Mercurial > repos > drosofff > lumpy
diff lumpy.xml @ 12:b3fb23bbca8e draft
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/lumpy commit 03ac2f3182f9e72db31297fa9e2fd5f0802343ea
| author | drosofff |
|---|---|
| date | Sun, 18 Dec 2016 10:35:43 -0500 |
| parents | ecbc563571ea |
| children | 02adb61c0246 |
line wrap: on
line diff
--- a/lumpy.xml Mon Dec 12 13:45:08 2016 -0500 +++ b/lumpy.xml Sun Dec 18 10:35:43 2016 -0500 @@ -1,4 +1,4 @@ -<tool id="lumpy" name="lumpy-sv" version="0.2.1"> +<tool id="lumpy" name="lumpy-sv" version="0.3.0"> <description>find structural variants</description> <requirements> <requirement type="package" version="0.2.12">lumpy-sv</requirement> @@ -9,101 +9,76 @@ <exit_code range="1:" level="fatal" description="Tool exception" /> </stdio> <command detect_errors="exit_code"><![CDATA[ + #import re + #set one_sample_bam = re.sub('[^\w\-]', '_', str($analysis_type.input_file.element_identifier)) #if $analysis_type.analysis_type_list == "one_sample": - ln -f -s '$analysis_type.input_file' input.bam && + ln -f -s '$analysis_type.input_file' '$one_sample_bam' && #else: - ln -f -s '$analysis_type.input_file' input.A.bam && - ln -f -s '$analysis_type.input_fileB' input.B.bam && + #set sample_a_bam = re.sub('[^\w\-]', '_', str($analysis_type.input_file.element_identifier)) + #set sample_b_bam = re.sub('[^\w\-]', '_', str($analysis_type.input_fileB.element_identifier)) + #if $sample_a_bam == $sample_b_bam: + #set sample_a_bam = "%s_a" % str($sample_a_bam) + #set sample_b_bam = "%s_b" % str($sample_b_bam) + #end if + ln -f -s '$analysis_type.input_file' '$sample_a_bam' && + ln -f -s '$analysis_type.input_fileB' '$sample_b_bam' && #end if #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 $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.splitters.unsorted.bam" && - samtools sort input.discordants.unsorted.bam > input.discordants.bam && - samtools sort input.splitters.unsorted.bam > input.splitters.bam && - samtools view input.bam - |tail -n +1 + samtools view -u -F 1294 '$one_sample_bam' | samtools sort -O bam -o input.discordants.bam && + samtools view -h '$one_sample_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -O bam -o input.splitters.bam && + samtools view '$one_sample_bam' |python $__tool_directory__/pairend_distro.py -r $analysis_type.readLength -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 + lumpy $seq_method.additional_params.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt #if $output_format == "BEDPE": -b #end if - -pe id:input.bam,bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$mean",stdev:"\$stdev",read_length:$analysis_type.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 $seq_method.additional_params.tt + -pe id:'$one_sample_bam',bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$mean",stdev:"\$stdev",read_length:$analysis_type.readLength,min_non_overlap:$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:'$one_sample_bam',bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > '$vcf_call' + #elif $seq_method.seq_method_list == "single-read": + samtools view -h '$one_sample_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -O bam -o input.splitters.bam && + lumpy $seq_method.additional_params.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt #if $output_format == "BEDPE": -b #end if - -sr id:input.bam,bam_file:input.splitters.unsorted.bam,back_distance:$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 $vcf_call + -sr id:'$one_sample_bam',bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > '$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 input.A.bam - |tail -n +1 - |python $__tool_directory__/pairend_distro.py -r $analysis_type.readLength -X 4 -N $seq_method.additional_params.samplingValue -o input.A.lib.histo > meandevA.txt && - samtools view input.B.bam - |tail -n +1 + samtools view -u -F 1294 '$sample_a_bam' | samtools sort -O bam -o input.discordants.bam && + samtools view -u -F 1294 '$sample_b_bam' | samtools sort -O bam -o input.B.discordants.bam && + samtools view -h '$sample_a_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -O bam -o input.splitters.bam && + samtools view -h '$sample_b_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -O bam -o input.B.splitters.bam && + samtools view '$sample_a_bam' + |python $__tool_directory__/pairend_distro.py -r $analysis_type.readLength -X 4 -N $seq_method.additional_params.samplingValue -o input.lib.histo > meandevA.txt && + samtools view '$sample_b_bam' |python $__tool_directory__/pairend_distro.py -r $analysis_type.readLengthB -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 + lumpy $seq_method.additional_params.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt #if $output_format == "BEDPE": -b #end if - -pe id:inputA.bam,bam_file:input.A.discordants.bam,histo_file:input.A.lib.histo,mean:"\$meanA",stdev:"\$stdevA",read_length:$analysis_type.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:$seq_method.additional_params.min_mapping_threshold + -pe id:inputA.bam,bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$meanA",stdev:"\$stdevA",read_length:$analysis_type.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:$seq_method.additional_params.min_mapping_threshold -pe id:inputB.bam,bam_file:input.B.discordants.bam,histo_file:input.B.lib.histo,mean:"\$meanB",stdev:"\$stdevA",read_length:$analysis_type.readLengthB,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 $seq_method.additional_params.tt + -sr id:inputA.bam,bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold + -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:$seq_method.additional_params.min_mapping_threshold > '$vcf_call' + #elif $seq_method.seq_method_list == "single-read": + samtools view -h '$sample_a_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -O bam -o input.splitters.bam && + samtools view -h '$sample_b_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -O bam -o input.B.splitters.bam && + lumpy $seq_method.additional_params.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt #if $output_format == "BEDPE": -b #end if - -sr id:input.A.bam,bam_file:input.A.splitters.unsorted.bam,back_distance:$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 $vcf_call + -sr id:'$sample_a_bam',bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold + -sr id:'$sample_b_bam',bam_file:input.B.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > '$vcf_call' #end if - - #end if ]]></command> @@ -140,6 +115,8 @@ <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" /> + <param name="probability_curve" argument="-P" type="boolean" truevalue="-P" falsevalue="" checked="true" label="output probability curve for each variant"/> + <param name="evidence" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="true" label="show evidence for each call"/> </section> </when> <when value="single-read"> @@ -149,6 +126,8 @@ <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" /> + <param name="probability_curve" argument="-P" type="boolean" truevalue="-P" falsevalue="" checked="false" label="output probability curve for each variant"/> + <param name="evidence" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="false" label="show evidence for each call"/> </section> </when> @@ -160,21 +139,21 @@ </inputs> <outputs> - <data format="tabular" name="histogram" label="Lumpy on ${on_string}: Fragment size distribution"> + <data format="tabular" name="histogram" label="Lumpy on ${on_string}: Fragment size distribution" from_work_dir="input.lib.histo"> <filter>seq_method['seq_method_list'] == "paired-end"</filter> </data> - <data format="tabular" name="histogramB" label="Lumpy on ${on_string}: Fragment size distribution"> + <data format="tabular" name="histogramB" label="Lumpy on ${on_string}: Fragment size distribution" from_work_dir="input.B.lib.histo"> <filter>seq_method['seq_method_list'] == "paired-end"</filter> <filter>analysis_type['analysis_type_list'] == "two_sample"</filter> </data> - <data format="bam" name="splits" label="Lumpy on ${on_string}: Split Reads (Bam format)"/> - <data format="bam" name="splitsB" label="Lumpy on ${on_string}: Split Reads (Bam format)"> + <data format="bam" name="splits" label="Lumpy on ${on_string}: Split Reads (Bam format)" from_work_dir="input.splitters.bam"/> + <data format="bam" name="splitsB" label="Lumpy on ${on_string}: Split Reads (Bam format)" from_work_dir="input.B.splitters.bam"> <filter>analysis_type['analysis_type_list'] == "two_sample"</filter> </data> - <data format="bam" name="discordants" label="Lumpy on ${on_string}: Discordant Pairs (Bam format)"> + <data format="bam" name="discordants" label="Lumpy on ${on_string}: Discordant Pairs (Bam format)" from_work_dir="input.discordants.bam"> <filter>seq_method['seq_method_list'] == "paired-end"</filter> </data> - <data format="bam" name="discordantsB" label="Lumpy on ${on_string}: Discordant Pairs (Bam format)"> + <data format="bam" name="discordantsB" label="Lumpy on ${on_string}: Discordant Pairs (Bam format)" from_work_dir="input.discordants.B.bam"> <filter>seq_method['seq_method_list'] == "paired-end"</filter> <filter>analysis_type['analysis_type_list'] == "two_sample"</filter> </data> @@ -187,7 +166,7 @@ <tests> <test> - <param name="analysis_type" value="one_sample" /> + <param name="analysis_type_list" 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"/> @@ -197,6 +176,31 @@ <param name="min_mapping_threshold" value="20" /> <output name="vcf_call" file="output.vcf" ftype="vcf"/> </test> + <test> + <param name="analysis_type_list" 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" /> + <param name="evidence" value="true" /> + <param name="probability_curve" value="true" /> + <output name="vcf_call" file="output_extended.vcf" ftype="vcf" compare="sim_size"/> + </test> + <test> + <param name="analysis_type_list" value="two_sample" /> + <param name="input_file" value="sr.input.bam" ftype="bam"/> + <param name="input_fileB" 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" /> + <output name="vcf_call" file="output_two.vcf" ftype="vcf"/> + </test> </tests> <help>