Mercurial > repos > iuc > delly_filter
changeset 2:6184cfc70e28 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/delly commit d18d984264f54b45e94d97b5b97ed499a32a334a"
author | iuc |
---|---|
date | Fri, 22 Jan 2021 14:32:03 +0000 |
parents | 9919057a466c |
children | d2590fe6793f |
files | filter.xml macros.xml |
diffstat | 2 files changed, 93 insertions(+), 74 deletions(-) [+] |
line wrap: on
line diff
--- a/filter.xml Thu Oct 29 20:50:57 2020 +0000 +++ b/filter.xml Fri Jan 22 14:32:03 2021 +0000 @@ -8,12 +8,12 @@ <expand macro="version_command"/> <command detect_errors="exit_code"><![CDATA[ ## initialize -#if $samples.is_of_type('vcf') - bcftools view -Ob '$samples' > 'sample.bcf.gz' && - bcftools index 'sample.bcf.gz' && +#if $input.is_of_type('vcf') + bcftools view -Ob '$input' > 'input.bcf.gz' && + bcftools index 'input.bcf.gz' && #else - ln -s '${samples}' 'sample.bcf.gz' && - ln -s '${samples.metadata.bcf_index}' 'sample.bcf.gz.csi' && + ln -s '${input}' 'input.bcf.gz' && + ln -s '${input.metadata.bcf_index}' 'input.bcf.gz.csi' && #end if ## run @@ -31,38 +31,37 @@ --samples '$sv.mode_cond.samples' --coverage $sv.mode_cond.coverage --controlcontamination $sv.mode_cond.controlcontamination -#end if ## germline options -#if $sv.mode_cond.mode_sel == 'germline' +#else if $sv.mode_cond.mode_sel == 'germline' --gq $sv.mode_cond.gq --rddel $sv.mode_cond.rddel --rddup $sv.mode_cond.rddup #end if -## samples -'sample.bcf.gz' ## input +## input +'input.bcf.gz' ## postprocessing @LOG@ @VCF@ ]]></command> <inputs> - <expand macro="samples" format="bcf,vcf" multiple="false" label="Select file"/> + <expand macro="input" format="bcf,vcf" label="Select input file"/> <section name="generic" title="Generic options" expanded="true"> <param argument="--altaf" type="float" value="0.2" min="0.0" max="1.0" label="Set minimum fractional ALT support"/> - <expand macro="minsize"/> - <expand macro="maxsize" default="500000000"/> + <expand macro="minsize" default="0" label="Set minimum SV size"/> + <expand macro="maxsize" default="500000000" label="Set maximum SV size"/> <param argument="--ratiogeno" type="float" value="0.75" min="0.0" max="1.0" label="Set minimum fraction of genotyped samples"/> <param argument="--pass" type="boolean" truevalue="--pass" falsevalue="" label="Filter sites for PASS?"/> </section> <section name="sv" title="SV calling options" expanded="true"> <conditional name="mode_cond"> - <param argument="mode_sel" type="select" label="Select filter mode"> + <param name="mode_sel" type="select" label="Select filter mode" help="(--filter)"> <option value="somatic" selected="true">Somatic</option> <option value="germline">Germline</option> </param> <when value="somatic"> - <param argument="--samples" type="data" format="tabular" label="Select sample file" help="Two-column sample file listing sample name and tumor or control."/> - <param argument="--coverage" type="integer" value="10" label="Set minimum coverage in tumor."/> + <expand macro="samples"/> + <expand macro="coverage" label="Set minimum coverage in tumor"/> <param argument="--controlcontamination" type="float" value="0.0" min="0.0" max="1.0" label="Set maximum fractional ALT support in control"/> </when> <when value="germline"> @@ -72,23 +71,23 @@ </when> </conditional> </section> - <section name="oo" title="Output options"> + <section name="oo" title="Output options" expanded="true"> <param name="out" type="select" multiple="true" optional="false" label="Select output file(s)"> <option value="bcf" selected="true">BCF</option> + <option value="log">Log</option> <option value="vcf">VCF</option> - <option value="log">Log</option> </param> </section> </inputs> <outputs> - <expand macro="vcf"/> <expand macro="bcf"/> <expand macro="log"/> + <expand macro="vcf"/> </outputs> <tests> <!-- #1 default, somatic, bcf --> <test expect_num_outputs="2"> - <param name="samples" value="call_1.bcf.gz"/> + <param name="input" value="call_1.bcf.gz"/> <section name="sv"> <conditional name="mode_cond"> <param name="mode_sel" value="somatic"/> @@ -113,7 +112,7 @@ </test> <!-- #2 somatic, bcf --> <test expect_num_outputs="3"> - <param name="samples" value="call_1.bcf.gz"/> + <param name="input" value="call_1.bcf.gz"/> <section name="generic"> <param name="altaf" value="0.3"/> <param name="minsize" value="1"/> @@ -137,6 +136,11 @@ <has_size value="2281" delta="10"/> </assert_contents> </output> + <output name="out_log"> + <assert_contents> + <has_text_matching expression=".+Done\."/> + </assert_contents> + </output> <output name="out_vcf"> <assert_contents> <has_n_lines n="140"/> @@ -144,15 +148,10 @@ <has_line line="#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NORMAL	TUMOR"/> </assert_contents> </output> - <output name="out_log"> - <assert_contents> - <has_text_matching expression=".+Done\."/> - </assert_contents> - </output> </test> <!-- #3 default, germline, bcf --> <test expect_num_outputs="2"> - <param name="samples" value="call_1.bcf.gz"/> + <param name="input" value="call_1.bcf.gz"/> <section name="sv"> <conditional name="mode_cond"> <param name="mode_sel" value="germline"/> @@ -176,7 +175,7 @@ </test> <!-- #4 germline, bcf --> <test expect_num_outputs="3"> - <param name="samples" value="call_1.bcf.gz"/> + <param name="input" value="call_1.bcf.gz"/> <section name="generic"> <param name="altaf" value="0.1"/> <param name="minsize" value="1"/> @@ -200,6 +199,11 @@ <has_size value="2264" delta="10"/> </assert_contents> </output> + <output name="out_log"> + <assert_contents> + <has_text_matching expression=".+Done\."/> + </assert_contents> + </output> <output name="out_vcf"> <assert_contents> <has_n_lines n="139"/> @@ -207,15 +211,10 @@ <has_line line="#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NORMAL	TUMOR"/> </assert_contents> </output> - <output name="out_log"> - <assert_contents> - <has_text_matching expression=".+Done\."/> - </assert_contents> - </output> </test> <!-- #5 default, somatic, vcf --> <test expect_num_outputs="2"> - <param name="samples" value="call_1.vcf.gz"/> + <param name="input" value="call_1.vcf.gz"/> <section name="sv"> <conditional name="mode_cond"> <param name="mode_sel" value="somatic"/> @@ -227,7 +226,7 @@ </section> <output name="out_bcf"> <assert_contents> - <has_size value="2440" delta="10"/> + <has_size value="2451" delta="10"/> </assert_contents> </output> <output name="out_vcf"> @@ -246,8 +245,6 @@ @WID@ -Delly *filter* contains workflows for germline and somatic SV calling. - **Input** *Somatic* filtering requires a called SV input with at least one tumor sample and a matched control sample. In addition, a tab-delimited sample description needs to be provided, in which the first column holds the sample ids (as found in the VCF/BCF input) and the second column specifies either tumor or control. @@ -256,7 +253,7 @@ **Output** -The output is available in BCF and VCF format. +The output is available in BCF and VCF format. Additionally a log file is provided. .. class:: infomark
--- a/macros.xml Thu Oct 29 20:50:57 2020 +0000 +++ b/macros.xml Fri Jan 22 14:32:03 2021 +0000 @@ -1,6 +1,6 @@ <?xml version="1.0"?> <macros> - <token name="@TOOL_VERSION@">0.8.5</token> + <token name="@TOOL_VERSION@">0.8.7</token> <token name="@VERSION_SUFFIX@">0</token> <xml name="requirements"> <requirements> @@ -17,14 +17,12 @@ </citations> </xml> - <!-- - command - --> + <!-- command --> <token name="@BAM@"><![CDATA[ -#for $i, $current in enumerate($samples) - ln -s '${current}' 'sample_${i}.bam' && - ln -s '${current.metadata.bam_index}' 'sample_${i}.bam.bai' && +#for $i, $current in enumerate($input) + ln -s '${current}' 'input_${i}.bam' && + ln -s '${current.metadata.bam_index}' 'input_${i}.bam.bai' && #end for ]]></token> <token name="@DUMP@"><![CDATA[ @@ -43,68 +41,79 @@ #end if ]]></token> - <!-- - input - --> + <!-- input --> + <xml name="cnoffset" token_default=""> + <param name="cnoffset" type="float" min="0.0" max="1.0" value="@DEFAULT@" label="Set minimum CN offset" help="(--cn-offset)"/> + </xml> + <xml name="coverage" token_label=""> + <param argument="--coverage" type="integer" value="10" label="@LABEL@"/> + </xml> <xml name="exclude"> <param argument="--exclude" type="data" format="tabular" optional="true" label="Select file with regions to exclude"/> </xml> <xml name="genome"> - <param argument="--genome" type="data" format="fasta" label="Select genome"/> + <param argument="--genome" type="data" format="fasta" label="Select genome file"/> </xml> <xml name="genoqual"> <param name="genoqual" type="integer" value="5" label="Set minimum mapping quality for genotyping" help="(--geno-qual)"/> </xml> + <xml name="input" token_format="" token_multiple="false" token_label=""> + <param name="input" type="data" format="@FORMAT@" multiple="@MULTIPLE@" label="@LABEL@"/> + </xml> + <xml name="maxreadsep" token_default=""> + <param argument="--maxreadsep" type="integer" value="@DEFAULT@" label="Set maximum read separation"/> + </xml> + <xml name="maxsize" token_default="" token_label=""> + <param argument="--maxsize" type="integer" value="@DEFAULT@" label="@LABEL@"/> + </xml> <xml name="minclip"> <param argument="--minclip" type="integer" value="25" label="Set minimum clipping length"/> </xml> - <xml name="maxreadsep" token_default="40"> - <param argument="--maxreadsep" type="integer" value="@DEFAULT@" label="Set maximum read separation"/> + <xml name="mincliquesize"> + <param name="mincliquesize" type="integer" value="2" label="Set minimum paired-end/single-read clique size" help="(--min-clique-size)"/> </xml> - <xml name="maxsize" token_default="1000000"> - <param argument="--maxsize" type="integer" value="@DEFAULT@" label="Set maximum SV size"/> - </xml> - <xml name="mincliquesize"> - <param name="mincliquesize" type="integer" value="2" label="Set minimum min. PE/SR clique size" help="(--min-clique-size)"/> - </xml> - <xml name="minrefsep" token_default="25"> + <xml name="minrefsep" token_default=""> <param argument="--minrefsep" type="integer" value="@DEFAULT@" label="Set minimum reference separation"/> </xml> - <xml name="minsize"> - <param argument="--minsize" type="integer" value="0" label="Set minimum SV size"/> + <xml name="minsize" token_default="" token_label=""> + <param argument="--minsize" type="integer" value="@DEFAULT@" label="@LABEL@"/> + </xml> + <xml name="pass"> + <param argument="--pass" type="boolean" truevalue="--pass" falsevalue="" label="Filter sites for PASS?"/> </xml> - <xml name="samples" token_format="bam" token_multiple="true" token_label="Select sample file(s)"> - <param name="samples" type="data" format="@FORMAT@" multiple="@MULTIPLE@" label="@LABEL@"/> + <xml name="ploidy"> + <param argument="--ploidy" type="integer" value="2" label="Set baseline ploidy"/> + </xml> + <xml name="samples"> + <param argument="--samples" type="data" format="tabular" label="Select sample file" help="Two-column sample file listing sample name and tumor or control."/> </xml> <xml name="svtype"> <param argument="--svtype" type="select" label="Select type(s) of structural variants to detect"> <option value="ALL" selected="true">All types (ALL)</option> <option value="DEL">Deletion (DEL)</option> + <option value="DUP">Duplication (DUP)</option> <option value="INS">Insertion (INS)</option> - <option value="DUP">Duplication (DUP)</option> <option value="INV">Inversion (INV)</option> <option value="BND">Translocation (BND)</option> </param> </xml> <xml name="vcffile"> - <param argument="--vcffile" type="data" format="vcf,bcf" optional="true" label="Select genotyping file"/> + <param argument="--vcffile" type="data" format="bcf,vcf" optional="true" label="Select genotyping file"/> </xml> - <!-- - output - --> + <!-- output --> + <xml name="bcf"> + <data name="out_bcf" format="bcf" from_work_dir="result.bcf" label="${tool.name} on ${on_string}: Result (BCF)"> + <filter>'bcf' in oo['out']</filter> + </data> + </xml> <xml name="vcf"> <data name="out_vcf" format="vcf" from_work_dir="result.vcf" label="${tool.name} on ${on_string}: Result (VCF)"> <filter>'vcf' in oo['out']</filter> </data> </xml> - <xml name="bcf"> - <data name="out_bcf" format="bcf" from_work_dir="result.bcf" label="${tool.name} on ${on_string}: Result (BCF)"> - <filter>'bcf' in oo['out']</filter> - </data> - </xml> <xml name="dump"> <data name="out_dump" format="tabular" from_work_dir="dump.tsv" label="${tool.name} on ${on_string}: SV-reads"> <filter>'dump' in oo['out']</filter> @@ -116,12 +125,25 @@ </data> </xml> - <!-- - Help - --> + <!-- help --> <token name="@WID@"><![CDATA[ Delly is an integrated structural variant (SV) prediction method that can discover, genotype and visualize deletions, tandem duplications, inversions and translocations at single-nucleotide resolution in short-read massively parallel sequencing data. It uses paired-ends, split-reads and read-depth to sensitively and accurately delineate genomic rearrangements throughout the genome. + +Short-read SV calling + +- *call* to discover and genotype structural variants +- *merge* structural variants across VCF/BCF files and within a single VCF/BCF file +- *filter* somatic or germline structural variants + +Long-read SV calling + +- *lr* for long-read SV discovery + +Copy-number variant calling + +- *cnv* to discover and genotype copy-number variants +- *classify* somatic or germline copy-number variants ]]></token> <token name="@REFERENCES@"><![CDATA[ More information are available on `GitHub <https://github.com/dellytools/delly>`_.