annotate bbmap.xml @ 2:e0ca2ec4f5d9 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bbtools commit ae31a678eb5c04fb74b94161db95705d597990ad"

<tool id="bbtools_bbmap" name="BBTools: BBMap" version="@WRAPPER_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>short-read aligner</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
#import os
#import re

#if str($ref_source_cond.ref_source) == 'cached'
    #set ref = str($ref_source_cond.reference.fields.path)
#else:
    #set ref = $ref_source_cond.reference
#end if

#if str($input_type_cond.input_type) in ['single', 'pair']:
    #set read1 = $input_type_cond.read1
    #set read1_identifier = re.sub('[^\s\w\-]', '_', str($read1.element_identifier))
    ## bbmap uses the file extension to determine the input format.
    #set ext = $read1_identifier + '.fastq'
    #if $read1.ext.endswith('.gz'):
        #set ext = $ext + '.gz'
    #end if
    #set read1_file = $read1_identifier + $ext
    ln -s '${read1}' '${read1_file}' &&
    #if str($input_type_cond.input_type) == 'pair':
        #set read2 = $input_type_cond.read2
        #set read2_identifier = re.sub('[^\s\w\-]', '_', str($read2.element_identifier))
        #set read2_file = $read2_identifier + $ext
        ln -s '${read2}' '${read2_file}' &&
    #end if
#else:
    #set read1 = $input_type_cond.reads_collection['forward']
    #set read1_identifier = re.sub('[^\s\w\-]', '_', str($read1.name))
    ## bbmap uses the file extension to determine the input format.
    #set ext = $read1_identifier + '.fastq'
    #if $read1.ext.endswith('.gz'):
        #set ext = $ext + '.gz'
    #end if
    #set read1_file = $read1_identifier + $ext
    ln -s '${read1}' '${read1_file}' &&
    #set read2 = $input_type_cond.reads_collection['reverse']
    #set read2_identifier = re.sub('[^\s\w\-]', '_', str($read2.name))
    #set read2_file = $read2_identifier + $ext
    ln -s '${read2}' '${read2_file}' &&
#end if

bbmap.sh t=\${GALAXY_SLOTS:-4} ref='${ref}'
#if str($input_type_cond.input_type) == 'single':
    in='${read1_file}'
#else:
    in1='${read1_file}' in2='${read2_file}'
#end if
#if str($output_sort) == 'coordinate':
    out='mapped.bam'; samtools sort -@\${GALAXY_SLOTS:-4} -T "\${TMPDIR:-.}" -O bam -o '$output' 'mapped.bam'
#elif str($output_sort) == 'name':
    out='mapped.bam'; samtools sort -n -@\${GALAXY_SLOTS:-4} -T '\${TMPDIR:-.}' -O bam -o '$output' 'mapped.bam'
#else:
    out='mapped.bam' && mv 'mapped.bam' '$output'
#end if
]]></command>
    <inputs>
        <expand macro="input_type_cond"/>
        <expand macro="reference_source_cond"/>
        <param name="output_sort" type="select" label="BAM sorting mode" help="The 'Not sorted' option can significantly extend the run time of the tool (it runs using a single thread).">
            <option value="coordinate" selected="True">Sort by chromosomal coordinates</option>
            <option value="name">Sort by read names</option>
            <option value="unsorted">Not sorted (sorted as input)</option>
        </param>
    </inputs>
    <outputs>
        <data format="bam" name="output" label="${tool.name} on ${on_string} (mapped reads in BAM format)">
            <expand macro="dbKeyActionsBBMap"/>
            <change_format>
                <when input="output_sort" value="name" format="qname_sorted.bam" />
                <when input="output_sort" value="unsorted" format="qname_input_sorted.bam" />
            </change_format>
        </data>
    </outputs>
    <tests>
        <!-- Single file, cached reference, output coordinate sorted -->
        <test expect_num_outputs="1">
            <param name="input_type" value="single"/>
            <param name="read1" value="13-1941-6_S4_L001_R1_600000.fastq.gz"/>
            <output name="output" file="output1.bam" ftype="bam" lines_diff="4">
                <metadata name="dbkey" value="89" />
            </output>
        </test>
        <!-- Paired reads in separate datasets, cached reference, output name sorted -->
        <test expect_num_outputs="1">
            <param name="input_type" value="pair"/>
            <param name="read1" value="13-1941-6_S4_L001_R1_600000.fastq.gz"/>
            <param name="read2" value="13-1941-6_S4_L001_R2_600000.fastq.gz"/>
            <param name="output_sort" value="name"/>
            <output name="output" file="output2.bam" ftype="qname_sorted.bam" lines_diff="4">
                <metadata name="dbkey" value="89" />
            </output>
        </test>
        <!-- Collection of Paired reads, history reference, output unsorted -->
        <test expect_num_outputs="1">
            <param name="input_type" value="paired"/>
            <param name="reads_collection">
                <collection type="paired">
                    <element name="forward" value="13-1941-6_S4_L001_R1_600000.fastq.gz"/>
                    <element name="reverse" value="13-1941-6_S4_L001_R2_600000.fastq.gz"/>
                </collection>
            </param>
            <param name="ref_source" value="history"/>
            <param name="reference" value="NC_002945v4.fasta" dbkey="89" ftype="fasta"/>
            <param name="output_sort" value="unsorted"/>
            <output name="output" file="output3.bam" ftype="qname_input_sorted.bam" lines_diff="4">
                <metadata name="dbkey" value="89" />
            </output>
        </test>
    </tests>
    <help>
**What it does**

BBMap is a splice-aware global aligner for DNA and RNA sequencing reads.  It is fast and extremely accurate, particularly
with highly mutated genomes or reads with long indels, even whole-gene deletions over 100kbp long. It has no upper limit
to genome size or number of contigs and has been successfully used for mapping to an 85 gigabase soil metagenome with over
200 million contigs. the indexing phase is very fast compared to other aligners.

BBMap can output many different statistics files; an empirical read quality histogram, insert-size distribution, and genome
coverage with or without generating a sam file.  It is useful in quality control of libraries and sequencing runs or
evaluating new sequencing platforms.

**Options**

  *Bam sorting mode* - the generated bam files can be sorted according to three criteria: coordinates, names and input order.

    * Sort by chromosomal coordinates - the file is sorted by coordinates (i.e., the reads from the beginning of the first
      chromosome are first in the file.
    * Sort by read names - the file is sorted by the reference ID (i.e., the QNAME field).
    * Not sorted (sorted as input) - the file is sorted in the order of the reads in the input file.

    </help>
    <expand macro="citations"/>
</tool>