# HG changeset patch # User drosofff # Date 1433804107 14400 # Node ID 726b1e233a08e731e6fd1ae111ed19a553a36810 planemo upload for repository https://bitbucket.org/drosofff/gedtools/ diff -r 000000000000 -r 726b1e233a08 cherry_pick_fasta.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cherry_pick_fasta.py Mon Jun 08 18:55:07 2015 -0400 @@ -0,0 +1,36 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +""" +Chery pick of fasta sequences satisfying a query string in their header/name +""" + +import argparse + +def Parser(): + the_parser = argparse.ArgumentParser( + description="Cherry pick fasta sequences") + the_parser.add_argument( + '--input', action="store", type=str, help="input fasta file") + the_parser.add_argument( + '--query-string', dest="query_string", action="store", type=str, + help="header containing the string will be extracted as well as the corresponding sequence") + the_parser.add_argument( + '--output', action="store", type=str, help="output fasta file") + args = the_parser.parse_args() + return args + +def __main__(): + """ main function """ + args = Parser() + search_term = args.query_string + CrudeFasta = open (args.input, "r").read() + Output = open (args.output, "w") + FastaListe = CrudeFasta.split(">") + for sequence in FastaListe: + if search_term in sequence: + print >> Output, ">%s" % sequence.rstrip() + Output.close() + + +if __name__ == "__main__": + __main__() diff -r 000000000000 -r 726b1e233a08 cherry_pick_fasta.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cherry_pick_fasta.xml Mon Jun 08 18:55:07 2015 -0400 @@ -0,0 +1,47 @@ + + with header satisfying a query string + cherry_pick-fasta.py + --input "$input" + --query-string $query + --output $output + + + + + + + + + + + + + + + + + + + + + + + + + + + + +**What it does** + +This tool retrieves nucleotide/peptide sequences from a fasta file whose headers match a given query string + +It is Copyright © 2015 `CNRS and University Pierre et Marie Curie`_ and is released under the `MIT license`_. + +.. _MIT license: http://opensource.org/licenses/MIT + + + + + + diff -r 000000000000 -r 726b1e233a08 test-data/input.fa diff -r 000000000000 -r 726b1e233a08 test-data/output.fa