Mercurial > repos > jjohnson > gmap
diff gmap.xml @ 5:14561eb803a5 draft
Uploaded v3.0.1b (still working on this prior to main Tool Shed release)
| author | peterjc |
|---|---|
| date | Fri, 21 Oct 2016 10:55:40 -0400 |
| parents | 488e9d642566 |
| children |
line wrap: on
line diff
--- a/gmap.xml Wed Sep 28 10:49:02 2016 -0400 +++ b/gmap.xml Fri Oct 21 10:55:40 2016 -0400 @@ -4,19 +4,19 @@ <requirement type="package" version="2013-05-09">gmap</requirement> </requirements> <version_command>gmap --version</version_command> - <command> + <command detect_errors="exit_code"><![CDATA[ #import os,os.path gmap - --nthreads=4 --ordered + --nthreads=\${GALAXY_SLOTS:-4} --ordered #if $refGenomeSource.genomeSource == "history": --gseg=$refGenomeSource.ownFile #elif $refGenomeSource.genomeSource == "gmapdb": - --dir=$refGenomeSource.gmapdb.extra_files_path --db=$refGenomeSource.gmapdb.metadata.db_name + --dir='$refGenomeSource.gmapdb.extra_files_path' --db='$refGenomeSource.gmapdb.metadata.db_name' #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2: --kmer=$refGenomeSource.kmer #end if #else: - --dir=$os.path.dirname($refGenomeSource.gmapindex.value) --db=$os.path.basename($refGenomeSource.gmapindex.value) + --dir='$os.path.dirname($refGenomeSource.gmapindex.value)' --db='$os.path.basename($refGenomeSource.gmapindex.value)' #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2: --kmer=$refGenomeSource.kmer #end if @@ -45,11 +45,6 @@ $result.sam_use_0M $result.force_xs_dir $result.md_lowercase_snp - #* Removed in gmap version 2011-11-30 - #if len($result.noncanonical_splices.__str__) > 0 - --noncanonical-splices=$result.noncanonical_splices - #end if - *# #if len($result.read_group_id.__str__) > 0 --read-group-id=$result.read_group_id #end if @@ -116,9 +111,7 @@ --wraplength=$advanced.wraplength #end if #end if - #if $split_output == True - $split_output - #end if + $split_output #if len($quality_protocol.__str__) > 0: --quality-protocol=$quality_protocol #end if @@ -126,15 +119,15 @@ #for $i in $inputs: ${i.added_input} #end for - #if $split_output == True + #if $split_output 2> $gmap_stderr #else 2> $gmap_stderr > $output #end if - </command> + ]]></command> <inputs> <!-- Input data --> - <param name="input" type="data" format="fasta,fastqsanger,fastqillumina" label="<H2>Input Sequences</H2>Select an mRNA or EST dataset to map" /> + <param name="input" type="data" format="fasta,fastqsanger,fastqillumina" label="Input Sequences" help="Select an mRNA or EST dataset to map" /> <repeat name="inputs" title="addtional mRNA or EST dataset to map"> <param name="added_input" type="data" format="fasta,fastqsanger,fastqillumina" label=""/> </repeat> @@ -146,14 +139,14 @@ <!-- GMAPDB for mapping --> <conditional name="refGenomeSource"> - <param name="genomeSource" type="select" label="<HR><H2>Map To</H2>Will you map to a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"> + <param name="genomeSource" type="select" label="Map to a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"> <option value="indexed">Use a built-in index</option> <option value="gmapdb">Use gmapdb from the history</option> <option value="history">Use a fasta reference sequence from the history</option> </param> <when value="indexed"> <param name="gmapindex" type="select" label="Select a reference genome" help="if your genome of interest is not listed - contact Galaxy team"> - <options from_file="gmap_indices.loc"> + <options from_data_table="gmap_indices"> <column name="uid" index="0" /> <column name="dbkey" index="1" /> <column name="name" index="2" /> @@ -164,7 +157,7 @@ </options> </param> <param name="kmer" type="select" data_ref="gmapindex" label="kmer size" help="Defaults to highest available kmer size"> - <options from_file="gmap_indices.loc"> + <options from_data_table="gmap_indices"> <column name="name" index="3"/> <column name="value" index="3"/> <filter type="param_value" ref="gmapindex" column="6"/> @@ -182,8 +175,9 @@ within selected basesize and k-mer size --> - <param name="map" type="select" data_ref="gmapindex" label="Look for splicing involving known sites or known introns" help=""> - <options from_file="gmap_indices.loc"> + <!-- Not currently used in the command tag, + <param name="map" type="select" data_ref="gmapindex" label="Look for splicing involving known sites or known introns" > + <options from_data_table="gmap_indices"> <column name="name" index="4"/> <column name="value" index="4"/> <filter type="param_value" ref="gmapindex" column="6"/> @@ -192,6 +186,7 @@ <filter type="sort_by" column="4"/> </options> </param> + --> </when> <when value="gmapdb"> <param name="gmapdb" type="data" format="gmapdb" label="Select a gmapdb" @@ -201,11 +196,13 @@ <filter type="data_meta" ref="gmapdb" key="kmers" multiple="True" separator=","/> </options> </param> - <param name="map" type="select" data_ref="gmapdb" label="Use map for splicing involving known sites or known introns" help=""> + <!-- Not currently used in the command tag, + <param name="map" type="select" data_ref="gmapdb" label="Use map for splicing involving known sites or known introns" > <options> <filter type="data_meta" ref="gmapdb" key="maps" multiple="True"/> </options> </param> + --> </when> <when value="history"> <param name="ownFile" type="data" format="fasta" label="Select the reference genome" @@ -216,7 +213,7 @@ <!-- Computation options --> <conditional name="computation"> - <param name="options" type="select" label="<HR>Computational Settings" help=""> + <param name="options" type="select" label="Computational Settings" > <option value="default">Use default settings</option> <option value="advanced">Set Computation Options</option> </param> @@ -249,7 +246,7 @@ <param name="trimendexons" type="integer" value="" optional="true" label="Trim end exons with fewer than given number of matches (in nt, default 12)" > <validator type="in_range" message="trimendexons must be positive" min="1" /> </param> - <param name="find_shifted_canonical" type="boolean" truevalue="--find-shifted-canonical-species" falsevalue="" checked="false" label="find-shifted-canonical Use a more sensitive search for canonical splicing" help=""/> + <param name="find_shifted_canonical" type="boolean" truevalue="--find-shifted-canonical-species" falsevalue="" checked="false" label="find-shifted-canonical Use a more sensitive search for canonical splicing" /> <param name="cross_species" type="boolean" truevalue="--cross-species" falsevalue="" checked="false" label="Cross-species alignment" help="For cross-species alignments, use a more sensitive search for canonical splicing"/> <param name="canonical" type="select" label="Reward for canonical and semi-canonical introns"> @@ -281,14 +278,14 @@ <!-- Advanced Settings --> <conditional name="advanced"> - <param name="options" type="select" label="<HR>Advanced Settings" help=""> + <param name="options" type="select" label="Advanced Settings" > <option value="default">Use default settings</option> <option value="used">Set Options</option> </param> <when value="default"/> <when value="used"> <param name="nolengths" type="boolean" checked="false" truevalue="--nolengths=true" falsevalue="" label="No intron lengths in alignment"/> - <param name="invertmode" type="select" label=" Mode for alignments to genomic (-) strand" help=""> + <param name="invertmode" type="select" label=" Mode for alignments to genomic (-) strand" > <option value="">Don't invert the cDNA (default)</option> <option value="--invertmode=1">Invert cDNA and print genomic (-) strand</option> <option value="--invertmode=2">Invert cDNA and print genomic (+) strand</option> @@ -313,7 +310,7 @@ </param> <param name="tolerant" type="boolean" checked="false" truevalue="--tolerant=true" falsevalue="" label="Translates cDNA with corrections for frameshifts"/> - <param name="protein" type="select" label="Protein alignment" help=""> + <param name="protein" type="select" label="Protein alignment" > <option value="">default</option> <option value="--fulllength=true">Assume full-length protein, starting with Met</option> <option value="--truncate=true">Truncate alignment around full-length protein, Met to Stop</option> @@ -323,7 +320,7 @@ <!-- Output data --> <conditional name="result"> - <param name="format" type="select" label="<HR><H2>Output</H2>Select the output format" help=""> + <param name="format" type="select" label="Output" help="Select the output format" > <option value="gmap">GMAP default output</option> <option value="summary">Summary of alignments</option> <option value="align">Alignment</option> @@ -345,15 +342,11 @@ <option value="coords">coords in table format</option> <option value="sam" selected="true">SAM format</option> </param> - <when value="gmap"> - </when> + <when value="gmap"/> <when value="summary"/> - <when value="align"> - </when> - <when value="continuous"> - </when> - <when value="continuous-by-exon"> - </when> + <when value="align"/> + <when value="continuous"/> + <when value="continuous-by-exon"/> <when value="compress"/> <when value="exons_dna"/> <when value="exons_gen"/> @@ -369,15 +362,8 @@ <when value="map_ranges"/> <when value="coords"/> <when value="sam"> - <param name="sam_paired_read" type="boolean" truevalue="sampe" falsevalue="samse" checked="false" label="SAM paired reads"/> - <param name="no_sam_headers" type="boolean" truevalue="--no-sam-headers" falsevalue="" checked="false" label="Do not print headers beginning with '@'"/> - <!-- Removed in gmap version 2011-11-30 - <param name="noncanonical_splices" type="select" label="Print non-canonical genomic gaps greater than 20 nt in CIGAR string as STRING."> - <option value="">Use default</option> - <option value="N">N</option> - <option value="D">D</option> - </param> - --> + <param name="sam_paired_read" type="boolean" truevalue="sampe" falsevalue="samse" checked="false" label="SAM paired reads" help="The sampe option will generate SAM flags to indicate whether the read is the first or second end of a pair"/> + <param name="no_sam_headers" type="boolean" truevalue="--no-sam-headers" falsevalue="" checked="false" label="Do not print SAM headers (lines beginning with '@')"/> <param name="read_group_id" type="text" value="" label="Value to put into read-group id (RG-ID) field"/> <param name="read_group_name" type="text" value="" label="Value to put into read-group name (RG-SM) field"/> <param name="read_group_library" type="text" value="" label="Value to put into read-group library (RG-LB) field"/> @@ -484,18 +470,50 @@ </data> </outputs> <tests> + <test> + <!-- + mimic first test from GMAP source code, mapping Human ERBB2 onto fragment of chr17 + $ gmap -A -g ss.chr17test ss.her2 + --> + <param name="input" value="ss.her2.fasta" ftype="fasta"/> + <!-- <param name="quality_protocol" value=""/> --> + <param name="genomeSource" value="history"/> + <param name="ownFile" value="ss.chr17.fasta" ftype="fasta"/> + <param name="format" value="align"/> + <param name="computation" value="default"/> + <param name="options" value="default"/> + <output name="output" file="ss.her2.chr17.txt" ftype="txt"/> + </test> </tests> <help> **What it does** -GMAP_ (Genomic Mapping and Alignment Program) The functionality provided by gmap allows a user to: (1) map and align a single cDNA interactively against a large genome in about a second, without the startup time of several minutes typically needed by existing mapping programs; (2) switch arbitrarily among different genomes, without the need for a preloaded server dedicated to each genome; (3) run the program on computers with as little as 128 MB of RAM (random access memory); (4) perform high-throughput batch processing of cDNAs by using memory mapping and multithreading when appropriate memory and hardware are available; (5) generate accurate gene models, even in the presence of substantial polymorphisms and sequence errors; (6) locate splice sites accurately without the use of probabilistic splice site models, allowing generalized use of the program across species; (7) detect statistically significant microexons and incorporate them into the alignment; and (8) handle mapping and alignment tasks on genomes having alternate assemblies, linkage groups or strains. It is developed by Thomas D. Wu of Genentech, Inc. +GMAP (Genomic Mapping and Alignment Program) + +The functionality provided by gmap allows a user to: -Publication_ citation: Thomas D. Wu, Colin K. Watanabe Bioinformatics 2005 21(9):1859-1875; doi:10.1093/bioinformatics/bti310 + 1. map and align a single cDNA interactively against a large genome in + about a second, without the startup time of several minutes typically + needed by existing mapping programs; + 2. switch arbitrarily among different genomes, without the need for a + preloaded server dedicated to each genome; + 3. run the program on computers with as little as 128 MB of RAM (random + access memory) + 4. perform high-throughput batch processing of cDNAs by using memory + mapping and multithreading when appropriate memory and hardware are + available; + 5. generate accurate gene models, even in the presence of substantial + polymorphisms and sequence errors; + 6. locate splice sites accurately without the use of probabilistic splice + site models, allowing generalized use of the program across species; + 7. detect statistically significant microexons and incorporate them into + the alignment; and + 8. handle mapping and alignment tasks on genomes having alternate + assemblies, linkage groups or strains. -.. _GMAP: http://research-pub.gene.com/gmap/ -.. _Publication: http://bioinformatics.oxfordjournals.org/cgi/content/full/21/9/1859 +It is developed by Thomas D. Wu of Genentech, Inc. ------