Mercurial > repos > peterjc > seq_select_by_id
diff tools/filters/seq_select_by_id.xml @ 0:838b9bebfa3c
Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
author | peterjc |
---|---|
date | Tue, 07 Jun 2011 17:43:38 -0400 |
parents | |
children | 50a8a6917a9c |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/filters/seq_select_by_id.xml Tue Jun 07 17:43:38 2011 -0400 @@ -0,0 +1,51 @@ +<tool id="seq_select_by_id" name="Select sequences by ID" version="0.0.1"> + <description>from a tabular file</description> + <command interpreter="python"> +seq_select_by_id.py $input_tabular $column $input_file $input_file.ext $output_file + </command> + <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> + </tests> + <requirements> + <requirement type="python-module">Bio</requirement> + </requirements> + <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. + +**Citation** + +This tool uses Biopython to read, write and index sequence files. If you use +this tool in scientific work leading to a publication, please 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. + + </help> +</tool>