annotate samtools_mpileup.xml @ 5:aa0ef6f0ee89 draft

planemo upload commit 7d9b478cd03f31705266596fe4c168e719c672b6

<tool id="samtools_mpileup" name="MPileup" version="2.0">
    <description>call variants</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command>
    <![CDATA[
    #if $reference_source.reference_source_selector == "history":
       ln -s "${reference_source.ref_file}" && samtools faidx `basename "${reference_source.ref_file}"` && samtools mpileup
    #else:
        samtools mpileup
    #end if
    #if $reference_source.reference_source_selector != "history":
        -f "${reference_source.ref_file.fields.path}"
    #else:
        -f "${reference_source.ref_file}"
    #end if
    #for $i, $input_bam in enumerate( $reference_source.input_bams ):
        "${input_bam.input_bam}"
    #end for
    #if str( $advanced_options.advanced_options_selector ) == "advanced":
        #if str( $advanced_options.filter_by_flags.filter_flags ) == "filter":
            #if $advanced_options.filter_by_flags.require_flags:
                --rf ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.require_flags).split(',')])}
            #end if
            #if $advanced_options.filter_by_flags.exclude_flags:
                --ff ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.exclude_flags).split(',')])}
            #end if
        #end if
        #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste":
            -l "$pasted_regions"
        #elif str( $advanced_options.limit_by_region.limit_by_regions ) == "history"
            -l "$advanced_options.limit_by_region.bed_regions"
        #end if
        #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste":
            -G "$excluded_read_groups"
        #elif str( $advanced_options.exclude_read_group.exclude_read_groups ) == "history"
            -G "$advanced_options.exclude_read_group.read_groups"
        #end if
        ${advanced_options.skip_anomalous_read_pairs}
        ${advanced_options.disable_probabilistic_realignment}
        -C "${advanced_options.coefficient_for_downgrading}"
        -d "${advanced_options.max_reads_per_bam}"
        ${advanced_options.extended_BAQ_computation}
        -q "${advanced_options.minimum_mapping_quality}"
        -Q "${advanced_options.minimum_base_quality}"
        #if str( $advanced_options.region_string ):
            -r "${advanced_options.region_string}"
        #end if
        
    #end if
    #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation':
        ##

        ${genotype_likelihood_computation_type.output_format}
        ${genotype_likelihood_computation_type.compressed}
        
        #if str( $genotype_likelihood_computation_type.output_tags ) != "None":
            -output-tags "${genotype_likelihood_computation_type.output_tags}"
        #end if

        #if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling':
            -o "${genotype_likelihood_computation_type.perform_indel_calling.gap_open_sequencing_error_probability}"
            -e "${genotype_likelihood_computation_type.perform_indel_calling.gap_extension_sequencing_error_probability}"
            -h "${genotype_likelihood_computation_type.perform_indel_calling.coefficient_for_modeling_homopolymer_errors}"
            -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}"
            -m "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_reads_for_indel_candidates}"
            --open-prob "${genotype_likelihood_computation_type.perform_indel_calling.open_seq_error_probability}"
            -F "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_read_fraction}"
            ${genotype_likelihood_computation_type.perform_indel_calling.gapped_read_per_sample}
            #if len( $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ):
                -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ] ) }"
            #end if
        #elif str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'do_not_perform_indel_calling':
            -I
        #end if
        
         
    #else:
        ${genotype_likelihood_computation_type.base_position_on_reads}
        ${genotype_likelihood_computation_type.output_mapping_quality}
    #end if
    --output "$output_mpileup" 2> "$output_log"
    ]]>
    </command>
    <inputs>
        <conditional name="reference_source">
            <param label="Choose the source for the reference genome" name="reference_source_selector" type="select">
                <option value="cached">Use a built-in genome</option>
                <option value="history">Use a genome from the history</option>
            </param>
            <when value="cached">
                <repeat min="1" name="input_bams" title="BAM file">
                    <param format="bam" label="BAM file" name="input_bam" type="data">
                        <validator type="unspecified_build" />
                        <validator message="Sequences are not currently available for the specified build." metadata_column="1" metadata_name="dbkey" table_name="fasta_indexes" type="dataset_metadata_in_data_table" />
                    </param>
                </repeat>
                <param label="Using reference genome" name="ref_file" type="select">
                    <options from_data_table="fasta_indexes" />
                </param>
            </when>
            <when value="history">
                <repeat min="1" name="input_bams" title="BAM file">
                    <param format="bam" label="BAM file" name="input_bam" type="data">
                        <validator check="bam_index" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue." type="metadata" />
                    </param>
                </repeat>
                <param format="fasta" label="Using reference genome" name="ref_file" type="data" />
            </when>
        </conditional>
        <conditional name="genotype_likelihood_computation_type">
            <param label="Genotype Likelihood Computation" name="genotype_likelihood_computation_type_selector" type="select">
                <option selected="True" value="perform_genotype_likelihood_computation">Perform genotype likelihood computation (--VCF, --BCF options)</option>
                <option value="do_not_perform_genotype_likelihood_computation">Do not perform genotype likelihood computation (output pileup)</option>
            </param>
            <when value="perform_genotype_likelihood_computation">
                <param label="Choose the output format" name="output_format" type="select">
                    <option value="--VCF">VCF</option>
                    <option value="--BCF">BCF</option>
                </param>
                <param checked="False" falsevalue="--uncompressed" label="Compress output" name="compressed" truevalue="" type="boolean" help="--incompressed; default=False"/>
                <param name="output_tags" optional="True" type="select" multiple="True" display="checkboxes" label="Optional tags to output" help="--output-tags">
                    <option value="DP">DP (Number of high-quality bases)</option>
                    <option value="DPR">DRP (Number of high-quality bases for each observed allele)</option>
                    <option value="DV">DV (Number of high-quality non-reference bases)</option>
                    <option value="DP4">DP4 (Number of high-quality ref-forward, ref-reverse, alt-forward and alt-reverse bases)</option>
                    <option value="INFO/DPR">INFO/DPR (Number of high-quality bases for each observed allele)</option>
                    <option value="SP">SP (Phred-scaled strand bias P-value)</option>
                </param>
                <conditional name="perform_indel_calling">
                    <param label="Perform INDEL calling" name="perform_indel_calling_selector" type="select">
                        <option selected="True" value="perform_indel_calling_def">Perform INDEL calling using default options</option>
                        <option value="perform_indel_calling">Perform INDEL calling and set advanced options</option>
                        <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option>
                    </param>
                    <when value="perform_indel_calling_def" />
                    <when value="perform_indel_calling">
                        <param label="Phred-scaled gap open sequencing error probability" name="gap_open_sequencing_error_probability" type="integer" value="40" help="--open-prob; Reducing this value leads to more indel calls; default=40"/>
                        <param label="Phred-scaled gap extension sequencing error probability" name="gap_extension_sequencing_error_probability" type="integer" value="20" help="--ext-prob;  Reducing this value leads to longer indels. default=20"/>
                        <param label="Coefficient for modeling homopolymer errors." name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" help="--tandem-qual; default=100"/>
                        <param label="Skip INDEL calling if the average per-sample depth is above" name="skip_indel_calling_above_sample_depth" type="integer" value="250" help="--max-idepth; default=250"/>
                        <param label="Minimum gapped reads for indel candidates" name="minimum_gapped_reads_for_indel_candidates" type="integer" value="1" help="--min-ireads; default=1"/>
                        <param label="Phred-scaled gap open sequencing error probability" name="open_seq_error_probability" type="integer" value="40" help="--open-prob; Reducing this value leads to more indel calls; default=40"/>
                        <param label="Minimum fraction of gapped reads" name="minimum_gapped_read_fraction" type="float" value="0.002" help="--gap-frac; default=0.002"/>
                        <param checked="False" falsevalue="" label="Apply --min-ireads and --gap-frac values on a per-sample basis" name="gapped_read_per_sample" truevalue="-p" type="boolean" help="--per-sample-mF;  by default both options are applied to reads pooled from all samples"/>
                        <repeat name="platform_list_repeat" title="Platform for INDEL candidates">
                            <param label="Platform to use for INDEL candidates" name="platform_entry" type="text" value="" help="It is recommended to collect indel candidates from sequencing technologies that have low indel error rate such as ILLUMINA"/>
                        </repeat>
                    </when>
                    <when value="do_not_perform_indel_calling" />
                </conditional>
                
            </when>
            <when value="do_not_perform_genotype_likelihood_computation">
                <param checked="False" falsevalue="" label="Output base positions on reads" name="base_position_on_reads" truevalue="-O" type="boolean" help="--output-BP"/>
                <param checked="False" falsevalue="" label="Output mapping quality" name="output_mapping_quality" truevalue="-s" type="boolean" help="--output-MQ"/>
            </when>
        </conditional>
        <conditional name="advanced_options">
            <param label="Set advanced options" name="advanced_options_selector" type="select">
                <option selected="True" value="basic">Basic</option>
                <option value="advanced">Advanced</option>
            </param>
            <when value="advanced">
                <conditional name="filter_by_flags">
                    <param label="Set filter by flags" name="filter_flags" type="select">
                        <option selected="True" value="nofilter">Do not filter</option>
                        <option value="filter">Filter by flags to exclude or require</option>
                    </param>
                    <when value="filter">
                        <param display="checkboxes" label="Require" multiple="True" name="require_flags" type="select" help="--incl-flags">
                            <option value="1">Read is paired</option>
                            <option value="2">Read is mapped in a proper pair</option>
                            <option value="4">The read is unmapped</option>
                            <option value="8">The mate is unmapped</option>
                            <option value="16">Read strand</option>
                            <option value="32">Mate strand</option>
                            <option value="64">Read is the first in a pair</option>
                            <option value="128">Read is the second in a pair</option>
                            <option value="256">The alignment or this read is not primary</option>
                            <option value="512">The read fails platform/vendor quality checks</option>
                            <option value="1024">The read is a PCR or optical duplicate</option>
                        </param>
                        <param display="checkboxes" label="Exclude" multiple="True" name="exclude_flags" type="select" help="--excl-flags">
                            <option value="1">Read is paired</option>
                            <option value="2">Read is mapped in a proper pair</option>
                            <option value="4">The read is unmapped</option>
                            <option value="8">The mate is unmapped</option>
                            <option value="16">Read strand</option>
                            <option value="32">Mate strand</option>
                            <option value="64">Read is the first in a pair</option>
                            <option value="128">Read is the second in a pair</option>
                            <option value="256">The alignment or this read is not primary</option>
                            <option value="512">The read fails platform/vendor quality checks</option>
                            <option value="1024">The read is a PCR or optical duplicate</option>
                        </param>
                    </when>
                    <when value="nofilter" />
                </conditional>
                <conditional name="limit_by_region">
                    <param label="Select regions to call" name="limit_by_regions" type="select">
                        <option selected="True" value="no_limit">Do not limit</option>
                        <option value="history">From an uploaded BED file (--positions)</option>
                        <option value="paste">Paste a list of regions or BED (--region)</option>
                    </param>
                    <when value="history">
                        <param format="bed" label="BED file" name="bed_regions" type="data" help="--positions">
                            <validator type="dataset_ok_validator" />
                        </param>
                    </when>
                    <when value="paste">
                        <param area="true" help="Paste a list of regions in BED format or as a list of chromosomes and positions" label="Regions" name="region_paste" size="10x35" type="text"/>
                    </when>
                    <when value="no_limit" />
                </conditional>
                <conditional name="exclude_read_group">
                    <param label="Select read groups to exclude" name="exclude_read_groups" type="select" help="--exclude-RG">
                        <option selected="True" value="no_limit">Do not exclude</option>
                        <option value="history">From an uploaded text file</option>
                        <option value="paste">Paste a list of read groups</option>
                    </param>
                    <when value="history">
                        <param format="txt" label="Text file" name="read_groups" type="data">
                            <validator type="dataset_ok_validator" />
                        </param>
                    </when>
                    <when value="paste">
                        <param area="true" help="Paste a list of read groups" label="Read groups" name="group_paste" size="10x35" type="text" />
                    </when>
                    <when value="no_limit" />
                </conditional>
                <param checked="False" falsevalue="" label="Disable read-pair overlap detection" name="ignore_overlaps" truevalue="-x" type="boolean" help="--ignore-overlaps"/>
                <param checked="False" falsevalue="" label="Do not skip anomalous read pairs in variant calling" name="skip_anomalous_read_pairs" truevalue="-A" type="boolean" help="--count-orphans"/>
                <param checked="False" falsevalue="" label="Disable probabilistic realignment for the computation of base alignment quality (BAQ)" name="disable_probabilistic_realignment" truevalue="-B" type="boolean" help="--no-BAQ; BAQ is the Phred-scaled probability of a read base being misaligned. Applying this option greatly helps to reduce false SNPs caused by misalignments"/>
                <param label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" name="coefficient_for_downgrading" type="integer" value="0" help="--adjust-MQ; Given a read with a phred-scaled probability q of being generated from the mapped position, the new mapping quality is about sqrt((INT-q)/INT)*INT. A zero value disables this functionality; if enabled, the recommended value for BWA is 50. default=0"/>
                <param label="Max reads per BAM" max="1024" min="1" name="max_reads_per_bam" type="integer" value="250" help="--max-depth; default=250"/>
                <param checked="False" falsevalue="" label="Redo BAQ computation" name="extended_BAQ_computation" truevalue="-E" type="boolean" help="--redo-BAQ; ignore existing BQ tags"/>
                <param label="Minimum mapping quality for an alignment to be used" name="minimum_mapping_quality" type="integer" value="0" help="-min-MQ; default=0"/>
                <param label="Minimum base quality for a base to be considered" name="minimum_base_quality" type="integer" value="13" help="--min-BQ; default=13"/>
                <param label="Only generate pileup in region" name="region_string" type="text" value="" help="--region; If used in conjunction with --positions, then considers the intersection of the two requests. Defaults to all sites" />
            </when>
            <when value="basic" />
        </conditional>
    </inputs>
    <outputs>
        <data format="pileup" label="${tool.name} on ${on_string}" name="output_mpileup">
            <change_format>
                <when format="bcf" input="genotype_likelihood_computation_type.output_format" value="--BCF" />
                <when format="vcf" input="genotype_likelihood_computation_type.output_format" value="--VCF" />
            </change_format>
        </data>
        <data format="txt" label="${tool.name} on ${on_string} (log)" name="output_log" />
    </outputs>
    <tests>
        <test>
            <param name="reference_source_selector" value="history" />
            <param ftype="fasta" name="ref_file" value="phiX.fasta" />
            <param ftype="bam" name="input_bam" value="samtools_mpileup_in_1.bam" />
            <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" />
            <param name="advanced_options_selector" value="basic" />
            <param name="base_position_on_reads" value="true" />
            <param name="output_mapping_quality" value="true" />
            <output file="samtools_mpileup_out_1.pileup" name="output_mpileup" />
            <output file="samtools_mpileup_out_1.log" name="output_log" />
        </test>
        <test>
            <param name="reference_source_selector" value="history" />
            <param ftype="fasta" name="ref_file" value="phiX.fasta" />
            <param ftype="bam" name="input_bam" value="phiX.bam" />
            <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" />
            <param name="gap_extension_sequencing_error_probability" value="20" />
            <param name="coefficient_for_modeling_homopolymer_errors" value="100" />
            <param name="perform_indel_calling_selector" value="perform_indel_calling" />
            <param name="skip_indel_calling_above_sample_depth" value="250" />
            <param name="gap_open_sequencing_error_probability" value="40" />
            <param name="platform_list_repeat" value="0" />
            <param name="advanced_options_selector" value="basic" />
            <param name="genotype_likelihood_computation_type|output_format" value="VCF" />
            <output file="samtools_mpileup_out_2.vcf" ftype="vcf" lines_diff="8" name="output_mpileup" />
            <output file="samtools_mpileup_out_2.log" name="output_log" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

Report variants for one or multiple BAM files. Alignment records are grouped by sample identifiers in @RG header lines. If sample identifiers are absent, each input file is regarded as one sample. 

------

**Input options**::

  -6, --illumina1.3+      quality is in the Illumina-1.3+ encoding
  -A, --count-orphans     do not discard anomalous read pairs
  -b, --bam-list FILE     list of input BAM filenames, one per line
  -B, --no-BAQ            disable BAQ (per-Base Alignment Quality)
  -C, --adjust-MQ INT     adjust mapping quality; recommended:50, disable:0 [0]
  -d, --max-depth INT     max per-BAM depth; avoids excessive memory usage [250]
  -E, --redo-BAQ          recalculate BAQ on the fly, ignore existing BQs
  -f, --fasta-ref FILE    faidx indexed reference sequence file
  -G, --exclude-RG FILE   exclude read groups listed in FILE
  -l, --positions FILE    skip unlisted positions (chr pos) or regions (BED)
  -q, --min-MQ INT        skip alignments with mapQ smaller than INT [0]
  -Q, --min-BQ INT        skip bases with baseQ/BAQ smaller than INT [13]
  -r, --region REG        region in which pileup is generated
  -R, --ignore-RG         ignore RG tags (one BAM = one sample)
  --rf, --incl-flags STR|INT  required flags: skip reads with mask bits unset []
  --ff, --excl-flags STR|INT  filter flags: skip reads with mask bits set
                                            [UNMAP,SECONDARY,QCFAIL,DUP]
  -x, --ignore-overlaps   disable read-pair overlap detection

**Output options**::

  -o, --output FILE       write output to FILE [standard output]
  -g, --BCF               generate genotype likelihoods in BCF format
  -v, --VCF               generate genotype likelihoods in VCF format

**Output options for mpileup format** (without -g/-v)::

  -O, --output-BP         output base positions on reads
  -s, --output-MQ         output mapping quality

**Output options for genotype likelihoods** (when -g/-v is used)::

  -t, --output-tags LIST  optional tags to output: DP,DPR,DV,DP4,INFO/DPR,SP []
  -u, --uncompressed      generate uncompressed VCF/BCF output

**SNP/INDEL genotype likelihoods options** (effective with -g/-v)::

  -e, --ext-prob INT      Phred-scaled gap extension seq error probability [20]
  -F, --gap-frac FLOAT    minimum fraction of gapped reads [0.002]
  -h, --tandem-qual INT   coefficient for homopolymer errors [100]
  -I, --skip-indels       do not perform indel calling
  -L, --max-idepth INT    maximum per-sample depth for INDEL calling [250]
  -m, --min-ireads INT    minimum number gapped reads for indel candidates [1]
  -o, --open-prob INT     Phred-scaled gap open seq error probability [40]
  -p, --per-sample-mF     apply -m and -F per-sample for increased sensitivity
  -P, --platforms STR     comma separated list of platforms for indels [all]

**Notes**: Assuming diploid individuals.
]]>
    </help>
    <configfiles>
        <configfile name="excluded_read_groups">
<![CDATA[
#set pasted_data = ''
#if str( $advanced_options.advanced_options_selector ) == "advanced":
    #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste":
        #set pasted_data = '\t'.join( str( $advanced_options.exclude_read_group['read_groups'] ).split() )
    #end if
#end if
${pasted_data}
]]>
        </configfile>
        <configfile name="pasted_regions">
<![CDATA[
#set pasted_data = ''
#if str( $advanced_options.advanced_options_selector ) == "advanced":
    #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste":
        #set pasted_data = '\t'.join( str( $advanced_options.limit_by_region['region_paste'] ).split() )
    #end if
#end if
${pasted_data}
]]>
        </configfile>
    </configfiles>
    <expand macro="citations" />
</tool>