comparison freebayes.xml @ 32:8a7a42541080 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/freebayes commit cce7fcdd5e8ba8636c751f9f974bf07a6845ba1c"

31:57def2d7c093

<tool id="freebayes" name="FreeBayes" version="@TOOL_VERSION@+galaxy1">
    <description>bayesian genetic variant detector</description>
    <xrefs>
        <xref type="bio.tools">freebayes</xref>
    </xrefs>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="4.1.3">gawk</requirement>
        <requirement type="package" version="20170422">parallel</requirement>
    </expand>
    <command detect_errors="exit_code"><![CDATA[
    ##set up input files

    #set $reference_fasta_filename = "localref.fa"

    #else:
        #set $input_bamfiles = [ $reference_source.batchmode.input_bams ]
    #end if

    #for $bam_count, $input_bam in enumerate( $input_bamfiles ):
        ln -s -f '${input_bam}' 'b_${bam_count}.bam' &&
        ln -s -f '${input_bam.metadata.bam_index}' 'b_${bam_count}.bam.bai' &&
    #end for

    ## Tabixize optional input_variant_vcf file (for --variant-input option)
    #if ( str( $options_type.options_type_selector ) == 'cline' or str( $options_type.options_type_selector ) == 'full' ) and str( $options_type.optional_inputs.optional_inputs_selector ) == 'set' and str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":
        ln -s -f '${options_type.optional_inputs.input_variant_type.input_variant_vcf}' input_variant_vcf.vcf.gz &&

    #elif str( $target_limit_type.target_limit_type_selector ) == "limit_by_region":
        printf '${target_limit_type.region_chromosome}\t${target_limit_type.region_start}\t${target_limit_type.region_end}' > regions_all.bed &&
    #else
        ##divide up the regions in the bam file for efficient processing
        #for $bam_count, $input_bam in enumerate( $input_bamfiles ):
            samtools view -H b_${bam_count}.bam |
            grep '^@SQ' |
            cut -f 2- |
            awk '{ gsub("^SN:","",$1); gsub("^LN:","",$2); print $1"\t0\t"$2; }' >> regions_all.bed &&
        #end for
    #end if

        freebayes

        --region '\$i'

        #for $bam_count, $input_bam in enumerate( $input_bamfiles ):
            --bam 'b_${bam_count}.bam'
        #end for
        --fasta-reference '${reference_fasta_filename}'

        ## Outputs
        --vcf './vcf_output/part_\$i.vcf'

                    --observation-bias '${options_type.optional_inputs.observation_bias}'
                #end if
                #if $options_type.optional_inputs.contamination_estimates:
                    --contamination-estimates '${options_type.optional_inputs.contamination_estimates}'
                #end if
            #end if

        ## REPORTING
            #if str( $options_type.reporting.reporting_selector ) == "set":
                --pvar ${options_type.reporting.pvar}

            </param>
            <when value="full">

                <conditional name="optional_inputs">
                    <param name="optional_inputs_selector" type="select" label="Additional inputs"
                           help="Sets --samples, --populations, --cnv-map, --trace, --failed-alleles, --variant-input, --only-use-input-alleles, --haplotype-basis-alleles, --report-all-haplotype-alleles, --report-monomorphic options, --observation-bias, and --contamination-estimates">
                        <option value="do_not_set" selected="true">Do not provide additional inputs</option>
                        <option value="set">Provide additional inputs</option>
                    </param>
                    <when value="set">
                        <param name="output_failed_alleles_option" argument="--failed-alleles" type="boolean" truevalue="--failed-alleles" falsevalue="" checked="false"

                               label="Load read length-dependent allele observation biases from"
                               help="The format is [length] [alignment efficiency relative to reference] where the efficiency is 1 if there is no relative observation bias" />
                        <param name="contamination_estimates" argument="--contamination-estimates" type="data" format="tabular" optional="true"
                               label="Upload per-sample estimates of contamination from"
                               help="The format should be: sample p(read=R|genotype=AR) p(read=A|genotype=AA) Sample '*' can be used to set default contamination estimates" />
                    </when>
                    <when value="do_not_set" />
                </conditional>

                <!-- reporting -->

            <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/>
            <param name="input_bams" ftype="bam" value="freebayes-phix174.bam"/>
            <param name="options_type_selector" value="full"/>
            <param name="population_model_selector" value="set"/>
            <param name="P" value="1"/>
            <output name="output_vcf" file="freebayes-phix174-test4.vcf" lines_diff="4" />
        </test>
        <test>
            <param name="reference_source_selector" value="history" />
            <param name="processmode" value="individual" />

            <param name="input_bams" ftype="bam" value="freebayes-hxb2.bam"/>
            <param name="options_type_selector" value="simple"/>
            <param name="coverage_options_selector" value="set" />
            <param name="skip_coverage" value="100" />
            <output name="output_vcf" file="freebayes-hxb2-test7.vcf" lines_diff="4" />
        </test>
    </tests>
    <help><![CDATA[
**What it does**

32:8a7a42541080

<tool id="freebayes" name="FreeBayes" version="@TOOL_VERSION@+galaxy0">
    <description>bayesian genetic variant detector</description>
    <xrefs>
        <xref type="bio.tools">freebayes</xref>
    </xrefs>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="5.1.0">gawk</requirement>
        <requirement type="package" version="20211022">parallel</requirement>
    </expand>
    <command detect_errors="exit_code"><![CDATA[
    ##set up input files

    #set $reference_fasta_filename = "localref.fa"

    #else:
        #set $input_bamfiles = [ $reference_source.batchmode.input_bams ]
    #end if

    #for $bam_count, $input_bam in enumerate( $input_bamfiles ):
        #if $input_bam.ext == 'bam':
            ln -s -f '${input_bam}' 'b_${bam_count}.bam' &&
            ln -s -f '${input_bam.metadata.bam_index}' 'b_${bam_count}.bam.bai' &&
        #elif $input_bam.ext == 'cram':
            ln -s -f '${input_bam}' 'b_${bam_count}.cram' &&
            ln -s -f '${input_bam.metadata.cram_index}' 'b_${bam_count}.cram.crai' &&
        #end if
    #end for

    ## Tabixize optional input_variant_vcf file (for --variant-input option)
    #if ( str( $options_type.options_type_selector ) == 'cline' or str( $options_type.options_type_selector ) == 'full' ) and str( $options_type.optional_inputs.optional_inputs_selector ) == 'set' and str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":
        ln -s -f '${options_type.optional_inputs.input_variant_type.input_variant_vcf}' input_variant_vcf.vcf.gz &&

    #elif str( $target_limit_type.target_limit_type_selector ) == "limit_by_region":
        printf '${target_limit_type.region_chromosome}\t${target_limit_type.region_start}\t${target_limit_type.region_end}' > regions_all.bed &&
    #else
        ##divide up the regions in the bam file for efficient processing
        #for $bam_count, $input_bam in enumerate( $input_bamfiles ):
            samtools view -H b_${bam_count}.${input_bam.ext}|
            grep '^@SQ' |
            cut -f 2- |
            awk '{ gsub("^SN:","",$1); gsub("^LN:","",$2); print $1"\t0\t"$2; }' >> regions_all.bed &&
        #end for
    #end if

        freebayes

        --region '\$i'

        #for $bam_count, $input_bam in enumerate( $input_bamfiles ):
            --bam 'b_${bam_count}.${input_bam.ext}'
        #end for
        --fasta-reference '${reference_fasta_filename}'

        ## Outputs
        --vcf './vcf_output/part_\$i.vcf'

                    --observation-bias '${options_type.optional_inputs.observation_bias}'
                #end if
                #if $options_type.optional_inputs.contamination_estimates:
                    --contamination-estimates '${options_type.optional_inputs.contamination_estimates}'
                #end if
                $options_type.optional_inputs.trim_complex_tail
            #end if

        ## REPORTING
            #if str( $options_type.reporting.reporting_selector ) == "set":
                --pvar ${options_type.reporting.pvar}

            </param>
            <when value="full">

                <conditional name="optional_inputs">
                    <param name="optional_inputs_selector" type="select" label="Additional inputs"
                           help="Sets --samples, --populations, --cnv-map, --trace, --failed-alleles, --variant-input, --only-use-input-alleles, --haplotype-basis-alleles, --report-all-haplotype-alleles, --report-monomorphic options, --observation-bias, --contamination-estimates and --trim-complex-tail">
                        <option value="do_not_set" selected="true">Do not provide additional inputs</option>
                        <option value="set">Provide additional inputs</option>
                    </param>
                    <when value="set">
                        <param name="output_failed_alleles_option" argument="--failed-alleles" type="boolean" truevalue="--failed-alleles" falsevalue="" checked="false"

                               label="Load read length-dependent allele observation biases from"
                               help="The format is [length] [alignment efficiency relative to reference] where the efficiency is 1 if there is no relative observation bias" />
                        <param name="contamination_estimates" argument="--contamination-estimates" type="data" format="tabular" optional="true"
                               label="Upload per-sample estimates of contamination from"
                               help="The format should be: sample p(read=R|genotype=AR) p(read=A|genotype=AA) Sample '*' can be used to set default contamination estimates" />
                        <param name="trim_complex_tail" argument="--trim-complex-tail" type="boolean" truevalue="--trim-complex-tail" falsevalue=""
                               label="Trim trailing reference matches" />
                    </when>
                    <when value="do_not_set" />
                </conditional>

                <!-- reporting -->

            <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/>
            <param name="input_bams" ftype="bam" value="freebayes-phix174.bam"/>
            <param name="options_type_selector" value="full"/>
            <param name="population_model_selector" value="set"/>
            <param name="P" value="1"/>
            <param name="trim_complex_tail" value="--trim-complex-tail"/>
            <output name="output_vcf" file="freebayes-phix174-test4.vcf" lines_diff="4" />
        </test>
        <test>
            <param name="reference_source_selector" value="history" />
            <param name="processmode" value="individual" />

            <param name="input_bams" ftype="bam" value="freebayes-hxb2.bam"/>
            <param name="options_type_selector" value="simple"/>
            <param name="coverage_options_selector" value="set" />
            <param name="skip_coverage" value="100" />
            <output name="output_vcf" file="freebayes-hxb2-test7.vcf" lines_diff="4" />
        </test>
        <test> <!-- Test with CRAM -->
            <param name="reference_source_selector" value="history" />
            <param name="processmode" value="individual" />
            <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/>
            <param name="input_bams" ftype="cram" value="freebayes-phix174.cram"/>
            <param name="options_type_selector" value="simple"/>
            <output name="output_vcf" file="freebayes-phix174-test1.vcf" lines_diff="4" />
        </test>
    </tests>
    <help><![CDATA[
**What it does**