view bam2wig.xml @ 45:eb339c5849bb draft

Reupload, toolshed removed all files of previous version.
author lparsons
date Fri, 26 Sep 2014 15:04:18 -0400
parents
children
line wrap: on
line source

<tool id="rseqc_bam2wig" name="BAM to Wiggle" version="2.4">
    <description> 
        converts all types of RNA-seq data from .bam to .wig 
    </description>
    <requirements>
        <requirement type="package" version="3.0.3">R</requirement>
        <requirement type="package" version="1.7.1">numpy</requirement>
        <requirement type="package" version="2.4">rseqc</requirement>
    </requirements>
    <command>
        tmp_input_name=\$(mktemp -u);
        bai='.bai';

        ln -s "${input}" \$tmp_input_name &amp;&amp;
        ln -s "${input.metadata.bam_index}" \$tmp_input_name\$bai &amp;&amp;
        bam2wig.py -i \$tmp_input_name -s $chromsize -o outfile

        #if str($strand_type.strand_specific) == "pair"
            -d
            #if str($strand_type.pair_type) == "sd"
                '1++,1--,2+-,2-+'
            #else
                '1+-,1-+,2++,2--'
            #end if
        #end if

        #if str($strand_type.strand_specific) == "single"
            -d
            #if str($strand_type.single_type) == "s"
                '++,--'
            #else
                '+-,-+'
            #end if
        #end if

        #if $wigsum.wigsum_type
            -t $wigsum.totalwig
        #end if

        #if $skipmultihits
            -u
        #end if
        ;
        rm "\$tmp_input_name\$bai";
        rm \$tmp_input_name
    </command>
    <inputs>
        <param name="input" type="data" label="Input .bam File" format="bam" />
        <param name="chromsize" type="data" label="Chromosome size file (tab or space separated)" format="txt,tabular" />
        <param name="skipmultihits" type="boolean" label="Skip Multiple Hit Reads/Only Use Uniquely Mapped Reads" value="false" />
        <conditional name="wigsum">
            <param name="wigsum_type" type="boolean" label="Specify wigsum?" value="false">
            </param>
            <when value="true">
                <param name="totalwig" value="0" type="integer" label="specified wigsum" />
            </when>
            <when value="false"/>
        </conditional>
        <conditional name="strand_type">
            <param name="strand_specific" type="select" label="Strand-specific?" value="none">
                <option value="none">none</option>
                <option value="pair">Pair-End RNA-seq</option>
                <option value="single">Single-End RNA-seq</option>
            </param>
            <when value="pair">
                <param name="pair_type" type="select" display="radio" label="Pair-End Read Type (format: mapped --> parent)" value="sd">
                    <option value="sd"> read1 (positive --> positive; negative --> negative), read2 (positive --> negative; negative --> positive)</option>
                    <option value="ds">read1 (positive --> negative; negative --> positive), read2 (positive --> positive; negative --> negative)</option>
                </param>
            </when>
            <when value="single">
                <param name="single_type" type="select" display="radio" label="Single-End Read Type (format: mapped --> parent)" value="s">
                    <option value="s">positive --> positive; negative --> negative</option>
                    <option value="d">positive --> negative; negative --> positive</option>
                </param>
            </when>
            <when value="none"></when>
        </conditional>
    </inputs>
    <outputs> 
        <data format="wig" name="output" from_work_dir="outfile.wig">
            <filter>strand_type['strand_specific'] == 'none'</filter>
        </data>
        <data format="wig" name="outputfwd" from_work_dir="outfile_Forward.wig" label="${tool.name} on ${on_string} (Forward Reads)">
            <filter>strand_type['strand_specific'] != 'none'</filter>
        </data>
        <data format="wig" name="outputrv" from_work_dir="outfile_Reverse.wig" label="${tool.name} on ${on_string} (Reverse Reads)">
            <filter>strand_type['strand_specific'] != 'none'</filter>
        </data>
    </outputs>
    <stdio>
        <exit_code range="1:" level="fatal" description="An error occured during execution, see stderr and stdout for more information" />
        <regex match="[Ee]rror" source="both" description="An error occured during execution, see stderr and stdout for more information" />
    </stdio>
    <help>
bam2wig.py
++++++++++

Visualization is the most straightforward and effective way to QC your RNA-seq
data. For example, change of expression or new splicing can be easily checked
by visually comparing two RNA-seq tracks using genome browser such as UCSC_,
IGB_ and IGV_.  `bam2wig.py` converts all types of RNA-seq data from BAM_
format into wiggle_ format in one-stop.  wiggle_ files can then be easily
converted into bigwig_.  Bigwig is indexed, binary format of wiggle file, and
it's particular useful to display large, continuous dataset on genome
browser.

Inputs
++++++++++++++

Input BAM file
    Alignment file in BAM format (SAM is not supported). BAM file will be sorted and indexed using samTools.

Chromosome size file
    Tab or space separated text file with 2 columns: first column is chromosome name, second column is size of the chromosome. Chromosome names (such as "chr1") should be consistent between this file and BAM file.

Specified wigsum (default=none)
    Specified wigsum. Wigsum of 100000000 equals to coverage achieved by 1 million 100nt reads. Ignore this option to disable normalization.

Skip multiple Hit reads
    skips multiple hit reads or only use uniquely mapped reads

Strand-specific (default=none)
    How read(s) were stranded during sequencing. If you are not sure about the strand rule, run infer_experiment.py

Outputs
++++++++++++++

If RNA-seq is not strand specific, one wig file will be generated, if RNA-seq
is strand specific, two wig files corresponding to Forward and Reverse will be generated.

-----

About RSeQC 
+++++++++++


The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation.

The RSeQC package is licensed under the GNU GPL v3 license.

.. image:: http://rseqc.sourceforge.net/_static/logo.png

.. _RSeQC: http://rseqc.sourceforge.net/
.. _UCSC: http://genome.ucsc.edu/index.html
.. _IGB: http://bioviz.org/igb/
.. _IGV: http://www.broadinstitute.org/igv/home
.. _BAM: http://genome.ucsc.edu/goldenPath/help/bam.html
.. _wiggle: http://genome.ucsc.edu/goldenPath/help/wiggle.html
.. _bigwig: http://genome.ucsc.edu/FAQ/FAQformat.html#format6.1

    </help>
</tool>