Mercurial > repos > bgruening > find_subsequences
view find_subsequences.xml @ 0:9bc84bbab418 draft
Uploaded
author | bgruening |
---|---|
date | Thu, 19 Mar 2015 09:40:43 -0400 |
parents | |
children | decaf3f8fec9 |
line wrap: on
line source
<tool id="bg_find_subsequences" name="Subsequence search" version="0.1"> <description>providing regions in BED format</description> <requirements> <requirement type="package" version="1.6.5">biopyhon</requirement> </requirements> <command interpreter="python"> <![CDATA[ find_subsequences.py --input $input --output $output --pattern "$pattern" #if $input.ext == 'fasta': --format 'fasta' #else: --format 'fastq' #end if ]]> </command> <inputs> <param format="fasta,fastq" name="input" type="data" label="Sequence to be searched" help="This can be in FASTA or FASTQ format." /> <param name="pattern" type="text" value="" label="Search pattern" help="For example GGATCC for BamH1."> <validator type="regex" message="Only letters are allowed.">^[a-zA-Z]+$</validator> </param> </inputs> <outputs> <data format="bed" name="output" /> </outputs> <tests> <test> <param name="input" value="find_subsequences_input1.fasta" ftype="fasta"/> <param name="pattern" value="atcg"/> <output name="output" file="find_subsequences_simple_result1.bed" ftype="bed"/> </test> <test> <param name="input" value="find_subsequences_input1.fasta" ftype="fasta"/> <param name="pattern" value="atnncg"/> <output name="output" file="find_subsequences_advanced_result1.bed" ftype="bed"/> </test> </tests> <help> <![CDATA[ **What it does** Searches for a subsequence in a larger sequence. For example to get all restriction enzymes for BamH1. If you are searching in a DNA sequence you can use ambiguous values using the standard `nucleotide ambiguity code <http://www.dnabaser.com/articles/IUPAC%20ambiguity%20codes.html>`_. This tool is searching on both strands. ]]> </help> <citations> <citation type="doi">10.1093/bioinformatics/btp163</citation> </citations> </tool>