view bamhash.xml @ 0:63f6f42d112b draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bamhash commit 7aa0b566d492b1830c0bd2e54ddf4a26be95f76d
author bgruening
date Thu, 17 Sep 2015 08:00:35 -0400
parents
children
line wrap: on
line source

<tool id="bamhash" name="BamHash" version="1.1">
    <description>Hash BAM and FASTQ files to verify data integrity</description>
    <requirements>
        <requirement type="package" version="1.1">bamhash</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
        <exit_code range=":-1" />
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <version_command>bamhash_checksum_fastq --version</version_command>
    <command><![CDATA[
        #if $tool.tool_choice=="bam":
            #for $counter, $file in enumerate($tool.input_bam):
                ln -s "${file}" "${counter}.bam" ## 1.bam ... 2.bam
                &&
            #end for
            bamhash_checksum_bam
            $tool.noQuality_bam
            $tool.noPaired_bam
            #for $counter, $filename in enumerate($tool.input_bam):
                "${counter}.bam"
            #end for
        #elif $tool.tool_choice=="fastq":
            #for $counter, $file in enumerate($tool.input_fastq):
                ln -s "${file}" "${counter}.fastq" ## 1.fastq ... 2.fastq
                &&
            #end for
            bamhash_checksum_fastq
            $tool.noQuality_fastq
            $tool.noPaired_fastq
            #for $counter, $filename in enumerate($tool.input_fastq):
                "${counter}.fastq"
            #end for
        #elif $tool.tool_choice=="fasta":
            #for $counter, $file in enumerate($tool.input_fasta):
                ln -s "${file}" "${counter}.fasta" ## 1.fasta ... 2.fasta
                &&
            #end for
            bamhash_checksum_fasta
            #for $counter, $filename in enumerate($tool.input_fasta):
                "${counter}.fasta"
            #end for
       #end if
       $readnames
       > output.txt
    ]]></command>
    <inputs>
        <conditional name="tool">
            <param name="tool_choice" type="select" label="Choose file type:"
                help="">
                <option value="bam">BAM file(s)</option>
                <option value="fastq">FASTQ file(s)</option>
                <option value="fasta">FASTA file(s)</option>
            </param>
            <when value="bam">
                <param name="input_bam" multiple="True" type="data" format="bam" label="Input file in BAM format"/>
                <param name="noQuality_bam" type="boolean" checked="false" truevalue="--no-quality"
                        falsevalue=""
                        label="Ignore read quality?" 
                        help="Do not use read quality as part of checksum. (--no-quality)"/>
                <param name="noPaired_bam" type="boolean" checked="false" truevalue="--no-paired"
                        falsevalue=""
                        label="Bam files were not generated with paired-end reads?"
                        help="(--no-paired)" />
            </when>
            <when value="fasta">
                <param name="input_fasta" multiple="True" type="data" format="fasta" label="Input file in FASTA format"/>
            </when>
            <when value="fastq">
                <param name="input_fastq" multiple="True" type="data" format="fastq" label="Input file in FASTQ format"/>
                <param name="noQuality_fastq" type="boolean" checked="false" truevalue="--no-quality"
                        falsevalue=""
                        label="Ignore read quality?" 
                        help="Do not use read quality as part of checksum. (--no-quality)"/>
                <param name="noPaired_fastq" type="boolean" checked="false" truevalue="--no-paired"
                        falsevalue=""
                        label="List of fastq files are not paired-end reads?"
                        help="(--no-paired)" />
            </when>
        </conditional>
        <param name="readnames" type="boolean" checked="false" truevalue="--no-readnames"
                falsevalue=""
                label="Ignore readnames?" 
                help="Do not use read names as part of checksum. (--no-readnames)"/>

    </inputs>
    <outputs>
        <data name="output" format="txt" from_work_dir="./output.txt" 
            label="${tool.name} on ${on_string}">
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input_bam" value="Example.bam" ftype="bam"/>
            <param name="tool_choice" value="bam"/>
            <output name="output" file="output1_bam.txt" ftype="txt"/>
        </test>
        <test>
            <param name="input_fasta" value="UnAligSeq24606.fasta" ftype="fasta"/>
            <param name="tool_choice" value="fasta"/>
            <param name="readnames" value="--no-readnames"/>
            <output name="output" file="output2_fasta.txt" ftype="txt"/>
        </test>
        <test>
            <param name="input_fastq" value="1_mismatch.fastq,2_mismatch.fastq" ftype="fastq"/>
            <param name="tool_choice" value="fastq"/>
            <param name="noQuality" value="--no-quality"/>
            <output name="output" file="output3_fastq.txt" ftype="txt"/>
        </test>
        <test>
            <param name="input_fastq" value="1_mismatch.fastq,2_mismatch.fastq" ftype="fastq"/>
            <param name="tool_choice" value="fastq"/>
            <output name="output" file="output4_fastq.txt" ftype="txt"/>
        </test>
    </tests>
    <help><![CDATA[

**WHAT IT DOES**

Hash BAM and FASTQ files to verify data integrity

For each pair of reads in a BAM or FASTQ file we compute a hash value composed of the readname,
whether it is first or last in pair, sequence and quality value. All the hash values are summed
up so the result is independent of the ordering within the files. The result can be compared to
verify that the pair of FASTQ files contain the same read information as the aligned BAM file.

-----

**BAM**

processes a number of BAM files. BAM files are assumed to contain paired end reads.
If you run with --no-paired it treats all reads as single end and displays a warning if any read is marked as "second in pair" in the BAM file.

-----

**FASTA**

processes a number of FASTA files. All FASTA files are assumed to be single end reads with no quality information.
To compare to a BAM file, run bamhash_checksum_bam --no-paired --no-quality

-----


**FASTQ**

processes a number of FASTQ files. FASTQ files are assumed to contain paired end reads,
such that the first two files contain the first pair of reads, etc. If any of the read names in the two pairs don't match the program exits with failure.


-----


**BamHash** is a Free and Open Source Software, see more details on the BamHash github_ Website.

.. _github: https://github.com/DecodeGenetics/BamHash

    ]]></help>
    <citations>
    </citations>
</tool>