Mercurial > repos > drosofff > lumpy
changeset 2:b1e152172de9 draft
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/lumpy commit 5f3fb85a6eb667b04c4de65eb722261f315c8241
| author | drosofff |
|---|---|
| date | Tue, 06 Dec 2016 17:29:34 -0500 |
| parents | a006d42dd759 |
| children | 0bd777f0d6d8 |
| files | lumpy.xml |
| diffstat | 1 files changed, 118 insertions(+), 31 deletions(-) [+] |
line wrap: on
line diff
--- a/lumpy.xml Tue Dec 06 09:29:31 2016 -0500 +++ b/lumpy.xml Tue Dec 06 17:29:34 2016 -0500 @@ -1,4 +1,4 @@ -<tool id="lumpy" name="lumpy-sv" version="0.1"> +<tool id="lumpy" name="lumpy-sv" version="0.2"> <description>find structural variants</description> <requirements> <requirement type="package" version="0.2.12">lumpy-sv</requirement> @@ -10,38 +10,107 @@ </stdio> <version_command>lumpy --version</version_command> <command><![CDATA[ - ln -f -s "$input_file" input.bam && - #if $seq_method.seq_method_list == "paired-end": - samtools view -b -F 1294 input.bam > "input.discordants.unsorted.bam" && - samtools view -h input.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.splitters.unsorted.bam" && - samtools sort input.discordants.unsorted.bam > input.discordants.bam && - samtools sort input.splitters.unsorted.bam > input.splitters.bam && - samtools view -r readgroup input.bam - |tail -n +$seq_method.additional_params.samplingValue - |python $__tool_directory__/pairend_distro.py -r 101 -X 4 -N $seq_method.additional_params.samplingValue -o input.lib.histo > meandev.txt && - mean=\$(cat meandev.txt | sed s/mean:// | sed -r s/stdev:.+//) && - stdev=\$(cat meandev.txt | sed -r s/mean:.+stdev://) && - lumpy -mw 4 -tt 0 - -pe id:input.bam,bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$mean",stdev:"\$stdev",read_length:$seq_method.readLength,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold - -sr id:input.bam,bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && - mv input.discordants.bam $discordants && - mv input.splitters.bam $splits && - mv input.lib.histo $histogram && - mv output.vcf $vcf_call && - rm input.discordants.unsorted.bam input.splitters.unsorted.bam meandev.txt + #if $analysis_type.analysis_type_list == "one_sample": + ln -f -s $analysis_type.input_file input.bam && + #else: + ln -f -s $analysis_type.input_file input.A.bam && + ln -f -s $analysis_type.input_fileB input.B.bam && #end if - #if $seq_method.seq_method_list == "single-read": - samtools view -h input.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.splitters.unsorted.bam" && - lumpy -mw 4 -tt 0 - -sr id:input.bam,bam_file:input.splitters.unsorted.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && - mv input.splitters.unsorted.bam $splits && - mv output.vcf $vcf_call + + #if $analysis_type.analysis_type_list == "one_sample": + + #if $seq_method.seq_method_list == "paired-end": + samtools view -b -F 1294 input.bam > "input.discordants.unsorted.bam" && + samtools view -h input.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.splitters.unsorted.bam" && + samtools sort input.discordants.unsorted.bam > input.discordants.bam && + samtools sort input.splitters.unsorted.bam > input.splitters.bam && + samtools view -r readgroup input.bam + |tail -n +$seq_method.additional_params.samplingValue + |python $__tool_directory__/pairend_distro.py -r 101 -X 4 -N $seq_method.additional_params.samplingValue -o input.lib.histo > meandev.txt && + mean=\$(cat meandev.txt | sed s/mean:// | sed -r s/stdev:.+//) && + stdev=\$(cat meandev.txt | sed -r s/mean:.+stdev://) && + lumpy -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt + -pe id:input.bam,bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$mean",stdev:"\$stdev",read_length:$seq_method.readLength,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold + -sr id:input.bam,bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && + mv input.discordants.bam $discordants && + mv input.splitters.bam $splits && + mv input.lib.histo $histogram && + mv output.vcf $vcf_call && + rm input.discordants.unsorted.bam input.splitters.unsorted.bam meandev.txt + #end if + #if $seq_method.seq_method_list == "single-read": + samtools view -h input.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.splitters.unsorted.bam" && + lumpy -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt + -sr id:input.bam,bam_file:input.splitters.unsorted.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && + mv input.splitters.unsorted.bam $splits && + mv output.vcf $vcf_call + #end if + + #else: + + #if $seq_method.seq_method_list == "paired-end": + samtools view -b -F 1294 input.A.bam > "input.A.discordants.unsorted.bam" && + samtools view -b -F 1294 input.B.bam > "input.B.discordants.unsorted.bam" && + samtools view -h input.A.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.A.splitters.unsorted.bam" && + samtools view -h input.B.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.B.splitters.unsorted.bam" && + samtools sort input.A.discordants.unsorted.bam > input.A.discordants.bam && + samtools sort input.B.discordants.unsorted.bam > input.B.discordants.bam && + samtools sort input.A.splitters.unsorted.bam > input.A.splitters.bam && + samtools sort input.B.splitters.unsorted.bam > input.B.splitters.bam && + samtools view -r readgroup input.A.bam + |tail -n +$seq_method.additional_params.samplingValue + |python $__tool_directory__/pairend_distro.py -r 101 -X 4 -N $seq_method.additional_params.samplingValue -o input.A.lib.histo > meandevA.txt && + samtools view -r readgroup input.B.bam + |tail -n +$seq_method.additional_params.samplingValue + |python $__tool_directory__/pairend_distro.py -r 101 -X 4 -N $seq_method.additional_params.samplingValue -o input.B.lib.histo > meandevB.txt && + meanA=\$(cat meandevA.txt | sed s/mean:// | sed -r s/stdev:.+//) && + meanB=\$(cat meandevB.txt | sed s/mean:// | sed -r s/stdev:.+//) && + stdevA=\$(cat meandevA.txt | sed -r s/mean:.+stdev://) && + stdevB=\$(cat meandevB.txt | sed -r s/mean:.+stdev://) && + lumpy -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt + -pe id:inputA.bam,bam_file:input.A.discordants.bam,histo_file:input.A.lib.histo,mean:"\$meanA",stdev:"\$stdevA",read_length:$seq_method.readLength,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold + -pe id:inputB.bam,bam_file:input.B.discordants.bam,histo_file:input.B.lib.histo,mean:"\$meanB",stdev:"\$stdevA",read_length:$seq_method.readLength,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold + -sr id:inputA.bam,bam_file:input.A.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold + -sr id:inputB.bam,bam_file:input.B.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && + mv input.A.discordants.bam $discordants && + mv input.B.discordants.bam $discordantsB && + mv input.A.splitters.bam $splits && + mv input.B.splitters.bam $splitsB && + mv input.A.lib.histo $histogram && + mv input.B.lib.histo $histogramB && + mv output.vcf $vcf_call && + rm input.A.discordants.unsorted.bam input.B.discordants.unsorted.bam input.A.splitters.unsorted.bam input.B.splitters.unsorted.bam meandevA.txt meandevB.txt + #end if + #if $seq_method.seq_method_list == "single-read": + samtools view -h input.A.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.A.splitters.unsorted.bam" && + samtools view -h input.B.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.B.splitters.unsorted.bam" && + lumpy -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt + -sr id:input.A.bam,bam_file:input.A.splitters.unsorted.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold + -sr id:input.B.bam,bam_file:input.B.splitters.unsorted.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && + mv input.A.splitters.unsorted.bam $splits && + mv input.B.splitters.unsorted.bam $splitsB && + mv output.vcf $vcf_call + #end if + + #end if ]]></command> <!-- basic error handling --> <inputs> - <param format="bam" name="input_file" type="data" label="One BAM alignment file produced by BWA-mem"/> + <conditional name="analysis_type"> + <param help="Single or paired conditions (eg tumor vs normal)" label="Analysis type" name="analysis_type_list" type="select"> + <option selected="True" value="one_sample">One Sample</option> + <option value="two_sample">Two samples</option> + </param> + <when value="one_sample"> + <param format="bam" name="input_file" type="data" label="One BAM alignment file produced by BWA-mem"/> + </when> + <when value="two_sample"> + <param format="bam" name="input_file" type="data" label="One BAM alignment file produced by BWA-mem"/> + <param format="bam" name="input_fileB" type="data" label="One BAM alignment file produced by BWA-mem"/> + </when> + </conditional> <conditional name="seq_method"> <param help="Paired-end or single-read sequencing" label="Sequencing method" name="seq_method_list" type="select"> <option selected="True" value="paired-end">Paired-end sequencing</option> @@ -51,6 +120,8 @@ <param name="readLength" value="151" type="integer" label="read length" help="e.g. 151 nt" /> <section name="additional_params" title="Additional Options" expanded="False"> <param name="samplingValue" value="100000" type="integer" label="number of reads to compute mean and stdev of read length" help="e.g. 10000" /> + <param name="mw" value="4" type="integer" label="-mw" help="minimum weight across all samples for a call (default: 4)" /> + <param name="tt" value="0" type="integer" label="-tt" help="trim threshold (default: 0)" /> <param name="min_non_overlap" value="101" type="integer" label="min_non_overlap" help="e.g. 101" /> <param name="discordant_z" value="5" type="integer" label="discordant_z" help="e.g. 5" /> <param name="back_distance" value="10" type="integer" label="back_distance" help="e.g. 10" /> @@ -60,6 +131,8 @@ </when> <when value="single-read"> <section name="additional_params" title="Additional Options" expanded="False"> + <param name="mw" value="4" type="integer" label="-mw" help="minimum weight across all samples for a call (default: 4)" /> + <param name="tt" value="0" type="integer" label="-tt" help="trim threshold (default: 0)" /> <param name="back_distance" value="10" type="integer" label="back_distance" help="e.g. 10" /> <param name="weight" value="1" type="integer" label="weight" help="e.g. 1" /> <param name="min_mapping_threshold" value="20" type="integer" label="min_mapping_threshold" help="e.g. 20" /> @@ -71,20 +144,34 @@ </inputs> <outputs> - <data format="tabular" name="histogram" type="data" label="Lumpy on ${input_file.element_identifier}: Fragment size distribution"> + <data format="tabular" name="histogram" type="data" label="Lumpy on ${analysis_type.input_file.element_identifier}: Fragment size distribution"> <filter>seq_method['seq_method_list'] == "paired-end"</filter> </data> - <data format="bam" name="splits" type="data" label="Lumpy on ${input_file.element_identifier}: Split Reads (Bam format)"/> - <data format="bam" name="discordants" type="data" label="Lumpy on ${input_file.element_identifier}: Discordant Pairs (Bam format)"> + <data format="tabular" name="histogramB" type="data" label="Lumpy on ${analysis_type.input_fileB.element_identifier}: Fragment size distribution"> + <filter>seq_method['seq_method_list'] == "paired-end"</filter> + <filter>analysis_type['analysis_type_list'] == "two_sample"</filter> + </data> + <data format="bam" name="splits" type="data" label="Lumpy on ${analysis_type.input_file.element_identifier}: Split Reads (Bam format)"/> + <data format="bam" name="splitsB" type="data" label="Lumpy on ${analysis_type.input_fileB.element_identifier}: Split Reads (Bam format)"> + <filter>analysis_type['analysis_type_list'] == "two_sample"</filter> + </data> + <data format="bam" name="discordants" type="data" label="Lumpy on ${analysis_type.input_file.element_identifier}: Discordant Pairs (Bam format)"> <filter>seq_method['seq_method_list'] == "paired-end"</filter> </data> - <data format="vcf" name="vcf_call" type="data" label="Lumpy on ${input_file.element_identifier}: Variant Calling (vcf format)"/> + <data format="bam" name="discordantsB" type="data" label="Lumpy on ${analysis_type.input_fileB.element_identifier}: Discordant Pairs (Bam format)"> + <filter>seq_method['seq_method_list'] == "paired-end"</filter> + <filter>analysis_type['analysis_type_list'] == "two_sample"</filter> + </data> + <data format="vcf" name="vcf_call" type="data" label="Lumpy Variant Calling (vcf format)"/> </outputs> <tests> <test> + <param name="analysis_type" value="one_sample" /> <param name="input_file" value="sr.input.bam" ftype="bam"/> <param name="seq_method_list" value="single-read" /> + <param name="mw" value="4"/> + <param name="tt" value="0"/> <param name="back_distance" value="10"/> <param name="weight" value="1" /> <param name="min_mapping_threshold" value="20" />