Mercurial > repos > jasper > dna_protein_transle
changeset 0:a55eb751d2d8 draft
Uploaded
| author | jasper |
|---|---|
| date | Tue, 09 May 2017 13:09:07 -0400 |
| parents | |
| children | 2513dbc3385d |
| files | test-data/._demo_protein.fasta test-data/demo_nucs.fasta test-data/demo_protein.fasta translate.py translate.xml |
| diffstat | 5 files changed, 81 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/demo_nucs.fasta Tue May 09 13:09:07 2017 -0400 @@ -0,0 +1,6 @@ +>Alpha +GATGAGGAACGA +>Beta +GATGAGCGT +>Gamma +GATCGG
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/demo_protein.fasta Tue May 09 13:09:07 2017 -0400 @@ -0,0 +1,9 @@ +>Alpha +DEER + +>Beta +DER + +>Gamma +DR +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/translate.py Tue May 09 13:09:07 2017 -0400 @@ -0,0 +1,35 @@ +import sys +import warnings +import argparse +from Bio import SeqIO, SeqRecord, BiopythonWarning +from Bio.Seq import Seq +from Bio.Alphabet import IUPAC + + +warnings.simplefilter("ignore", BiopythonWarning) +parser = argparse.ArgumentParser(description="Translation") +parser.add_argument('-r', action='store', dest='read_frame', type=int) +parser.add_argument('-i', action='store', dest='input_file') +parser.add_argument('-o', action='store', dest='output_file') + +inputs = parser.parse_args() +with open(inputs.output_file, 'w') as f: + for seq_record in SeqIO.parse(inputs.input_file, 'fasta'): + seqid = seq_record.id + name=seq_record.name + description = seq_record.description + if inputs.read_frame > 0: + seq_record = seq_record[(inputs.read_frame - 1):] + elif inputs.read_frame == -1: + seq_record = seq_record.reverse_complement() + elif inputs.read_frame == -2: + seq_record = seq_record.reverse_complement() + seq_record = seq_record[2:] + elif inputs.read_frame == -3: + seq_record = seq_record.reverse_complement() + seq_record = seq_record[1:] + dna = Seq(str(seq_record.seq), IUPAC.ambiguous_dna) + protein = SeqRecord.SeqRecord(seq=dna.translate(), id=seqid, name=name, description=description) + SeqIO.write(protein, f, 'fasta') + f.write('\n') +f.close()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/translate.xml Tue May 09 13:09:07 2017 -0400 @@ -0,0 +1,31 @@ +<tool id="dna_protein_transle" name="Translate DNA to protein" version="1.0"> + <description>Translate nucleic acid to protein </description> + <requirements> + <requirement type="package" version="1.69">biopython</requirement> + <requirement type="python-module">Bio</requirement> + </requirements> + <command interpreter="python" > + translate.py -i $dna -o $output -r $read_frame + </command> + <inputs> + <param name="dna" type="data" format="fasta" label="DNA fasta file" help="DNA fasta file" /> + <param name="read_frame" type="select" label="Choose a read frame"> + <option value="1">1</option> + <option value="2">2</option> + <option value="3">3</option> + <option value="-1">-1</option> + <option value="-2">-2</option> + <option value="-3">-3</option> + </param> + </inputs> + <outputs> + <data name="output" type="data" format="fasta"/> + </outputs> + <tests> + <test> + <param name="dna" file="demo_nucs.fasta" /> + <param name="read_frame" type="select" value="1" /> + <output name="output" file="demo_protein.fasta" /> + </test> + </tests> +</tool>