view samtools_stats.xml @ 6:47035d167365 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_stats commit 558d30ff047fe2f62658e8b57e27ebe8db77ede1"
author iuc
date Fri, 06 Sep 2019 11:23:05 -0400
parents 5a08c09b9311
children 145f6d74ff5e
line wrap: on
line source

<tool id="samtools_stats" name="Samtools stats" version="2.0.2+galaxy2">
    <description>generate statistics for BAM dataset</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    <expand macro="version_command"/>
    <command><![CDATA[
        @ADDTHREADS@
        @PREPARE_IDX@
        @PREPARE_FASTA_IDX@
        samtools stats
            #if $coverage_cond.coverage_select == 'yes':
                --coverage ${coverage_cond.coverage_min},${coverage_cond.coverage_max},${coverage_cond.coverage_step}
            #end if
            ${remove_dups}
            #if str( $filter_by_flags.filter_flags ) == "filter":
                #if $filter_by_flags.require_flags:
                    #set $filter = $filter_by_flags.require_flags
                    @FLAGS@
                    --required-flag $flags
                #end if
                #if $filter_by_flags.exclude_flags:
                    #set $filter = $filter_by_flags.exclude_flags
                    @FLAGS@
                    --filtering-flag $flags
                #end if
            #end if
            #if str($gc_depth):
                --GC-depth ${gc_depth}
            #end if
            #if str($insert_size):
                --insert-size ${insert_size}
            #end if
            ## The code below is commented out because using -I/--id options causes 
            ## in samtools up to 1.9 the following exception
            ## Samtools-htslib: init_group_id() header parsing not yet implemented
            ##if str($read_group) != "":
            ##    -I "${read_group}"
            ##end if
            #if str($read_length):
                --read-length ${read_length}
            #end if
            #if str($most_inserts):
                --most-inserts ${most_inserts}
            #end if
            #if str($trim_quality):
                --trim-quality ${trim_quality}
            #end if

            #if $reffa != None:
                --ref-seq '$reffa'
            #end if
            ## TODO currently not implemented in Galaxy
            ## generates STR_VALUE.bamstat where STR is given by -P and VALUE is a value of the TAG given by -S
            ## needs some discover data sets action...
            ## -P, --split-prefix STR
            ## -S, --split TAG
            $sparse
            @REGIONS_FILE@
            $remove_overlaps
            #if str($cov_threshold):
                -g $cov_threshold
            #end if
            -@ \$addthreads 
            infile
            @REGIONS_MANUAL@
            > '$output'

            #if $split_output_cond.split_output_selector == "yes":
                #set outputs_to_split = str($split_output_cond.generate_tables).split(',')
                && mkdir split
                #for s in str($split_output_cond.generate_tables).split(','):
                    && name=`cat '$output' | grep '\^$s' | cut -d'.' -f 1 | sed 's/^# //'`
                    && awk '/\^/{out=0} /\^$s/{out=1} {if(out==1){print $0}}' '$output' | sed 's/Use `grep .*` to extract this part.//' | sed 's/$s\t//' > "split/\$name.tab"
                #end for
            #end if
    ]]></command>
    <inputs>
        <param name="input" type="data" format="sam,bam,cram" label="BAM file" />
        <conditional name="coverage_cond">
            <param name="coverage_select" type="select" label="Set coverage distribution">
                <option value="no" selected="True">No</option>
                <option value="yes">Yes</option>
            </param>
            <when value="no"/>
            <when value="yes">
                <param name="coverage_min" type="integer" value="1" label="Minimum coverage" help="Minimum coverage" />
                <param name="coverage_max" type="integer" value="1000" label="Maximum coverage" help="Maximum coverage" />
                <param name="coverage_step" type="integer" value="1" label="Coverage step" help="Step value for coverage" />
            </when>
        </conditional>
        <param name="remove_dups" argument="--remove-dups" type="boolean" truevalue="--remove-dups" falsevalue="" checked="False" label="Exclude reads marked as duplicates" />
        <conditional name="split_output_cond">
            <param name="split_output_selector" type="select" label="Output" help="Select between one single output or separate outputs for each statistics">
                <option value="no" selected="True">One single summary file</option>
                <option value="yes">Separate datasets for each statistic</option>
            </param>
            <when value="no" />
            <when value="yes">
                <param name="generate_tables" type="select" display="checkboxes" multiple="True" label="Desired output files">
                    <option value="SN">Summary numbers</option>
                    <option value="FFQ">First Fragment Qualities</option>
                    <option value="LFQ">Last Fragment Qualities</option>
                    <option value="MPC">Mismatches per cycle</option>
                    <option value="GCF">GC Content of first fragments</option>
                    <option value="GCL">GC Content of last fragments</option>
                    <option value="GCC">ACGT content per cycle</option>
                    <option value="FBC">ACGT content per cycle for first fragments</option>
                    <option value="LBC">ACGT content per cycle for last fragments</option>
                    <option value="IS">Insert sizes</option>
                    <option value="RL">Read lengths</option>
                    <option value="FRL">Read lengths for first fragments</option>
                    <option value="LRL">Read lengths for last fragments</option>
                    <option value="ID">Indel distribution</option>
                    <option value="IC">Indels per cycle</option>
                    <option value="COV">Coverage distribution</option>
                    <option value="GCD">GC depth</option>
                </param>
            </when>
        </conditional>
        <conditional name="filter_by_flags">
            <param name="filter_flags" type="select" label="Filter by SAM flags" help="More info on the flags: https://samtools.github.io/hts-specs/SAMv1.pdf">
                <option value="nofilter" selected="True">Do not filter</option>
                <option value="filter">Filter by flags to exclude or require</option>
            </param>
            <when value="filter">
                <param name="require_flags" argument="-f" type="select" display="checkboxes" multiple="True" label="Require">
                    <expand macro="flag_options" />
                </param>
                <param name="exclude_flags" argument="-F" type="select" display="checkboxes" multiple="True" label="Exclude">
                    <expand macro="flag_options" />
                </param>
            </when>
            <when value="nofilter" />

        </conditional>
        <!-- TODO I would like to set the default values of float and int parameters as on the samtools stats help page, but then the tests don't work. Hence I leave the optional and give the defaults in the help -->
        <param name="gc_depth" argument="--GC-depth" type="float" optional="True" label="Size of GC-depth bins" help="Decreasing bin size increases memory requirement. default=2e4" />
        <param name="insert_size" argument="--insert-size" type="integer" optional="True" label="Maximum insert size" help="default=8000" />
        <!--
            The -I option of samtools stats returns the following message up to version 1.9:
            Samtools-htslib: init_group_id() header parsing not yet implemented
            Because of this the section below is commented out until this stats bug is fixed
            <param name="read_group" type="select" optional="true" label="Limit to a specific read group name" >
                <options>
                    <filter type="data_meta" ref="input" key="read_groups" />
                </options>
            </param>
        -->
        <param name="read_length" argument="--read-length" type="integer" optional="true" label="Minimum read length to generate statistics for" help="No cutoff if left empty" />
        <param name="most_inserts" argument="--most-inserts" type="float" optional="true" label="Report only the main part of inserts" help="default=0.99" />
        <param name="trim_quality" argument="--trim-quality" type="integer" optional="true" label="BWA trim parameter" help="default=0" />

        <conditional name="addref_cond">
            <param name="addref_select" type="select" label="Use a reference sequence" help="Required for GC-depth and mismatches-per-cycle calculation">
                <option value="no">No</option>
                <option value="cached">Locally cached</option>
                <option value="history">History</option>
            </param>
            <when value="no"/>
            <when value="cached">
                <param name="ref" type="select" label="Using genome">
                    <options from_data_table="fasta_indexes">
                        <filter type="data_meta" ref="input" key="dbkey" column="1" />
                    </options>
                </param>
            </when>
            <when value="history">
                <param name="ref" type="data" format="fasta" label="Using file" />
            </when>
        </conditional>
        <!-- unfortunately -t takes tabular and not bed like view (otherwise a macro might have simplified this) -->
        
        <expand macro="regions_macro"/>

        <param name="sparse" argument="-x/--sparse" type="boolean" truevalue="-x" falsevalue="" checked="False" label="Suppress absence of insertions" help="Suppress outputting IS rows where there are no insertions."/>
        <param name="remove_overlaps" argument="-p/--remove-overlaps" type="boolean" truevalue="-p" falsevalue="" checked="False" label="Remove overlaps of paired-end reads from coverage and base count computations" />
        <param name="cov_threshold" argument="-g/--cov-threshold"  optional="true" type="integer" label="Only bases with coverage above this value will be included in the target percentage computation" />
    </inputs>

    <outputs>
        <data name="output" format="tabular" label="${tool.name} on ${on_string}">
            <discover_datasets directory="split" pattern="(?P&lt;designation&gt;.+)\.tab" format="tabular" visible="true" assign_primary_output="true"/>
            <filter>split_output_cond['split_output_selector'] == 'no'</filter>
        </data>
        <collection name="output_collection" type="list" label="${tool.name} on ${on_string}">
            <discover_datasets directory="split" pattern="(?P&lt;designation&gt;.+)\.tab" format="tabular" visible="false"/>
            <filter>split_output_cond['split_output_selector'] == 'yes'</filter>
        </collection>
    </outputs>
    <tests>
        <!-- https://github.com/samtools/samtools/blob/9ce8c64493f7ea3fa69bc5c1ac980b1a8e3dcf1f/test/test.pl#L2402 -->
        <test>
            <param name="input" value="1_map_cigar.sam" ftype="sam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" ftype="fasta" />
            </conditional>
            <output name="output" file="1.stats.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/1.stats.expected',cmd=>"$$opts{bin}/samtools stats -r $$opts{path}/stat/test.fa $$opts{path}/stat/1_map_cigar.sam | tail -n+4", exp_fix=>$efix);-->
        <test>
            <param name="input" value="2_equal_cigar_full_seq.sam" ftype="sam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" ftype="fasta" />
            </conditional>
            <output name="output" file="2.stats.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/2.stats.expected',cmd=>"$$opts{bin}/samtools stats -r $$opts{path}/stat/test.fa $$opts{path}/stat/2_equal_cigar_full_seq.sam | tail -n+4", exp_fix=>$efix);-->
        <!-- test_cmd($opts,out=>'stat/3.stats.expected',cmd=>"$$opts{bin}/samtools stats -r $$opts{path}/stat/test.fa $$opts{path}/stat/3_map_cigar_equal_seq.sam | tail -n+4", exp_fix=>$efix);-->
        <!-- test_cmd($opts,out=>'stat/4.stats.expected',cmd=>"$$opts{bin}/samtools stats -r $$opts{path}/stat/test.fa $$opts{path}/stat/4_X_cigar_full_seq.sam | tail -n+4", exp_fix=>$efix);-->
        <!-- test_cmd($opts,out=>'stat/5.stats.expected',cmd=>"$$opts{bin}/samtools stats -r $$opts{path}/stat/test.fa $$opts{path}/stat/5_insert_cigar.sam | tail -n+4", exp_fix=>$efix); -->
        <test>
            <param name="input" value="5_insert_cigar.sam" ftype="sam" />
            <param name="insert_size" value="0" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" ftype="fasta" />
            </conditional>
            <output name="output" file="6.stats.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/6.stats.expected',cmd=>"$$opts{bin}/samtools stats -r $$opts{path}/stat/test.fa -i 0 $$opts{path}/stat/5_insert_cigar.sam | tail -n+4", exp_fix=>$efix); -->
        <!-- test_cmd($opts,out=>'stat/7.stats.expected',cmd=>"$$opts{bin}/samtools stats -r $$opts{path}/stat/test.fa $$opts{path}/stat/7_supp.sam | tail -n+4", exp_fix=>$efix); -->
        <!-- test_cmd($opts,out=>'stat/8.stats.expected',cmd=>"$$opts{bin}/samtools stats -r $$opts{path}/stat/test.fa $$opts{path}/stat/8_secondary.sam | tail -n+4", exp_fix=>$efix);-->
        <!-- test_cmd($opts,out=>'stat/9.stats.expected',cmd=>"$$opts{bin}/samtools stats -S RG -r $$opts{path}/stat/test.fa $$opts{path}/stat/1_map_cigar.sam | tail -n+4", exp_fix=>$efix,out_map=>{"stat/1_map_cigar.sam_s1_a_1.bamstat"=>"stat/1_map_cigar.sam_s1_a_1.expected.bamstat"},hskip=>3);-->
        <!-- test_cmd($opts,out=>'stat/10.stats.expected',cmd=>"$$opts{bin}/samtools stats -S RG -r $$opts{path}/stat/test.fa $$opts{path}/stat/10_map_cigar.sam | tail -n+4", exp_fix=>$efix,out_map=>{"stat/10_map_cigar.sam_s1_a_1.bamstat"=>"stat/10_map_cigar.sam_s1_a_1.expected.bamstat", "stat/10_map_cigar.sam_s1_b_1.bamstat"=>"stat/10_map_cigar.sam_s1_b_1.expected.bamstat"},hskip=>3);-->
        <test>
            <param name="input" value="11_target.sam" ftype="sam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="no" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="tab"/>
                <param name="targetregions" value="11.stats.targets" ftype="tabular" />
            </conditional>
            <output name="output" file="11.stats.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/11.stats.expected',cmd=>"$$opts{bin}/samtools stats -t $$opts{path}/stat/11.stats.targets $$opts{path}/stat/11_target.sam | tail -n+4", exp_fix=>$efix); -->

        <test>
            <param name="input" value="11_target.bam" ftype="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="no" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="text"/>
                <param name="regions_repeat_0|region" value="ref1:10-24"/>
                <param name="regions_repeat_1|region" value="ref1:30-46"/>
                <param name="regions_repeat_2|region" value="ref1:39-56"/>
            </conditional>
            <output name="output" file="11.stats.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/11.stats.expected',cmd=>"$$opts{bin}/samtools stats $$opts{path}/stat/11_target.bam ref1:10-24 ref1:30-46 ref1:39-56 | tail -n+4", exp_fix=>$efix);
-->
        <test>
            <param name="input" value="11_target.sam" ftype="sam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="no" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="tab"/>
                <param name="targetregions" value="11.stats.targets" ftype="tabular" />
            </conditional>
            <param name="cov_threshold" value="4" />
            <output name="output" file="11.stats.g4.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/11.stats.g4.expected',cmd=>"$$opts{bin}/samtools stats -g 4 -t $$opts{path}/stat/11.stats.targets $$opts{path}/stat/11_target.sam | tail -n+4", exp_fix=>$efix);-->
        <test>
            <param name="input" value="11_target.bam" ftype="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="no" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="text"/>
                <param name="regions_repeat_0|region" value="ref1:10-24"/>
                <param name="regions_repeat_1|region" value="ref1:30-46"/>
                <param name="regions_repeat_2|region" value="ref1:39-56"/>
            </conditional>
            <param name="cov_threshold" value="4" />
            <output name="output" file="11.stats.g4.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/11.stats.g4.expected',cmd=>"$$opts{bin}/samtools stats -g 4 $$opts{path}/stat/11_target.bam ref1:10-24 ref1:30-46 ref1:39-56 | tail -n+4", exp_fix=>$efix); -->
        <test>
            <param name="input" value="12_overlaps.bam" ftype="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="no" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="tab"/>
                <param name="targetregions" value="12_3reads.bed" ftype="tabular" />
            </conditional>
            <output name="output" file="12.3reads.overlap.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/12.3reads.overlap.expected',cmd=>"$$opts{bin}/samtools stats $$opts{path}/stat/12_overlaps.bam -t $$opts{path}/stat/12_3reads.bed | tail -n+4", exp_fix=>$efix);-->
        <test>
            <param name="input" value="12_overlaps.bam" ftype="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="no" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="tab"/>
                <param name="targetregions" value="12_3reads.bed" ftype="tabular" />
            </conditional>
            <param name="remove_overlaps" value="-p"/>
            <output name="output" file="12.3reads.nooverlap.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/12.3reads.nooverlap.expected',cmd=>"$$opts{bin}/samtools stats $$opts{path}/stat/12_overlaps.bam -p -t $$opts{path}/stat/12_3reads.bed | tail -n+4", exp_fix=>$efix);-->
        <test>
            <param name="input" value="12_overlaps.bam" ftype="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="no" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="tab"/>
                <param name="targetregions" value="12_2reads.bed" ftype="tabular" />
            </conditional>
            <output name="output" file="12.2reads.overlap.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/12.2reads.overlap.expected',cmd=>"$$opts{bin}/samtools stats $$opts{path}/stat/12_overlaps.bam -t $$opts{path}/stat/12_2reads.bed | tail -n+4", exp_fix=>$efix);-->
        <test>
            <param name="input" value="12_overlaps.bam" ftype="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="no" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="tab"/>
                <param name="targetregions" value="12_2reads.bed" ftype="tabular" />
            </conditional>
            <param name="remove_overlaps" value="-p"/>
            <output name="output" file="12.2reads.nooverlap.expected" ftype="tabular" lines_diff="3" />
        </test>
        <!-- test_cmd($opts,out=>'stat/12.2reads.nooverlap.expected',cmd=>"$$opts{bin}/samtools stats $$opts{path}/stat/12_overlaps.bam -p -t $$opts{path}/stat/12_2reads.bed | tail -n+4", exp_fix=>$efix);-->
        <test>
            <param name="input" value="samtools_stats_input.bam" ftype="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="samtools_stats_ref.fa" ftype="fasta" />
            </conditional>
            <output name="output" file="samtools_stats_out1.tab" ftype="tabular" lines_diff="2" />
        </test>
        <test>
            <param name="input" value="samtools_stats_input.bam" ftype="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="samtools_stats_ref.fa" ftype="fasta" />
            </conditional>
            <conditional name="split_output_cond">
                <param name="split_output_selector" value="yes" />
                <param name="generate_tables" value="SN,MPC,GCC" />
            </conditional>
            <output_collection name="output_collection" type="list">
                <element name="ACGT content per cycle" ftype="tabular" file="samtools_stats_out1__gcc.tab"/>
                <element name="Mismatches per cycle and quality" ftype="tabular" file="samtools_stats_out1__mpc.tab" />
                <element name="Summary Numbers" ftype="tabular" file="samtools_stats_out1__sn.tab" />
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

This tool runs the ``samtools stats`` command.

The results of samtools stats can be visualized with MultiQC (for this the default of a single output file needs to be selected).
    ]]></help>
    <expand macro="citations"/>
</tool>