Mercurial > repos > rnateam > graphclust_preprocessing

comparison splitSHAPE.py @ 11:c0c9d19bc7b2 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/branchForIterations/tools/GraphClust commit 746497a64b955f6b9afc1944d1c1d8d877e53267
author rnateam
date Tue, 18 Jul 2017 01:43:49 -0400
parents 0690d59881b9
children
comparison
equal deleted inserted replaced
10:16bcaef3dc1e 11:c0c9d19bc7b2
1 import os 1 import os
2 import re 2 import re
3 import sys 3 import sys
4 4
5 shape_file = sys.argv[1] 5 shape_file = sys.argv[1]
6 win_size = int(sys.argv[2])
7 6
8 pattern = re.compile("^>.*$") 7 pattern = re.compile("^>.*$")
9 toWrite = "" 8 toWrite = ""
10 9
11 count_for_id = 1 10 count_for_id = 1
16 seq_string = [] 15 seq_string = []
17 orig_id = [] 16 orig_id = []
18 name_file = "FASTA/data.names" 17 name_file = "FASTA/data.names"
19 array_all_chunks = [] 18 array_all_chunks = []
20 with open(name_file, 'r') as f: 19 with open(name_file, 'r') as f:
21 content = f.read() 20 for line in f:
22 lines = content.split('\n')[:-1] 21 if len(line.strip()) == 0:
23 for line in lines: 22 continue
24 seq_id.append(int(line.split()[0])) 23 seq_id.append(int(line.split()[0]))
25 seq_string.append(line.split()[1]) 24 seq_string.append(line.split()[1])
26 orig_id_srt = line.split()[3] 25 orig_id_srt = line.split()[3]
27 orig_id_srt = orig_id_srt.rsplit('_',1)[0] 26 orig_id_srt = orig_id_srt.rsplit('_',1)[0]
28 orig_id.append(orig_id_srt) 27 orig_id.append(orig_id_srt)