-
Notifications
You must be signed in to change notification settings - Fork 0
/
debruijin2.py
57 lines (41 loc) · 1.25 KB
/
debruijin2.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
"""
DeBruijn Graph from k-mers Problem: Construct the de Bruijn graph from a set of k-mers.
Input: A collection of k-mers Patterns.
Output: The adjacency list of the de Bruijn graph DeBruijn(Patterns).
Sample Input:
GAGG CAGG GGGG GGGA CAGG AGGG GGAG
Sample Output:
AGG: GGG
CAG: AGG AGG
GAG: AGG
GGA: GAG
GGG: GGA GGG
"""
def debruijin(kmers):
uniques = {}
k = len(kmers[0])
for kmer in kmers:
if kmer[: k-1] not in uniques:
uniques[kmer[: k-1]] = []
if kmer[1:] not in uniques:
uniques[kmer[1:]] = []
for kmer in kmers:
uniques[kmer[: k-1]].append(kmer[1:])
uniques[kmer[: k-1]].sort()
uniques = dict(sorted(uniques.items()))
for key in list(uniques):
if len(uniques[key]) == 0:
del uniques[key]
return uniques
def OutputFormat(txt):
out = []
for key, value in txt.items():
values = " ".join(x for x in value)
out.append(f"{str(key)}: {str(values)}")
return "\n".join(out)
pattern = "GAGG CAGG GGGG GGGA CAGG AGGG GGAG"
inp = pattern.split(" ")
print(OutputFormat(debruijin(inp)))
# data = open("./data/dataset_200_8.txt").read().split()
# with open("./file5.txt", "w") as file:
# file.write(OutputFormat(debruijin(data)))