not listed in the mothur.*.logfile, so we'll added them in here + if options.cmd == 'chimera.check': + svgs = [] + mothurlog = None + for fname in flist: + if fname.endswith('.svg'): + svgs.append(fname) + elif fname.endswith('.logfile'): + mothurlog = fname # process option result first # These are the known galaxy datasets listed in the --result= param if len(flist) > 0 and options.result: @@ -573,23 +781,31 @@ if fname.endswith('.logfile'): # Make the logfile into html logfile_to_html(fpath,path,inputdir,outputdir,title="Mothur %s Logfile" % options.cmd) - elif False and outputdir == options.outputdir: - # Use a hard link if outputdir is the extra_files_path + elif outputdir == options.outputdir: + # Use a hard link if outputdir is the extra_files_path, allows link from mothur logfile without copying data. try: + if debug: print >> sys.stdout, 'link %s %s' % (fpath, path) os.link(fpath, path) except: + if debug: print >> sys.stdout, 'copy %s %s' % (fpath, path) shutil.copy2(fpath, path) else: + if debug: print >> sys.stdout, 'copy2 %s %s' % (fpath, path) shutil.copy2(fpath, path) break + # mothur.*.logfile may be in tmp_dir # chimera.pintail e.g. generates files in the working dir that we might want to save if not found: for fname in os.listdir(tmp_dir): if debug: print >> sys.stdout, 'tmpdir %s match: %s' % (fname,re.match(pattern,fname)) if re.match(pattern,fname): fpath = os.path.join(tmp_dir,fname) - shutil.copy2(fpath, path) - break + if fname.endswith('.logfile'): + # Make the logfile into html + logfile_to_html(fpath,path,inputdir,outputdir,title="Mothur %s Logfile" % options.cmd) + else: + shutil.copy2(fpath, path) + break # Handle the dynamically generated galaxy datasets # http://bitbucket.org/galaxy/galaxy-central/wiki/ToolsMultipleOutput # --new_datasets= specifies files to copy to the new_file_path @@ -605,7 +821,8 @@ if m: fpath = os.path.join(outputdir,fname) if len(m.groups()) > 0: - root = m.groups()[0] + # remove underscores since galaxy uses that as a field separator for dynamic datasets + root = m.groups()[0].replace('_','') else: # remove the ext from the name if it exists, galaxy will add back later # remove underscores since galaxy uses that as a field separator for dynamic datasets @@ -632,13 +849,18 @@ try: if outputdir != options.outputdir and os.path.exists(outputdir): if os.path.islink(outputdir): + if debug: print >> sys.stdout, 'rm outputdir %s' % outputdir os.remove(outputdir) + if debug: print >> sys.stdout, 'rmtree outputdir %s' % outputdir shutil.rmtree(os.path.dirname(outputdir)) else: + if debug: print >> sys.stdout, 'rmtree %s' % outputdir shutil.rmtree(outputdir) if inputdir != options.inputdir and os.path.exists(inputdir): + if debug: print >> sys.stdout, 'rmtree %s' % inputdir shutil.rmtree(inputdir) except: + if debug: print >> sys.stdout, 'rmtree failed' pass
--- a/mothur/tools/mothur/nmds.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/nmds.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,9 +1,9 @@ -<tool id="mothur_nmds" name="Nmds" version="1.16.0"> +<tool id="mothur_nmds" name="Nmds" version="1.19.0"> <description>generate non-metric multidimensional scaling data</description> <command interpreter="python"> mothur_wrapper.py --cmd='nmds' - --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.nmds\.axes$:'$nmds_axes,'^\S+\.nmds\.iters$:'$nmds_iters,'^\S+\.stress\.nmds$:'$stress_nmds + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.nmds\.axes$:'$nmds_axes,'^\S+\.nmds\.iters$:'$nmds_iters,'^\S+\.nmds\.stress$:'$stress_nmds --outputdir='$logfile.extra_files_path' --phylip=$dist #if $axes.__str__ != "None" and len($axes.__str__) > 0: @@ -38,7 +38,7 @@ <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> <data format="axes" name="nmds_axes" label="${tool.name} on ${on_string}: nmds.axes"/> <data format="tabular" name="nmds_iters" label="${tool.name} on ${on_string}: nmds.iters"/> - <data format="tabular" name="stress_nmds" label="${tool.name} on ${on_string}: stress.nmds"/> + <data format="tabular" name="stress_nmds" label="${tool.name} on ${on_string}: nmds.stress"/> </outputs> <requirements> <requirement type="binary">mothur</requirement> @@ -56,8 +56,9 @@ **Command Documenation** -The nmds_ command generates non-metric multidimensional scaling data +The nmds_ command generates non-metric multidimensional scaling data from a phylip_distance_matrix_. +.. _phylip_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix .. _nmds: http://www.mothur.org/wiki/Nmds
--- a/mothur/tools/mothur/normalize.shared.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/normalize.shared.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,27 +1,21 @@ -<tool id="mothur_normalize_shared" name="Normalize.shared" version="1.16.0"> +<tool id="mothur_normalize_shared" name="Normalize.shared" version="1.19.0"> <description>Normalize the number of sequences per group to a specified level</description> <command interpreter="python"> mothur_wrapper.py --cmd='normalize.shared' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.norm\.shared$:'$shared --outputdir='$logfile.extra_files_path' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if + #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__): + --shared=$otu + $makerelabund + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('relabund').__class__): + --relabund=$otu #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' + #end if + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups=$groups #end if #if $method.__str__ != "None" and len($method.__str__) > 0: --method=$method @@ -31,53 +25,29 @@ #end if </command> <inputs> - <conditional name="input"> - <param name="source" type="select" label="Generate Heatmap for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> + <param name="otu" type="data" format="shared,relabund" label="shared,relabund - OTU Shared or Relabund file"/> + <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + <param name="groups" type="select" label="groups - Groups to include" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> <param name="norm" type="integer" value="0" label="norm - Number to normalize to (Uses default if < 1)" help="By default this is set to the number of sequences in your smallest group."/> <param name="method" type="select" optional="true" label="method - Normalization method"> <option value="">Use Default</option> - <option value="totalgroup">Total Group</option> + <option value="totalgroup" selected="true">Total Group</option> <option value="zscore">Z Score</option> </param> + <param name="makerelabund" type="boolean" truevalue="--makerelabund=true" falsevalue="" checked="false" label="makerelabund - convert a shared file to a relabund file before you normalize" /> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -99,8 +69,10 @@ **Command Documenation** -The normalize.shared_ command normalizes the number of sequences per group to a specified level. +The normalize.shared_ command normalizes the number of sequences per group to a specified level. The input is a shared_ or relabund_ file. +.. _shared: http://www.mothur.org/wiki/Shared_file +.. _relabund: http://www.mothur.org/wiki/Get.relabund .. _normalize.shared: http://www.mothur.org/wiki/Normalize.shared </help>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/otu.hierarchy.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,61 @@ +<tool id="mothur_otu_hierarchy" name="Otu.hierarchy" version="1.19.0"> + <description>Relate OTUs at different distances</description> + <command interpreter="python"> + mothur_wrapper.py + ## output {group_file_name}.pick.{label}.groups {list_file_name}.pick.{label}.list + #import re, os.path + --cmd='otu.hierarchy' + --outputdir='$logfile.extra_files_path' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.otu\.hierarchy$:'$hierarchy + --list=$list + --label=$label1,$label2 + --output=$output + </command> + <inputs> + <param name="list" type="data" format="list" label="list - OTU List"/> + <param name="label1" type="select" label="label - OTU Label 1" > + <options from_dataset="list"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + <param name="label2" type="select" label="label - OTU Label 2" help="Must be different than Label 1"> + <options from_dataset="list"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="param_value" ref="label1" column="value" keep="false"/> + </options> + </param> + <param name="output" type="select" optional="true" label="output - display the names of the sequences in the otus or the otu numbers"> + <option value="name" selected="treu">OTU sequence names</option> + <option value="number">OTU numbers</option> + </param> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="tabular" name="hierarchy" label="${tool.name} on ${on_string}: otu.hierarchy"/> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The otu.hierarchy_ command relates OTUs from a list_ at different distances. + +.. _list_file: http://www.mothur.org/wiki/List_file +.. _otu.hierarchy: http://www.mothur.org/wiki/Otu.hierarchy + + + </help> +</tool>
--- a/mothur/tools/mothur/pairwise.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/pairwise.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_pairwise_seqs" name="Pairwise.seqs" version="1.16.0"> +<tool id="mothur_pairwise_seqs" name="Pairwise.seqs" version="1.19.0"> <description>calculate uncorrected pairwise distances between sequences</description> <command interpreter="python"> mothur_wrapper.py @@ -14,10 +14,12 @@ #if float($cutoff.__str__) > 0.0: --cutoff=$cutoff #end if - --match=$scoring.match - --mismatch=$scoring.mismatch - --gapopen=$scoring.gapopen - --gapextend=$scoring.gapextend + #if $scoring.setby == 'user': + --match=$scoring.match + --mismatch=$scoring.mismatch + --gapopen=$scoring.gapopen + --gapextend=$scoring.gapextend + #end if #if len($output.__str__) > 0: --output=$output #end if @@ -40,10 +42,21 @@ help="Penalize terminal gaps"/> <param name="cutoff" type="float" value="0.0" label="cutoff - Distance Cutoff threshold - ignored if not > 0" help="Do not save any distances larger than this, a common value would be 0.10"/> - <param name="match" type="integer" value="1" label="match - Pairwise alignment reward for a match"/> - <param name="mismatch" type="integer" value="-1" label="mismatch - Pairwise alignment penalty for a mismatch"/> - <param name="gapopen" type="integer" value="-2" label="gapopen - Pairwise alignment penalty for opening a gap"/> - <param name="gapextend" type="integer" value="-1" label="gapextend - Pairwise alignment penalty for extending a gap"/> + + <conditional name="scoring"> + <param name="setby" type="select" label="Scoring match, mismatch, gapopen, and gapextend" help=""> + <option value="default">Use default settings</option> + <option value="user">Manually set scoring values</option> + </param> + <when value="default"/> + <when value="user"> + <param name="match" type="integer" value="1" label="match - Pairwise alignment reward for a match"/> + <param name="mismatch" type="integer" value="-1" label="mismatch - Pairwise alignment penalty for a mismatch"/> + <param name="gapopen" type="integer" value="-2" label="gapopen - Pairwise alignment penalty for opening a gap"/> + <param name="gapextend" type="integer" value="-1" label="gapextend - Pairwise alignment penalty for extending a gap"/> + </when> + </conditional> + <param name="output" type="select" label="output - Distance Matrix Output Format" help=""> <option value="">Default Column-Formatted Matrix</option> @@ -76,8 +89,10 @@ **Command Documenation** -The pairwise.seqs_ command will calculate uncorrected pairwise distances between sequences. +The pairwise.seqs_ command will calculate uncorrected pairwise distances between sequencesi as a column-formatted_distance_matrix_ or phylip-formatted_distance_matrix_. +.. _column-formatted_distance_matrix: http://www.mothur.org/wiki/Column-formatted_distance_matrix +.. _phylip-formatted_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix .. _pairwise.seqs: http://www.mothur.org/wiki/Pairwise.seqs
--- a/mothur/tools/mothur/parse.list.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/parse.list.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,5 +1,5 @@ -<tool id="mothur_parse_list" name="Parse.list" version="1.16.0" force_history_refresh="True"> - <description>Order Sequences by OTU</description> +<tool id="mothur_parse_list" name="Parse.list" version="1.19.0" force_history_refresh="True"> + <description>Generate a List file for each group</description> <command interpreter="python"> mothur_wrapper.py --cmd='parse.list' @@ -16,7 +16,8 @@ <inputs> <param name="otu" type="data" format="list" label="list - OTU List"/> <param name="group" type="data" format="groups" label="group - Sequences Name reference"/> - <param name="label" type="select" optional="true" label="label - Select OTU Labels to filter out all but selected labels" multiple="true"> + <param name="label" type="select" optional="true" label="label - To filter: Select OTU Labels to include" multiple="true"> + <help>All labels are included if none are selected</help> <options from_dataset="otu"> <column name="name" index="0"/> <column name="value" index="0"/> @@ -42,8 +43,10 @@ **Command Documenation** -The parse.list_ command prints out a fasta-formatted file where sequences are ordered according to the OTU that they belong to. Such an output may be helpful for generating primers specific to an OTU or for classification of sequences. +The parse.list_ command reads a list_ file and group_ file and generates a list_ file for each group_ in the groupfile. +.. _list: http://www.mothur.org/wiki/List_file +.. _group: http://www.mothur.org/wiki/Group_file .. _parse.list: http://www.mothur.org/wiki/Parse.list </help>
--- a/mothur/tools/mothur/parsimony.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/parsimony.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,36 +1,37 @@ -<tool id="mothur_parsimony" name="Parsimony" version="1.16.0"> +<tool id="mothur_parsimony" name="Parsimony" version="1.19.0"> <description>Describes whether two or more communities have the same structure</description> <command interpreter="python"> mothur_wrapper.py --cmd='parsimony' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.psummary$:'$psummary,'^\S+\.parsimony$:'$parsimony --outputdir='$logfile.extra_files_path' - --READ_cmd='read.tree' - --READ_tree=$tree + --tree=$tree #if $group.__str__ != "None" and len($group.__str__) > 0: - --READ_group='$group' + --group='$group' #end if #if $groups.__str__ != "None" and len($groups.__str__) > 0: --groups='$groups' #end if + #if $name.__str__ != "None" and len($name.__str__) > 0: + --name='$name' + #end if #if int($iters.__str__) > 0: --iters=$iters #end if --processors=2 </command> <inputs> - <param name="tree" type="data" format="tre" label="read.tree(tree=) - Phylogenetic Tree"/> - <param name="group" type="data" format="groups" label="read.tree(group=) - Group file for the tree"/> - <!-- - <param name="name" type="data" format="names" optional="true" label="read.tree(name=) - Sequences Name reference file for the tree"/> - --> - <param name="groups" type="select" label="groups - Groups to display" multiple="true"> + <param name="tree" type="data" format="tre" label="tree - Phylogenetic Tree"/> + <param name="group" type="data" format="groups" label="group - Group file for the tree"/> + <param name="groups" type="select" label="groups - Groups to display" multiple="true" + help="By default all are included if no selection is made."> <options from_dataset="group"> <column name="name" index="1"/> <column name="value" index="1"/> <filter type="unique_value" name="unq_grp" column="1" /> </options> </param> + <param name="name" type="data" format="names" optional="true" label="name - Sequences Name reference file for the tree"/> <param name="iters" type="integer" value="1000" label="iters - Number of bootstrap iterations to try (default 1000)"/> <!-- random uses input prompts, not sure how to model that <param name="random" type="text" value="" label="random - The root name for random tests"/>
--- a/mothur/tools/mothur/pca.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/pca.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,5 +1,5 @@ -<tool id="mothur_pca" name="Pca" version="1.16.0"> - <description>generate principle components plot data</description> +<tool id="mothur_pca" name="Pca" version="1.19.0"> + <description>Principal Coordinate Analysis for a shared file</description> <command interpreter="python"> mothur_wrapper.py ## 98_sq_phylip_amazon.fn.unique.pca.axes @@ -7,71 +7,36 @@ --cmd='pca' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.pca.axes$:'$pca_axes,'^\S+\.pca.loadings$:'$pca_loadings --outputdir='$logfile.extra_files_path' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --READ_groups='$input.groups' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --READ_groups='$input.groups' - #end if + #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__): + --shared=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('relabund').__class__): + --relabund=$otu + #end if + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' + #end if + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups='$groups' #end if $metric </command> <inputs> - <conditional name="input"> - <param name="source" type="select" label="Generate principle components for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> - <param name="metric" type="boolean" truevalue="" falsevalue="--Metric=False" checked="true" label="metric - Calculate pearson correlation coefficient" /> + <param name="otu" type="data" format="shared,relabund" label="shared,relabund - OTU Shared or Relabund file"/> + <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + <param name="metric" type="boolean" truevalue="" falsevalue="--metric=False" checked="true" label="metric - Calculate pearson correlation coefficient" /> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -94,8 +59,10 @@ **Command Documenation** -The pca_ command generate principle components plot data. +The pca_ command generate principle components plot data for a shared_ or relabund_ file. +.. _shared: http://www.mothur.org/wiki/Shared_file +.. _relabund: http://www.mothur.org/wiki/Get.relabund .. _pca: http://www.mothur.org/wiki/Pca </help>
--- a/mothur/tools/mothur/pcoa.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/pcoa.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,14 +1,16 @@ -<tool id="mothur_pcoa" name="Pcoa" version="1.16.0" > - <description>Principal Coordinate Analysis</description> +<tool id="mothur_pcoa" name="Pcoa" version="1.19.0" > + <description>Principal Coordinate Analysis for a distance matrix</description> <command interpreter="python"> mothur_wrapper.py --cmd='pcoa' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.pcoa\.axes$:'$pcoa,'^\S+\.pcoa.loadings$:'$loadings --outputdir='$logfile.extra_files_path' --phylip=$phylip + $metric </command> <inputs> <param name="phylip" type="data" format="lower.dist,square.dist" label="phylip - Phylip Distance Matrix"/> + <param name="metric" type="boolean" truevalue="" falsevalue="--metric=False" checked="true" label="metric - Calculate pearson correlation coefficient" /> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -31,8 +33,9 @@ **Command Documenation** -The pcoa_ command performs principal coordinate analysis. +The pcoa_ command performs principal coordinate analysis on a phylip-formatted_distance_matrix_. +.. _phylip-formatted_distance_matrix: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix .. _pcoa: http://www.mothur.org/wiki/Pcoa </help>
--- a/mothur/tools/mothur/phylo.diversity.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/phylo.diversity.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,18 +1,20 @@ -<tool id="mothur_phylo_diversity" name="Phylo.diversity" version="1.16.0"> - <description>Alpha Diversity calculate unique branch length</description> +<tool id="mothur_phylo_diversity" name="Phylo.diversity" version="1.19.0"> + <description>Alpha Diversity calculates unique branch length</description> <command interpreter="python"> mothur_wrapper.py --cmd='phylo.diversity' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.phylodiv\.summary$:'$summary_out,'^\S+\.phylodiv$:'$collectors_out,'^\S+\.rarefaction$:'$rarefaction_out --outputdir='$logfile.extra_files_path' - --READ_cmd='read.tree' - --READ_tree=$tree + --tree=$tree #if $group.__str__ != "None" and len($group.__str__) > 0: - --READ_group='$group' + --group='$group' #end if #if $groups.__str__ != "None" and len($groups.__str__) > 0: --groups='$groups' #end if + #if $name.__str__ != "None" and len($name.__str__) > 0: + --name='$name' + #end if #if int($iters.__str__) > 0: --iters=$iters #end if @@ -20,15 +22,17 @@ --freq=$freq #end if $scale - $summary $collect $rarefy + #if len($rarefy.__str__) > 0 or len($collect.__str__) > 0: + $summary + #end if --processors=2 </command> <inputs> <!-- list,group or shared --> - <param name="tree" type="data" format="tre" label="read.tree(tree=) - Phylogenetic Tree"/> - <param name="group" type="data" format="groups" label="read.tree(group=) - Group file for the tree"/> + <param name="tree" type="data" format="tre" label="tree - Phylogenetic Tree"/> + <param name="group" type="data" format="groups" label="group - Group file for the tree"/> <param name="groups" type="select" label="groups - Groups to display" multiple="true"> <options from_dataset="group"> <column name="name" index="1"/> @@ -36,6 +40,7 @@ <filter type="unique_value" name="unq_grp" column="1" /> </options> </param> + <param name="name" type="data" format="names" optional="true" label="name - Sequences Name reference file for the tree"/> <param name="iters" type="integer" value="1000" label="iters - Number of iterations to try (default 1000)"/> <param name="freq" type="float" value="0.0" label="freq - Reporting frequency" help="if between 0 and 1 the fraction of sequences to sample, if greater than one - report every n iterations"/>
--- a/mothur/tools/mothur/phylotype.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/phylotype.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,9 +1,9 @@ -<tool id="mothur_phylotype" name="Phylotype" version="1.16.0"> +<tool id="mothur_phylotype" name="Phylotype" version="1.19.0"> <description>Assign sequences to OTUs based on taxonomy</description> <command interpreter="python"> mothur_wrapper.py --cmd='phylotype' - --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.[fna]n\.sabund$:'$sabund,'^\S+\.[fna]n\.rabund$:'$rabund,'^\S+\.[fna]n\.list$:'$otulist + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.sabund$:'$sabund,'^\S+\.rabund$:'$rabund,'^\S+\.list$:'$otulist --outputdir='$logfile.extra_files_path' --taxonomy=$taxonomy #if 50 >= int($cutoff.__str__) > 0: @@ -17,7 +17,7 @@ #end if </command> <inputs> - <param name="taxonomy" type="data" format="taxonomy" label="taxonomy - Taxonomy"/> + <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy"/> <param name="name" type="data" format="names" optional="true" label="name - Names reference file for the taxonomy"/> <param name="label" type="select" label="label - Taxonomy Levels to report (All when none are selected)" multiple="true"> <option value="0">0</option> @@ -36,8 +36,8 @@ </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="rabund" name="rabund" label="${tool.name} on ${on_string}: rabund (Rank)"/> - <data format="sabund" name="sabund" label="${tool.name} on ${on_string}: sabund (Species)"/> + <data format="rabund" name="rabund" label="${tool.name} on ${on_string}: rabund (Rank Abundance)"/> + <data format="sabund" name="sabund" label="${tool.name} on ${on_string}: sabund (Species Abundance)"/> <data format="list" name="otulist" label="${tool.name} on ${on_string}: list (OTU List)"/> </outputs> <requirements> @@ -56,8 +56,11 @@ **Command Documenation** -The phylotype_ command assign sequences to OTUs based on their taxonomy and outputs a .list, .rabund and .sabund files. +The phylotype_ command assign sequences to OTUs based on their taxonomy and outputs a a list_, a sabund_ (Species Abundance), and a rabund_ (Relative Abundance) file. +.. _list: http://www.mothur.org/wiki/List_file +.. _rabund: http://www.mothur.org/wiki/Rabund_file +.. _sabund: http://www.mothur.org/wiki/Sabund_file .. _phylotype: http://www.mothur.org/wiki/Phylotype
--- a/mothur/tools/mothur/pre.cluster.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/pre.cluster.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,16 +1,22 @@ -<tool id="mothur_pre_cluster" name="Pre.cluster" version="1.16.0"> +<tool id="mothur_pre_cluster" name="Pre.cluster" version="1.19.0"> <description>Remove sequences due to pyrosequencing errors</description> <command interpreter="python"> mothur_wrapper.py + #import re, os.path + #set results = ["'^mothur.\S+\.logfile$:'" + $logfile.__str__] + ## adds .precluster before the last extension to the input file + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.precluster.\2',$os.path.basename($fasta.__str__)) + ":'" + $fasta_out.__str__] + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.precluster.names',$os.path.basename($fasta.__str__)) + ":'" + $names_out.__str__] --cmd='pre.cluster' - --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.precluster\.fasta$:'$fasta_out,'^\S+\.precluster\.names$:'$names_out --outputdir='$logfile.extra_files_path' --fasta=$fasta - #if $matrix.name.__str__ != "None" and len($matrix.name.__str__) > 0: + #if $name.__str__ != "None" and len($name.__str__) > 0: --name=$name + #end if #if 20 >= int($diffs.__str__) >= 0: --diffs=$diffs #end if + --result=#echo ','.join($results) </command> <inputs> <param name="fasta" type="data" format="fasta" label="fasta - Sequence Fasta"/>
--- a/mothur/tools/mothur/rarefaction.shared.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/rarefaction.shared.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,27 +1,16 @@ -<tool id="mothur_rarefaction_shared" name="Rarefaction.shared" version="1.16.0"> +<tool id="mothur_rarefaction_shared" name="Rarefaction.shared" version="1.19.0"> <description>Generate inter-sample rarefaction curves for OTUs</description> <command interpreter="python"> mothur_wrapper.py --cmd='rarefaction.shared' --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.rarefaction$:'$rarefaction --outputdir='$logfile.extra_files_path' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if + --shared=$otu + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups=$groups #end if #if int($iters.__str__) > 0: --iters=$iters @@ -32,46 +21,23 @@ #end if </command> <inputs> - <conditional name="input"> - <param name="source" type="select" label="Generate Heatmap for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> + <param name="otu" type="data" format="shared" label="shared - OTU Shared"/> + <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + <param name="groups" type="select" label="groups - Groups to analyze" multiple="true"> + <help>All groups will be analyzed by default if none are selected</help> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + <filter type="add_value" name="all" value="all" /> + </options> + </param> <param name="iters" type="integer" value="0" label="iters - Number of randomizations"/> <param name="jumble" type="boolean" truevalue="" falsevalue="--jumble=false" checked="true" label="jumble"/> <param name="calc" type="select" label="calc - Calculators (Uses defaults if none selected)" multiple="true"> @@ -103,7 +69,7 @@ **Command Documenation** -The rarefaction.shared_ command generates inter-sample rarefaction curves using a re-sampling without replacement approach. The traditional way that ecologists use rarefaction is not to randomize the sampling order within a sample, rather between samples. For instance, if we wanted to know the number of OTUs in the human colon, we might sample from various sites within the colon, and sequence a bunch of 16S rRNA genes. By determining the number of OTUs in each sample and comparing the composition of those samples it is possible to determine how well you have sampled the biodiversity within the individual. +The rarefaction.shared_ command generates inter-sample rarefaction curves using a re-sampling without replacement approach. The traditional way that ecologists use rarefaction is not to randomize the sampling order within a sample, rather between samples. For instance, if we wanted to know the number of OTUs in the human colon, we might sample from various sites within the colon, and sequence a bunch of 16S rRNA genes. By determining the number of OTUs in each sample and comparing the composition of those samples it is possible to determine how well you have sampled the biodiversity within the individual. For calc parameter choices see: http://www.mothur.org/wiki/Calculators .. _rarefaction.shared: http://www.mothur.org/wiki/Rarefaction.shared
--- a/mothur/tools/mothur/rarefaction.single.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/rarefaction.single.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_rarefaction_single" name="Rarefaction.single" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_rarefaction_single" name="Rarefaction.single" version="1.19.0" force_history_refresh="True"> <description>Generate intra-sample rarefaction curves for OTUs</description> <command interpreter="python"> mothur_wrapper.py @@ -6,11 +6,15 @@ --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?\.(((\S+)\.)?rarefaction)$:tabular' - --READ_cmd='read.otu' - --READ_list=$otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' + --new_datasets='^\S+?\.(((\S+)\.)?(rarefaction|r_\w*))$:tabular' + #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__): + --shared=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('rabund').__class__): + --rabund=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sabund').__class__): + --sabund=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('list').__class__): + --list=$otu #end if #if $label.__str__ != "None" and len($label.__str__) > 0: --label='$label' @@ -30,8 +34,7 @@ --processors=2 </command> <inputs> - <param name="otu" type="data" format="list,shared" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" optional="true" label="read.otu(lis =) - Group file for the OTU List"/> + <param name="otu" type="data" format="list,rabund,sabund,shared" label="list,rabund,sabund,shared - OTU List"/> <param name="label" type="select" label="label - OTU Labels" multiple="true"> <options from_dataset="otu"> <column name="name" index="0"/> @@ -71,7 +74,7 @@ **Command Documenation** -The rarefaction.single_ command generates intra-sample rarefaction curves using a re-sampling without replacement approach. Rarefaction curves provide a way of comparing the richness observed in different samples. +The rarefaction.single_ command generates intra-sample rarefaction curves using a re-sampling without replacement approach. Rarefaction curves provide a way of comparing the richness observed in different samples. For calc parameter choices see: http://www.mothur.org/wiki/Calculators .. _rarefaction.single: http://www.mothur.org/wiki/Rarefaction.single
--- a/mothur/tools/mothur/remove.groups.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/remove.groups.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,5 +1,5 @@ -<tool id="mothur_remove_groups" name="Remove.groups" version="1.16.0"> - <description>Remove groups</description> +<tool id="mothur_remove_groups" name="Remove.groups" version="1.19.0"> + <description>Remove groups from groups,fasta,names,list,taxonomy</description> <command interpreter="python"> mothur_wrapper.py #import re, os.path @@ -9,11 +9,14 @@ --cmd='remove.groups' --outputdir='$logfile.extra_files_path' --group=$group_in - #if $groups.__str__ != "None" and len($groups.__str__) > 0: - --groups=$groups - #end if - #if $accnos.__str__ != "None" and len($accnos.__str__) > 0: - --accnos=$accnos + #if $groupnames.source == 'groups': + #if $groupnames.groups.__str__ != "None" and len($groupnames.groups.__str__) > 0: + --groups=$groupnames.groups + #end if + #else + #if $groupnames.accnos.__str__ != "None" and len($groupnames.accnos.__str__) > 0: + --accnos=$groupnames.accnos + #end if #end if #if $fasta_in.__str__ != "None" and len($fasta_in.__str__) > 0: --fasta=$fasta_in @@ -36,24 +39,34 @@ </command> <inputs> <param name="group_in" type="data" format="groups" label="group - Groups"/> - <param name="groups" type="select" optional="true" label="groups - Pick groups to remove" multiple="true"> - <options from_dataset="group_in"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - <param name="accnos" type="data" format="accnos" optional="true" label="accnos - Accession Names"/> - <param name="fasta_in" type="data" format="fasta" optional="true" label="fasta - Fasta Sequences"/> + <conditional name="groupnames"> + <param name="source" type="select" label="Select Group Names from"> + <option value="groups">A List of Group Names</option> + <option value="accnos">A History Group Name Accnos Dataset</option> + </param> + <when value="groups"> + <param name="groups" type="select" label="groups - Pick groups to remove" multiple="true"> + <options from_dataset="group_in"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + </when> + <when value="accnos"> + <param name="accnos" type="data" format="accnos" label="accnos - Group Names from your history"/> + </when> + </conditional> + <param name="fasta_in" type="data" format="fasta,align" optional="true" label="fasta - Fasta Sequences"/> <param name="name_in" type="data" format="names" optional="true" label="name - Sequences Name reference"/> <param name="list_in" type="data" format="list" optional="true" label="list - OTU List"/> - <param name="taxonomy_in" type="data" format="taxonomy" optional="true" label="taxonomy - Taxonomy"/> + <param name="taxonomy_in" type="data" format="seq.taxonomy" optional="true" label="taxonomy - Taxonomy"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> <data format="groups" name="group_out" label="${tool.name} on ${on_string}: pick.groups"/> <!-- fix format --> - <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: pick.fasta"> + <data format_source="fasta_in" name="fasta_out" label="${tool.name} on ${on_string}: pick.fasta"> <filter>fasta_in != None</filter> </data> <data format="names" name="name_out" label="${tool.name} on ${on_string}: pick.name"> @@ -62,7 +75,7 @@ <data format="list" name="list_out" label="${tool.name} on ${on_string}: pick.list"> <filter>list_in != None</filter> </data> - <data format="taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"> + <data format="seq.taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"> <filter>taxonomy_in != None</filter> </data> </outputs> @@ -82,8 +95,12 @@ **Command Documenation** -The remove.groups_ command removes sequences from a specific group or set of groups from the following file types: fasta, name, group, list, taxonomy. +The remove.groups_ command removes sequences from a specific group or set of groups from the following file types: fasta, name_, group_, list_, taxonomy_. +.. _name: http://www.mothur.org/wiki/Name_file +.. _group: http://www.mothur.org/wiki/Group_file +.. _list: http://www.mothur.org/wiki/List_file +.. _taxonomy: http://www.mothur.org/wiki/Taxonomy_outline .. _remove.groups: http://www.mothur.org/wiki/Remove.groups
--- a/mothur/tools/mothur/remove.lineage.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/remove.lineage.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_remove_lineage" name="Remove.lineage" version="1.16.0"> +<tool id="mothur_remove_lineage" name="Remove.lineage" version="1.19.0"> <description>Picks by taxon</description> <command interpreter="python"> mothur_wrapper.py @@ -20,7 +20,7 @@ #end if #if $alignreport_in.__str__ != "None" and len($alignreport_in.__str__) > 0: --alignreport=$alignreport_in - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($alignreport_in.__str__)) + ":'" + $alignreport_out.__str__] + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.pick.align.report',$os.path.basename($alignreport_in.__str__)) + ":'" + $alignreport_out.__str__] #end if #if $list_in.__str__ != "None" and len($list_in.__str__) > 0: --list=$list_in @@ -34,7 +34,7 @@ --result=#echo ','.join($results) </command> <inputs> - <param name="taxonomy" type="data" format="taxonomy" label="taxonomy - Taxonomy"/> + <param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy"/> <param name="taxons" type="select" size="120" label="Browse Taxons from Taxonomy"> <options from_dataset="taxonomy"> <column name="name" index="1"/> @@ -53,7 +53,7 @@ <outputs> <!-- fix format --> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"/> + <data format="seq.taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"/> <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: pick.fasta"> <filter>fasta_in != None</filter> </data> @@ -86,8 +86,13 @@ **Command Documenation** -The remove.lineage_ command reads a taxonomy file and a taxon and generates a new file that contains only the sequences in the that are not from that taxon. You may also include either a fasta, name, group, list, or align.report file to this command and mothur will generate new files for each of those containing only the selected sequences. +The remove.lineage_ command reads a taxonomy_ file and a taxon and generates a new file that contains only the sequences in the that are not from that taxon. You may also include either a fasta_, name_, group_, list_, or align.report_ file to this command and mothur will generate new files for each of those containing only the selected sequences. +.. _taxonomy: http://www.mothur.org/wiki/Taxonomy_outline +.. _name: http://www.mothur.org/wiki/Name_file +.. _group: http://www.mothur.org/wiki/Group_file +.. _list: http://www.mothur.org/wiki/List_file +.. _align.report: http://www.mothur.org/wiki/Align.seqs .. _remove.lineage: http://www.mothur.org/wiki/Remove.lineage
--- a/mothur/tools/mothur/remove.otus.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/remove.otus.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_remove_otus" name="Remove.otus" version="1.16.0"> +<tool id="mothur_remove_otus" name="Remove.otus" version="1.19.0"> <description>Remove otus containing sequences from specified groups</description> <command interpreter="python"> mothur_wrapper.py @@ -9,11 +9,14 @@ --group=$group_in --list=$list_in --label=$label - #if $groups.__str__ != "None" and len($groups.__str__) > 0: - --groups=$groups - #end if - #if $accnos.__str__ != "None" and len($accnos.__str__) > 0: - --accnos=$accnos + #if $groupnames.source == 'groups': + #if $groupnames.groups.__str__ != "None" and len($groupnames.groups.__str__) > 0: + --groups=$groupnames.groups + #end if + #else + #if $groupnames.accnos.__str__ != "None" and len($groupnames.accnos.__str__) > 0: + --accnos=$groupnames.accnos + #end if #end if #set results = ["'^mothur.\S+\.logfile$:'" + $logfile.__str__] #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.' + $label.__str__ + '.\2',$os.path.basename($group_in.__str__)) + ":'" + $group_out.__str__] @@ -29,14 +32,25 @@ <column name="value" index="0"/> </options> </param> - <param name="groups" type="select" optional="true" label="groups - Pick groups to include" multiple="true"> - <options from_dataset="group_in"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - <param name="accnos" type="data" format="accnos" optional="true" label="accnos - Group Names from your history"/> + <conditional name="groupnames"> + <param name="source" type="select" label="Select Group Names from"> + <option value="groups">A List of Group Names</option> + <option value="accnos">A History Group Name Accnos Dataset</option> + </param> + <when value="groups"> + <param name="groups" type="select" label="groups - Pick groups to include" multiple="true" force_select="true"> + <help>At least one group must be selected</help> + <options from_dataset="group_in"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + </when> + <when value="accnos"> + <param name="accnos" type="data" format="accnos" optional="true" label="accnos - Group Names from your history"/> + </when> + </conditional> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -59,8 +73,9 @@ **Command Documenation** -The remove.otus_ command removes otus containing sequences from a specific group or set of groups. +The remove.otus_ command removes otus from a list_ containing sequences from a specific group or set of groups. +.. _list: http://www.mothur.org/wiki/List_file .. _remove.otus: http://www.mothur.org/wiki/Remove.otus
--- a/mothur/tools/mothur/remove.rare.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/remove.rare.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,71 +1,103 @@ -<tool id="mothur_remove_rare" name="Remove.rare" version="1.16.0"> +<tool id="mothur_remove_rare" name="Remove.rare" version="1.19.0"> <description>Remove rare OTUs</description> <command interpreter="python"> mothur_wrapper.py - ## output {group_file_name}.pick.{label}.groups {list_file_name}.pick.{label}.list + ## output {group_file_name}.pick.groups {list_file_name}.pick.{format} #import re, os.path #set results = ["'^mothur.\S+\.logfile$:'" + $logfile.__str__] --cmd='remove.rare' --outputdir='$logfile.extra_files_path' - #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__): - --shared=$otu - #if $group_in.__str__ != "None" and len($group_in.__str__) > 0: - --group=$group_in + #if isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__): + --shared=$input.otu + $input.bygroup + #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: + --groups=$input.groups #end if - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.otu_in.__str__)) + ":'" + $pick_shared.__str__] - #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('rabund').__class__): - --rabund=$otu - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.otu_in.__str__)) + ":'" + $pick_rabund.__str__] - #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sabund').__class__): - --sabund=$otu - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.otu_in.__str__)) + ":'" + $pick_sabund.__str__] - #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('list').__class__): - --list=$otu - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.otu_in.__str__)) + ":'" + $pick_list.__str__] - $bygroup + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.otu.__str__)) + ":'" + $pick_otu.__str__] + #elif isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('rabund').__class__): + --rabund=$input.otu + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.otu.__str__)) + ":'" + $pick_otu.__str__] + #elif isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sabund').__class__): + --sabund=$input.otu + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.otu.__str__)) + ":'" + $pick_otu.__str__] + #elif isinstance($input.otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('list').__class__): + --list=$input.otu + #if $input.group.__str__ != "None" and len($input.group.__str__) > 0: + --group=$input.group + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.group.__str__)) + ":'" + $pick_group.__str__] + #end if + #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: + --groups=$input.groups + #end if + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($input.otu.__str__)) + ":'" + $pick_otu.__str__] #end if - #if $label.__str__ != "None" and len($label.__str__) > 0: - --label=$label - #end if - #if $groups.__str__ != "None" and len($groups.__str__) > 0: - --groups=$groups + #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: + --label=$input.label #end if --nseqs=$nseqs --result=#echo ','.join($results) </command> <inputs> - <param name="otu" type="data" format="list,rabund,sabund,shared" label="shared/relabund - Otu dataset"/> - <param name="group_in" type="data" format="groups" label="group - Groups" optional="true"/> - <param name="label" type="select" optional="true" label="label - OTU Labels" > - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" optional="true" label="groups - Pick groups to annalyze" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - <param name="nseqs" type="integer" value="1" label="nseqs - iNumber of sequences cutoff for an otu to be deemed rare"/> - <param name="bygroup" type="boolean" truevalue="--bygroup=true" falsevalue="" checked="false" label="bygroup - Remove any OTU that has nseqs or fewer sequences across all groups"/> + <conditional name="input"> + <param name="source" type="select" label="Select Input Format"> + <option value="shared">shared</option> + <option value="list">list and groups</option> + <option value="default">rabund, sabund, or list</option> + </param> + <when value="shared"> + <param name="otu" type="data" format="shared" label="shared - Otu dataset"/> + <param name="groups" type="select" optional="true" label="groups - Pick groups to analyze" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + <param name="bygroup" type="boolean" truevalue="--bygroup=true" falsevalue="" checked="false" label="bygroup - Remove any OTU that has nseqs or fewer sequences across all groups"/> + <param name="label" type="select" multiple="true" optional="true" label="label - OTU Labels" > + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + </when> + <when value="list"> + <param name="otu" type="data" format="list" label="list - Otu dataset"/> + <param name="group" type="data" format="groups" label="group - Groups" /> + <param name="groups" type="select" optional="true" label="groups - Pick groups to analyze" multiple="true"> + <options from_dataset="group"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + <param name="label" type="select" multiple="false" optional="true" label="label - OTU Labels" > + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + </when> + <when value="default"> + <param name="otu" type="data" format="shared,list,rabund,sabund" label="shared,list,rabund,sabund - Otu dataset"/> + <param name="label" type="select" multiple="true" optional="true" label="label - OTU Labels" > + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + </when> + </conditional> + <param name="nseqs" type="integer" value="1" label="nseqs - Number of sequences cutoff for an otu to be deemed rare"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="list" name="pick_list" label="${tool.name} on ${on_string}: pick.list"> - <filter>otu.datatype == 'list'</filter> - </data> - <data format="rabund" name="pick_rabund" label="${tool.name} on ${on_string}: pick.rabund"> - <filter>otu.datatype == 'rabund'</filter> - </data> - <data format="sabund" name="pick_sabund" label="${tool.name} on ${on_string}: pick.sabund"> - <filter>otu.datatype == 'sabund'</filter> - </data> - <data format="shared" name="pick_shared" label="${tool.name} on ${on_string}: pick.shared"> - <filter>otu.datatype == 'shared'</filter> + <data format_source="otu" name="pick_otu" label="${tool.name} on ${on_string}: pick.${input.otu.ext}"/> + <data format="groups" name="pick_group" label="${tool.name} on ${on_string}: pick.groups"> + <filter>input['source'] == 'list'</filter> </data> </outputs> <requirements> @@ -84,8 +116,12 @@ **Command Documenation** -The remove.rare_ command reads one of the following file types: list, rabund, sabund or shared file. It outputs a new file after removing the rare otus. +The remove.rare_ command reads one of the following file types: list_, rabund_, sabund_ or shared_ file. It outputs a new file after removing the rare otus. +.. _list: http://www.mothur.org/wiki/List_file +.. _sabund: http://www.mothur.org/wiki/Sabund_file +.. _rabund: http://www.mothur.org/wiki/Rabund_file +.. _shared: http://www.mothur.org/wiki/Shared_file .. _remove.rare: http://www.mothur.org/wiki/Remove.rare
--- a/mothur/tools/mothur/remove.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/remove.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_remove_seqs" name="Remove.seqs" version="1.16.0"> +<tool id="mothur_remove_seqs" name="Remove.seqs" version="1.19.0"> <description>Remove sequences by name</description> <command interpreter="python"> mothur_wrapper.py @@ -47,7 +47,7 @@ <param name="group_in" type="data" format="groups" optional="true" label="group - Sequences Groups"/> <param name="alignreport_in" type="data" format="align.report" optional="true" label="alignreport - Align Report"/> <param name="list_in" type="data" format="list" optional="true" label="list - OTU List"/> - <param name="taxonomy_in" type="data" format="taxonomy" optional="true" label="taxonomy - Taxonomy"/> + <param name="taxonomy_in" type="data" format="seq.taxonomy" optional="true" label="taxonomy - Taxonomy"/> <param name="dups" type="boolean" truevalue="" falsevalue="--dups=false" checked="true" label="dups - Apply to duplicates"/> </inputs> <outputs> @@ -83,7 +83,7 @@ <data format="list" name="list_out" label="${tool.name} on ${on_string}: pick.list"> <filter>list_in != None</filter> </data> - <data format="taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"> + <data format="seq.taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"> <filter>taxonomy_in != None</filter> </data> </outputs> @@ -103,8 +103,14 @@ **Command Documenation** -The remove.seqs_ command takes a list of sequence names and either a fasta, name, group, list, or align.report file to generate a new file that does not contain the sequences in the list. This command may be used in conjunction with the list.seqs command to help screen a sequence collection. +The remove.seqs_ command takes a list of sequence names and either a fasta, name_, group_, list_, align.report_ or taxonomy_ file to generate a new file that does not contain the sequences in the list. This command may be used in conjunction with the list.seqs_ command to help screen a sequence collection. +.. _name: http://www.mothur.org/wiki/Name_file +.. _group: http://www.mothur.org/wiki/Group_file +.. _list: http://www.mothur.org/wiki/List_file +.. _align.report: http://www.mothur.org/wiki/Align.seqs +.. _taxonomy: http://www.mothur.org/wiki/Taxonomy_outline +.. _list.seqs: http://www.mothur.org/wiki/list.seqs .. _remove.seqs: http://www.mothur.org/wiki/Remove.seqs </help>
--- a/mothur/tools/mothur/reverse.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/reverse.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_reverse_seqs" name="Reverse.seqs" version="1.16.0"> +<tool id="mothur_reverse_seqs" name="Reverse.seqs" version="1.19.0"> <description>Reverse complement the sequences</description> <command interpreter="python"> mothur_wrapper.py @@ -8,11 +8,11 @@ --fasta=$fasta </command> <inputs> - <param name="fasta" type="data" format="fasta" label="fasta - Sequences to reverse complement"/> + <param name="fasta" type="data" format="fasta,align" label="fasta - Sequences to reverse complement"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="fasta" name="out_fasta" label="${tool.name} on ${on_string}: rc.fasta" /> + <data format_source="fasta" name="out_fasta" label="${tool.name} on ${on_string}: rc.fasta" /> </outputs> <requirements> <requirement type="binary">mothur</requirement>
--- a/mothur/tools/mothur/screen.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/screen.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,12 +1,12 @@ -<tool id="mothur_screen_seqs" name="Screen.seqs" version="1.16.0"> +<tool id="mothur_screen_seqs" name="Screen.seqs" version="1.19.0"> <description>Screen sequences</description> <command interpreter="python"> mothur_wrapper.py #import re, os.path --cmd='screen.seqs' #set results = ["'^mothur.\S+\.logfile$:'" + $logfile.__str__] - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.good.\2',$os.path.basename($input.__str__)) + ":'" + $out_file.__str__] - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.bad.accnos',$os.path.basename($input.__str__)) + ":'" + $bad_accnos.__str__] + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.good.\2',$os.path.basename($input.__str__)) + ":'" + $out_file.__str__] + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.bad.accnos',$os.path.basename($input.__str__)) + ":'" + $bad_accnos.__str__] --outputdir='$logfile.extra_files_path' --tmpdir='${logfile.extra_files_path}/input' --fasta=$input @@ -34,17 +34,21 @@ #if $optimize != None and $optimize.__str__ != "None": --optimize=$optimize #end if + #if $input_qfile != None and $input_qfile.__str__ != "None": + --qfile=$input_qfile + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.good.\2',$os.path.basename($input_qfile.__str__)) + ":'" + $output_qfile.__str__] + #end if #if $input_names != None and $input_names.__str__ != "None": --name=$input_names - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.good.\2',$os.path.basename($input_names.__str__)) + ":'" + $output_names.__str__] + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.good.\2',$os.path.basename($input_names.__str__)) + ":'" + $output_names.__str__] #end if #if $input_groups != None and $input_groups.__str__ != "None": --group=$input_groups - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.good.\2',$os.path.basename($input_groups.__str__)) + ":'" + $output_groups.__str__] + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.good.\2',$os.path.basename($input_groups.__str__)) + ":'" + $output_groups.__str__] #end if #if $input_alignreport != None and $input_alignreport.__str__ != "None": --alignreport=$input_alignreport - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.good.\2',$os.path.basename($input_alignreport.__str__)) + ":'" + $output_alignreport.__str__] + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.good.\2',$os.path.basename($input_alignreport.__str__)) + ":'" + $output_alignreport.__str__] #end if --result=#echo ','.join($results) --processors=2 @@ -66,18 +70,18 @@ <option value="maxambig">maxambig</option> <option value="maxhomop">maxhomop</option> </param> - <param name="input_names" type="data" format="names" optional="true" label="name - Sequece Names to screen"/> + <param name="input_qfile" type="data" format="qual" optional="true" label="qfile - Sequence Quality file to screen"/> + <param name="input_names" type="data" format="names" optional="true" label="name - Sequence Names to screen"/> <param name="input_groups" type="data" format="groups" optional="true" label="group - Groups to screen"/> <param name="input_alignreport" type="data" format="align.report" optional="true" label="alignreport - Align Report to screen"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="fasta" name="out_file" label="${tool.name} on ${on_string}: good.${input.datatype.file_ext}" > - <change_format> - <when input_dataset="input" attribute="ext" value="align" format="align"/> - </change_format> + <data format_source="input" name="out_file" label="${tool.name} on ${on_string}: good.${input.datatype.file_ext}" /> + <data format="accnos" name="bad_accnos" label="${tool.name} on ${on_string}: bad.accnos" /> + <data format_source="input_qfile" name="output_qfile" label="${tool.name} on ${on_string}: qfile" > + <filter>input_qfile != None</filter> </data> - <data format="accnos" name="bad_accnos" label="${tool.name} on ${on_string}: bad.accnos" /> <data format="names" name="output_names" label="${tool.name} on ${on_string}: names" > <filter>input_names != None</filter> </data> @@ -104,8 +108,11 @@ **Command Documenation** -The screen.seqs_ command enables you to keep sequences that fulfill certain user defined criteria. Furthermore, it enables you to cull those sequences not meeting the criteria from a names, group, or align.report file. +The screen.seqs_ command enables you to keep sequences that fulfill certain user defined criteria. Furthermore, it enables you to cull those sequences not meeting the criteria from a name_, group_, or align.report_ file. +.. _name: http://www.mothur.org/wiki/Name_file +.. _group: http://www.mothur.org/wiki/Group_file +.. _align.report: http://www.mothur.org/wiki/Align.seqs .. _screen.seqs: http://www.mothur.org/wiki/Screen.seqs
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mothur/tools/mothur/sens.spec.xml Tue Jun 07 17:05:08 2011 -0400 @@ -0,0 +1,70 @@ +<tool id="mothur_sens_spec" name="Sens.spec" version="1.19.0" > + <description>Determine the quality of OTU assignment</description> + <command interpreter="python"> + mothur_wrapper.py + #import re, os.path + --cmd='sens.spec' + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.sensspec$:'$sensspec + --outputdir='$logfile.extra_files_path' + --list=$list + #if isinstance($dist.datatype, $__app__.datatypes_registry.get_datatype_by_extension('pair.dist').__class__): + --column=$dist + #else + --phylip=$dist + #end if + #if $label.__str__ != "None" and len($label.__str__) > 0: + --label='$label' + #end if + #if len($precision.__str__) > 0: + --precision=$precision + #end if + #if float($cutoff.__str__) > 0.0: + --cutoff=$cutoff + #end if + $hard + </command> + <inputs> + <param name="list" type="data" format="list" label="list - OTU List"/> + <param name="dist" type="data" format="dist" label="phylip,column - Distance Matrix"/> + <param name="label" type="select" optional="true" label="label - Select OTU Labels to include" multiple="true" + help="By default all are included if no selection is made."> + <options from_dataset="list"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + <param name="precision" type="integer" value="100" optional="true" label="precision - Precision for rounding distance values"/> + <param name="cutoff" type="float" value="0.0" label="cutoff - Distance Cutoff threshold - ignored if not > 0" + help="Ignore pairwise distances larger than this, a common value would be 0.10"/> + <param name="hard" type="boolean" checked="false" truevalue="--hard=true" falsevalue="" label="hard - Use hard cutoff instead of rounding"/> + </inputs> + <outputs> + <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="tabular" name="sensspec" label="${tool.name} on ${on_string}: sensspec" /> + </outputs> + <requirements> + <requirement type="binary">mothur</requirement> + </requirements> + <tests> + </tests> + <help> +**Mothur Overview** + +Mothur_, initiated by Dr. Patrick Schloss and his software development team +in the Department of Microbiology and Immunology at The University of Michigan, +provides bioinformatics for the microbial ecology community. + +.. _Mothur: http://www.mothur.org/wiki/Main_Page + +**Command Documenation** + +The sens.spec_ command takes a list_ and either a column_ or phylip_ distance matrix to determine the quality of OTU assignment. + + +.. _list: http://www.mothur.org/wiki/List_file +.. _column: http://www.mothur.org/wiki/Column-formatted_distance_matrix +.. _phylip: http://www.mothur.org/wiki/Phylip-formatted_distance_matrix +.. _sens.spec: http://www.mothur.org/wiki/Sens.spec + + </help> +</tool>
--- a/mothur/tools/mothur/sffinfo.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/sffinfo.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_sffinfo" name="Sffinfo" version="1.16.0"> +<tool id="mothur_sffinfo" name="Sffinfo" version="1.19.0"> <description>Summarize the quality of sequences</description> <command interpreter="python"> mothur_wrapper.py
--- a/mothur/tools/mothur/split.abund.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/split.abund.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,29 +1,50 @@ -<tool id="mothur_split_abund" name="Split.abund" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_split_abund" name="Split.abund" version="1.19.0" force_history_refresh="True"> <description>Separate sequences into rare and abundant groups</description> <command interpreter="python"> mothur_wrapper.py --cmd='split.abund' - --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.abund\.list$:'$abund_list,'^\S+\.rare\.list$:'$rare_list,'^\S+\.rare\.accnos$:'$rare_accnos,'^\S+\.abund\.accnos$:'$abund_accnos + #import re, os.path + --result='^mothur.\S+\.logfile$:'$logfile + ## --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.abund\.list$:'$abund_list,'^\S+\.rare\.list$:'$rare_list,'^\S+\.rare\.accnos$:'$rare_accnos,'^\S+\.abund\.accnos$:'$abund_accnos --outputdir='$logfile.extra_files_path' - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?\.((unique|[0-9.]+)\.(rare|abund)\.fasta)$:fasta','^\S+?\.((unique|[0-9.]+)\.(rare|abund)\.groups)$:groups','^\S+?\.((unique|[0-9.]+)\.(rare|abund)\.accnos)$:accnos' + #set datasets = [] + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.((unique|[0-9.]+)\.(rare|abund)\.fasta)$:fasta','^\S+?\.((unique|[0-9.]+)\.(rare|abund)\.groups)$:groups','^\S+?\.((unique|[0-9.]+)\.(rare|abund)\.accnos)$:accnos' + #end if --fasta=$fasta + #set datasets = $datasets + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'^\1.(.*\.fasta)$',$os.path.basename($fasta.__str__)) + ":fasta'"] #if $search.type == "list": --list=$search.input + #set datasets = $datasets + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'^\1.(.*\.list)$',$os.path.basename($search.input.__str__)) + ":list'"] + #if $accnos: + #set datasets = $datasets + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'^\1.(.*\.accnos)$',$os.path.basename($search.input.__str__)) + ":accnos'"] + #end if #if $search.label.__str__ != "None" and len($search.label.__str__) > 0: --label=$search.label #end if #elif $search.type == "name": --name=$search.input + #set datasets = $datasets + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'^\1.(.*\.names)$',$os.path.basename($search.input.__str__)) + ":names'"] + #if $accnos: + #set datasets = $datasets + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'^\1.(.*\.accnos)$',$os.path.basename($search.input.__str__)) + ":accnos'"] + #end if #end if --cutoff=$cutoff - #if $group.__str__ != "None" and len($group.__str__) > 0: - --group=$group - #end if - #if $groups.__str__ != "None" and len($groups.__str__) > 0: - --groups=$groups + #if $split.type == 'yes': + #if $split.group.__str__ != "None" and len($split.group.__str__) > 0: + --group=$split.group + #set datasets = $datasets + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'^\1.(.*\.groups)$',$os.path.basename($split.group.__str__)) + ":groups'"] + #end if + #if $split.groups.__str__ != "None" and len($split.groups.__str__) > 0: + --groups=$split.groups + #end if #end if $accnos + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets=#echo ','.join($datasets) + #end if </command> <inputs> <param name="fasta" type="data" format="fasta" label="fasta - Fasta"/> @@ -37,27 +58,38 @@ </when> <when value="list"> <param name="input" type="data" format="list" label="list - OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <param name="label" type="select" label="label - OTU Labels" multiple="true" help="Select OTU Labels to filter out all but selected labels"> <options from_dataset="input"> <column name="name" index="0"/> <column name="value" index="0"/> </options> </param> </when> - </conditional> + </conditional> <!-- search --> <param name="cutoff" type="integer" value="10" label="cutoff - Cutoff parameter is used to qualify what is abundant and rare."/> - <param name="group" type="data" format="groups" optional="true" label="group - Group dataset"/> - <param name="groups" type="select" label="groups - Group Selection (all used if none are selected)" multiple="true"> - <options from_dataset="group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> + <conditional name="split"> + <param name="type" type="select" label="Parse a group file into abundant and rare groups?" help=""> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> + <when value="no"/> + <when value="yes"> + <param name="group" type="data" format="groups" label="group - Group dataset"/> + <param name="groups" type="select" label="groups - Group Selection (all used if none are selected)" multiple="true"> + <options from_dataset="group"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> + </when> + </conditional> <!-- split --> <param name="accnos" type="boolean" truevalue="--accnos=true" falsevalue="" checked="false" label="accnos - Produce rare and abundant Accession outputs"/> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Create a new history dataset for each label"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <!-- <data format="list" name="abund_list" label="${tool.name} on ${on_string}: abund.list" /> <data format="list" name="rare_list" label="${tool.name} on ${on_string}: rare.list" /> <data format="accnos" name="rare_accnos" label="${tool.name} on ${on_string}: rare.accnos"> @@ -66,6 +98,7 @@ <data format="accnos" name="abund_accnos" label="${tool.name} on ${on_string}: abund.accnos"> <filter>accnos == True</filter> </data> + --> </outputs> <requirements> <requirement type="binary">mothur</requirement> @@ -83,8 +116,10 @@ **Command Documenation** -The split.abund_ command reads a fasta file and a list or a names file and splits the sequences into rare and abundant groups. +The split.abund_ command reads a fasta file and a list_ or a name_ file and splits the sequences into rare and abundant groups. +.. _list: http://www.mothur.org/wiki/List_file +.. _name: http://www.mothur.org/wiki/Name_file .. _split.abund: http://www.mothur.org/wiki/Split.abund </help>
--- a/mothur/tools/mothur/split.groups.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/split.groups.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_split_groups" name="Split.groups" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_split_groups" name="Split.groups" version="1.19.0" force_history_refresh="True"> <description>Generates a fasta file for each group</description> <command interpreter="python"> mothur_wrapper.py @@ -6,13 +6,27 @@ --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?\.(\S+\.fasta)$:fasta' + --new_datasets='^\S+?\.(\S+\.fasta)$:fasta','^\S+?\.(\S+\.names)$:names' --fasta=$fasta --group=$group + #if $name.__str__ != "None" and len($name.__str__) > 0: + --name=$name + #end if + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups=$groups + #end if </command> <inputs> - <param name="fasta" type="data" format="fasta" label="fasta - Fasta"/> + <param name="fasta" type="data" format="fasta" label="fasta - Fasta to split by group"/> + <param name="name" type="data" format="names" label="name - Names to split by group" optional="true"/> <param name="group" type="data" format="groups" label="group - Groups"/> + <param name="groups" type="select" optional="true" label="groups - Pick groups to analyze" multiple="true"> + <options from_dataset="group"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -33,8 +47,10 @@ **Command Documenation** -The split.groups_ command reads a fasta file group file and generates a fasta file for each group in the groupfile. +The split.groups_ command reads a fasta file and group_ file and generates a fasta file for each group in the groupfile. A name_ file can also be split into groups. +.. _group: http://www.mothur.org/wiki/Group_file +.. _name: http://www.mothur.org/wiki/Name_file .. _split.groups: http://www.mothur.org/wiki/Split.groups </help>
--- a/mothur/tools/mothur/sub.sample.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/sub.sample.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_sub_sample" name="Sub.sample" version="1.16.0"> +<tool id="mothur_sub_sample" name="Sub.sample" version="1.19.0"> <description>Create a sub sample</description> <command interpreter="python"> mothur_wrapper.py @@ -12,26 +12,30 @@ #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.subsample.\2',$os.path.basename($input.fasta_in.__str__)) + ":'" + $fasta_out.__str__] #if $input.name_in.__str__ != "None" and len($input.name_in.__str__) > 0: --name=$input.name_in - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.subsample.\2',$os.path.basename($input.name_in.__str__)) + ":'" + $names_out.__str__] + ## #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.subsample.\2',$os.path.basename($input.name_in.__str__)) + ":'" + $names_out.__str__] #end if - #if $input.use_group.group_in.__str__ != "None" and len($input.use_group.group_in.__str__) > 0: - --group=$input.use_group.group_in - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.subsample.\2',$os.path.basename($input.use_group.group_in.__str__)) + ":'" + $group_out.__str__] - #if $input.use_group.groups.__str__ != "None" and len($input.use_group.groups.__str__) > 0: - --groups=$input.use_group.groups + #if $input.use_group.to_filter == "yes": + #if $input.use_group.group_in.__str__ != "None" and len($input.use_group.group_in.__str__) > 0: + --group=$input.use_group.group_in + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.subsample.\2',$os.path.basename($input.use_group.group_in.__str__)) + ":'" + $group_out.__str__] + #if $input.use_group.groups.__str__ != "None" and len($input.use_group.groups.__str__) > 0: + --groups=$input.use_group.groups + #end if + $input.use_group.persample #end if - $input.use_group.persample #end if #elif $input.format == "list": --list=$input.otu_in #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.subsample.\2',$os.path.basename($input.otu_in.__str__)) + ":'" + $list_out.__str__] - #if $input.use_group.group_in.__str__ != "None" and len($input.use_group.group_in.__str__) > 0: - --group=$input.use_group.group_in - #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.subsample.\2',$os.path.basename($input.use_group.group_in.__str__)) + ":'" + $group_out.__str__] - #if $input.use_group.groups.__str__ != "None" and len($input.use_group.groups.__str__) > 0: - --groups=$input.use_group.groups + #if $input.use_group.to_filter == "yes": + #if $input.use_group.group_in.__str__ != "None" and len($input.use_group.group_in.__str__) > 0: + --group=$input.use_group.group_in + #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.subsample.\2',$os.path.basename($input.use_group.group_in.__str__)) + ":'" + $group_out.__str__] + #if $input.use_group.groups.__str__ != "None" and len($input.use_group.groups.__str__) > 0: + --groups=$input.use_group.groups + #end if + $input.use_group.persample #end if - $input.use_group.persample #end if #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: --label=$input.label @@ -176,9 +180,11 @@ <data format="rabund" name="rabund_out" label="${tool.name} on ${on_string}: subsample.rabund"> <filter>input['format'] == 'rabund'</filter> </data> + <!-- This doesn't appear to be generated even though the documentation says it is <data format="names" name="names_out" label="${tool.name} on ${on_string}: subsample.names"> <filter>(input['format'] == 'fasta' and input['name_in'] != None)</filter> </data> + --> <data format="groups" name="group_out" label="${tool.name} on ${on_string}: subsample.groups"> <filter>input['use_group']['group_in'] != None</filter> </data> @@ -199,8 +205,12 @@ **Command Documenation** -The sub.sample_ command selects otus containing sequences from a specific group or set of groups. +The sub.sample_ command can be used as a way to normalize your data, or to create a smaller set from your original set. It takes as an input the following file types: fasta, list_, shared_, rabund_ and sabund_ to generate a new file that contains a sampling of your original file. +.. _list: http://www.mothur.org/wiki/List_file +.. _shared: http://www.mothur.org/wiki/Shared_file +.. _rabund: http://www.mothur.org/wiki/Rabund_file +.. _sabund: http://www.mothur.org/wiki/Sabund_file .. _sub.sample: http://www.mothur.org/wiki/Sub.sample
--- a/mothur/tools/mothur/summary.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/summary.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_summary_seqs" name="Summary.seqs" version="1.16.0"> +<tool id="mothur_summary_seqs" name="Summary.seqs" version="1.19.0"> <description>Summarize the quality of sequences</description> <command interpreter="python"> mothur_wrapper.py @@ -6,9 +6,13 @@ --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.summary$:'$out_summary --outputdir='$logfile.extra_files_path' --fasta=$fasta + #if $name.__str__ != "None" and len($name.__str__) > 0: + --name=$name + #end if </command> <inputs> <param name="fasta" type="data" format="fasta,align" label="fasta - Dataset"/> + <param name="name" type="data" format="names" label="name - Names" optional="true"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" />
--- a/mothur/tools/mothur/summary.shared.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/summary.shared.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_summary_shared" name="Summary.shared" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_summary_shared" name="Summary.shared" version="1.19.0" force_history_refresh="True"> <description>Summary of calculator values for OTUs</description> <command interpreter="python"> mothur_wrapper.py @@ -7,81 +7,35 @@ --outputdir='$logfile.extra_files_path' --datasetid='$logfile.id' --new_file_path='$__new_file_path__' --new_datasets='^\S+?\.((\S+)\.(unique|[0-9.]*)\.dist)$:lower.dist' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' - #end if - #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups - #end if - #* - --READ_list=$otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' + --shared=$otu + #if $groups.__str__ != "None" and len($groups.__str__) > 0: + --groups=$groups #end if #if $label.__str__ != "None" and len($label.__str__) > 0: --label='$label' #end if - *# #if $calc.__str__ != "None" and len($calc.__str__) > 0: --calc='$calc' #end if $all + $distance </command> <inputs> - <!-- list,group or shared --> - <conditional name="input"> - <param name="source" type="select" label="Generate Collector Curvers for"> - <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> - </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - <filter type="unique_value" name="unq_lbl" column="0" /> - </options> - </param> - <param name="groups" type="select" label="groups - Pairwise comparision groups" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - </conditional> + <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> + <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> + </options> + </param> + <param name="groups" type="select" label="groups - Pairwise comparision groups" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="1"/> + <column name="value" index="1"/> + <filter type="unique_value" name="unq_grp" column="1" /> + </options> + </param> <param name="calc" type="select" label="calc - Calculators (Uses defaults if none selected)" multiple="true"> <options from_file="mothur_calculators.loc"> <column name="mult" index="1"/> @@ -113,8 +67,10 @@ **Command Documenation** -The summary.shared_ command produce a summary file that has the calculator value for each line in the OTU data and for all possible comparisons between the different groups in the group file. +The summary.shared_ command produce a summary file that has the calculator value for each line in the OTU data of the shared_ file and for all possible comparisons between the different groups in the group_ file. This can be useful if you aren't interested in generating collector's or rarefaction curves for your multi-sample data analysis. It would be worth your while, however, to look at the collector's curves for the calculators you are interested in to determine how sensitive the values are to sampling. If the values are not sensitive to sampling, then you can trust the values. Otherwise, you need to keep sampling. For calc parameter choices see: http://www.mothur.org/wiki/Calculators +.. _shared: http://www.mothur.org/wiki/Shared_file +.. _group: http://www.mothur.org/wiki/Group_file .. _summary.shared: http://www.mothur.org/wiki/Summary.shared </help>
--- a/mothur/tools/mothur/summary.single.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/summary.single.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,16 +1,25 @@ -<tool id="mothur_summary_single" name="Summary.single" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_summary_single" name="Summary.single" version="1.19.0" force_history_refresh="True"> <description>Summary of calculator values for OTUs</description> <command interpreter="python"> mothur_wrapper.py --cmd='summary.single' - --result='^mothur.\S+\.logfile$:'$logfile + #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__) and not $groupmode.__str__ == '--groupmode=true': + --result='^mothur.\S+\.logfile$:'$logfile + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+\.((\S+?)\.summary)$:tabular' + #else: + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.summary$:'$summary + #end if --outputdir='$logfile.extra_files_path' - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+\.((\S+?)\.summary)$:tabular' - --READ_cmd='read.otu' - --READ_list=$otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' + #if isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('shared').__class__): + --shared=$otu + $groupmode + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('rabund').__class__): + --rabund=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sabund').__class__): + --sabund=$otu + #elif isinstance($otu.datatype, $__app__.datatypes_registry.get_datatype_by_extension('list').__class__): + --list=$otu #end if #if $label.__str__ != "None" and len($label.__str__) > 0: --label='$label' @@ -24,16 +33,14 @@ #if int($size.__str__) > 0: --size=$size #end if - $groupmode - --processors=2 </command> <inputs> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" optional="true" label="read.otu(group=) - Group file for the OTU List"/> + <param name="otu" type="data" format="list,rabund,sabund,shared" label="list,rabund,sabund,shared - OTU List"/> <param name="label" type="select" label="label - OTU Labels" multiple="true"> <options from_dataset="otu"> <column name="name" index="0"/> <column name="value" index="0"/> + <filter type="unique_value" name="unq_lbl" column="0" /> </options> </param> <param name="calc" type="select" label="calc - Calculators (Uses defaults if none selected)" multiple="true"> @@ -46,10 +53,15 @@ </param> <param name="abund" type="integer" value="10" label="abund - ACE Estimator threshold for abundant versus rare OTUs"/> <param name="size" type="integer" value="0" label="size - "/> - <param name="groupmode" type="boolean" truevalue="--groupmode=true" falsevalue="--groupmode=false" checked="true" label="groupmode - Collate shared summary results in one file"/> + <param name="groupmode" type="boolean" truevalue="--groupmode=true" falsevalue="--groupmode=false" checked="true" + label="groupmode - Collate shared summary results in one file" + help="If false, create a summary file per group."/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="tabular" name="summary" label="${tool.name} on ${on_string}: summary" > + <filter>(otu.file_ext == 'shared' and groupmode == True)</filter> + </data> </outputs> <requirements> <requirement type="binary">mothur</requirement> @@ -67,7 +79,7 @@ **Command Documenation** -The summary.single_ command produce a summary file that has the calculator value for each line in the OTU data and for all possible comparisons between the different groups in the group file. +The summary.single_ command produce a summary file that has the calculator value for each line in the OTU data and for all possible comparisons between the different groups in the group_ file. This can be useful if you aren't interested in generating collector's or rarefaction curves for your multi-sample data analysis. It would be worth your while, however, to look at the collector's curves for the calculators you are interested in to determine how sensitive the values are to sampling. If the values are not sensitive to sampling, then you can trust the values. Otherwise, you need to keep sampling. For calc parameter choices see: http://www.mothur.org/wiki/Calculators .. _summary.single: http://www.mothur.org/wiki/Summary.single
--- a/mothur/tools/mothur/tree.shared.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/tree.shared.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,69 +1,66 @@ -<tool id="mothur_tree_shared" name="Tree.shared" version="1.16.0" force_history_refresh="True"> +<tool id="mothur_tree_shared" name="Tree.shared" version="1.19.0" force_history_refresh="True"> <description>Generate a newick tree for dissimilarity among groups</description> <command interpreter="python"> mothur_wrapper.py --cmd='tree.shared' - --result='^mothur.\S+\.logfile$:'$logfile - --outputdir='$logfile.extra_files_path' - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?([a-z]+\.(unique|[0-9.]*)\.tre)$:tre' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' + #if $input.source == 'shared': + --result='^mothur.\S+\.logfile$:'$logfile + #if $input.as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?([a-z]+\.(unique|[0-9.]*)\.tre)$:tre' + #end if + --shared=$input.dist + #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: + --groups=$input.groups #end if #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' + --label='$input.label' #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu - #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: - --READ_label='$input.label' + #else: + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.tre$:'$tre + --outputdir='$logfile.extra_files_path' + #if $input.source == 'column': + --column=$input.dist + --name=$input.name + #elif $input.source == 'phylip': + --phylip=$input.dist + #if $input.name.__str__ != "None" and len($input.name.__str__) > 0: + --name=$input.name + #end if #end if #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups - #end if #if $calc.__str__ != "None" and len($calc.__str__) > 0: --calc=$calc #end if </command> <inputs> - <!-- list,group or shared --> + <!-- column,name phylip or shared --> <conditional name="input"> - <param name="source" type="select" label="Generate Heatmap for"> - <option value="similarity">OTU list</option> + <param name="source" type="select" label="Select input format"> <option value="shared">OTU Shared</option> + <option value="column">Pairwise Column Distance Matrix</option> + <option value="phylip">Phylip Distance Matrix</option> </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> + <when value="column"> + <param name="dist" type="data" format="pair.dist" label="column - Distance Matrix"/> + <param name="name" type="data" format="names" label="name - Sequences Name reference"/> + </when> + <when value="phylip"> + <param name="dist" type="data" format="lower.dist,square.dist" label="phylip - Distance Matrix"/> + <param name="name" type="data" format="names" optional="true" label="name - Names"/> </when> <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> + <param name="dist" type="data" format="shared" label="shared - OTU Shared"/> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Create a new history dataset for each label and calculator"/> <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> + <options from_dataset="dist"> <column name="name" index="0"/> <column name="value" index="0"/> <filter type="unique_value" name="unq_lbl" column="0" /> </options> </param> <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu"> + <options from_dataset="dist"> <column name="name" index="1"/> <column name="value" index="1"/> <filter type="unique_value" name="unq_grp" column="1" /> @@ -82,6 +79,9 @@ </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> + <data format="tre" name="tre" label="${tool.name} on ${on_string}: tre"> + <filter>input['source'] != 'shared'</filter> + </data> </outputs> <requirements> <requirement type="binary">mothur</requirement> @@ -99,7 +99,7 @@ **Command Documenation** -The tree.shared_ command will generate a newick-formatted tree file that describes the dissimilarity (1-similarity) among multiple groups. +The tree.shared_ command will generate a newick-formatted tree file that describes the dissimilarity (1-similarity) among multiple groups. For calc parameter choices see: http://www.mothur.org/wiki/Calculators .. _tree.shared: http://www.mothur.org/wiki/Tree.shared
--- a/mothur/tools/mothur/trim.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/trim.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_trim_seqs" name="Trim.seqs" version="1.16.0"> +<tool id="mothur_trim_seqs" name="Trim.seqs" version="1.19.0" force_history_refresh="True"> <description>Trim sequences - primers, barcodes, quality</description> <command interpreter="python"> mothur_wrapper.py @@ -34,6 +34,11 @@ #if $oligo.tdiffs > 0: --tdiffs=$oligo.tdiffs #end if + $oligo.allfiles + #if $oligo.allfiles.value: + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.(\S+\.fasta)$:fasta','^\S+?\.(\S+\.groups)$:groups' + #end if #end if #if $qual.add == "yes": --qfile=$qual.qfile @@ -59,20 +64,21 @@ <param name="removelast" type="integer" value="0" label="removelast - ignored if < 0)" help="removes the last removelast number of bases after the barcode or primers are removed, before the sequence is checked to see if it meets the other requirements."/> <conditional name="oligo"> - <param name="add" type="select" label="add - trim with an oligos file" help=""> + <param name="add" type="select" label="Trim with an oligos file?" help=""> <option value="no">no</option> <option value="yes">yes</option> </param> <when value="no"/> <when value="yes"> - <param name="oligos" type="data" format="oligos" label="oligos - oligos - barcodes and primers"/> + <param name="oligos" type="data" format="oligos" label="oligos - barcodes and primers"/> <param name="bdiffs" type="integer" value="0" label="bdiffs - number of differences to allow in the barcode (default 0)"/> <param name="pdiffs" type="integer" value="0" label="pdiffs - number of differences to allow in the primer (default 0)"/> <param name="tdiffs" type="integer" value="0" label="tdiffs - total number of differences to allow in primer and barcode (ignored if < 1)"/> + <param name="allfiles" type="boolean" truevalue="--allfiles=true" falsevalue="" checked="false" label="allfiles - separate into file per barcode"/> </when> </conditional> <conditional name="qual"> - <param name="add" type="select" label="add - trim based on a quality file" help=""> + <param name="add" type="select" label="Trim based on a quality file?" help=""> <option value="no">no</option> <option value="yes">yes</option> </param> @@ -88,15 +94,17 @@ </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> - <data format="fasta" name="trim_fasta" label="${tool.name} on ${on_string}: trim.fasta"/> + <data format_source="fasta" name="trim_fasta" label="${tool.name} on ${on_string}: trim.fasta"/> <data format="qual" name="trim_qual" label="${tool.name} on ${on_string}: trim.qual"> - <filter>qfile != none and len(qfile) > 0</filter> + <filter>(qual['add'] == 'yes' and len(qual['qfile'].__str__) > 0)</filter> </data> <data format="fasta" name="scrap_fasta" label="${tool.name} on ${on_string}: scrap.fasta"/> - <data format="qual454" name="scrap_qual" label="${tool.name} on ${on_string}: scrap.qual"> - <filter>qfile != none and len(qfile) > 0</filter> + <data format="qual" name="scrap_qual" label="${tool.name} on ${on_string}: scrap.qual"> + <filter>(qual['add'] == 'yes' and len(qual['qfile'].__str__) > 0)</filter> </data> - <data format="groups" name="groups_file" label="${tool.name} on ${on_string}: groups"/> + <data format="groups" name="groups_file" label="${tool.name} on ${on_string}: groups"> + <filter>(oligo['add'] == 'yes' and len(oligo['oligos']) > 0)</filter> + </data> </outputs> <requirements> <requirement type="binary">mothur</requirement>
--- a/mothur/tools/mothur/unifrac.unweighted.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/unifrac.unweighted.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,20 +1,19 @@ -<tool id="mothur_unifrac_unweighted" name="unifrac.unweighted" version="1.16.0"> +<tool id="mothur_unifrac_unweighted" name="unifrac.unweighted" version="1.19.0"> <description>Describes whether two or more communities have the same structure</description> <command interpreter="python"> mothur_wrapper.py --cmd='unifrac.unweighted' - --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.uwsummary$:'$summary,'^\S+\.unweighted\.(column\.|philip\.)?dist$:'$dist + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.uwsummary$:'$summary,'^\S+\.unweighted\.(column\.|phylip\.)?dist$:'$dist,'^\S+\.unweighted$:'$unweighted --outputdir='$logfile.extra_files_path' - --READ_cmd='read.tree' - --READ_tree=$tree + --tree=$tree #if $group.__str__ != "None" and len($group.__str__) > 0: - --READ_group='$group' + --group='$group' #end if #if $groups.__str__ != "None" and len($groups.__str__) > 0: --groups='$groups' #end if #if $name.__str__ != "None" and len($name.__str__) > 0: - --READ_name='$name' + --name='$name' #end if #if int($iters.__str__) > 0: --iters=$iters @@ -23,13 +22,15 @@ #if $distance.__str__ != "false": --distance=$distance #end if + $root --processors=2 </command> <inputs> <!-- list,group or shared --> - <param name="tree" type="data" format="tre" label="read.tree(tree=) - Tree"/> - <param name="group" type="data" format="groups" label="read.tree(group=) - Group file for the tree"/> - <param name="groups" type="select" label="groups - Groups to display" multiple="true"> + <param name="tree" type="data" format="tre" label="tree - Tree"/> + <param name="group" type="data" format="groups" label="group - Group file for the tree"/> + <param name="groups" type="select" label="groups - Select groups for pairwise comparisons" multiple="true"> + <help></help> <options from_dataset="group"> <column name="name" index="1"/> <column name="value" index="1"/> @@ -39,20 +40,21 @@ <param name="name" type="data" format="names" optional="true" label="name - Names file for the tree"/> <param name="iters" type="integer" value="1000" label="iters - Number of iterations to try (default 1000)"/> <param name="random" type="boolean" truevalue="--random=true" falsevalue="" checked="false" label="random - Compare your trees with randomly generated trees" /> - <param name="distance" type="select" label="distance - Select a distance matrix for your history"> + <param name="distance" type="select" label="distance - Create a distance matrix for your history"> <option value="false">None</option> - <option value="lt">Philip Lower Triangle Matrix</option> - <option value="square">Philip Square Matrix</option> + <option value="lt">Phylip Lower Triangle Matrix</option> + <option value="square">Phylip Square Matrix</option> <option value="column">Pairwise Distance Matrix</option> </param> - <!-- random uses input prompts, not sure how to model that - <param name="random" type="text" value="" label="random - The root name for random tests"/> - --> + <param name="root" type="boolean" truevalue="--root=true" falsevalue="" checked="false" label="root - the entire root in your calculations" /> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> <data format="tabular" name="summary" label="${tool.name} on ${on_string}: summary"> </data> + <data format="tabular" name="unweighted" label="${tool.name} on ${on_string}: unweighted"> + <filter>(random == True)</filter> + </data> <data format="lower.dist" name="dist" label="${tool.name} on ${on_string}: dist"> <filter>distance != 'false'</filter> <change_format> @@ -60,10 +62,6 @@ <when input="distance" value="column" format="pair.dist" /> </change_format> </data> - <!-- random uses input prompts, not sure how to model that - <data format="tabular" name="random" label="${tool.name} on ${on_string}: random"> - </data> - --> </outputs> <requirements> <requirement type="binary">mothur</requirement>
--- a/mothur/tools/mothur/unifrac.weighted.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/unifrac.weighted.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,20 +1,19 @@ -<tool id="mothur_unifrac_weighted" name="unifrac.weighted" version="1.16.0"> +<tool id="mothur_unifrac_weighted" name="unifrac.weighted" version="1.19.0"> <description>Describes whether two or more communities have the same structure</description> <command interpreter="python"> mothur_wrapper.py --cmd='unifrac.weighted' - --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.wsummary$:'$summary,'^\S+\.weighted\.(column\.|philip\.)?dist$:'$dist + --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.wsummary$:'$summary,'^\S+\.weighted\.(column\.|phylip\.)?dist$:'$dist,'^\S+\.weighted$:'$weighted --outputdir='$logfile.extra_files_path' - --READ_cmd='read.tree' - --READ_tree=$tree + --tree=$tree #if $group.__str__ != "None" and len($group.__str__) > 0: - --READ_group='$group' + --group='$group' #end if #if $groups.__str__ != "None" and len($groups.__str__) > 0: --groups='$groups' #end if #if $name.__str__ != "None" and len($name.__str__) > 0: - --READ_name='$name' + --name='$name' #end if #if int($iters.__str__) > 0: --iters=$iters @@ -23,13 +22,14 @@ #if $distance.__str__ != "false": --distance=$distance #end if + $root --processors=2 </command> <inputs> - <!-- list,group or shared --> - <param name="tree" type="data" format="tre" label="read.tree(tree=) - Tree"/> - <param name="group" type="data" format="groups" label="read.tree(group=) - Group file for the tree"/> - <param name="groups" type="select" label="groups - Groups to display" multiple="true"> + <param name="tree" type="data" format="tre" label="tree - Tree"/> + <param name="group" type="data" format="groups" label="group - Group file for the tree"/> + <param name="groups" type="select" label="groups - Select groups for pairwise comparisons" multiple="true"> + <help></help> <options from_dataset="group"> <column name="name" index="1"/> <column name="value" index="1"/> @@ -40,20 +40,21 @@ <param name="iters" type="integer" value="1000" label="iters - Number of iterations to try (default 1000)"/> <param name="random" type="boolean" truevalue="--random=true" falsevalue="" checked="false" label="random - Compare your trees with randomly generated trees" /> <param name="distance" type="boolean" truevalue="--distance=true" falsevalue="" checked="false" label="distance - Add the distance matrix to your history" /> - <param name="distance" type="select" label="distance - Select a distance matrix for your history"> + <param name="distance" type="select" label="distance - Create a distance matrix for your history"> <option value="false">None</option> - <option value="lt">Philip Lower Triangle Matrix</option> - <option value="square">Philip Square Matrix</option> + <option value="lt">Phylip Lower Triangle Matrix</option> + <option value="square">Phylip Square Matrix</option> <option value="column">Pairwise Distance Matrix</option> </param> - <!-- random uses input prompts, not sure how to model that - <param name="random" type="text" value="" label="random - The root name for random tests"/> - --> + <param name="root" type="boolean" truevalue="--root=true" falsevalue="" checked="false" label="root - the entire root in your calculations" /> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> <data format="tabular" name="summary" label="${tool.name} on ${on_string}: summary"> </data> + <data format="tabular" name="weighted" label="${tool.name} on ${on_string}: weighted"> + <filter>(random == True)</filter> + </data> <data format="lower.dist" name="dist" label="${tool.name} on ${on_string}: dist"> <filter>distance != 'false'</filter> <change_format>
--- a/mothur/tools/mothur/unique.seqs.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/unique.seqs.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,4 +1,4 @@ -<tool id="mothur_unique_seqs" name="Unique.seqs" version="1.16.0"> +<tool id="mothur_unique_seqs" name="Unique.seqs" version="1.19.0"> <description>Return unique sequences</description> <command interpreter="python"> mothur_wrapper.py @@ -6,7 +6,9 @@ --result='^mothur.\S+\.logfile$:'$logfile,'^\S+\.unique\.\w+$:'$out_fasta,'^\S+\.names$:'$out_names --outputdir='$logfile.extra_files_path' --fasta=$fasta - --name=$names + #if $names.__str__ != "None" and len($names.__str__) > 0: + --name=$names + #end if </command> <inputs> <param name="fasta" type="data" format="fasta" label="fasta - Sequences to filter"/> @@ -33,8 +35,9 @@ **Command Documenation** -The unique.seqs_ command returns only the unique sequences found in a fasta-formatted sequence file and a file that indicates those sequences that are identical to the reference sequence. +The unique.seqs_ command returns only the unique sequences found in a fasta-formatted sequence file and a name_ file that indicates those sequences that are identical to the reference sequence. +.. _name: http://www.mothur.org/wiki/Name_file .. _unique.seqs: http://www.mothur.org/wiki/Unique.seqs
--- a/mothur/tools/mothur/venn.xml Tue Jun 07 17:01:07 2011 -0400 +++ b/mothur/tools/mothur/venn.xml Tue Jun 07 17:05:08 2011 -0400 @@ -1,72 +1,51 @@ -<tool id="mothur_venn" name="Venn" version="1.16.0" force_history_refresh="True"> - <description>Generate Venn diagrams gor groups </description> +<tool id="mothur_venn" name="Venn" version="1.19.0" force_history_refresh="True"> + <description>Generate Venn diagrams for groups </description> <command interpreter="python"> mothur_wrapper.py --cmd='venn' --result='^mothur.\S+\.logfile$:'$logfile --outputdir='$logfile.extra_files_path' - --datasetid='$logfile.id' --new_file_path='$__new_file_path__' - --new_datasets='^\S+?\.(\S+\.svg)$:svg' - --READ_cmd='read.otu' - #if $input.source == 'similarity': - --READ_list=$input.otu - #if $otu_group.__str__ != "None" and len($otu_group.__str__) > 0: - --READ_group='$otu_group' - #end if + #if $as_datasets.__str__ == "yes": + --datasetid='$logfile.id' --new_file_path='$__new_file_path__' + --new_datasets='^\S+?\.(\S+\.svg)$:svg' + #end if + #if $input.source == 'shared': + --shared=$input.otu #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: --label='$input.label' #end if #if $input.calc.__str__ != "None" and len($input.calc.__str__) > 0: --calc='$input.calc' #end if - #elif $input.source == 'shared': - --READ_shared=$input.otu + $nseqs + $permute + #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: + --groups=$input.groups + #end if + #elif $input.source == 'similarity': + --list=$input.otu #if $input.label.__str__ != "None" and len($input.label.__str__) > 0: --label='$input.label' #end if - #if $calc.__str__ != "None" and len($calc.__str__) > 0: - --calc='$calc' + #if $input.calc.__str__ != "None" and len($input.calc.__str__) > 0: + --calc='$input.calc' #end if - $nseqs - $permute - #end if - #if $input.groups.__str__ != "None" and len($input.groups.__str__) > 0: - --groups=$input.groups + #if $input.abund >= 5: + --abund='$input.abund' + #end if + #end if </command> <inputs> - <!-- get.relabund relabund type should also work --> <conditional name="input"> <param name="source" type="select" label="Generate Heatmap for"> + <option value="shared">OTU Shared</option> <option value="similarity">OTU list</option> - <option value="shared">OTU Shared</option> </param> - <when value="similarity"> - <param name="otu" type="data" format="list" label="read.otu(list=) - OTU List"/> - <param name="otu_group" type="data" format="groups" label="read.otu(group=) - Group file for the OTU List"/> + <when value="shared"> + <param name="otu" type="data" format="shared" label="shared - OTU Shared"/> <param name="calc" type="select" multiple="true" label="calc - Calculators (Uses defaults if none selected)"> - <option value="sob">Chao</option> - <option value="chao">Chao</option> - <option value="ace">Ace</option> - </param> - <param name="label" type="select" label="label - OTU Labels" multiple="true"> - <options from_dataset="otu"> - <column name="name" index="0"/> - <column name="value" index="0"/> - </options> - </param> - <param name="groups" type="select" label="groups - Groups to consider" multiple="true"> - <options from_dataset="otu_group"> - <column name="name" index="1"/> - <column name="value" index="1"/> - <filter type="unique_value" name="unq_grp" column="1" /> - </options> - </param> - </when> - <when value="shared"> - <param name="otu" type="data" format="shared" label="read.otu(shared=) - OTU Shared"/> - <param name="calc" type="select" multiple="true" label="calc - Calculators (Uses defaults if none selected)"> - <option value="sharedsobs">Shared Chao</option> + <option value="sharedsobs">Shared Sobs</option> <option value="sharedchao">Shared Chao</option> <option value="sharedace">Shared Ace</option> </param> @@ -85,9 +64,27 @@ </options> </param> </when> + <when value="similarity"> + <param name="otu" type="data" format="list" label="list - OTU List"/> + <param name="calc" type="select" multiple="true" label="calc - Calculators (Uses defaults if none selected)"> + <option value="sobs">Sobs</option> + <option value="chao">Chao</option> + <option value="ace">Ace</option> + </param> + <param name="abund" type="integer" value="10" label="abund - Abundance when using the ace calculator ( >= 5 )"> + <validator type="in_range" min="5" /> + </param> + <param name="label" type="select" label="label - OTU Labels" multiple="true"> + <options from_dataset="otu"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + </when> </conditional> <param name="nseqs" type="boolean" truevalue="--nseqs=true" falsevalue="" checked="false" label="nseqs - Output the number of sequences represented by the otus in the picture"/> <param name="permute" type="boolean" truevalue="--permute=true" falsevalue="" checked="false" label="permute - Create pictures with all possible 4-way permutations of groups"/> + <param name="as_datasets" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Create a new history dataset for each image"/> </inputs> <outputs> <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" /> @@ -108,7 +105,7 @@ **Command Documenation** -The venn_ command generates Venn diagrams to compare the richness shared among 2, 3, or 4 groups. +The venn_ command generates Venn diagrams to compare the richness shared among 2, 3, or 4 groups. For calc parameter choices see: http://www.mothur.org/wiki/Calculators .. _venn: http://www.mothur.org/wiki/Venn