-
Notifications
You must be signed in to change notification settings - Fork 0
/
rosalind_dna.py
400 lines (346 loc) · 10.7 KB
/
rosalind_dna.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
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
import re
import urllib.request
import string
import itertools
# DNA
def counting_dna_nucleotides(dna):
return (dna.count("A"), dna.count("C"), dna.count("G"), dna.count("T"))
# RNA
def transcribing_dna_into_rna(dna):
return dna.replace("T","U")
# REVC
def complementing_a_string_of_dna(dna):
return "".join([ {"A":"T", "T":"A", "C":"G", "G":"C"}[n] for n in dna])[::-1]
# IPRB
def mendels_first_law(k,m,n):
total = k + m + n
Kp = k/total
Mp = ((m/total) * (k/(total-1))) + ((m/total) * ((m-1)/(total-1)) * 0.75) + ((m/total) * (n/(total-1)) * 0.5)
Np = ((n/total) * (k/(total-1))) + ((n/total) * (m/(total-1)) * 0.5)
return Kp + Mp + Np
# FIB
def rabbits_and_recurrense_relations(n , k):
i = 1
C = 0
c = 0
while i <= n:
if i == 1:
C = 0
c = 1
else:
C_aux = C
C = C + c
c = C_aux * k
i += 1
return C + c
# GC
def read_fasta(fasta):
dnas = {}
arquivo = fasta.split(">")
for linha in arquivo:
ls = linha.strip()
if ls:
l = ls.split('\n')
label = l[0]
dna = "".join(l[1:])
dnas[label] = dna
return dnas
def gc_content(dna):
return ((dna.count("G") + dna.count("C")) * 100) / len(dna)
def max_gc_content(filename):
dnas = read_fasta(filename)
max_label = ""
max_dna = ""
max_gc = 0
for label, dna in dnas.items():
gc = gc_content(dna)
if gc > max_gc:
max_gc = gc
max_label = label
max_dna = dna
return max_label, max_dna, max_gc
# PROT
def translating_rna_into_protein(rna):
table = {'UUU':'F', 'CUU':'L', 'AUU':'I',
'GUU':'V', 'UUC':'F', 'CUC':'L',
'AUC':'I', 'GUC':'V', 'UUA':'L',
'CUA':'L', 'AUA':'I', 'GUA':'V',
'UUG':'L', 'CUG':'L', 'AUG':'M',
'GUG':'V', 'UCU':'S', 'CCU':'P',
'ACU':'T', 'GCU':'A', 'UCC':'S',
'CCC':'P', 'ACC':'T', 'GCC':'A',
'UCA':'S', 'CCA':'P', 'ACA':'T',
'GCA':'A', 'UCG':'S', 'CCG':'P',
'ACG':'T', 'GCG':'A', 'UAU':'Y',
'CAU':'H', 'AAU':'N', 'GAU':'D',
'UAC':'Y', 'CAC':'H', 'AAC':'N',
'GAC':'D', 'UAA':'Stop', 'CAA':'Q',
'AAA':'K', 'GAA':'E', 'UAG':'Stop',
'CAG':'Q', 'AAG':'K', 'GAG':'E',
'UGU':'C', 'CGU':'R', 'AGU':'S',
'GGU':'G', 'UGC':'C', 'CGC':'R',
'AGC':'S', 'GGC':'G', 'UGA':'Stop',
'CGA':'R', 'AGA':'R', 'GGA':'G',
'UGG':'W', 'CGG':'R', 'AGG':'R', 'GGG':'G'}
regex = re.compile(r'.{3}')
protein = ""
for n in regex.finditer(rna):
p = table[n.group()]
if p == "Stop":
break
protein += p
return protein
# SUBS
def finding_a_motif_in_dna(motif, dna):
regex = re.compile(r'(?=%s)' % motif)
return [ m.start() + 1 for m in regex.finditer(dna)]
#HAMM
def counting_point_mutations(dna1, dna2):
i = 0
total = 0
while i < len(dna1):
if dna1[i] != dna2[i]:
total += 1
i += 1
return total
#GRAPH
def overlap_graphs(dnas, k):
adj_list = []
for label, dna in dnas.items():
for label2, dna2 in dnas.items():
if label != label2:
if dna[-k:] == dna2[:k]:
adj_list.append([label, label2])
return adj_list
#MPRT
def fetch_uniprot_fasta(protein):
fasta = urllib.request.urlopen("http://www.uniprot.org/uniprot/" + protein + ".fasta")
return fasta.read().decode("utf-8")
def finding_a_protein_motif(protein):
regex = re.compile(r'(?=N[^P][ST][^P])')
return [m.start() + 1 for m in regex.finditer(protein)]
def show_a_protein_motif_position(proteins):
for p in proteins:
dnas = read_fasta(fetch_uniprot_fasta(p))
for label, dna in dnas.items():
positions = finding_a_protein_motif(dna)
if positions:
print(p)
print(" ".join([ str(n) for n in positions ]))
#CONS
def consensus_and_profile(dnas):
profile = {}
for p in ["A", "C", "T", "G"]:
profile[p] = [0 for i in dnas[0]]
for dna in dnas:
for i, n in enumerate(dna):
profile[n][i] += 1
i = 0
consensus = ""
while i < len(profile["A"]):
max_value = 0
p = ""
if profile["A"][i] > max_value:
p = "A"
max_value = profile["A"][i]
if profile["T"][i] > max_value:
p = "T"
max_value = profile["T"][i]
if profile["C"][i] > max_value:
p = "C"
max_value = profile["C"][i]
if profile["G"][i] > max_value:
p = "G"
max_value = profile["G"][i]
consensus += p
i += 1
return profile, consensus
#SPLC
def delete_instrons(dna, introns):
points = []
for i in introns:
regex = re.compile(r'%s' % i)
for m in regex.finditer(dna):
for n in range(m.start(), m.start() + len(i)):
points.append(n)
dna_res = ""
for i, l in enumerate(dna):
if i not in points:
dna_res += l
return dna_res
def read_fasta_list(fasta):
dnas = []
arquivo = fasta.split(">")
for linha in arquivo:
ls = linha.strip()
if ls:
l = ls.split('\n')
dna = "".join(l[1:])
dnas.append(dna)
return dnas
#FIBD
def mortal_fibonacci_rabbits(n , m):
i = 1
C = 0
c = [0]
while i <= n:
if i == 1:
C = 0
c.append(1)
else:
C_aux = C
if i <= m:
C = C + c[i-1]
else:
C = C + c[i-1] - (c[i-m])
c.append(C_aux)
i += 1
return C + c[i-1]
#LCSM
def longest_common_substring(string1, string2):
longest_substring = ""
initial = 0
length = 1
max_length = len(string1)
while True:
if string1[initial:initial+length] in string2:
longest_substring = string1[initial:initial+length]
length += 1
else:
initial += 1
length = len(longest_substring)
if initial + length > max_length:
break
return longest_substring
def finding_a_shared_motif(dnas):
current_lcs = ""
total_lcs = set()
for i in range(1, len(dnas)):
current_lcs = longest_common_substring(dnas[0], dnas[i])
for j in range(1, len(dnas)):
if not current_lcs in dnas[j]:
current_lcs = longest_common_substring(current_lcs, dnas[j])
total_lcs.add(current_lcs)
return max(total_lcs, key=len)
#SSEQ
def subsequence_indexes(palavra, sub):
indexes = []
init = 0
for l in sub:
init = palavra.find(l,init) + 1
indexes.append(init)
return indexes
#LCSQ
def montar_matriz_lcs(palavra1, palavra2):
matriz = [[ 0 for i in range(len(palavra2) + 1)] for j in range(len(palavra1) + 1)]
for i, a in enumerate(palavra1):
for j, b in enumerate(palavra2):
if a == b:
matriz[i+1][j+1] = matriz[i][j] + 1
else:
matriz[i+1][j+1] = max(matriz[i][j+1], matriz[i+1][j])
return matriz
def descobrir_sequencia(matriz, palavra1, palavra2):
i = len(palavra1) - 1
j = len(palavra2) - 1
sec = ""
while i >= 0 and j >= 0:
if palavra1[i] == palavra2[j]:
sec = sec + palavra1[i]
i -= 1
j -= 1
elif matriz[i][j+1] >= matriz[i+1][j]:
i -= 1
else:
j -= 1
return sec[::-1]
def lcs(palavra1, palavra2):
matriz = montar_matriz_lcs(palavra1, palavra2)
return descobrir_sequencia(matriz, palavra1, palavra2)
def finding_a_shared_spliced_motif(palavra1, palavra2):
return lcs(palavra1, palavra2)
#ORF
def open_reading_frames(rna):
table = {'UUU':'F', 'CUU':'L', 'AUU':'I',
'GUU':'V', 'UUC':'F', 'CUC':'L',
'AUC':'I', 'GUC':'V', 'UUA':'L',
'CUA':'L', 'AUA':'I', 'GUA':'V',
'UUG':'L', 'CUG':'L', 'AUG':'M',
'GUG':'V', 'UCU':'S', 'CCU':'P',
'ACU':'T', 'GCU':'A', 'UCC':'S',
'CCC':'P', 'ACC':'T', 'GCC':'A',
'UCA':'S', 'CCA':'P', 'ACA':'T',
'GCA':'A', 'UCG':'S', 'CCG':'P',
'ACG':'T', 'GCG':'A', 'UAU':'Y',
'CAU':'H', 'AAU':'N', 'GAU':'D',
'UAC':'Y', 'CAC':'H', 'AAC':'N',
'GAC':'D', 'UAA':'Stop', 'CAA':'Q',
'AAA':'K', 'GAA':'E', 'UAG':'Stop',
'CAG':'Q', 'AAG':'K', 'GAG':'E',
'UGU':'C', 'CGU':'R', 'AGU':'S',
'GGU':'G', 'UGC':'C', 'CGC':'R',
'AGC':'S', 'GGC':'G', 'UGA':'Stop',
'CGA':'R', 'AGA':'R', 'GGA':'G',
'UGG':'W', 'CGG':'R', 'AGG':'R', 'GGG':'G'}
start_condons = [i.start() for i in re.finditer('AUG', rna)]
regex = re.compile(r'.{3}')
proteins = set()
for sc in start_condons:
protein = ""
for n in regex.finditer(rna[sc:]):
p = table[n.group()]
if p == "Stop":
if protein:
proteins.add(protein)
break
protein += p
return proteins
def distinct_protein_candidates(dna):
rna = transcribing_dna_into_rna(dna)
dna = complementing_a_string_of_dna(dna)
rna2 = transcribing_dna_into_rna(dna)
return open_reading_frames(rna) | open_reading_frames(rna2)
#PERM
def permutations(number):
return [p for p in itertools.permutations(range(1,number+1))]
#REVP
def reverse_palindrome(dna):
min_length = 4
max_length = 12
l = min_length
i = 0
positions = []
while True:
if i + min_length > len(dna):
break
if dna[i:i+l] == complementing_a_string_of_dna(dna[i:i+l]):
positions.append((i+1,l))
if l == max_length or i + l >= len(dna):
l = min_length
i += 1
else:
l += 1
return positions
#PRTM
def calculating_protein_mass(protein):
table = {'A': 71.03711,
'C': 103.00919,
'D': 115.02694,
'E': 129.04259,
'F': 147.06841,
'G': 57.02146,
'H': 137.05891,
'I': 113.08406,
'K': 128.09496,
'L': 113.08406,
'M': 131.04049,
'N': 114.04293,
'P': 97.05276,
'Q': 128.05858,
'R': 156.10111,
'S': 87.03203,
'T': 101.04768,
'V': 99.06841,
'W': 186.07931,
'Y': 163.06333 }
return sum([table[a] for a in protein])