Mercurial > repos > peterjc > seq_select_by_id
diff tools/seq_select_by_id/seq_select_by_id.xml @ 4:6842c0c7bc70 draft
Uploaded v0.0.7, depend on Biopython 1.62, tabs to spaces in XML
author | peterjc |
---|---|
date | Mon, 28 Oct 2013 05:21:45 -0400 |
parents | |
children | 91f55ee8fea5 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/seq_select_by_id/seq_select_by_id.xml Mon Oct 28 05:21:45 2013 -0400 @@ -0,0 +1,72 @@ +<tool id="seq_select_by_id" name="Select sequences by ID" version="0.0.6"> + <description>from a tabular file</description> + <requirements> + <requirement type="package" version="1.62">biopython</requirement> + <requirement type="python-module">Bio</requirement> + </requirements> + <version_command interpreter="python">seq_select_by_id.py --version</version_command> + <command interpreter="python"> +seq_select_by_id.py $input_tabular $column $input_file $input_file.ext $output_file + </command> + <stdio> + <!-- Anything other than zero is an error --> + <exit_code range="1:" /> + <exit_code range=":-1" /> + </stdio> + <inputs> + <param name="input_file" type="data" format="fasta,qual,fastq,sff" label="Sequence file to select from" help="FASTA, QUAL, FASTQ, or SFF format." /> + <param name="input_tabular" type="data" format="tabular" label="Tabular file containing sequence identifiers"/> + <param name="column" type="data_column" data_ref="input_tabular" multiple="False" numerical="False" label="Column containing sequence identifiers"/> + </inputs> + <outputs> + <data name="output_file" format="fasta" label="Selected sequences"> + <!-- TODO - Replace this with format="input:input_fastq" if/when that works --> + <change_format> + <when input_dataset="input_file" attribute="extension" value="sff" format="sff" /> + <when input_dataset="input_file" attribute="extension" value="fastq" format="fastq" /> + <when input_dataset="input_file" attribute="extension" value="fastqsanger" format="fastqsanger" /> + <when input_dataset="input_file" attribute="extension" value="fastqsolexa" format="fastqsolexa" /> + <when input_dataset="input_file" attribute="extension" value="fastqillumina" format="fastqillumina" /> + <when input_dataset="input_file" attribute="extension" value="fastqcssanger" format="fastqcssanger" /> + </change_format> + </data> + </outputs> + <tests> + <test> + <param name="input_file" value="k12_ten_proteins.fasta" ftype="fasta" /> + <param name="input_tabular" value="k12_hypothetical.tabular" ftype="tabular" /> + <param name="column" value="1" /> + <output name="output_file" file="k12_hypothetical.fasta" ftype="fasta" /> + </test> + </tests> + <help> +**What it does** + +Takes a FASTA, QUAL, FASTQ or Standard Flowgram Format (SFF) file and produces a +new sequence file (of the same format) containing only the records with identifiers +in the tabular file (in the order from the tabular file). + +WARNING: If you have any duplicates in the tabular file identifiers, you will get +duplicate sequences in the output. + +**References** + +If you use this Galaxy tool in work leading to a scientific publication please +cite the following papers: + +Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013). +Galaxy tools and workflows for sequence analysis with applications +in molecular plant pathology. PeerJ 1:e167 +http://dx.doi.org/10.7717/peerj.167 + +This tool uses Biopython to read, write and index sequence files, so you may +also wish to cite the Biopython application note (and Galaxy too of course): + +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_select_by_id + </help> +</tool>