-
Notifications
You must be signed in to change notification settings - Fork 0
/
nt2aa.py
362 lines (348 loc) · 6.52 KB
/
nt2aa.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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
# Nucleotide to Amino Acid Translator
# Input file must be cluster count csv file with the following fields: gene,pos,base,A,C,G,T,N,
# These input files contain the total read counts for each nucleotide type
# Usage: python nt2aa.py -i inputfile.csv -o outputfile.csv -s start_pos_value -t threshold_aa_proportion_display
# if the -v TRUE option is used the codon preference details are displayed in the output file
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("-t", "--treshold", help="file input name")
parser.add_argument("-s", "--start_position", help="date to filter data and get most cookie active")
parser.add_argument("-i", "--file_to_process", help="date to filter data and get most cookie active")
parser.add_argument("-o", "--output_file_name", help="date to filter data and get most cookie active")
parser.add_argument("-v", "--verbose", help="date to filter data and get most cookie active")
cases={"1":"2","2":"0","0":"1"}
args = parser.parse_args()
r=int(cases[str(int(args.start_position)%3)])
print(int(args.start_position)%3)
cols="""gene
pos
sorted
AAA
AAC
AAG
AAT
ACA
ACC
ACG
ACT
AGA
AGC
AGG
AGT
ATA
ATC
ATG
ATT
CAA
CAC
CAG
CAT
CCA
CCC
CCG
CCT
CGA
CGC
CGG
CGT
CTA
CTC
CTG
CTT
GAA
GAC
GAG
GAT
GCA
GCC
GCG
GCT
GGA
GGC
GGG
GGT
GTA
GTC
GTG
GTT
TAA
TAC
TAG
TAT
TCA
TCC
TCG
TCT
TGA
TGC
TGG
TGT
TTA
TTC
TTG
TTT
A
C
D
E
F
G
H
I
K
L
M
N
P
Q
R
S
T
V
W
X
Y
ref
alt""".split("\n")
verbos="""gene
pos
AAA
AAC
AAG
AAT
ACA
ACC
ACG
ACT
AGA
AGC
AGG
AGT
ATA
ATC
ATG
ATT
CAA
CAC
CAG
CAT
CCA
CCC
CCG
CCT
CGA
CGC
CGG
CGT
CTA
CTC
CTG
CTT
GAA
GAC
GAG
GAT
GCA
GCC
GCG
GCT
GGA
GGC
GGG
GGT
GTA
GTC
GTG
GTT
TAA
TAC
TAG
TAT
TCA
TCC
TCG
TCT
TGA
TGC
TGG
TGT
TTA
TTC
TTG
TTT
A
C
D
E
F
G
H
I
K
L
M
N
P
Q
R
S
T
V
W
X
Y
ref
alt""".split("\n")
table = {
"ATA":"I", "ATC":"I", "ATT":"I", "ATG":"M",
"ACA":"T", "ACC":"T", "ACG":"T", "ACT":"T",
"AAC":"N", "AAT":"N", "AAA":"K", "AAG":"K",
"AGC":"S", "AGT":"S", "AGA":"R", "AGG":"R",
"CTA":"L", "CTC":"L", "CTG":"L", "CTT":"L",
"CCA":"P", "CCC":"P", "CCG":"P", "CCT":"P",
"CAC":"H", "CAT":"H", "CAA":"Q", "CAG":"Q",
"CGA":"R", "CGC":"R", "CGG":"R", "CGT":"R",
"GTA":"V", "GTC":"V", "GTG":"V", "GTT":"V",
"GCA":"A", "GCC":"A", "GCG":"A", "GCT":"A",
"GAC":"D", "GAT":"D", "GAA":"E", "GAG":"E",
"GGA":"G", "GGC":"G", "GGG":"G", "GGT":"G",
"TCA":"S", "TCC":"S", "TCG":"S", "TCT":"S",
"TTC":"F", "TTT":"F", "TTA":"L", "TTG":"L",
"TAC":"Y", "TAT":"Y", "TAA":"X", "TAG":"X",
"TGC":"C", "TGT":"C", "TGA":"X", "TGG":"W",
}
import pandas
import os
mylist=" AAA, AAC, AAG, AAT, ACA, ACC, ACG, ACT, AGA, AGC, AGG, AGT, ATA, ATC, ATG, ATT, CAA, CAC, CAG, CAT, CCA, CCC, CCG, CCT, CGA, CGC, CGG, CGT, CTA, CTC, CTG, CTT, GAA, GAC, GAG, GAT, GCA, GCC, GCG, GCT, GGA, GGC, GGG, GGT, GTA, GTC, GTG, GTT, TAA, TAC, TAG, TAT, TCA, TCC, TCG, TCT, TGA, TGC, TGG, TGT, TTA, TTC, TTG, TTT"
mylist1="""A = GCA + GCC + GCG + GCT
C = TGC + TGT
D = GAC + GAT
E = GAA + GAG
F = TTC + TTT
G = GGA + GGC + GGG + GGT
H = CAC + CAT
I = ATA + ATC + ATT
K = AAA + AAG
L = CTA + CTC + CTG + CTT + TTA + TTG
M = ATG
N = AAC + AAT
P = CCA + CCC + CCG + CCT
Q = CAA + CAG
R = CGA + CGC + CGG + CGT + AGA + AGG
S = AGC + AGT + TCA + TCC + TCG + TCT
T = ACA + ACC + ACG + ACT
V = GTA + GTC + GTG + GTT
W = TGG
X = TAA + TAG+ TGA
Y = TAC + TAT"""
for u in [args.file_to_process]: #os.listdir("datas")
#topics_data = pd.DataFrame(new)
p=0
df = pandas.read_csv(u)
#df=df[16:len(df)-int(len(df)/3)]
df=df[df["pos"]>int(args.start_position)]
pi=[]
for pa in "ACGTN":
df["P("+pa+")"]=(df[pa]/(df["A"]+df["C"]+df["G"]+df["T"]+df["N"])).round(3)
pi.append("P("+pa+")")
pi.append(pa)
for comb in mylist.split(","):
pi.append(comb[1:])
comb=comb[1:]
print(comb)
#df["P("+comb[0]+")"]=list(range(len(df["P("+comb[0]+")"])))
#if not el=="A":
# df["P("+el+")"]=list(range(len(somme)))
new=[]
new.extend(df["P("+comb[1]+")"])
new.extend([0])
new1=[]
new1.extend(df["P("+comb[2]+")"])
new1.extend([0,0])
bb1=[]
bb1.extend(df["base"])
bb1.extend([""])
bb2=[]
bb2.extend(df["base"])
bb2.extend(["",""])
b=[]
b.extend(df["base"]+bb1[1:]+bb2[2:])
#b.extend(["",""])
df["ref"]=b
nu=[]
nu.extend((df["P("+comb[0]+")"]*new1[2:]*new[1:]).round(3))
nu.extend([0.000,0.00])
li=[1.000,0.000,0.000]*(int(len(nu[2:])/3)+1)
df[comb]=nu[:-2]
df[comb]=df[comb]*li[0:len(df[comb])]
els=[]
for line in mylist1.split("\n"):
newd=line.split("=")[0].replace(" ","")[0]
els.append(newd)
ops=line.split("=")[1].split("+")
df[newd]=df[ops[0].replace(" ","")]
for el in ops[1:]:
df[newd]= (df[newd]+ df[el.replace(" ","")]).round(3)
df["newcol1"]=df[els].max(axis=1)
df["alt"]=df[els].idxmax(axis="columns")
tx=(df['pos']%3 ==r )
emp=[]
emp.extend(pi)
emp.extend(els)
emp.append("ref")
emp.append("alt")
emp.append("sorted")
def add(arg):
def floating(a):
tt=args.treshold
a0=int(a[0]*1000)/1000
a1=a[1]
return a0,a1
def get_proba(a):
return a[0]
arg=list(map(floating,arg))
arg.sort(key=get_proba,reverse=True)
return arg
def itere(row):
return add(list(zip(list(map(row.get,els)),els)))
df['sorted'] = df.apply(itere , axis = 1)
rr=len(df['sorted'])
llo=list(range(2,(len(els)+3)*20000))
df = df[cols]
bahaee=[]
for i in range(len(els)):
try:
def getit(row):
tt=args.treshold
res=row.get("sorted")[i]
#print(res[0],eval(tt))
if res[0]>eval(tt):
return res
else:
return ""
bahae=" "*i
df[bahae] = df.apply(getit , axis = 1)
bahaee.append(bahae)
except Exception as eror:
print(eror)
conteur=0
verbos.extend(bahaee)
try:
if args.verbose:
df=df[verbos]
print(111111111111111)
else:
newi=["gene","pos","ref","alt"]
newi.extend(bahaee)
df=df[newi]
except:
print("looooooooooooooooool")
newi=["gene","pos","ref","alt"]
newi.extend(bahaee)
df=df[newi]
for el,val in list(table.items()):
df.loc[df['ref']==el.lower(),"ref"]=val
#
new=df[tx]
new['pos'] = range(1,len(new['pos'])+1)
new.to_csv(args.output_file_name, index=False)