view tools/seq_composition/seq_composition.xml @ 3:7a26bb458806 draft

v0.0.4 using Biopython 1.67 via Tool Shed or (Bio)Conda

<tool id="seq_composition" name="Sequence composition" version="0.0.4">
    <description>Count bases or amino-acids</description>
    <requirements>
        <requirement type="package" version="1.67">biopython</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>
    <version_command interpreter="python">seq_composition.py --version</version_command>
    <command interpreter="python">
seq_composition.py -o "$output_file"
##For loop over inputs
#for i in $input_file
--$i.ext "${i}"
#end for
    </command>
    <inputs>
        <param name="input_file" type="data" format="fasta,fastq,sff" multiple="true" label="Sequence file" help="FASTA, FASTQ, or SFF format." />
    </inputs>
    <outputs>
        <data name="output_file" format="tabular" label="Sequence composition ${on_string}"/>
    </outputs>
    <tests>
        <test>
            <param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />
            <output name="output_file" file="four_human_proteins.seq_composition.tabular" ftype="tabular" />
        </test> 
        <test>
            <param name="input_file" value="ecoli.fastq" ftype="fastq" />
            <output name="output_file" file="ecoli.seq_composition.tabular" ftype="tabular" />
        </test>
        <test>
            <param name="input_file" value="ecoli.fastq" ftype="fastqsanger" />
            <output name="output_file" file="ecoli.seq_composition.tabular" ftype="tabular" />
        </test>
        <test>
            <param name="input_file" value="MID4_GLZRM4E04_rnd30_frclip.sff" ftype="sff" />
            <output name="output_file" file="MID4_GLZRM4E04_rnd30_frclip.seq_composition.tabular" ftype="tabular"/>
        </test>
    </tests>
    <help>
**What it does**

Takes input files of sequences (typically FASTA or FASTQ, but also
Standard Flowgram Format (SFF) is supported), counts all the letters
in each sequence, and returns a summary table of their counts and
percentages.

**Citation**

This tool uses Biopython, so if you use this Galaxy tool in work leading to a
scientific publication please cite the following paper:

Cock et al (2009). Biopython: freely available Python tools for computational
molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878.

This tool is available to install into other Galaxy Instances via the Galaxy
Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/seq_composition
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btp163</citation>
    </citations>
</tool>