Mercurial > repos > refinery-platform > picard_merge_sam_files
changeset 0:40d9376df6d6 draft
planemo upload for repository https://github.com/scottx611x/picard_MergeSamFiles commit 46a5f872db68a7664cfae127b777e85fde8e6d98-dirty
| author | refinery-platform |
|---|---|
| date | Mon, 04 Dec 2017 09:23:06 -0500 |
| parents | |
| children | 90af7b99cb14 |
| files | picard_MergeSamFiles.xml picard_macros.xml read_group_macros.xml test-data/picard_MergeSamFiles_input1.bam test-data/picard_MergeSamFiles_input2.bam test-data/picard_MergeSamFiles_input3.bam test-data/picard_MergeSamFiles_test1.bam tool-data/picard_index.loc.sample tool_data_table_conf.xml.sample |
| diffstat | 9 files changed, 545 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/picard_MergeSamFiles.xml Mon Dec 04 09:23:06 2017 -0500 @@ -0,0 +1,117 @@ +<tool name="MergeSamFiles" id="picard_MergeSamFiles" version="@TOOL_VERSION@.0"> + <description>merges multiple SAM/BAM datasets into one</description> + <macros> + <import>picard_macros.xml</import> + </macros> + <expand macro="requirements" /> + <command detect_errors="exit_code"><![CDATA[ + @java_options@ + #for $index, $listCollection in enumerate($inputList): + && + picard + MergeSamFiles + + #for $element in $listCollection: + INPUT="${element}" + #end for + + OUTPUT="${'merged{}.bam'.format($index)}" + MERGE_SEQUENCE_DICTIONARIES="${merge_sequence_dictionaries}" + ASSUME_SORTED="${assume_sorted}" + #for $element in $comments: + COMMENT="${element.comment}" + #end for + USE_THREADING=true + SORT_ORDER=coordinate + VALIDATION_STRINGENCY="${validation_stringency}" + QUIET=true + VERBOSITY=ERROR + #end for + ]]></command> + <inputs> + <param format="sam,bam" name="inputList" type="data_collection" collection_type="list:list" label="Select SAM/BAM dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> + <param name="merge_sequence_dictionaries" type="boolean" label="Merge the sequence dictionaries of the datasets being merged" help="MERGE_SEQUENCE_DICTIONARIES; default=False"/> + <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" help="ASSUME_SORTED; default=False"/> + + <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments"> + <param name="comment" type="text" label="Add this comment to BAM dataset" help="COMMENT"/> + </repeat> + + <expand macro="VS" /> + + </inputs> + + <outputs> + <data format="bam" name="merged"> + <discover_datasets pattern="__designation_and_ext__" visible="true" /> + </data> + </outputs> + + <tests> + <test> + <param name="inputList"> + <collection type="list:list"> + <element name="list 1"> + <collection type="list"> + <element name="l1_input1" value="picard_MergeSamFiles_input1.bam" /> + <element name="l1_input2" value="picard_MergeSamFiles_input2.bam" /> + <element name="l1_input3" value="picard_MergeSamFiles_input3.bam" /> + </collection> + </element> + <element name="list 2"> + <collection type="list"> + <element name="l2_input1" value="picard_MergeSamFiles_input1.bam" /> + <element name="l2_input2" value="picard_MergeSamFiles_input2.bam" /> + <element name="l2_input3" value="picard_MergeSamFiles_input3.bam" /> + </collection> + </element> + </collection> + </param> + <param name="assume_sorted" value="False"/> + <param name="merge_sequence_dictionaries" value="False"/> + <param name="validation_stringency" value="LENIENT"/> + <output name="merged0" ftype="bam"> + <assert_contents> + <has_text text=""/> + </assert_contents> + </output> + <output name="merged1" ftype="bam"> + <assert_contents> + <has_text text=""/> + </assert_contents> + </output> + </test> + </tests> + + <stdio> + <exit_code range="1:" level="fatal"/> + </stdio> + + <help> + +**Purpose** + +Merges multiple SAM/BAM datasets into one. + +@dataset_collections@ + +@description@ + + ASSUME_SORTED=Boolean + AS=Boolean If true, assume that the input files are in the same sort order as the requested output + sort order, even if their headers say otherwise. Default value: false. This option can + be set to 'null' to clear the default value. Possible values: {true, false} + + MERGE_SEQUENCE_DICTIONARIES=Boolean + MSD=Boolean Merge the sequence dictionaries Default value: false. This option can be set to 'null' + to clear the default value. Possible values: {true, false} + + COMMENT=String + CO=String Comment(s) to include in the merged output file's header. This option may be specified 0 + or more times. + + +@more_info@ + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/picard_macros.xml Mon Dec 04 09:23:06 2017 -0500 @@ -0,0 +1,100 @@ +<macros> + <xml name="VS"> + <param name="validation_stringency" type="select" label="Select validation stringency" help=" Setting stringency to SILENT can improve performance when processing a BAM file in which variable-length data (read, qualities, tags) do not otherwise need to be decoded."> + <option value="LENIENT" selected="True">Lenient</option> + <option value="SILENT">Silent</option> + <option value="STRICT">Strict</option> + </param> + </xml> + + <token name="@TOOL_VERSION@">2.7.1</token> + + <xml name="requirements"> + <requirements> + <requirement type="package" version="2.7.1">picard</requirement> + <yield/> + </requirements> + </xml> + + <token name="@symlink_element_identifier@"><![CDATA[ + #import re + #set escaped_element_identifier = re.sub('[^\w\-]', '_', str($inputFile.element_identifier)) + ln -f -s '$inputFile' '$escaped_element_identifier' && + ]]></token> + + <token name="@java_options@"><![CDATA[ + _JAVA_OPTIONS=\${_JAVA_OPTIONS:-'-Xmx2048m -Xms256m'} && + export _JAVA_OPTIONS + ]]></token> + + <token name="@more_info@"> +------ + +**Additional information** + +Additional information about Picard tools is available from Picard web site at http://broadinstitute.github.io/picard/ . + </token> + + + <token name="@description@"> +------ + +**Inputs, outputs, and parameters** + +Either a SAM file or a BAM file must be supplied. Galaxy automatically coordinate-sorts all uploaded BAM files. + +From Picard documentation( http://broadinstitute.github.io/picard/):: + + </token> + <token name="@RG@"> +------- + +**Read Groups are Important!** + +Setting read groups correctly from the start will simplify your life greatly because you can merge multiple BAM files into one significantly reducing the number of analysis steps. Below we provide an explanation of read groups fields taken from GATK FAQ webpage: + +.. csv-table:: + :header-rows: 1 + + Tag,Importance,Definition,Meaning + "ID","Required","Read group identifier. Each @RG line must have a unique ID. The value of ID is used in the RG tags of alignment records. Must be unique among all read groups in header section. Read group IDs may be modified when merging SAM files in order to handle collisions.","Ideally, this should be a globally unique identify across all sequencing data in the world, such as the Illumina flowcell + lane name and number. Will be referenced by each read with the RG:Z field, allowing tools to determine the read group information associated with each read, including the sample from which the read came. Also, a read group is effectively treated as a separate run of the NGS instrument in tools like base quality score recalibration (a GATK component) -- all reads within a read group are assumed to come from the same instrument run and to therefore share the same error model." + "SM","Sample. Use pool name where a pool is being sequenced.","Required. As important as ID.","The name of the sample sequenced in this read group. GATK tools treat all read groups with the same SM value as containing sequencing data for the same sample. Therefore it's critical that the SM field be correctly specified, especially when using multi-sample tools like the Unified Genotyper (a GATK component)." + "PL","Platform/technology used to produce the read. Valid values: ILLUMINA, SOLID, LS454, HELICOS and PACBIO.","Important. Not currently used in the GATK, but was in the past, and may return. The only way to known the sequencing technology used to generate the sequencing data","It's a good idea to use this field." + "LB","DNA preparation library identify","Essential for MarkDuplicates","MarkDuplicates uses the LB field to determine which read groups might contain molecular duplicates, in case the same DNA library was sequenced on multiple lanes." + +**Example of Read Group usage** + +Support we have a trio of samples: MOM, DAD, and KID. Each has two DNA libraries prepared, one with 400 bp inserts and another with 200 bp inserts. Each of these libraries is run on two lanes of an illumina hiseq, requiring 3 x 2 x 2 = 12 lanes of data. When the data come off the sequencer, we would create 12 BAM files, with the following @RG fields in the header:: + + Dad's data: + @RG ID:FLOWCELL1.LANE1 PL:illumina LB:LIB-DAD-1 SM:DAD PI:200 + @RG ID:FLOWCELL1.LANE2 PL:illumina LB:LIB-DAD-1 SM:DAD PI:200 + @RG ID:FLOWCELL1.LANE3 PL:illumina LB:LIB-DAD-2 SM:DAD PI:400 + @RG ID:FLOWCELL1.LANE4 PL:illumina LB:LIB-DAD-2 SM:DAD PI:400 + + Mom's data: + @RG ID:FLOWCELL1.LANE5 PL:illumina LB:LIB-MOM-1 SM:MOM PI:200 + @RG ID:FLOWCELL1.LANE6 PL:illumina LB:LIB-MOM-1 SM:MOM PI:200 + @RG ID:FLOWCELL1.LANE7 PL:illumina LB:LIB-MOM-2 SM:MOM PI:400 + @RG ID:FLOWCELL1.LANE8 PL:illumina LB:LIB-MOM-2 SM:MOM PI:400 + + Kid's data: + @RG ID:FLOWCELL2.LANE1 PL:illumina LB:LIB-KID-1 SM:KID PI:200 + @RG ID:FLOWCELL2.LANE2 PL:illumina LB:LIB-KID-1 SM:KID PI:200 + @RG ID:FLOWCELL2.LANE3 PL:illumina LB:LIB-KID-2 SM:KID PI:400 + @RG ID:FLOWCELL2.LANE4 PL:illumina LB:LIB-KID-2 SM:KID PI:400 + +Note the hierarchical relationship between read groups (unique for each lane) to libraries (sequenced on two lanes) and samples (across four lanes, two lanes for each library). + </token> + <token name="@dataset_collections@"> +------ + +**Dataset collections - processing large numbers of datasets at once** + +This tool accepts nested lists of .bam files to be merged. This type of structure is modeled in Galaxy as a `list:list` Dataset Collection. + + + </token> + + +</macros> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/read_group_macros.xml Mon Dec 04 09:23:06 2017 -0500 @@ -0,0 +1,294 @@ +<macros> + <!-- Import this at the top of your command block and then + define rg_auto_name. --> + <token name="@define_read_group_helpers@"> +#def identifier_or_name($input1) + #if hasattr($input1, 'element_identifier') + #return $input1.element_identifier + #else + #return $input1.name.rstrip('.gz').rstrip('.fastq').rstrip('.fq') + #end if +#end def + +#def clean(name) + #import re + #set $name_clean = re.sub('[^\w\-_\.]', '_', $name) + #return $name_clean +#end def + +#def read_group_name_default($input1, $input2=None) + #if $input2 is None + #return $clean($identifier_or_name($input1)) + #else + #import itertools + #set $input_name1 = $clean($identifier_or_name($input1)) + #set $input_name2 = $clean($identifier_or_name($input2)) + #set $common_prefix = ''.join([c[0] for c in itertools.takewhile(lambda x: all(x[0] == y for y in x), itertools.izip(*[$input_name1, $input_name2]))]) + #if len($common_prefix) > 3 + #return $common_prefix + #else + #return $input_name1 + #end if + #end if +#end def + +#def format_read_group(prefix, value, quote='', arg='') + #if $value + #return $arg + $quote + $prefix + $value + $quote + #else + #return '' + #end if +#end def + +#def rg_param(name) + #if $varExists("rg") + #return $rg.get($name, None) + #else + #return $getVar($name, None) + #end if +#end def + +#set $use_rg = True + </token> + <!-- preconditions use_rg and rg_auto_name have been + defined. + --> + <token name="@set_read_group_vars@"> +#if $use_rg + #if $rg_param('read_group_id_conditional') is None + #set $rg_id = $rg_auto_name + #elif $rg_param('read_group_id_conditional').do_auto_name + #set $rg_id = $rg_auto_name + #else + #set $rg_id = str($rg_param('read_group_id_conditional').ID) + #end if + + #if $rg_param('read_group_sm_conditional') is None + #set $rg_sm = '' + #elif $rg_param('read_group_sm_conditional').do_auto_name + #set $rg_sm = $rg_auto_name + #else + #set $rg_sm = str($rg_param('read_group_sm_conditional').SM) + #end if + + #if $rg_param('PL') + #set $rg_pl = str($rg_param('PL')) + #else + #set $rg_pl = '' + #end if + + #if $rg_param('read_group_lb_conditional') is None + #set $rg_lb = '' + #elif $rg_param('read_group_lb_conditional').do_auto_name + #set $rg_lb = $rg_auto_name + #else + #set $rg_lb = str($rg_param('read_group_lb_conditional').LB) + #end if + + #if $rg_param('CN') + #set $rg_cn = str($rg_param('CN')) + #else + #set $rg_cn = '' + #end if + + #if $rg_param("DS") + #set $rg_ds = str($rg_param("DS")) + #else + #set $rg_ds = '' + #end if + + #if $rg_param("DT") + #set $rg_dt = str($rg_param("DT")) + #else + #set $rg_dt = '' + #end if + + #if $rg_param("FO") + #set $rg_fo = str($rg_param("FO")) + #else + #set $rg_fo = '' + #end if + + #if $rg_param("KS") + #set $rg_ks = str($rg_param("KS")) + #else + #set $rg_ks = '' + #end if + + #if $rg_param("PG") + #set $rg_pg = str($rg_param("PG")) + #else + #set $rg_pg = '' + #end if + + #if $rg_param("PI") != None + #set $rg_pi = str($rg_param("PI")) + #else + #set $rg_pi = '' + #end if + + #if $rg_param("PU") + #set $rg_pu = str($rg_param("PU")) + #else + #set $rg_pu = '' + #end if +#end if + </token> + <token name="@set_use_rg_var@"> +#set $use_rg = str($rg.rg_selector) != "do_not_set" + </token> + <xml name="read_group_auto_name_conditional"> + <param name="do_auto_name" type="boolean" label="Auto-assign" help="Use dataset name or collection information to automatically assign this value" checked="no" /> + <when value="true"> + </when> + <when value="false"> + <yield /> + </when> + </xml> + <xml name="read_group_id_param"> + <param name="ID" type="text" value="" label="Read group identifier (ID)" help="This value must be unique among multiple samples in your experiment" optional="false"> + <validator type="empty_field" /> + </param> + </xml> + <xml name="read_group_id_conditional"> + <conditional name="read_group_id_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_id_param" /> + </expand> + </conditional> + </xml> + <xml name="read_group_sm_param"> + <param name="SM" type="text" value="" label="Read group sample name (SM)" help="This value should be descriptive. Use pool name where a pool is being sequenced" /> + </xml> + <xml name="read_group_sm_conditional"> + <conditional name="read_group_sm_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_sm_param" /> + </expand> + </conditional> + </xml> + <!-- Above SM param is optional (for SAM/BAM spec, this is required + as per Picard. + --> + <xml name="read_group_sm_param_required"> + <param name="SM" type="text" value="" label="Read group sample name (SM)" optional="false" help="This value should be descriptive. Use pool name where a pool is being sequenced"> + <validator type="empty_field" /> + </param> + </xml> + <xml name="read_group_sm_required_conditional"> + <conditional name="read_group_sm_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_sm_param" /> + </expand> + </conditional> + </xml> + <xml name="read_group_pl_param"> + <param name="PL" type="select" label="Platform/technology used to produce the reads (PL)"> + <option value="CAPILLARY">CAPILLARY</option> + <option value="LS454">LS454</option> + <option selected="True" value="ILLUMINA">ILLUMINA</option> + <option value="SOLID">SOLID</option> + <option value="HELICOS">HELICOS</option> + <option value="IONTORRENT">IONTORRENT</option> + <option value="PACBIO">PACBIO</option> + </param> + </xml> + <xml name="read_group_lb_param"> + <param name="LB" type="text" label="Library name (LB)" optional="true" /> + </xml> + <xml name="read_group_lb_conditional"> + <conditional name="read_group_lb_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_lb_param" /> + </expand> + </conditional> + </xml> + <xml name="read_group_lb_required_param"> + <param name="LB" type="text" label="Library name (LB)" optional="false"> + <validator type="empty_field" /> + </param> + </xml> + <xml name="read_group_lb_required_conditional"> + <conditional name="read_group_lb_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_lb_required_param" /> + </expand> + </conditional> + </xml> + <xml name="read_group_cn_param"> + <param name="CN" type="text" label="Sequencing center that produced the read (CN)" /> + </xml> + <xml name="read_group_ds_param"> + <param name="DS" type="text" label="Description (DS)" /> + </xml> + <xml name="read_group_dt_param"> + <param name="DT" type="text" label="Date that run was produced (DT)" help="ISO8601 format date or date/time, like YYYY-MM-DD" /> + </xml> + <xml name="read_group_fo_param"> + <param name="FO" type="text" optional="true" label="Flow order (FO)" help="The array of nucleotide bases that correspond to the nucleotides used for each flow of each read. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by various other characters. Format: /\*|[ACMGRSVTWYHKDBN]+/"> + <validator type="regex" message="Invalid flow order">\*|[ACMGRSVTWYHKDBN]+$</validator> + </param> + </xml> + <xml name="read_group_ks_param"> + <param name="KS" type="text" label="The array of nucleotide bases that correspond to the key sequence of each read (KS)" /> + </xml> + <xml name="read_group_pg_param"> + <param name="PG" type="text" label="Programs used for processing the read group (PG)" /> + </xml> + <xml name="read_group_pi_param"> + <param name="PI" type="integer" optional="true" label="Predicted median insert size (PI)" /> + </xml> + <xml name="read_group_pu_param"> + <param name="PU" type="text" label="Platform unit (PU)" help="Unique identifier (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)" optional="True" /> + </xml> + <xml name="read_group_pu_required_param"> + <param name="PU" type="text" label="Platform unit (PU)" help="Unique identifier (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)" optional="False" /> + </xml> + <!-- Only ID is required - all groups available --> + <xml name="read_group_inputs_spec"> + <expand macro="read_group_id_conditional" /> + <expand macro="read_group_sm_conditional" /> + <expand macro="read_group_pl_param" /> + <expand macro="read_group_lb_conditional" /> + <expand macro="read_group_cn_param" /> + <expand macro="read_group_ds_param" /> + <expand macro="read_group_dt_param" /> + <expand macro="read_group_fo_param" /> + <expand macro="read_group_ks_param" /> + <expand macro="read_group_pg_param" /> + <expand macro="read_group_pi_param" /> + <expand macro="read_group_pu_param" /> + </xml> + <!-- ID, SM, LB, PU, PL all required - not ks, pg, or fo params. --> + <xml name="read_group_inputs_picard"> + <expand macro="read_group_id_conditional" /> + <expand macro="read_group_sm_required_conditional" /> + <expand macro="read_group_lb_required_conditional" /> + <expand macro="read_group_pl_param" /> + <expand macro="read_group_pu_required_param" /> + <expand macro="read_group_cn_param" /> + <expand macro="read_group_ds_param" /> + <expand macro="read_group_pi_param" /> + <expand macro="read_group_dt_param" /> + </xml> + <xml name="read_group_conditional"> + <conditional name="rg"> + <param name="rg_selector" type="select" label="Set read groups information?" help="Specifying read group information can greatly simplify your downstream analyses by allowing combining multiple datasets."> + <option value="set">Set read groups (SAM/BAM specification)</option> + <option value="set_picard">Set read groups (Picard style)</option> + <option value="set_id_auto">Automatically assign ID</option> + <option value="do_not_set" selected="True">Do not set</option> + </param> + <when value="set_picard"> + <expand macro="read_group_inputs_picard" /> + </when> + <when value="set"> + <expand macro="read_group_inputs_spec" /> + </when> + <when value="set_id_auto"> + </when> + <when value="do_not_set"> + </when> + </conditional> + </xml> +</macros> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/picard_index.loc.sample Mon Dec 04 09:23:06 2017 -0500 @@ -0,0 +1,26 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of Picard dict and associated files. You will need +#to create these data files and then create a picard_index.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The picard_index.loc +#file has this format (longer white space is the TAB character): +# +#<unique_build_id> <dbkey> <display_name> <fasta_file_path> +# +#So, for example, if you had hg18 indexed and stored in +#/depot/data2/galaxy/srma/hg18/, +#then the srma_index.loc entry would look like this: +# +#hg18 hg18 hg18 Pretty /depot/data2/galaxy/picard/hg18/hg18.fa +# +#and your /depot/data2/galaxy/srma/hg18/ directory +#would contain the following three files: +#hg18.fa +#hg18.dict +#hg18.fa.fai +# +#The dictionary file for each reference (ex. hg18.dict) must be +#created via Picard (http://picard.sourceforge.net). Note that +#the dict file does not have the .fa extension although the +#path list in the loc file does include it. +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Mon Dec 04 09:23:06 2017 -0500 @@ -0,0 +1,8 @@ +<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc--> +<tables> + <!-- Location of Picard dict file and other files --> + <table name="picard_indexes" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/picard_index.loc" /> + </table> +</tables> \ No newline at end of file