Mercurial > repos > artbio > cherry_pick_fasta

comparison cherry_pick_fasta.py @ 6:d8fa616a228a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/cherry_pick_fasta commit 8384f1bb5378232bbe78319e06a3522674c7c1fe"
author artbio
date Fri, 08 Apr 2022 16:56:42 +0000
parents ba6c4aeb22ea
children 6c0aefd9fee3
comparison
equal deleted inserted replaced
5:144b856e926c 6:d8fa616a228a
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3 # Chery pick of fasta sequences satisfying a query string in their header/name
4 import argparse 1 import argparse
5
6 from Bio import SeqIO
7 2
8 3
9 def Parser(): 4 def Parser():
10 the_parser = argparse.ArgumentParser( 5 the_parser = argparse.ArgumentParser(
11 description='Cherry pick fasta sequences') 6 description='Cherry pick fasta sequences')
66 querylist.append(line.rstrip()) 61 querylist.append(line.rstrip())
67 return querylist 62 return querylist
68 63
69 64
70 def buid_fasta_dict(fasta): 65 def buid_fasta_dict(fasta):
71 seq_dict = {rec.id: rec.seq for rec in SeqIO.parse(fasta, "fasta")} 66 seq_dict = dict()
67 f = open(fasta, 'r')
68 content = f.read()
69 segmented_content = content.split('>')
70 segmented_content = segmented_content[1:]
71 for seq in segmented_content:
72 sliced_seq = seq.split('\n')
73 header = sliced_seq[0]
74 sliced_seq = sliced_seq[1:]
75 sequence = ''.join(sliced_seq)
76 seq_dict[header] = sequence
72 return seq_dict 77 return seq_dict
73 78
74 79
75 def write_fasta_result(fasta_dict, file): 80 def write_fasta_result(fasta_dict, file):
76 line_length = 60 81 line_length = 60