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

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

5:6ae3a402b9af

<tool id="lumpy" name="lumpy-sv" version="1.2.2">
    <description>find structural variants</description>
    <requirements>
        <requirement type="package" version="0.2.13">lumpy-sv</requirement>
        <requirement type="package" version="1.3.1">samtools</requirement>
        <requirement type="package" version="1.11.2=py27_0">numpy</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>
    <command detect_errors="exit_code"><![CDATA[

                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.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                    #if $output_format == "BEDPE":
                        -b
                    #end if
                    -pe id:'$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.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                    #if $output_format == "BEDPE":
                        -b
                    #end if
                    -sr id:'$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

                    |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.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                    #if $output_format == "BEDPE":
                        -b
                    #end if
                    -pe id:inputA.bam,bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$meanA",stdev:"\$stdevA",read_length:$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.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                    #if $output_format == "BEDPE":
                        -b
                    #end if
                    -sr id:'$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'

                    <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"/>
                    <param name="evidence" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="true" label="show evidence for each call"/>
                </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"/>
                    <param name="evidence" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="false" label="show evidence for each call"/>
                </section>
            </when>

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

                <option value="BEDPE">BEDPE</option>
            </param>
    </inputs>

    <outputs>
        <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" 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}: 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)" 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)" 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>

            </change_format>
        </data>
    </outputs>

    <tests>
        <test>
            <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="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>
            <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>
            <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"/>

6:48e97429a749

<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[

                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

                    |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'

                    <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 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>

            </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="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"/>