annotate lumpy.xml @ 6:48e97429a749 draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/lumpy_sv commit 37c0f0938a5cad74c954a89827a6a08bbbb81cb0

<tool id="lumpy" name="lumpy-sv" version="1.3">
    <description>find structural variants</description>
    <requirements>
        <requirement type="package" version="0.3.1">lumpy-sv</requirement>
        <requirement type="package" version="1.18">samtools</requirement>
        <requirement type="package" version="1.16.5">numpy</requirement>
    </requirements>
    <stdio>
        <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' '$one_sample_bam' &&
        #else:
            #set sample_a_bam = re.sub('[^\w\-]', '_', str($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 $seq_method.seq_method_list == "paired-end":
                samtools view -@ \${GALAXY_SLOTS:-4} -u -F 1294 '$one_sample_bam' | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.discordants.bam &&
                samtools view -@ \${GALAXY_SLOTS:-4} -h '$one_sample_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.splitters.bam &&
                samtools view -@ \${GALAXY_SLOTS:-4} '$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 $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                    #if $output_format == "BEDPE":
                        -b
                    #end if
                    -pe id:'$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 $seq_method.seq_method_list == "single-read":
                samtools view -@ \${GALAXY_SLOTS:-4} -h '$one_sample_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.splitters.bam &&
                lumpy $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                    #if $output_format == "BEDPE":
                        -b
                    #end if
                    -sr id:'$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 $seq_method.seq_method_list == "paired-end":
                samtools view -@ \${GALAXY_SLOTS:-4} -u -F 1294 '$sample_a_bam' | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.discordants.bam &&
                samtools view -@ \${GALAXY_SLOTS:-4} -u -F 1294 '$sample_b_bam' | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.B.discordants.bam &&
                samtools view -@ \${GALAXY_SLOTS:-4} -h '$sample_a_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.splitters.bam &&
                samtools view -@ \${GALAXY_SLOTS:-4} -h '$sample_b_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.B.splitters.bam &&
                samtools view -@ \${GALAXY_SLOTS:-4} '$sample_a_bam'
                    |python $__tool_directory__/pairend_distro.py -r $analysis_type.readLength -X 4 -N $seq_method.additional_params.samplingValue -o input.lib.histo > meandevA.txt &&
                samtools view -@ \${GALAXY_SLOTS:-4} '$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 $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                    #if $output_format == "BEDPE":
                        -b
                    #end if
                    -pe id:inputA.bam,bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$meanA",stdev:"\$stdevA",read_length:$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:$seq_method.additional_params.min_mapping_threshold
                    -sr id:inputA.bam,bam_file:input.splitters.bam,back_distance:$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 $seq_method.seq_method_list == "single-read":
                samtools view -@ \${GALAXY_SLOTS:-4} -h '$sample_a_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.splitters.bam &&
                samtools view -@ \${GALAXY_SLOTS:-4} -h '$sample_b_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.B.splitters.bam &&
                lumpy $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                    #if $output_format == "BEDPE":
                        -b
                    #end if
                    -sr id:'$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>
    <!-- basic error handling -->
    <inputs>
        <conditional name="analysis_type">
            <param help="Single or paired conditions (eg tumor vs normal)" label="Input(s)" 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"/>
                <param name="readLength" value="151"  type="integer" label="read length" help="e.g. 151 nt" />
            </when>
            <when value="two_sample">
                <param format="bam" name="input_file" type="data" label="One BAM alignment file produced by BWA-mem"/>
                <param name="readLength" value="151"  type="integer" label="read length" help="e.g. 151 nt" />
                <param format="bam" name="input_fileB" type="data" label="One BAM alignment file produced by BWA-mem"/>
                <param name="readLengthB" value="151"  type="integer" label="read length" help="e.g. 151 nt" />
            </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>
                <option value="single-read">Single-read sequencing</option>
            </param>
            <when value="paired-end">
                <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" />
                    <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"/>
                </section>
            </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" />
                    <param name="probability_curve" argument="-P" type="boolean" truevalue="-P" falsevalue="" checked="false" label="output probability curve for each variant"/>
                </section>
            </when>

        </conditional>
            <param help="get variant calling in vcf or BEDPE format" label="variant calling format" name="output_format" type="select">
                <option selected="True" value="vcf">vcf</option>
                <option value="BEDPE">BEDPE</option>
            </param>
    </inputs>

    <outputs>
        <data format="tabular" name="histogram" label="Lumpy-sv: 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-sv: FragmentB 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)" from_work_dir="input.splitters.bam"/>
        <data format="bam" name="splitsB" label="Lumpy on ${on_string}: SplitB 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)" 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}: DiscordantB Pairs (Bam format)" from_work_dir="input.B.discordants.bam">
            <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" label="Lumpy Variant Calling">
            <change_format>
                <when format="tabular" input="output_format" value="BEDPE" />
            </change_format>
        </data>
    </outputs>

    <tests>
        <test expect_num_outputs="7">
            <param name="analysis_type_list" value="two_sample" />
            <param name="input_file" value="sample_Del.bam" ftype="bam"/>
            <param name="input_fileB" value="sample_cle.bam" ftype="bam"/>
            <param name="seq_method_list" value="paired-end" />
            <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.paired_end.vcf" ftype="vcf"/>
        </test>
        <test expect_num_outputs="2">
            <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" />
            <output name="vcf_call" file="output.vcf" ftype="vcf"/>
        </test>
        <test expect_num_outputs="2">
            <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="probability_curve" value="true" />
            <output name="vcf_call" file="output_extended.vcf" ftype="vcf" compare="sim_size"/>
        </test>
        <test expect_num_outputs="3">
            <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>

**Input(s)**

*One sample* : lumpy search structural variations inside a single sequencing dataset

*Two samples*: lumpy search structural variations inside and across two sequencing datasets from two samples

Analysis of sample replicates is not implemented yet in this wrapper

*BAM files*: Only BAM alignments produced by BWA-mem have been tested with this tool

**Sequencing method**

*Paired-end sequencing*: Both ends of library fragments have been sequenced, resulting in two paired sequencing datasets

*Single-read sequencing*: Only one end of library fragment has been sequenced, resulting in a single sequencing dataset. Under these conditions, evidences of structural variation are obtained only from splited read alignments

*Read length*: The length of the sequencing reads in the library. This information is required only for paired-end sequencing data

*Additional options*: refer to lumpy-sv_ documentation and the publication (doi 10.1186/gb-2014-15-6-r84)

**lumpy-sv manual**

Read the lumpy-sv_ documentation for details on using lumpy.

.. _lumpy-sv: https://github.com/arq5x/lumpy-sv

**lumpy options**

v 0.2.13
Author:  Ryan Layer ([e-mail])

Summary: Find structural variations in various signals.

Options::
<![CDATA[

	-g	Genome file (defines chromosome order)
	-e	Show evidence for each call
	-w	File read windows size (default 1000000)
	-mw	minimum weight for a call
	-msw	minimum per-sample weight for a call
	-tt	trim threshold
	-x	exclude file bed file
	-t	temp file prefix, must be to a writeable directory
	-P	output probability curve for each variant
	-b	output BEDPE instead of VCF
	-sr	bam_file:<file name>,
		id:<sample name>,
		back_distance:<distance>,
		min_mapping_threshold:<mapping quality>,
		weight:<sample weight>,
		min_clip:<minimum clip length>,
		read_group:<string>

	-pe	bam_file:<file name>,
		id:<sample name>,
		histo_file:<file name>,
		mean:<value>,
		stdev:<value>,
		read_length:<length>,
		min_non_overlap:<length>,
		discordant_z:<z value>,
		back_distance:<distance>,
		min_mapping_threshold:<mapping quality>,
		weight:<sample weight>,
		read_group:<string>

	-bedpe	bedpe_file:<bedpe file>,
		id:<sample name>,
		weight:<sample weight>
]]>
    </help>

    <citations>
    <citation type="doi">10.1186/gb-2014-15-6-r84</citation>
  </citations>
</tool>