Mercurial > repos > stephenshank > abayesqr
diff parse_output.py @ 0:598c3e720567 draft default tip
planemo upload commit 4a2876135fca2f46ffa6451e463eb167a0b51b65
author | stephenshank |
---|---|
date | Thu, 21 Mar 2019 12:47:00 -0400 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/parse_output.py Thu Mar 21 12:47:00 2019 -0400 @@ -0,0 +1,27 @@ +import os + +from Bio.Seq import Seq +from Bio.SeqRecord import SeqRecord +from Bio import SeqIO + + +def parse_abayesqr_output(input_text, output_fasta): + wd = os.path.join(os.getcwd()) + with open(os.path.join(wd, input_text)) as input_file: + lines = input_file.readlines() + records = [] + for i, line in enumerate(lines): + if i % 2 == 0: + freq = float(line.split()[-1]) + number = int(i/2)+1 + header = 'haplotype-%d_freq-%f' % (number, freq) + else: + seq = Seq(line.strip()) + record = SeqRecord(seq, id=header, description='') + records.append(record) + SeqIO.write(records, os.path.join(wd, output_fasta), 'fasta') + + +if __name__ == '__main__': + parse_abayesqr_output("test_ViralSeq.txt", "haplotypes.fasta") +