-
Notifications
You must be signed in to change notification settings - Fork 1
/
nfeat.py
135 lines (115 loc) · 2.9 KB
/
nfeat.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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
# -*- coding: utf-8 -*-
"""
Created on Tue Jul 14 10:44:18 2020
@author: Megha Mathur
"""
from ml_run import *
import argparse
import warnings
from collections import defaultdict
import pandas as pd
import os
def allp(k):
n =['A','T','C','G']
s=[]
if (k==1):
return n
elif(k==2):
for i in n:
for j in n:
se = i+j
if (se not in s):
s.append(se)
return s
elif(k==3):
for i in n:
for j in n:
for k in n:
se = i+j+k
if (se not in s):
s.append(se)
return s
elif(k==4):
for i in n:
for j in n:
for k in n:
for l in n:
se = i+j+k+l
if (se not in s):
s.append(se)
return s
def kmer(k,seq,order):
s=[]
for i in range(len(seq)):
se=""
if (i+k > len(seq)):
break
for j in range(k):
if i+(j*order)>=len(seq):
break
else:
se = se+seq[i+(j*order)]
if len(se)<k:
break
s.append(se)
return s
def k_mer_comp(f1,k,order,dict_n):
a=allp(k)
rs = kmer(k,f1,order)
#calculating basic k-mer composition
for i in a:
ct =(rs.count(i)/len(rs))*100
dict_n[i].append(ct)
def calcNfeat(f1):
k = 3
order = int(1)
dict_n = defaultdict(list)
a=allp(k)
filename, file_extension = os.path.splitext(f1)
cdk = pd.DataFrame()
if(file_extension==""):
f1=f1.upper()
alphabet=['A','C','G','T']
for i in f1:
if i not in alphabet:
print("Invalid Character found in the given sequence")
exit()
k_mer_comp(f1,k,order,dict_n)
s = []
s.append(f1)
if 'Sequence' not in cdk.columns:
cdk['Sequence']=s
for i in a:
cdk["CDK_"+i]= dict_n[i]
# cdk.to_csv(out,index=False)
computeML(cdk)
else:
f=open(f1,"r")
b= f.readlines()
sequence=[]
s_id =[]
s=""
f.close()
for i in b:
if i[0] == '>':
i=i.split("\n")
s_id.append(i[0])
if s!= "":
sequence.append(s)
s=""
else:
continue
else:
for j in i:
j=j.capitalize()
if(j in ['A','G','C','T']):
s = s+j
if s!="":
sequence.append(s)
for i in sequence:
k_mer_comp(i,k,order,dict_n)
if 'Sequence_ID' not in cdk.columns:
cdk['Sequence_ID'] = s_id
for i in a:
cdk["CDK_"+i]= dict_n[i]
computeML(cdk)