Mercurial > repos > iuc > delly_lr
changeset 2:ceda4714f3a1 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/delly commit d18d984264f54b45e94d97b5b97ed499a32a334a"
| author | iuc |
|---|---|
| date | Fri, 22 Jan 2021 14:32:45 +0000 |
| parents | d5124d5c8131 |
| children | d30785dbe6b7 |
| files | lr.xml macros.xml |
| diffstat | 2 files changed, 120 insertions(+), 92 deletions(-) [+] |
line wrap: on
line diff
--- a/lr.xml Thu Oct 29 20:51:54 2020 +0000 +++ b/lr.xml Fri Jan 22 14:32:45 2021 +0000 @@ -9,7 +9,7 @@ <command detect_errors="exit_code"><![CDATA[ ## initialize @BAM@ - + ## run delly lr ## generic options @@ -26,99 +26,97 @@ --min-clique-size $discovery.mincliquesize --minrefsep $discovery.minrefsep --maxreadsep $discovery.maxreadsep +## consensus options +--max-reads $consensus.maxreads +--flank-size $consensus.flanksize +--flank-quality $consensus.flankquality ## genotyping options -#if $genotyping.vcffile - --vcffile '$genotyping.vcffile' -#end if --geno-qual $genotyping.genoqual #if 'dump' in $oo.out --dump 'dump.tsv.gz' #end if -## samples -#for $i, $current in enumerate($samples) - 'sample_${i}.bam' +## input +#for $i, $current in enumerate($input) + 'input_${i}.bam' #end for ## postprocessing @LOG@ +@DUMP@ @VCF@ -@DUMP@ ]]></command> <inputs> - <expand macro="samples"/> + <expand macro="input" format="bam" multiple="true" label="Select input file(s)"/> <section name="generic" title="Generic options" expanded="true"> - <expand macro="genome"/> <expand macro="svtype"/> - <expand macro="exclude"/> <param argument="--technology" type="select" label="Select sequencing technology"> <option value="ont" selected="true">Oxford Nanopore (ont)</option> - <option value="pb">Pacbio (pb)</option> + <option value="pb">PacBio (pb)</option> </param> + <expand macro="genome"/> + <expand macro="exclude"/> </section> <section name="discovery" title="Discovery options" expanded="true"> - <param argument="--mapqual" type="integer" value="1" label="Set minimum mapping quality"/> + <param argument="--mapqual" type="integer" value="10" label="Set minimum mapping quality"/> <expand macro="minclip"/> <expand macro="mincliquesize"/> - <expand macro="minrefsep" defaut="30"/> - <expand macro="maxreadsep" defaut="75"/> + <expand macro="minrefsep" default="30"/> + <expand macro="maxreadsep" default="75"/> + </section> + <section name="consensus" title="Consensus options" expanded="true"> + <param name="maxreads" type="integer" value="5" label="Set maximum reads for consensus computation" help="(--max-reads)"/> + <param name="flanksize" type="integer" value="400" label="Set minimum flank size" help="(--flank-size)"/> + <param name="flankquality" type="float" min="0.0" max="1.0" value="0.9" label="Set minimum flank quality" help="(--flank-quality)"/> </section> <section name="genotyping" title="Genotyping options" expanded="true"> - <expand macro="vcffile"/> <expand macro="genoqual"/> </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="vcf">VCF</option> + <option value="log">Log</option> <option value="dump">SV-reads</option> - <option value="log">Log</option> + <option value="vcf">VCF</option> </param> </section> </inputs> <outputs> - <expand macro="vcf"/> <expand macro="bcf"/> <expand macro="dump"/> <expand macro="log"/> + <expand macro="vcf"/> </outputs> <tests> - <!-- no test implemented for parameter vcffile --> - <!-- #1 default, single --> <test expect_num_outputs="2"> - <param name="samples" value="normal.bam"/> + <param name="input" value="normal.bam"/> <section name="generic"> <param name="genome" value="genome.fasta"/> </section> <section name="oo"> <param name="out" value="vcf,bcf"/> </section> + <output name="out_bcf"> + <assert_contents> + <has_size value="1184" delta="10"/> + </assert_contents> + </output> <output name="out_vcf"> <assert_contents> <has_size value="3661" delta="10"/> <has_line line="#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	normal"/> </assert_contents> </output> - <output name="out_bcf"> - <assert_contents> - <has_size value="1184" delta="10"/> - </assert_contents> - </output> </test> <!-- #2 default, multi; test data to small, results are empty --> <test expect_num_outputs="3"> - <param name="samples" value="normal.bam,tumor.bam"/> + <param name="input" value="normal.bam,tumor.bam"/> <section name="generic"> <param name="genome" value="genome.fasta"/> </section> <section name="oo"> <param name="out" value="vcf,bcf,log"/> </section> - <output name="out_vcf"> - <assert_contents> - <has_size value="3667" delta="10"/> - </assert_contents> - </output> <output name="out_bcf"> <assert_contents> <has_size value="1189" delta="10"/> @@ -129,10 +127,15 @@ <has_text_matching expression=".+Done.+"/> </assert_contents> </output> + <output name="out_vcf"> + <assert_contents> + <has_size value="3667" delta="10"/> + </assert_contents> + </output> </test> <!-- #3 --> <test expect_num_outputs="4"> - <param name="samples" value="normal.bam"/> + <param name="input" value="normal.bam"/> <section name="generic"> <param name="genome" value="genome.fasta"/> <param name="exclude" value="exclude.tsv"/> @@ -140,11 +143,6 @@ <section name="oo"> <param name="out" value="vcf,bcf,dump,log"/> </section> - <output name="out_vcf"> - <assert_contents> - <has_size value="3661" delta="10"/> - </assert_contents> - </output> <output name="out_bcf"> <assert_contents> <has_size value="1186" delta="10"/> @@ -160,10 +158,15 @@ <has_text_matching expression=".+Done.+"/> </assert_contents> </output> + <output name="out_vcf"> + <assert_contents> + <has_size value="3661" delta="10"/> + </assert_contents> + </output> </test> <!-- #4 --> <test expect_num_outputs="4"> - <param name="samples" value="normal.bam"/> + <param name="input" value="normal.bam"/> <section name="generic"> <param name="genome" value="genome.fasta"/> <param name="svtype" value="DEL"/> @@ -178,6 +181,11 @@ <param name="minrefsep" value="24"/> <param name="maxreadsep" value="39"/> </section> + <section name="consensus"> + <param name="maxreads" value="6"/> + <param name="flanksize" value="399"/> + <param name="flankquality" value="0.91"/> + </section> <section name="genotyping"> <param name="genoqual" value="4"/> </section> @@ -189,12 +197,6 @@ <has_size value="1182" delta="10"/> </assert_contents> </output> - <output name="out_vcf"> - <assert_contents> - <has_size value="3661" delta="10"/> - <has_line line="#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	normal"/> - </assert_contents> - </output> <output name="out_dump"> <assert_contents> <has_size value="0"/> @@ -205,10 +207,16 @@ <has_text_matching expression=".+"/> </assert_contents> </output> + <output name="out_vcf"> + <assert_contents> + <has_size value="3661" delta="10"/> + <has_line line="#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	normal"/> + </assert_contents> + </output> </test> <!-- #5 --> <test expect_num_outputs="1"> - <param name="samples" value="normal.bam"/> + <param name="input" value="normal.bam"/> <section name="generic"> <param name="genome" value="genome.fasta"/> <param name="svtype" value="INS"/> @@ -225,7 +233,7 @@ </test> <!-- #6 --> <test expect_num_outputs="1"> - <param name="samples" value="normal.bam"/> + <param name="input" value="normal.bam"/> <section name="generic"> <param name="genome" value="genome.fasta"/> <param name="svtype" value="DUP"/> @@ -241,7 +249,7 @@ </test> <!-- #7 --> <test expect_num_outputs="1"> - <param name="samples" value="normal.bam"/> + <param name="input" value="normal.bam"/> <section name="generic"> <param name="genome" value="genome.fasta"/> <param name="svtype" value="INV"/> @@ -257,7 +265,7 @@ </test> <!-- #8 --> <test expect_num_outputs="1"> - <param name="samples" value="normal.bam"/> + <param name="input" value="normal.bam"/> <section name="generic"> <param name="genome" value="genome.fasta"/> <param name="svtype" value="BND"/> @@ -279,15 +287,13 @@ @WID@ -Delly *long-read (lr)* uses the long-read SV discovery mode. - **Input** -Delly *long-read (lr)* needs a sorted, indexed and duplicate marked BAM file for every input sample. An indexed reference genome is required to identify split-reads. Additionally a VCF/BCF file for genotyping can be applied. +Delly *long-read (lr)* needs a sorted, indexed and duplicate marked BAM file for every input sample. An indexed reference genome is required to identify split-reads. **Output** -The output is available in BCF and VCF format. Additionally an output file for SV-reads is provided. +The output is available in BCF and VCF format. Additionally an output file for SV-reads and a log file are provided. .. class:: infomark
--- a/macros.xml Thu Oct 29 20:51:54 2020 +0000 +++ b/macros.xml Fri Jan 22 14:32:45 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>`_.