-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.py
60 lines (51 loc) · 1.46 KB
/
utils.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
from itertools import groupby
import screed
import numpy as np
from Bio.Seq import reverse_complement
import os
import pandas as pd
def compl(base):
basedict = {'A':'T', 'T':'A', 'G': 'C', 'C':'G'}
return(basedict.get(base))
def rangedict(accranges):
rng_dict = {}
for r in accranges:
start, end = r
for i in range(start, end+1):
rng_dict[i] = '-'
return rng_dict
def canon(naivekmers):
allkmers = []
for kmer in naivekmers:
canonical_kmer=kmer
rckmer = str(reverse_complement(kmer))
if kmer> rckmer:
canonical_kmer=rckmer
allkmers.append(canonical_kmer)
return allkmers
def build_kmers(sequence, ksize):
kmers = []
naivekmers = [sequence[x:x+ksize].upper() for x in range(len(sequence) - ksize + 1)]
kmers =canon(naivekmers)
return kmers
def read_kmers_from_file(filename, ksize):
all_kmers = []
sequence=''
for record in screed.open(filename):
sequence += record.sequence
all_kmers=build_kmers(sequence, ksize)
return all_kmers
def get_uniques(kmer1set, kmer2set):
kmeruniq = kmer1set - kmer2set
return kmeruniq
def get_ranges(lst):
pos = (j - i for i, j in enumerate(lst))
t = 0
for i, els in groupby(pos):
l = len(list(els))
el = lst[t]
t += l
yield (el, el+l)
def get_indices(kmeruniq, kmers):
indexlist = [i for i, e in enumerate(kmers) if e in kmeruniq]
return indexlist