Mercurial > repos > peterjc > seq_rename
diff tools/filters/seq_rename.xml @ 0:a4b9836f8f47
Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
author | peterjc |
---|---|
date | Tue, 07 Jun 2011 17:43:26 -0400 |
parents | |
children | 9c8c5079c8af |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/filters/seq_rename.xml Tue Jun 07 17:43:26 2011 -0400 @@ -0,0 +1,56 @@ +<tool id="seq_rename" name="Rename sequences" version="0.0.1"> + <description>with ID mapping from a tabular file</description> + <command interpreter="python"> +seq_rename.py $input_tabular $old_column $new_column $input_file $input_file.ext $output_file + </command> + <inputs> + <param name="input_file" type="data" format="fasta,qual,fastq,sff" label="Sequence file" help="FASTA, QUAL, FASTQ, or SFF format." /> + <param name="input_tabular" type="data" format="tabular" label="Tabular file containing sequence identifiers"/> + <param name="old_column" type="data_column" data_ref="input_tabular" multiple="False" numerical="False" label="Column containing current (old) sequence identifiers"/> + <param name="new_column" type="data_column" data_ref="input_tabular" multiple="False" numerical="False" label="Column contai +ning new sequence identifiers"/> + </inputs> + <outputs> + <data name="output_file" format="fasta" label="Renamed ${on_string}"> + <!-- 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) where the sequence identifiers have been +renamed according two the specified columns a the tabular file. + +WARNING: If you have any duplicates in the intput sequence file, you will still +have duplicate sequences in the output. + +WARNING: If the tabular file has more than one new name for any old ID, the +last one is used. + +**Citation** + +This tool uses Biopython to read and write SFF 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>