Mercurial > repos > devteam > samtools_split
changeset 2:135c85f4cfaf draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_split commit ca0d1d44099fd21e0f8214102f4d8a2fd2d054d6
| author | iuc |
|---|---|
| date | Mon, 29 Jul 2019 08:49:33 -0400 |
| parents | b7f7826ef1cd |
| children | 5d9ae78f34d3 |
| files | macros.xml samtools_split.xml test-data/phiX_Elephant.bam test-data/phiX_Human.bam test-data/phiX_Mouse.bam |
| diffstat | 5 files changed, 133 insertions(+), 28 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Tue May 09 11:18:30 2017 -0400 +++ b/macros.xml Mon Jul 29 08:49:33 2019 -0400 @@ -1,11 +1,131 @@ <macros> <xml name="requirements"> <requirements> - <requirement type="package" version="1.3.1">samtools</requirement> + <requirement type="package" version="@TOOL_VERSION@">samtools</requirement> <yield/> </requirements> </xml> - <token name="@TOOL_VERSION@">1.3.1</token> + <token name="@TOOL_VERSION@">1.9</token> + <token name="@FLAGS@">#set $flags = sum(map(int, str($filter).split(',')))</token> + <token name="@PREPARE_IDX@"><![CDATA[ + ##prepare input and indices + ln -s '$input' infile && + #if $input.is_of_type('bam'): + #if str( $input.metadata.bam_index ) != "None": + ln -s '${input.metadata.bam_index}' infile.bai && + #else: + samtools index infile infile.bai && + #end if + #elif $input.is_of_type('cram'): + #if str( $input.metadata.cram_index ) != "None": + ln -s '${input.metadata.cram_index}' infile.crai && + #else: + samtools index infile infile.crai && + #end if + #end if + ]]></token> + <token name="@PREPARE_IDX_MULTIPLE@"><![CDATA[ + ##prepare input and indices + #for $i, $bam in enumerate( $input_bams ): + ln -s '$bam' '${i}' && + #if $bam.is_of_type('bam'): + #if str( $bam.metadata.bam_index ) != "None": + ln -s '${bam.metadata.bam_index}' '${i}.bai' && + #else: + samtools index '${i}' '${i}.bai' && + #end if + #elif $bam.is_of_type('cram'): + #if str( $bam.metadata.cram_index ) != "None": + ln -s '${bam.metadata.cram_index}' '${i}.crai' && + #else: + samtools index '${i}' '${i}.crai' && + #end if + #end if + #end for + ]]></token> + <token name="@PREPARE_FASTA_IDX@"><![CDATA[ + ##checks for reference data ($addref_cond.addref_select=="history" or =="cached") + ##and sets the -t/-T parameters accordingly: + ##- in case of history a symbolic link is used because samtools (view) will generate + ## the index which might not be possible in the directory containing the fasta file + ##- in case of cached the absolute path is used which allows to read the cram file + ## without specifying the reference + #if $addref_cond.addref_select == "history": + ln -s '${addref_cond.ref}' reference.fa && + samtools faidx reference.fa && + #set reffa="reference.fa" + #set reffai="reference.fa.fai" + #elif $addref_cond.addref_select == "cached": + #set reffa=str($addref_cond.ref.fields.path) + #set reffai=str($addref_cond.ref.fields.path)+".fai" + #else + #set reffa=None + #set reffai=None + #end if + ]]></token> + <token name="@ADDTHREADS@"><![CDATA[ + ##compute the number of ADDITIONAL threads to be used by samtools (-@) + addthreads=\${GALAXY_SLOTS:-1} && (( addthreads-- )) && + ]]></token> + <token name="@ADDMEMORY@"><![CDATA[ + ##compute the number of memory available to samtools sort (-m) + ##use only 75% of available: https://github.com/samtools/samtools/issues/831 + addmemory=\${GALAXY_MEMORY_MB_PER_SLOT:-768} && + ((addmemory=addmemory*75/100)) && + ]]></token> + <xml name="seed_input"> + <param name="seed" type="integer" optional="True" label="Seed for random number generator" help="If empty a random seed is used." /> + </xml> + <xml name="flag_options"> + <option value="1">read is paired</option> + <option value="2">read is mapped in a proper pair</option> + <option value="4">read is unmapped</option> + <option value="8">mate is unmapped</option> + <option value="16">read reverse strand</option> + <option value="32">mate reverse strand</option> + <option value="64">read is the first in a pair</option> + <option value="128">read is the second in a pair</option> + <option value="256">alignment or read is not primary</option> + <option value="512">read fails platform/vendor quality checks</option> + <option value="1024">read is a PCR or optical duplicate</option> + <option value="2048">supplementary alignment</option> + </xml> + + <!-- region specification macros and tokens for tools that allow the specification + of region by bed file / space separated list of regions --> + <token name="@REGIONS_FILE@"><![CDATA[ + #if $cond_region.select_region == 'tab': + -t '$cond_region.targetregions' + #end if + ]]></token> + <token name="@REGIONS_MANUAL@"><![CDATA[ + #if $cond_region.select_region == 'text': + #for $i, $x in enumerate($cond_region.regions_repeat): + '${x.region}' + #end for + #end if + ]]></token> + <xml name="regions_macro"> + <conditional name="cond_region"> + <param name="select_region" type="select" label="Filter by regions" help="restricts output to only those alignments which overlap the specified region(s)"> + <option value="no" selected="True">No</option> + <option value="text">Manualy specify regions</option> + <option value="tab">Regions from tabular file</option> + </param> + <when value="no"/> + <when value="text"> + <repeat name="regions_repeat" min="1" default="1" title="Regions"> + <param name="region" type="text" label="region" help="format chr:from-to"> + <validator type="regex" message="Required format: CHR[:FROM[-TO]]; where CHR: string containing any character except quotes, whitespace and colon; FROM and TO: any integer">^[^\s'\":]+(:\d+(-\d+){0,1}){0,1}$</validator> + </param> + </repeat> + </when> + <when value="tab"> + <param name="targetregions" argument="-t/--target-regions" type="data" format="tabular" label="Target regions file" help="Do stats in these regions only. Tab-delimited file chr,from,to (1-based, inclusive)" /> + </when> + </conditional> + </xml> + <xml name="citations"> <citations> <citation type="bibtex"> @@ -49,21 +169,4 @@ <exit_code range="1:" level="fatal" description="Error" /> </stdio> </xml> - <token name="@no-chrom-options@"> ------ - -.. class:: warningmark - -**No options available? How to re-detect metadata** - -If you see a "No options available" within the "**Select references (chromosomes and contigs) you would like to restrict bam to**" drop down, you need to re-detect metadata for the dataset you are trying to process. To do this follow these steps: - -1. Click on the **pencil** icon adjacent to the dataset in the history -2. A new menu will appear in the center pane of the interface -3. Click **Datatype** tab -4. Set **New Type** to **BAM** -5. Click **Save** - -The medatada will be re-detected and you will be able to see the list of reference sequences in the "**Select references (chromosomes and contigs) you would like to restrict bam to**" drop-down. - </token> </macros>
--- a/samtools_split.xml Tue May 09 11:18:30 2017 -0400 +++ b/samtools_split.xml Mon Jul 29 08:49:33 2019 -0400 @@ -7,13 +7,15 @@ <expand macro="stdio"/> <expand macro="version_command"/> <command><![CDATA[ - samtools split -f 'Read_Group_%!.bam' - #if $header: - -u '${output}:${header}' - #else: - -u '${output}' - #end if - "${input_bam}" + @ADDTHREADS@ + samtools split -f 'Read_Group_%!.bam' + #if $header: + -u '${output}:${header}' + #else: + -u '${output}' + #end if + -@ \$addthreads + '$input_bam' ]]></command> <inputs> <param name="input_bam" type="data" format="bam" label="BAM file" /> @@ -21,13 +23,13 @@ </inputs> <outputs> <data name="output" format="bam" label="${tool.name} on ${on_string}"> - <discover_datasets pattern="Read_Group_(?P<designation>.+)\.bam" ext="bam" visible="true" directory="" /> + <discover_datasets pattern="Read_Group_(?P<designation>.+)\.bam" ext="bam" visible="true" directory="" assign_primary_output="false"/> </data> </outputs> <tests> <test> <param name="input_bam" value="phiX.bam" ftype="bam" /> - <output name="output" file="samtools_split_out.bam"> + <output name="output"> <discovered_dataset designation="Mouse" ftype="bam" file="phiX_Mouse.bam" /> <discovered_dataset designation="Elephant" ftype="bam" file="phiX_Elephant.bam" /> <discovered_dataset designation="Human" ftype="bam" file="phiX_Human.bam" />