annotate rgFastQC.xml @ 15:2b0c9d9fc6ca draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 35d722c0cafe2a2f2e4e2f73c265ae56ae237997

<tool id="fastqc" name="FastQC" version="0.70">
    <description>Read Quality reports</description>
    <requirements>
        <requirement type="package" version="0.11.5">fastqc</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #import re
        #set input_name = re.sub('[^\w\-\s]', '_', str($input_file.element_identifier))
        
        #if $input_file.ext.endswith('.gz'):
            #set input_file_sl = $input_name + '.gz'
        #elif $input_file.ext.endswith('.bz2'):
            #set input_file_sl = $input_name + '.bz2'
        #else
            #set input_file_sl = $input_name
        #end if

        #if 'bam' in $input_file.ext:
            #set format = 'bam'
        #elif 'sam' in $input_file.ext:
            #set format = 'sam'
        #else
            #set format = 'fastq'
        #end if


        ln -s '${input_file}' '${input_file_sl}' &&
        mkdir -p '${html_file.files_path}' &&
        fastqc
            --outdir '${html_file.files_path}'
            
            #if $contaminants.dataset and str($contaminants) > ''
                --contaminants '${contaminants}'
            #end if
            
            #if $limits.dataset and str($limits) > ''
                --limits '${limits}'
            #end if
            
            --quiet
            --extract
            -f '${format}'
            '${input_file_sl}'

        && cp '${html_file.files_path}'/*/fastqc_data.txt output.txt
        && cp '${html_file.files_path}'/*\.html output.html

    ]]></command>
    <inputs>
        <param format="fastq,fastq.gz,fastq.bz2,bam,sam" name="input_file" type="data"
               label="Short read data from your current history" />
        <param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list"
               help="tab delimited file with 2 columns: name and sequence.  For example: Illumina Small RNA RT Primer CAAGCAGAAGACGGCATACGA" />
        <param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file"
               help="a file that specifies which submodules are to be executed (default=all) and also specifies the thresholds for the each submodules warning parameter" />
    </inputs>
    <outputs>
        <data format="html" name="html_file" from_work_dir="output.html" label="${tool.name} on ${on_string}: Webpage" />
        <data format="txt" name="text_file"  from_work_dir="output.txt" label="${tool.name} on ${on_string}: RawData" />
    </outputs>
    <tests>
        <test>
            <param name="input_file" value="1000gsample.fastq" />
            <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" />
            <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/>
            <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="2"/>
        </test>
        <test>
            <param name="input_file" value="1000gsample.fastq" />
            <param name="limits" value="fastqc_customlimits.txt" ftype="txt" />
            <output name="html_file" file="fastqc_report2.html" ftype="html" compare="sim_size" delta="4096"/>
            <output name="text_file" file="fastqc_data2.txt" ftype="txt" lines_diff="2"/>
        </test>
        <test>
            <param name="input_file" value="1000gsample.fastq.gz" ftype="fastq.gz" />
            <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" />
            <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/>
            <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="2"/>
        </test>
        <test>
            <param name="input_file" value="1000gsample.fastq.bz2" ftype="fastq.bz2" />
            <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" />
            <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/>
            <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="2"/>
        </test>
        <test>
            <param name="input_file" value="hisat_output_1.bam" ftype="bam" />
            <output name="html_file" file="fastqc_report_hisat.html" ftype="html" lines_diff="100"/>
            <output name="text_file" file="fastqc_data_hisat.txt" ftype="txt" lines_diff="2"/>
        </test>
    </tests>
    <help>
.. class:: infomark

**Purpose**

FastQC aims to provide a simple way to do some quality control checks on raw
sequence data coming from high throughput sequencing pipelines.
It provides a modular set of analyses which you can use to give a quick
impression of whether your data has any problems of
which you should be aware before doing any further analysis.

The main functions of FastQC are:

- Import of data from BAM, SAM or FastQ/FastQ.gz files (any variant),
- Providing a quick overview to tell you in which areas there may be problems
- Summary graphs and tables to quickly assess your data
- Export of results to an HTML based permanent report
- Offline operation to allow automated generation of reports without running the interactive application

-----

.. class:: infomark

**FastQC**

This is a Galaxy wrapper. It merely exposes the external package FastQC_ which is documented at FastQC_
Kindly acknowledge it as well as this tool if you use it.
FastQC incorporates the Picard-tools_ libraries for SAM/BAM processing.

The contaminants file parameter was borrowed from the independently developed
fastqcwrapper contributed to the Galaxy Community Tool Shed by J. Johnson.
Adaption to version 0.11.2 by T. McGowan.

-----

.. class:: infomark

**Inputs and outputs**

FastQC_ is the best place to look for documentation - it's very good.
A summary follows below for those in a tearing hurry.

This wrapper will accept a Galaxy fastq, fastq.gz, sam or bam as the input read file to check.
It will also take an optional file containing a list of contaminants information, in the form of
a tab-delimited file with 2 columns, name and sequence. As another option the tool takes a custom
limits.txt file that allows setting the warning thresholds for the different modules and also specifies
which modules to include in the output.

The tool produces a basic text and a HTML output file that contain all of the results, including the following:

- Basic Statistics
- Per base sequence quality
- Per sequence quality scores
- Per base sequence content
- Per base GC content
- Per sequence GC content
- Per base N content
- Sequence Length Distribution
- Sequence Duplication Levels
- Overrepresented sequences
- Kmer Content

All except Basic Statistics and Overrepresented sequences are plots.
 .. _FastQC: http://www.bioinformatics.babraham.ac.uk/projects/fastqc/
 .. _Picard-tools: https://broadinstitute.github.io/picard/
    </help>
    <citations>
        <citation type="bibtex">
        @unpublished{andrews_s,
            author = {Andrews, S.},
            keywords = {bioinformatics, ngs, qc},
            priority = {2},
            title = {{FastQC A Quality Control tool for High Throughput Sequence Data}},
            url = {http://www.bioinformatics.babraham.ac.uk/projects/fastqc/}
        }
        </citation>
    </citations>
</tool>