annotate samtools_stats.xml @ 2:24c5d43cb545 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_stats commit 411130b45dc30f7f24f41cdeec5e148c5d8faf40

<tool id="samtools_stats" name="Stats" version="2.0.1">
    <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[
        #if $use_reference.use_ref_selector == "yes":
            #if $use_reference.reference_source.reference_source_selector == "history":
               ln -s '${use_reference.reference_source.ref_file}' &&
               samtools faidx `basename '${use_reference.reference_source.ref_file}'` &&
            #end if
        #end if

        samtools stats
            '${input_file}'
            --coverage ${coverage_min},${coverage_max},${coverage_step}
            ${remove_dups}

            #if str( $filter_by_flags.filter_flags ) == "filter":
                #if $filter_by_flags.require_flags:
                    --required-flag ${sum([int(flag) for flag in str($filter_by_flags.require_flags).split(',')])}
                #end if
                #if $filter_by_flags.exclude_flags:
                    --filtering-flag ${sum([int(flag) for flag in str($filter_by_flags.exclude_flags).split(',')])}
                #end if
            #end if

            --GC-depth ${gc_depth}
            --insert-size ${insert_size}

            ## The code below is commented out because using -I/--id options causes 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

            --most-inserts ${most_inserts}
            --trim-quality ${trim_quality}

            #if $use_reference.use_ref_selector == "yes":
                #if $use_reference.reference_source.reference_source_selector != "history":
                    --ref-seq '${use_reference.reference_source.ref_file.fields.path}'
                #else:
                    --ref-seq '${use_reference.reference_source.ref_file}'
                #end if
            #end if
            > '${output}'

        #if $split_output.split_output_selector == "yes":
            #set outputs_to_split = str($split_output.generate_tables).split(',')
            && mkdir split &&
            echo ${split_output.generate_tables}

            #if 'sn' in $outputs_to_split:
                && echo "# Summary Numbers" > 'split/Summary numbers.tab' &&
                echo "" >> 'split/Summary numbers.tab' &&
                if grep -q ^SN '${output}'; then
                    grep ^SN '${output}' | cut -f 2- >> 'split/Summary numbers.tab';
                fi
            #end if

            #if 'ffq' in $outputs_to_split:
                && echo "# Columns correspond to qualities and rows to cycles. First column is the cycle number\n" > 'split/First Fragment Qualities.tab' &&
                if grep -q ^FFQ '${output}'; then
                    grep ^FFQ '${output}' | cut -f 2- >> 'split/First Fragment Qualities.tab';
                fi
            #end if

            #if 'lfq' in $outputs_to_split:
                && echo "# Columns correspond to qualities and rows to cycles. First column is the cycle number" > 'split/Last Fragment Qualities.tab' &&
                if grep -q ^LFQ '${output}'; then
                    grep ^LFQ '${output}' | cut -f 2- >> 'split/Last Fragment Qualities.tab';
                fi
            #end if

            #if 'mpc' in $outputs_to_split:
                && echo "# Columns correspond to qualities, rows to cycles. First column is the cycle number, second is the number of N's and the rest is the number of mismatches" > 'split/Mismatches per cycle.tab' &&
                if grep -q ^MPC '${output}'; then
                    grep ^MPC '${output}' | cut -f 2- >> 'split/Mismatches per cycle.tab';
                fi
            #end if

            #if 'gcf' in $outputs_to_split:
                && echo "# GC Content of first fragments" > 'split/GC Content of first fragments.tab' &&
                if grep -q ^GCF '${output}'; then
                    grep ^GCF '${output}' | cut -f 2- >> 'split/GC Content of first fragments.tab';
                fi
            #end if

            #if 'gcl' in $outputs_to_split:
                && echo "# GC Content of last fragments" > 'split/GC Content of last fragments.tab' &&
                if grep -q ^GCL '${output}'; then
                    grep ^GCL '${output}' | cut -f 2- >> 'split/GC Content of last fragments.tab';
                fi
            #end if

            #if 'gcc' in $outputs_to_split:
                && echo "# ACGT content per cycle. The columns are: cycle, and A,C,G,T counts (percent)" > 'split/ACGT content per cycle.tab' &&
                if grep -q ^GCC '${output}'; then
                    grep ^GCC '${output}' | cut -f 2- >> 'split/ACGT content per cycle.tab';
                fi
            #end if

            #if 'is' in $outputs_to_split:
                && echo "# Insert sizes. The columns are: insert size, pairs total, inward oriented pairs, outward oriented pairs, other pairs" > 'split/Insert sizes.tab' &&
                if grep -q ^IS '${output}'; then
                    grep ^IS '${output}' | cut -f 2- >> 'split/Insert sizes.tab';
                fi
            #end if

            #if 'rl' in $outputs_to_split:
                && echo "# Read lengths. The columns are: read length, count" > 'split/Read lengths.tab' &&
                if grep -q ^RL '${output}'; then
                    grep ^RL '${output}' | cut -f 2- >> 'split/Read lengths.tab';
                fi
            #end if

            #if 'id' in $outputs_to_split:
                && echo "# Indel distribution. The columns are: length, number of insertions, number of deletions" > 'split/Indel distribution.tab' &&
                if grep -q ^ID '${output}'; then
                    grep ^ID '${output}' | cut -f 2- >> 'split/Indel distribution.tab';
                fi
            #end if

            #if 'ic' in $outputs_to_split:
                && echo "# Indels per cycle. The columns are: cycle, number of insertions (fwd), .. (rev) , number of deletions (fwd), .. (rev)" > 'split/Indels per cycle.tab' &&
                if grep -q ^IC '${output}'; then
                    grep ^IC '${output}' | cut -f 2- >> 'split/Indels per cycle.tab';
                fi
            #end if

            #if 'cov' in $outputs_to_split:
                && echo "# Coverage distribution" > 'split/Coverage distribution.tab' &&
                if grep -q ^COV '${output}'; then
                    grep ^COV '${output}' | cut -f 2- >> 'split/Coverage distribution.tab';
                fi
            #end if

            #if 'gcd' in $outputs_to_split:
                && echo "# GC-depth. The columns are: GC%, unique sequence percentiles, 10th, 25th, 50th, 75th and 90th depth percentile" > 'split/GC depth.tab' &&
                if grep -q ^GCD '${output}'; then
                    grep ^GCD '${output}' | cut -f 2- >> 'split/GC depth.tab';
                fi
            #end if
        #end if
        ]]></command>
    <inputs>
        <param name="input_file" type="data" format="sam,bam" label="BAM file" />
        <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" />
        <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">
            <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="is">Insert sizes</option>
                    <option value="rl">Read lengths</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">
                    <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 name="exclude_flags" argument="-F" type="select" display="checkboxes" multiple="True" label="Exclude">
                    <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>
        <param name="gc_depth" argument="--GC-depth" type="float" value="20000" label="Size of GC-depth bins" help="Decreasing bin size increases memory requirement" />
        <param name="insert_size" argument="--insert-size" type="integer" value="8000" label="Maximum insert size" />
        <!--

            The -I option of samtools stats returns the following message in version 1.2:

            Samtools-htslib: init_group_id() header parsing not yet implemented
            Abort trap: 6

            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_file" key="read_groups" />
                </options>
            </param>

        -->

        <param name="read_length" argument="--read-length" type="integer" value="" 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" value="0.99" label="Report only the main part of inserts" />
        <param name="trim_quality" argument="--trim-quality" type="integer" value="0" label="BWA trim parameter" />

        <conditional name="use_reference">
            <param name="use_ref_selector" argument="--ref-seq" type="select" label="Use reference sequence" help="Required for GC-depth and mismatches-per-cycle calculation">
                <option value="yes">Use reference</option>
                <option selected="True" value="no">Do not use reference</option>
            </param>
            <when value="yes">
                <conditional name="reference_source">
                    <param name="reference_source_selector" type="select" label="Choose a reference sequence for GC depth">
                        <option value="cached">Locally cached</option>
                        <option value="history">History</option>
                    </param>
                    <when value="cached">
                        <param name="ref_file" type="select" label="Using genome">
                            <options from_data_table="fasta_indexes">
                                <filter type="data_meta" ref="input_file" key="dbkey" column="1" />
                            </options>
                        </param>
                    </when>
                    <when value="history">
                        <param name="ref_file" type="data" format="fasta" label="Using file" />
                    </when>
                </conditional>
            </when>
            <when value="no" />
        </conditional>

    </inputs>

    <outputs>
        <data name="output" format="tabular" label="${tool.name} on ${on_string}">
            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tab" ext="tabular" visible="true" directory="split" />
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input_file" value="samtools_stats_input.bam" ftype="bam" />
            <param name="use_ref_selector" value="yes" />
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" value="samtools_stats_ref.fa" ftype="fasta" />
            <output name="output" file="samtools_stats_out1.tab" ftype="tabular" lines_diff="4" />
        </test>
        <test>
            <param name="input_file" value="samtools_stats_input.bam" ftype="bam" />
            <param name="use_ref_selector" value="yes" />
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" value="samtools_stats_ref.fa" ftype="fasta" />
            <param name="split_output_selector" value="yes" />
            <param name="generate_tables" value="sn,mpc,gcc" />
            <output name="output" file="samtools_stats_out2.tab" lines_diff="4">
                <discovered_dataset designation="Summary numbers" ftype="tabular" file="samtools_stats_out2__sn.tab" />
                <discovered_dataset designation="ACGT content per cycle" ftype="tabular" file="samtools_stats_out2__gcc.tab" />
                <discovered_dataset designation="Mismatches per cycle" ftype="tabular" file="samtools_stats_out2__mpc.tab" />
            </output>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

This tool runs the ``samtools stats`` command.
    ]]></help>
    <expand macro="citations"/>
</tool>