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
|
#!/usr/bin/python
"""
Returns a bed-like translation of a CDS in which each record corresponds to
a single site in the CDS and includes additional fields for site degenaracy,
position ind CDS, and amino acid encoded.
usage: %prog nibdir genefile [options]
-o, --outfile=o: output file
-f, --format=f: format bed (default), or gtf|gff
-a, --allpositions: 1st, 2nd and 3rd positions are evaluated for degeneracy given the sequence at the other two positions. Many 1d sites in 1st codon positions become 2d sites when considered this way.
-n, --include_name: include the 'name' or 'id' field from the source file on every line of output
"""
import os
import re
import sys
from bx.cookbook import doc_optparse
from bx.gene_reader import CDSReader
from bx.seq import nib
GENETIC_CODE = """
TTT (Phe/F)Phenylalanine
TTC (Phe/F)Phenylalanine
TTA (Leu/L)Leucine
TTG (Leu/L)Leucine, Start
TCT (Ser/S)Serine
TCC (Ser/S)Serine
TCA (Ser/S)Serine
TCG (Ser/S)Serine
TAT (Tyr/Y)Tyrosine
TAC (Tyr/Y)Tyrosine
TAA Ochre (Stop)
TAG Amber (Stop)
TGT (Cys/C)Cysteine
TGC (Cys/C)Cysteine
TGA Opal (Stop)
TGG (Trp/W)Tryptophan
CTT (Leu/L)Leucine
CTC (Leu/L)Leucine
CTA (Leu/L)Leucine
CTG (Leu/L)Leucine, Start
CCT (Pro/P)Proline
CCC (Pro/P)Proline
CCA (Pro/P)Proline
CCG (Pro/P)Proline
CAT (His/H)Histidine
CAC (His/H)Histidine
CAA (Gln/Q)Glutamine
CAG (Gln/Q)Glutamine
CGT (Arg/R)Arginine
CGC (Arg/R)Arginine
CGA (Arg/R)Arginine
CGG (Arg/R)Arginine
ATT (Ile/I)Isoleucine, Start2
ATC (Ile/I)Isoleucine
ATA (Ile/I)Isoleucine
ATG (Met/M)Methionine, Start1
ACT (Thr/T)Threonine
ACC (Thr/T)Threonine
ACA (Thr/T)Threonine
ACG (Thr/T)Threonine
AAT (Asn/N)Asparagine
AAC (Asn/N)Asparagine
AAA (Lys/K)Lysine
AAG (Lys/K)Lysine
AGT (Ser/S)Serine
AGC (Ser/S)Serine
AGA (Arg/R)Arginine
AGG (Arg/R)Arginine
GTT (Val/V)Valine
GTC (Val/V)Valine
GTA (Val/V)Valine
GTG (Val/V)Valine, Start2
GCT (Ala/A)Alanine
GCC (Ala/A)Alanine
GCA (Ala/A)Alanine
GCG (Ala/A)Alanine
GAT (Asp/D)Aspartic acid
GAC (Asp/D)Aspartic acid
GAA (Glu/E)Glutamic acid
GAG (Glu/E)Glutamic acid
GGT (Gly/G)Glycine
GGC (Gly/G)Glycine
GGA (Gly/G)Glycine
GGG (Gly/G)Glycine
"""
def translate(codon, genetic_code):
c1, c2, c3 = codon
return genetic_code[c1][c2][c3]
""" parse the doc string to hash the genetic code"""
GEN_CODE = {}
for line in GENETIC_CODE.split("\n"):
if line.strip() == "":
continue
f = re.split(r"\s|\(|\)|\/", line)
codon = f[0]
c1, c2, c3 = codon
aminoacid = f[3]
if c1 not in GEN_CODE:
GEN_CODE[c1] = {}
if c2 not in GEN_CODE[c1]:
GEN_CODE[c1][c2] = {}
GEN_CODE[c1][c2][c3] = aminoacid
def getnib(nibdir):
seqs = {}
for nibf in os.listdir(nibdir):
if not nibf.endswith(".nib"):
continue
chr = nibf.replace(".nib", "")
file = os.path.join(nibdir, nibf)
seqs[chr] = nib.NibFile(open(file))
return seqs
REVMAP = str.maketrans("ACGTacgt", "TGCAtgca")
def revComp(seq):
return seq[::-1].translate(REVMAP)
def Comp(seq):
return seq.translate(REVMAP)
def main():
options, args = doc_optparse.parse(__doc__)
try:
if options.outfile:
out = open(options.outfile, "w")
else:
out = sys.stdout
if options.format:
format = options.format
else:
format = "bed"
allpositions = bool(options.allpositions)
include_name = bool(options.include_name)
nibdir = args[0]
bedfile = args[1]
except Exception:
doc_optparse.exit()
nibs = getnib(nibdir)
for chrom, strand, cds_exons, name in CDSReader(open(bedfile), format=format):
cds_seq = ""
# genome_seq_index maps the position in CDS to position on the genome
genome_seq_index = []
for c_start, c_end in cds_exons:
cds_seq += nibs[chrom].get(c_start, c_end - c_start)
for i in range(c_start, c_end):
genome_seq_index.append(i)
cds_seq = cds_seq.upper()
if strand == "+":
frsts = range(0, len(cds_seq), 3)
offsign = 1
else:
cds_seq = Comp(cds_seq)
frsts = range(2, len(cds_seq), 3)
offsign = -1
offone = 1 * offsign
offtwo = 2 * offsign
all = ["A", "C", "G", "T"]
for first_pos in frsts:
c1 = first_pos
c2 = first_pos + offone
c3 = first_pos + offtwo
try:
assert c3 < len(cds_seq)
except AssertionError:
print("out of sequence at %d for %s, %d" % (c3, chrom, genome_seq_index[first_pos]), file=sys.stderr)
continue
codon = cds_seq[c1], cds_seq[c2], cds_seq[c3]
aa = translate(codon, GEN_CODE)
degeneracy3 = str(list(GEN_CODE[codon[0]][codon[1]].values()).count(aa)) + "d"
if not include_name:
name_text = ""
else:
name_text = name.replace(" ", "_")
if allpositions:
try:
degeneracy1 = str([GEN_CODE[k][codon[1]][codon[2]] for k in all].count(aa)) + "d"
degeneracy2 = str([GEN_CODE[codon[0]][k][codon[2]] for k in all].count(aa)) + "d"
except TypeError as s:
print(list(GEN_CODE.values()), file=sys.stderr)
raise TypeError(s)
if strand == "+":
print(
chrom,
genome_seq_index[c1],
genome_seq_index[c1] + 1,
cds_seq[c1],
degeneracy1,
aa,
name_text,
file=out,
)
print(
chrom,
genome_seq_index[c2],
genome_seq_index[c2] + 1,
cds_seq[c2],
degeneracy2,
aa,
name_text,
file=out,
)
print(
chrom,
genome_seq_index[c3],
genome_seq_index[c3] + 1,
cds_seq[c3],
degeneracy3,
aa,
name_text,
file=out,
)
else:
print(
chrom,
genome_seq_index[c3],
genome_seq_index[c3] + 1,
cds_seq[c3],
degeneracy3,
aa,
name_text,
file=out,
)
print(
chrom,
genome_seq_index[c2],
genome_seq_index[c2] + 1,
cds_seq[c2],
degeneracy2,
aa,
name_text,
file=out,
)
print(
chrom,
genome_seq_index[c1],
genome_seq_index[c1] + 1,
cds_seq[c1],
degeneracy1,
aa,
name_text,
file=out,
)
else:
if strand == "+":
for b in c1, c2:
print(
chrom,
genome_seq_index[b],
genome_seq_index[b] + 1,
cds_seq[b],
"1d",
aa,
name_text,
file=out,
)
print(
chrom,
genome_seq_index[c3],
genome_seq_index[c3] + 1,
cds_seq[c3],
degeneracy3,
aa,
name_text,
file=out,
)
else:
print(
chrom,
genome_seq_index[c3],
genome_seq_index[c3] + 1,
cds_seq[c3],
degeneracy3,
aa,
name_text,
file=out,
)
for b in c2, c1:
print(
chrom,
genome_seq_index[b],
genome_seq_index[b] + 1,
cds_seq[b],
"1d",
aa,
name_text,
file=out,
)
out.close()
if __name__ == "__main__":
main()
|
