comparison samblaster.xml @ 0:aa72470e14f7 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/samblaster commit 82097013a9eb5a6161d400e5b6c493113c440687

0:aa72470e14f7

<tool id="samblaster" name="samblaster" version="0.1.24">
    <description>marks duplicates, outputs split reads, discordant read pairs and unmapped reads</description>
    <requirements>
        <requirement type="package" version="0.1.24">samblaster</requirement>
        <requirement type="package" version="0.6.5">sambamba</requirement>
    </requirements>
    <version_command>samblaster --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
        #if $input.is_of_type('sam'):
        #set stream="<(sambamba view -S -f bam -t ${GALAXY_SLOTS:-4} -h '%s')" % $input
        #else:
            #set stream="'%s'" % $input
        #end if
        sambamba view -t \${GALAXY_SLOTS:-4} -h <(sambamba sort -t \${GALAXY_SLOTS:-4} -n $stream -o /dev/stdout) |
        samblaster
        $output
        $discordantFile
        $splitterFile
        $unmappedFile
        $acceptDupMarks
        $excludeDups
        $removeDups
        $addMateTags
        $compatibility_mode
        --maxSplitCount '$maxSplitCount'
        --maxUnmappedBases '$maxUnmappedBases'
        --minIndelSize '$minIndelSize'
        --minNonOverlap '$minNonOverlap'
        --minClipSize '$minClipSize'
        #if $output != "-o /dev/null":
            && sambamba sort -o output.bam -l 6 -t \${GALAXY_SLOTS:-4} <(sambamba view -S -f bam output.sam)
        #end if
        #if $discordantFile:
            && sambamba sort -o discordant.bam -l 6 -t \${GALAXY_SLOTS:-4} <(sambamba view -S -f bam discordant.sam)
        #end if
        #if $splitterFile:
            && sambamba sort -o splitter.bam -l 6 -t \${GALAXY_SLOTS:-4} <(sambamba view -S -f bam splitter.sam)
        #end if
    ]]></command>
    <inputs>
        <param argument="--input" type="data" format="bam,sam"/>
        <param argument="--output" label="Output bam file for all input alignments" type="boolean" checked="true" truevalue="-o output.sam" falsevalue="-o /dev/null"/>
        <param argument="--discordantFile" label="Output discordant read pairs?" type="boolean" truevalue="-d discordant.sam" falsevalue=""/>
        <param argument="--splitterFile" label="Output split reads?" type="boolean" truevalue="-s splitter.sam" falsevalue=""/>
        <param argument="--unmappedFile" label="Output unmapped/clipped reads as FASTQ?" type="boolean" truevalue="-u unmapped.fastq" falsevalue=""/>
        <param argument="--acceptDupMarks" label="Accept duplicate marks already in input file instead of looking for duplicates in the input?" type="boolean" truevalue="-a" falsevalue=""/>
        <param argument="--excludeDups" label="Exclude reads marked as duplicates from discordant, splitter, and/or unmapped file?" type="boolean" truevalue="-a" falsevalue=""/>
        <param argument="--removeDups" label="Remove duplicates reads from all output files?" help="(Implies --excludeDups)" type="boolean" truevalue="-e" falsevalue=""/>
        <param argument="--addMateTags" label="Add MC and MQ tags?" type="boolean" truevalue="--addMateTags" falsevalue=""/>
        <param name="compatibility_mode" argument="-M" label="Run in compatibility mode?" help="Both 0x100 and 0x800 are considered chimeric. Similar to BWA MEM -M option." type="boolean" truevalue="-M" falsevalue="" />
        <param argument="--maxSplitCount" label="Maximum number of split alignments for a read to be included in splitter file." type="integer" value="2"/>
        <param argument="--maxUnmappedBases" label="Maximum number of un-aligned bases between two alignments to be included in splitter file." type="integer" value="50" min="1"/>
        <param argument="--minIndelSize" label="Minimum structural variant feature size for split alignments to be included in splitter file." type="integer" value="50" min="1"/>
        <param argument="--minNonOverlap" label="Minimum non-overlaping base pairs between two alignments for a read to be included in splitter file." type="integer" value="20" min="1"/>
        <param argument="--minClipSize" label="Minumum number of bases a mapped read must be clipped to be included in unmapped file." type="integer" value="20" min="1"/>
    </inputs>
    <outputs>
        <data name="output_bam" format="bam" label="samblaster alignments on ${on_string}" from_work_dir="output.bam">
            <filter>output</filter>
        </data>
        <data name="discordant_bam" format="bam" label="samblaster discordant alignments on ${on_string}" from_work_dir="discordant.bam">
            <filter>discordantFile</filter>
        </data>
        <data name="splitter_bam" format="bam" label="samblaster split alignments on ${on_string}" from_work_dir="splitter.bam">
            <filter>splitterFile</filter>
        </data>
        <data name="unmapped_fastq" format="fastqsanger" label="samblaster unmapped fastq on ${on_string}" from_work_dir="unmapped.fastq">
            <filter>unmappedFile</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input" value="sr.input.bam"/>
            <param name="output" value="true"/>
            <param name="discordandFile" value="false"/>
            <param name="splitterFile" value="true"/>
            <param name="unmappedFile" value="true"/>
            <output name="output_bam" file="output.bam" compare="sim_size"/>
            <output name="splitter_bam" file="splitters.bam" compare="sim_size"/>
            <output name="unmapped_fastq">
                <assert_contents>
                    <has_line line="@M00860:26:000000000-A6UGV:1:1101:10000:6072" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input" value="sr.input.sam.gz" ftype="sam"/>
            <param name="output" value="true"/>
            <param name="discordandFile" value="false"/>
            <param name="splitterFile" value="true"/>
            <param name="unmappedFile" value="true"/>
            <output name="output_bam" file="output.bam" compare="sim_size"/>
            <output name="splitter_bam" file="splitters.bam" compare="sim_size"/>
            <output name="unmapped_fastq">
                <assert_contents>
                    <has_line line="@M00860:26:000000000-A6UGV:1:1101:10000:6072" />
                </assert_contents>
            </output>
         </test>
    </tests>
    <help><![CDATA[

*samblaster*
============

Summary
-------

*samblaster* is a fast and flexible program for marking duplicates in
**read-id grouped** paired-end SAM files. It can also optionally output
discordant read pairs and/or split read mappings to separate SAM files,
and/or unmapped/clipped reads to a separate FASTQ file. When marking
duplicates, *samblaster* will require approximately 20MB of memory per
1M read pairs.

Usage
-----

See the `SAM File Format
Specification <http://samtools.sourceforge.net/SAMv1.pdf>`__ for details
about the SAM alignment format.

By default, samblaster marks duplicates with SAM FLAG 0x400. The
**--removeDups** option will instead remove duplicate alignments from the
output file.

**ALIGNMENT TYPE DEFINITIONS:** Below, we will use the following
definitions for alignment types. Starting with *samblaster* release
0.1.22, these definitions are affected by the use of the **-M** option.
By default, *samblaster* will use the current definitions of alignment
types as specified in the `SAM
Specification <http://samtools.sourceforge.net/SAMv1.pdf>`__. Namely,
alignments marked with FLAG 0x100 are considered *secondary*, while
those marked with FLAG 0x800 are considered *supplemental*. If the
**-M** option is specified, alignments marked with either FLAG 0x100 or
0x800 are considered *supplemental*, and no alignments are considered
*secondary*. A *primary* alignment is always one that is neither
*secondary* nor *supplemental*. Only *primary* and *supplemental*
alignments are used to find chimeric (split-read) mappings. The **-M**
flag is used for backward compatibility with older SAM/BAM files in
which "chimeric" alignments were marked with FLAG 0x100, and should also
be used with output from more recent runs of *bwa mem* using its **-M**
option.

**DISCORDANT READ PAIR IDENTIFICATION:** A **discordant** read pair is
one which meets all of the following criteria:

1. Both side of the read pair are mapped (neither FLAG 0x4 or 0x8 is
   set).
2. The *properly paired* FLAG (0x2) is not set.
3. *Secondary* or *supplemental* alignments are never output as
   discordant, although a discordant read pair can have such alignments
   associated with them.
4. Duplicate read pairs that meet the above criteria will be output as
   discordant unless the **-e** option is used.

**UNMAPPED/CLIPPED READ IDENTIFICATION:** An **unmapped** or **clipped**
read is a *primary* alignment that is unaligned over all or part of its
length respectively. The lack of a full alignment may be caused by a SV
breakpoint that falls within the read. Therefore, *samblaster* will
optionally output such reads to a FASTQ file for re-alignment by a tool,
such as `YAHA <https://github.com/GregoryFaust/yaha/>`__, geared toward
finding split-read mappings. *samblaster* applies the following strategy
to identify and output unmapped/clipped reads:

1. An **unmapped** read has the *unmapped read* FLAG set (0x4).
2. A **clipped** read is a mapped read with a CIGAR string that begins
   or ends with at least **--minClipSize** unaligned bases (CIGAR code S
   and/or H), and is not from a read that has one or more *supplemental*
   alignments.
3. In order for *samblaster* to output the entire sequence for clipped
   reads, the input SAM file must have soft clipped primary alignments.
4. *samblaster* will output unmapped/clipped reads into a FASTQ file if
   QUAL information is available in the input file, and a FASTA file if
   not.
5. Unmapped/clipped reads that are part of a duplicate read pair will be
   output unless the **-e** option is used.


**Written by:** Greg Faust ([e-mail]) `Ira Hall Lab,
University of Virginia <http://faculty.virginia.edu/irahall/>`__

**Please cite:** `Faust, G.G. and Hall, I.M., “\ *SAMBLASTER*: fast
duplicate marking and structural variant read extraction,”
*Bioinformatics* Sept. 2014; **30**\ (17):
2503-2505. <http://bioinformatics.oxfordjournals.org/content/30/17/2503>`__

**Also see:** `SAMBLASTER\_Supplemental.pdf
<https://github.com/GregoryFaust/samblaster/raw/master/SAMBLASTER_Supplemental.pdf>`__
for additonal discussion and statistics about the duplicates marked by
*samblaster* vs. *Picard* using the NA12878 sample dataset. Click the
preceeding link or download the file from this repository.
**Written by:** Greg Faust ([e-mail]) `Ira Hall Lab,
University of Virginia <http://faculty.virginia.edu/irahall/>`__

**Please cite:** `Faust, G.G. and Hall, I.M., “\ *SAMBLASTER*: fast
duplicate marking and structural variant read extraction,”
*Bioinformatics* Sept. 2014; **30**\ (17):
2503-2505. <http://bioinformatics.oxfordjournals.org/content/30/17/2503>`__

**Also see:** `SAMBLASTER\_Supplemental.pdf
<https://github.com/GregoryFaust/samblaster/raw/master/SAMBLASTER_Supplemental.pdf>`__
for additonal discussion and statistics about the duplicates marked by
*samblaster* vs. *Picard* using the NA12878 sample dataset. Click the
preceeding link or download the file from this repository.

   ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btu314</citation>
    </citations>
</tool>