Mercurial > repos > mons > genbanktofasta
changeset 0:6b5153d02ac2 draft
Uploaded
author | mons |
---|---|
date | Sat, 01 Nov 2014 10:34:38 -0400 |
parents | |
children | a5ef7a9e5cb7 |
files | README.txt genbanktofasta.py genbanktofasta.xml repository_dependencies.xml |
diffstat | 4 files changed, 109 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.txt Sat Nov 01 10:34:38 2014 -0400 @@ -0,0 +1,15 @@ + +---------------- +GenBank to FASTA +---------------- + +This package contains the GenBank to FASTA converter. + +-------------------------------------------------------------------- +Instructions for integration of the "GenBank to FASTA" tool into the workflow-system +Galaxy (http://getgalaxy.org) +-------------------------------------------------------------------- + +For best results, we recommand you to install it via the toolshed. + +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/genbanktofasta.py Sat Nov 01 10:34:38 2014 -0400 @@ -0,0 +1,40 @@ +#!/usr/bin/env python +""" +Input: genbank file +Output: fasta nucleotide or protein sequences +This bit of code will record the full DNA nucleotide sequence for each record in the GenBank file as a fasta record. +http://www.warwick.ac.uk/go/peter_cock/python/genbank2fasta/ +""" + +import sys, os +from Bio import SeqIO + + +def __main__(): + + infile = sys.argv[1] + outfile= sys.argv[2] + input_handle = open(infile, "r") + output_handle = open(outfile, "w") + gbk_to_fna(input_handle,output_handle) + + +#Short version: +#SeqIO.write(SeqIO.parse(input_handle, "genbank"), output_handle, "fasta") +#Long version, allows full control of fasta output + +def gbk_to_fna(input_handle,output_handle): + for seq_record in SeqIO.parse(input_handle, "genbank") : + print "Dealing with GenBank record %s" % seq_record.id + output_handle.write(">%s %s\n%s\n" % ( + seq_record.id, + seq_record.description, + seq_record.seq.tostring())) + output_handle.close() + input_handle.close() + print "Done" + + + +if __name__ == "__main__" : __main__() +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/genbanktofasta.xml Sat Nov 01 10:34:38 2014 -0400 @@ -0,0 +1,50 @@ +<tool id="genbank_to_fa" name="Converting GenBank files" version="1.0.0"> + + <!-- [REQUIRED] Tool description displayed after the tool name --> + <description>to Fasta format</description> + + <!-- [OPTIONAL] 3rd party tools, binaries, modules... required for the tool to work --> + <requirements> + <requirement type="binary">python</requirement> + </requirements> + + <command interpreter="python"> + genbanktofasta.py $input $output + </command> + + <!-- [REQUIRED] Input files and tool parameters --> + <inputs> + <param name="input" type="data" format="genbank" label="Your Genbank input file" help="" /> + </inputs> + + <!-- [REQUIRED] Output files --> + <outputs> + <data name="output" format="fasta" label="${input.name}.fasta" /> <!-- Output file of any format --> + </outputs> + + <!-- [STRONGLY RECOMMANDED] Exit code rules --> + <stdio> + <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> + <exit_code range="1:" level="fatal" /> + </stdio> + + + <!-- [OPTIONAL] Help displayed in Galaxy --> + <help> + + +================ +GenBank to Fasta +================ + +----------- +Description +----------- + + | This tool converts a GenBank file to FASTA nucleotides format. + | Reference: http://www.warwick.ac.uk/go/peter_cock/python/genbank2fasta/ + + + </help> + +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/repository_dependencies.xml Sat Nov 01 10:34:38 2014 -0400 @@ -0,0 +1,4 @@ +<?xml version="1.0"?> +<repositories description="GenBank to FASTA tool requires the Galaxy applicable data format GenBank"> + <repository changeset_revision="a4a890259b82" name="genbank_complete_datatype" owner="mons" toolshed="https://testtoolshed.g2.bx.psu.edu" /> +</repositories>