-
Notifications
You must be signed in to change notification settings - Fork 10
/
output.py
289 lines (237 loc) · 7.9 KB
/
output.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
"""
Consensus module
Generate consensus based on multiple sequence alignment
Written by Marshall Beddoe <mbeddoe@baselineresearch.net>
Copyright (c) 2004 Baseline Research
Licensed under the LGPL
"""
from curses.ascii import *
class Output:
def __init__(self, sequences):
self.sequences = sequences
self.consensus = []
self._go()
def _go(self):
pass
class Ansi(Output):
def __init__(self, sequences):
# Color defaults for composition
self.gap = "\033[41;30m%s\033[0m"
self.printable = "\033[42;30m%s\033[0m"
self.space = "\033[43;30m%s\033[0m"
self.binary = "\033[44;30m%s\033[0m"
self.zero = "\033[45;30m%s\033[0m"
self.bit = "\033[46;30m%s\033[0m"
self.default = "\033[47;30m%s\033[0m"
Output.__init__(self, sequences)
def _go(self):
seqLength = len(self.sequences[0][1])
rounds = seqLength / 18
remainder = seqLength % 18
l = len(self.sequences[0][1])
start = 0
end = 18
dtConsensus = []
mtConsensus = []
for i in range(rounds):
for id, seq in self.sequences:
print "%04d" % id,
for byte in seq[start:end]:
if byte == 256:
print self.gap % "___",
elif isspace(byte):
print self.space % " ",
elif isprint(byte):
print self.printable % "x%02x" % byte,
elif byte == 0:
print self.zero % "x00",
else:
print self.default % "x%02x" % byte,
print ""
# Calculate datatype consensus
print "DT ",
for j in range(start, end):
column = []
for id, seq in self.sequences:
column.append(seq[j])
dt = self._dtConsensus(column)
print dt,
dtConsensus.append(dt)
print ""
print "MT ",
for j in range(start, end):
column = []
for id, seq in self.sequences:
column.append(seq[j])
rate = self._mutationRate(column)
print "%03d" % (rate * 100),
mtConsensus.append(rate)
print "\n"
start += 18
end += 18
if remainder:
for id, seq in self.sequences:
print "%04d" % id,
for byte in seq[start:start + remainder]:
if byte == 256:
print self.gap % "___",
elif isspace(byte):
print self.space % " ",
elif isprint(byte):
print self.printable % "x%02x" % byte,
elif byte == 0:
print self.zero % "x00",
else:
print self.default % "x%02x" % byte,
print ""
print "DT ",
for j in range(start, start + remainder):
column = []
for id, seq in self.sequences:
column.append(seq[j])
dt = self._dtConsensus(column)
print dt,
dtConsensus.append(dt)
print ""
print "MT ",
for j in range(start, start + remainder):
column = []
for id, seq in self.sequences:
column.append(seq[j])
rate = self._mutationRate(column)
mtConsensus.append(rate)
print "%03d" % (rate * 100),
print ""
# Calculate consensus sequence
l = len(self.sequences[0][1])
for i in range(l):
histogram = {}
for id, seq in self.sequences:
try:
histogram[seq[i]] += 1
except:
histogram[seq[i]] = 1
items = histogram.items()
items.sort()
m = 1
v = 257
for j in items:
if j[1] > m:
m = j[1]
v = j[0]
self.consensus.append(v)
real = []
for i in range(len(self.consensus)):
if self.consensus[i] == 256:
continue
real.append((self.consensus[i], dtConsensus[i], mtConsensus[i]))
#
# Display consensus data
#
totalLen = len(real)
rounds = totalLen / 18
remainder = totalLen % 18
start = 0
end = 18
print "\nUngapped Consensus:"
for i in range(rounds):
print "CONS",
for byte,type,rate in real[start:end]:
if byte == 256:
print self.gap % "___",
elif byte == 257:
print self.default % "???",
elif isspace(byte):
print self.space % " ",
elif isprint(byte):
print self.printable % "x%02x" % byte,
elif byte == 0:
print self.zero % "x00",
else:
print self.default % "x%02x" % byte,
print ""
print "DT ",
for byte,type,rate in real[start:end]:
print type,
print ""
print "MT ",
for byte,type,rate in real[start:end]:
print "%03d" % (rate * 100),
print "\n"
start += 18
end += 18
if remainder:
print "CONS",
for byte,type,rate in real[start:start + remainder]:
if byte == 256:
print self.gap % "___",
elif byte == 257:
print self.default % "???",
elif isspace(byte):
print self.space % " ",
elif isprint(byte):
print self.printable % "x%02x" % byte,
elif byte == 0:
print self.zero % "x00",
else:
print self.default % "x%02x" % byte,
print ""
print "DT ",
for byte,type,rate in real[start:end]:
print type,
print ""
print "MT ",
for byte,type,rate in real[start:end]:
print "%03d" % (rate * 100),
print ""
def _dtConsensus(self, data):
histogram = {}
for byte in data:
if byte == 256:
try:
histogram["G"] += 1
except:
histogram["G"] = 1
elif isspace(byte):
try:
histogram["S"] += 1
except:
histogram["S"] = 1
elif isprint(byte):
try:
histogram["A"] += 1
except:
histogram["A"] = 1
elif byte == 0:
try:
histogram["Z"] += 1
except:
histogram["Z"] = 1
else:
try:
histogram["B"] += 1
except:
histogram["B"] = 1
items = histogram.items()
items.sort()
m = 1
v = '?'
for j in items:
if j[1] > m:
m = j[1]
v = j[0]
return v * 3
def _mutationRate(self, data):
histogram = {}
for x in data:
try:
histogram[x] += 1
except:
histogram[x] = 1
items = histogram.items()
items.sort()
if len(items) == 1:
rate = 0.0
else:
rate = len(items) * 1.0 / len(data) * 1.0
return rate