annotate samtools_view.xml @ 6:ff313de5f7f4 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_view commit 851f81495c875ac09d936537ffd2b32e6af2c8c5"

<tool id="samtools_view" name="Samtools view" version="@TOOL_VERSION@">
    <description>reformat, filter, or subsample</description>
    <macros>
    <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package">gawk</requirement>
    </expand>
    <expand macro="stdio"/>
    <expand macro="version_command"/>
    <command><![CDATA[
        @ADDTHREADS@
        ## prepare reference data
        @PREPARE_FASTA_IDX@
        @PREPARE_IDX@
        #if $cond_subsample.select_subsample == 'target':
            ##this must be done before the main command because we don't know the total # reads until execution time
            #if str($cond_subsample.seed) == '':
                #set seed_expr="int(rand() * 32768)"
            #else
                #set seed_expr=$cond_subsample.seed
            #end if
            #if $input.is_of_type('sam'):
                sample_fragment=`samtools view -c infile | awk '{s=\$1} END {frac=$cond_subsample.target/s; print(frac < 1 ? "-s "  $seed_expr+frac : "")}'` &&
            #else
                sample_fragment=`samtools idxstats infile | awk '{s+=\$4+\$3} END {frac=$cond_subsample.target/s; print(frac < 1 ? "-s " $seed_expr+frac : "")}'` &&
            #end if
        #end if
        ##call samtools view
        samtools view
        -@ \$addthreads

        #if $outtype == 'count':
            -c
        #elif $outtype == 'bam':
            -b
        #elif $outtype == 'cram':
            -C
        #end if

        ## filter options (regions filter is the last parameter)
        #if $cond_filter.select_filter == 'yes':
            #if $cond_filter.cond_region.select_region == 'bed' and str( $cond_filter.cond_region.bedfile ) != 'None'
                -L '$cond_filter.cond_region.bedfile'
            #end if
            #if $cond_filter.cond_rg.select_rg == 'text':
                -r '$cond_filter.cond_rg.readgr'
            #else if $cond_filter.cond_rg.select_rg == 'file':
                -R '$cond_filter.cond_rg.rgfile'
            #end if
            #if str($cond_filter.quality) != '' and int( $cond_filter.quality ) > 0
                -q $cond_filter.quality
            #end if
            #if str( $cond_filter.library ) != ''
                -l '$cond_filter.library'
            #end if
            #if str( $cond_filter.cigarcons ) != ''
                -m $cond_filter.cigarcons
            #end if
            #if str($cond_filter.inclusive_filter) != 'None':
                #set $filter = $cond_filter.inclusive_filter
                @FLAGS@
                -f $flags
            #end if
            #if str($cond_filter.exclusive_filter) != 'None':
                #set $filter = $cond_filter.exclusive_filter
                @FLAGS@
                -F $flags
            #end if
            #if str($cond_filter.exclusive_filter_all) != 'None':
                #set $filter = $cond_filter.exclusive_filter_all
                @FLAGS@
                -G $flags
            #end if
            #for $i, $s in enumerate($cond_filter.readtags)
                -x '${s.readtag}'
            #end for
        #end if
        #if $cond_subsample.select_subsample != 'no':
            #if $cond_subsample.select_subsample == "target":
                ##this is calculated at execution time before the main samtools command
                "\${sample_fragment}"
            #else
                #set fraction=str($cond_subsample.fraction).split('.')[1]
                #if  str($cond_subsample.seed) == '':
                    -s "\${RANDOM}".$fraction
                #else
                    -s $cond_subsample.seed.$fraction
                #end if
            #end if
        #end if

        ## output options
        $adv_output.header
        $adv_output.collapsecigar
        #if $adv_output.outputpassing == 'yes'
            -U inv_outfile
        #end if
        -o outfile

        ## additional reference data
        #if $reffa!=None:
            -T '$reffa'
            -t '$reffai'
        #end if

        ##currently reference based CRAM is disabled (see https://github.com/galaxyproject/tools-iuc/pull/1963)
        #if $outtype=='cram':
            --output-fmt-option no_ref
        #end if

        infile
        
        ## region filter need to be at the end
        #if $cond_filter.select_filter == 'yes' and $cond_filter.cond_region.select_region == 'text':
            '$cond_filter.cond_region.regions'
        #end if

        ## if data is converted from an unsorted file (SAM, CRAM, or unsorted BAM) to BAM
        ## then sort the output by coordinate, 
        #if not $input.is_of_type('bam') and $outtype == 'bam':
            && samtools sort
                -@ \$addthreads -m \${GALAXY_MEMORY_MB:-768}M -T "\${TMPDIR:-.}"
                -O bam
                -o 'tmpsam'
                outfile
                && mv tmpsam outfile
            #if $adv_output.outputpassing == 'yes':
                && samtools sort
                    -@ \$addthreads -m \${GALAXY_MEMORY_MB:-768}M -T "\${TMPDIR:-.}"
                    -O bam
                    -o 'tmpsam'
                    inv_outfile
                && mv tmpsam inv_outfile
            #end if
        #end if
    ]]></command>
    <inputs>
        <!-- note unsorted bam includes all derived bam types (inlcuding bam which is sorted) -->
        <param name="input" format="sam,unsorted.bam,cram" type="data" label="SAM/BAM/CRAM data set" />
        <param name="outtype" type="select" argument="-b/-C/-c" label="Output type">
            <help>Select output type. In case of counts only the total number of alignments is returned. All filters are taken into account</help>
            <option value="sam">SAM</option>
            <option value="bam">BAM (-b)</option>
            <option value="cram">CRAM (-C)</option>
            <option value="count">Count of alignments (-c)</option>
        </param>
        <conditional name="cond_filter">
            <param name="select_filter" type="select" label="Filter alignment">
                <option value="yes">Yes</option>
                <option value="no" selected="True">No</option>
            </param>
            <when value="yes">
                <conditional name="cond_region">
                    <param name="select_region" type="select" label="Filter by regions">
                        <option value="no" selected="True">No</option>
                        <option value="text">Manualy specify regions</option>
                        <option value="bed">Regions from BED file</option>
                    </param>
                    <when value="no"/>
                    <when value="text">
                        <param name="regions" type="text" optional="false" label="Filter by regions" help="One or more space-separated region specifications to restrict output to only those alignments which overlap the specified region(s)."/>
                    </when>
                    <when value="bed">
                        <param name="bedfile" format="bed" argument="-L" optional="false" type="data" label="Filter by intervals in a bed file" help="Only output alignments overlapping the intervals in the input bed file." />
                    </when>
                </conditional>
                <conditional name="cond_rg">
                    <param name="select_rg" type="select" label="Filter by readgroup">
                        <option value="no" selected="True">No</option>
                        <option value="text">Single read group </option>
                        <option value="file">Read groups from file</option>
                    </param>
                    <when value="no"/>
                    <when value="text">
                        <param name="readgr" type="text" argument="-r" label="Filter by read group" help="Only output alignments in read group." />
                    </when>
                    <when value="file">
                        <param name="rgfile" type="data" format="tabular" argument="-R" label="Filter by read groups in file" help="Output alignments in read groups listed in FILE." />
                    </when>
                </conditional>
                <param name="quality" type="integer" argument="-q" optional="true" min="0" label="Filter by quality" help="Skip alignments with MAPQ smaller than INT." />
                <param name="library" type="text" argument="-l" optional="true" label="Filter by library" help="Only output alignments in library STR" />
                <param name="cigarcons" type="integer" argument="-m" optional="true" min="0" label="Filter by number of CIGAR bases consuming query sequence" help="Only output alignments with number of CIGAR bases consuming query sequence greater than or equal INT." />
                <param name="inclusive_filter" argument="-f" type="select" multiple="True" label="Require that these flags are set">
                    <expand macro="flag_options" />
                </param>
                <param name="exclusive_filter" argument="-F" type="select" multiple="True" label="Exclude reads with any of the following flags set">
                    <expand macro="flag_options" />
                </param>
                <param name="exclusive_filter_all" argument="-G" type="select" multiple="True" label="Exclude reads with all of the following flags set">
                    <expand macro="flag_options" />
                </param>
                <!-- TODO could also make this a text field (comma/space separated) -->
                <repeat name="readtags" title="Filter by read tags">
                    <param name="readtag" type="text" argument="-x" label="Filter by read tag" help="Read tag to exclude from output."/>
                </repeat>
            </when>
            <when value="no"/>
        </conditional>
        <conditional name="cond_subsample">
            <param name="select_subsample" type="select" argument="-s" label="Subsample alignment">
                <option value="fraction">Specify a fraction to keep</option>
                <option value="target">Specify a target # of reads</option>
                <option value="no" selected="True">No downsampling</option>
            </param>
            <when value="fraction">
                <param name="fraction" type="float" optional="False" value="0.5" min="0" max="1" label="Subsampling fraction" help="sets the fraction of templates/pairs to subsample." />
                <expand macro="seed_input" />
            </when>
            <when value='target'>
                <param name="target" type="integer" optional="False" value="" min="0"  label="Target # of reads" help="sets the target number of reads to subsample." />
                <expand macro="seed_input" />
            </when>
            <when value="no"/>
        </conditional>
        <conditional name="addref_cond">
            <param name="addref_select" type="select" label="Reference data">
                <help>Reference data as fasta(.gz). Required for SAM input without @SQ headers and useful/required for writing CRAM output (see help).</help>
                <option value="no" selected="True">No, see help (-output-fmt-option no_ref)</option>
                <option value="history">Use a genome/index from the history (-t/-T)</option>
                <option value="cached">Use a built-in genome (-t/-T)</option>
            </param>
            <when value="no"/>
            <when value="history">
                <param name="ref" format="fasta,fasta.gz" optional="true" type="data" label="Reference file"/>
            </when>
            <when value="cached">
                <param name="ref" type="select" label="Using reference genome">
                    <options from_data_table="fasta_indexes">
                        <filter column="dbkey" key="dbkey" ref="input" type="data_meta" />
                        <validator message="No reference genome is available for the build associated with the selected input dataset" type="no_options" />
                    </options>
                </param>
            </when>
        </conditional>
        <section name="adv_output" title="Output Options" expanded="false">
            <param name="header" type="select" argument="-h/-H" label="Header options">
                <option value="-h" selected="True">Include header in SAM output (-h)</option>
                <option value="-H">Return header only (-H)</option>
                <option value="">Exclude header</option>
            </param>
            <param name="outputpassing" type="boolean" argument="-U" truevalue="yes" falsevalue="no" checked="false" label="Output alignments not passing the filter" help="Write alignments that are not selected by the various filter options to an extra data set. When this option is used, all alignments (or all alignments intersecting the regions specified) are written to either the output data set or this extra output data set, but never both." />
            <param name="collapsecigar" type="boolean" argument="-B" truevalue="-B" falsevalue="" checked="false" label="Collapse backward CIGAR operation" help="Collapse the backward CIGAR operation." />
        </section>
    </inputs>
    <outputs>
        <!-- TODO do I need an action for dbkey? -->
        <data name="outputsam" format_source="input" from_work_dir="outfile" label="${tool.name} on ${on_string}: filtered alignments">
            <filter>outtype != 'count'</filter>
            <!-- TODO is change_format deprecated? how can I modify the type for the different bam types? -->
            <change_format>
                <when input="outtype" value="sam" format="sam" />
                <when input="outtype" value="bam" format="bam" />
                <when input="outtype" value="cram" format="cram" />
            </change_format>
        </data>
        <data name="invoutputsam" format_source="input" from_work_dir="inv_outfile"  label="${tool.name} on ${on_string}: unfiltered alignments">
            <filter>adv_output['outputpassing'] == 'yes' and outtype != 'count'</filter>
            <change_format>
                <when input="outtype" value="sam" format="sam" />
                <when input="outtype" value="bam" format="bam" />
                <when input="outtype" value="cram" format="cram" />
            </change_format>
        </data>
        <data name="outputcnt" format="txt" from_work_dir="outfile" label="${tool.name} on ${on_string}: Counts">
            <filter>outtype == 'count'</filter>
        </data>
    </outputs>
    <tests>
        <!-- sam to bam (copied from the sam_to_bam tool) -->
        <test>
            <param name="input" ftype="sam" value="sam_to_bam_in1.sam" />
            <param name="outtype" value="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" ftype="fasta" dbkey="equCab2" value="chr_m.fasta" />
            </conditional>
            <output name="outputsam" ftype="bam" file="sam_to_bam_out1.bam" />
        </test>
        <test>
            <param name="input" ftype="sam" dbkey="equCab2" value="sam_to_bam_in1.sam" />
            <param name="outtype" value="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="cached" />
                <param name="ref" value="equCab2chrM" />
            </conditional>
            <output name="outputsam" ftype="bam" file="sam_to_bam_out2.bam" />
        </test>
        <test>
            <param name="input" ftype="sam" value="sam_to_bam_noheader_in2.sam" />
            <param name="outtype" value="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" ftype="fasta" dbkey="equCab2" value="chr_m.fasta" />
            </conditional>
            <output name="outputsam" ftype="bam" file="sam_to_bam_out3.bam" />
        </test>
        <!-- bam to cram + region filter (adapted from bam_to_cram tool)-->
        <test>
            <param name="input" value="test.bam" ftype="bam" />
            <param name="outtype" value="cram" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" />
            </conditional>
            <conditional name="cond_filter">
                <param name="select_filter" value="yes" />
                <conditional name="cond_region">
                    <param name="select_region" value="no"/>
                </conditional>
            </conditional>
            <output name="outputsam" file="test.cram" ftype="cram" compare="sim_size" delta="250" />
        </test>
       <!-- count alignments -->
       <test>
            <param name="input" value="test.bam" ftype="bam" />
            <param name="outtype" value="count" />
            <output name="outputcnt" file="test_counts.tab" ftype="txt" />
        </test>
        <test>
            <param name="input" value="test.sam" ftype="sam" />
            <param name="outtype" value="cram" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" />
            </conditional>
            <conditional name="cond_filter">
                <param name="select_filter" value="yes" />
                <conditional name="cond_region">
                    <param name="select_region" value="no"/>
                </conditional>
            </conditional>
            <output name="outputsam" file="test.cram" ftype="cram" compare="sim_size" delta="250" />
        </test>
        <test>
            <param name="input" value="test.bam" ftype="bam" />
            <param name="outtype" value="cram" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" />
            </conditional>
            <conditional name="cond_filter">
                <param name="select_filter" value="yes" />
                <conditional name="cond_region">
                    <param name="select_region" value="text"/>
                    <param name="regions" value="CHROMOSOME_I" />
                </conditional>
            </conditional>
            <output name="outputsam" file="test.cram" ftype="cram" compare="sim_size" delta="250" />
        </test>
        <!-- bam to sam + header options (adapted from bam_to_sam tool)-->
        <test>
            <param ftype="bam" name="input" value="bam_to_sam_in1.bam" />
            <param name="outtype" value="sam" />
            <param name="header" value="-h" />
            <output file="bam_to_sam_out1.sam" ftype="sam" name="outputsam" />
        </test>
        <test>
            <param ftype="bam" name="input" value="bam_to_sam_in1.bam" />
            <param name="outtype" value="sam" />
            <param name="header" value="-H" />
            <output file="bam_to_sam_out2.sam" ftype="sam" name="outputsam" />
        </test>
        <test>
            <param ftype="bam" name="input" value="bam_to_sam_in1.bam" />
            <param name="outtype" value="sam" />
            <param name="header" value="" />
            <output file="bam_to_sam_out3.sam" ftype="sam" name="outputsam" />
        </test>
        <!-- cram to bam + region (adapted from cram_to_bam tool)-->
        <test>
            <param name="input" value="test.cram" ftype="cram" />
            <param name="outtype" value="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" />
            </conditional>
            <output name="outputsam" file="test.bam" ftype="bam" />
        </test>
        <test>
            <param name="input" value="test.cram" ftype="cram" />
            <param name="outtype" value="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" />
            </conditional>
            <param name="target_region" value="region" />
            <param name="region_string" value="CHROMOSOME_I" />
            <output name="outputsam" file="test.bam" ftype="bam" />
        </test>
        <test>
            <param name="input" value="test.cram" ftype="cram" />
            <param name="outtype" value="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="history" />
                <param name="ref" value="test.fa" />
            </conditional>
            <param name="target_region" value="regions_bed_file" />
            <param name="regions_bed_file" value="test.bed" ftype="bed" />

            <output name="outputsam" file="test.bam" ftype="bam" />
        </test>
        <test>
            <param name="input" value="test2.cram" dbkey="equCab2" ftype="cram" />
            <param name="outtype" value="bam" />
            <conditional name="addref_cond">
                <param name="addref_select" value="cached" />
                <param name="ref" value="equCab2chrM" />
            </conditional>
            <conditional name="cond_region">
                <param name="select_region" value="no"/>
            </conditional>
            <output name="outputsam" file="sam_to_bam_out2.bam" ftype="bam" />
        </test>
        <!-- sampling options-->
        <test>
            <param name="input" value="test.sam" ftype="sam" />
            <param name="outtype" value="sam" />
            <conditional name="cond_subsample">
                <param name="select_subsample" value="target" />
                <param name="target" value="2" />
            </conditional>
            <output name="outputsam" file="test_ds.sam" ftype="sam" compare="diff" lines_diff="6" />
        </test>
        <test>
            <param name="input" value="test.sam" ftype="sam" />
            <param name="outtype" value="sam" />
            <conditional name="cond_subsample">
                <param name="select_subsample" value="target" />
                <param name="seed" value="7" />
                <param name="target" value="2" />
            </conditional>
            <output name="outputsam" file="test_ds.sam" ftype="sam" compare="diff" lines_diff="6" />
        </test>
        <test>
            <param name="input" value="test.bam" ftype="bam" />
            <param name="outtype" value="bam" />
            <conditional name="cond_subsample">
                <param name="select_subsample" value="target" />
                <param name="seed" value="7" />
                <param name="target" value="2" />
            </conditional>
            <output name="outputsam" file="test_ds.bam" ftype="bam" />
        </test>        
        <test>
            <param name="input" value="test.bam" ftype="bam" />
            <param name="outtype" value="bam" />
            <conditional name="cond_subsample">
                <param name="select_subsample" value="fraction" />
                <param name="seed" value="7" />
                <param name="fraction" value=".2" />
            </conditional>
            <output name="outputsam" file="test_ds.bam" ftype="bam" />
        </test>        
    </tests>
    <help>
**What it does**

Samtools view can: 

1. filter alignments according to various criteria 
2. convert between alignment formats (SAM, BAM, CRAM)

With no options or regions specified, prints all alignments in the specified input alignment file (in SAM, BAM, or CRAM format) to standard output in SAM format (with no header). 

**Alignment format conversion**

Inputs of type SAM, BAM, and CRAM are accepted and can be converted to each of these formats (alternatively alignment counts can be computed) by selecting the appropriate "Output type". 

.. class:: infomark 

samtools view allows to specify a reference sequence. This is required for SAM input with missing @SQ headers (which include sequence names, length, md5, etc) and useful (and sometimes necessary) for CRAM input and output. In the following the use of reference sequence in the CRAM format is detailed. 
CRAM is (intended as a primarily) a reference-based compressed format, i.e. only differences between the stored sequences and the reference are stored. As a consequence the reference that was used to generate the alignemnts is always needed in order to interpret the alignments (a checksum stored in the CRAM file is used to verify that the only the correct sequence can be used), i.e. the CRAM file on its own is not useful per default. This allows for a more space efficient storage compared to BAM. 
But it is also possible to use CRAM without a reference with the disadvantage that the reference is stored explicitely (as in SAM and BAM). 

The Galaxy tool **currently generates only CRAM without reference sequence**.

For reference based CRAM input the correct refernce sequence needs to be specified.

**Filtering alignments**

samtools view allows to filter alignements based on various criteria, i.e. the output will contain only alignemnts matching all criteria (an additional output containing the remaining alignments can be created additionally, see "Output alignments not passing the filter" in "output options"): e.g. by regions (see below), alignment quality (see below), and tags or flags set in the alignments. 



**Filtering by regions**

You may specify one or more space-separated region specifications after the input filename to restrict output to only those alignments which overlap the specified region(s). Use of region specifications requires a coordinate-sorted and indexed input file (in BAM or CRAM format).

Regions can be specified as: RNAME[:STARTPOS[-ENDPOS]] and all position coordinates are 1-based.

Important note: when multiple regions are given, some alignments may be output multiple times if they overlap more than one of the specified regions.

Examples of region specifications:

- chr1 Output all alignments mapped to the reference sequence named 'chr1' (i.e. @SQ SN:chr1).
- chr2:1000000 The region on chr2 beginning at base position 1,000,000 and ending at the end of the chromosome.
- chr3:1000-2000 The 1001bp region on chr3 beginning at base position 1,000 and ending at base position 2,000 (including both end positions).
- '*' Output the unmapped reads at the end of the file. (This does not include any unmapped reads placed on a reference sequence alongside their mapped mates.)
- . Output all alignments. (Mostly unnecessary as not specifying a region at all has the same effect.)

**Filtering by quality**

This filters based on the MAPQ column of the SAM format which gives an estimate about the correct placement of the alignemnt. Note that aligners do not follow a consistent definition. 

The -x, -B, and -s options modify the data which is contained in each alignment.
    </help>
    <expand macro="citations"/>
</tool>