-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathcalcT1T2.allel.py
357 lines (341 loc) · 15.7 KB
/
calcT1T2.allel.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
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Mar 26 17:59:46 2018
calcT1T2.py -t trees -v vcf -g group --nodes
Calculates the T1 and T2 divergence times in a quartet
@author: stsmall
"""
from __future__ import print_function
from __future__ import division
import numpy as np
import allel
import h5py
from itertools import product
from collections import defaultdict
import os.path
import bisect
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('-v', "--vcfFile", type=str, required=True,
help="vcf file of variants")
parser.add_argument('-g', "--groups", nargs='+', action="append",
required=True, help="index of group"
"-g 1 2 3 -g 6 7 8 -g 11 12 13")
parser.add_argument('-o', "--outgroup", required=True,
help="index of outgroup")
parser.add_argument('-s', "--size", type=int, default=0,
help="size of window for calculations")
parser.add_argument('-P', "--permutations", type=int, default=0,
help="number of permutations, default is all")
args = parser.parse_args()
def loadvcf(vcfFile):
"""Reads VCF using scikit-allel, object is stored as pandas DF
"""
print("loading vcf file...")
print("using scitkit allele version:", allel.__version__)
h5 = "{}h5".format(vcfFile.strip("vcf"))
if os.path.isfile(h5):
callset = h5py.File(h5, 'r')
else:
callset = allel.read_vcf(vcfFile)
print("creating h5 for faster loading")
allel.vcf_to_hdf5(vcfFile, h5)
# assert len(set(callset['variants/CHROM'])) == 1
chrom = callset['variants/CHROM'][0]
return(callset, chrom)
def calct1t2(AAAA, BAAA, ABAA, AABA, BBAA, ABBA, BABA, BBBA):
"""
"""
t1list = []
t2list = []
sites = AAAA + BAAA + ABAA + AABA + BBAA + ABBA + BABA + BBBA
if sites != 0:
# BAAA,ABAA,BBAA
t2_inner = (BAAA + ABAA) / 2
t2 = t2_inner / sites
t1 = (t2_inner + BBAA) / sites
t1list.append(t1)
t2list.append(t2)
# ABAA, AABA, ABBA
t2_inner = (ABAA + AABA) / 2
t2 = t2_inner / sites
t1 = (t2_inner + ABBA) / sites
t1list.append(t1)
t2list.append(t2)
# BAAA,AABA, BABA
t2_inner = (BAAA + AABA) / 2
t2 = t2_inner / sites
t1 = (t2_inner + BABA) / sites
t1list.append(t1)
t2list.append(t2)
else:
t1list = [0, 0, 0]
t2list = [0, 0, 0]
return(t1list, t2list)
def countPattern(callset, sample_ix, outgroup):
"""Count patterns for all samples
"""
print("counting patterns in file...")
gt = allel.GenotypeArray(callset['calldata/GT'])
pos = allel.SortedIndex(callset['variants/POS'])
# remove any sites where outgroup is ./. or 0/1
keep = gt[:, outgroup].is_hom() & gt.count_alleles().is_biallelic()
gt = gt.compress(keep, axis=0)
pos = pos[keep]
# permute among all sample indexes, list of lists
# [[1,2,3,4,5],[6,7,8,9],[12,14,15,16]]
t1t2dict = defaultdict(list)
windict = {}
permute = 1
g1, g2, g3 = sample_ix
quartet = list(product(g1, g2, g3))
print("total number of combinations: {}".format(len(quartet)))
for quart in quartet:
print("permutation number {}".format(permute))
i, j, k = quart
gt_sub = gt.take([i, j, k, outgroup], axis=1)
keep = gt_sub.is_hom().all(axis=1)
gt_sub = gt_sub.compress(keep, axis=0)
pos_sub = pos[keep]
count_array = gt_sub.is_hom_alt()
pattern_array = np.packbits(count_array, axis=1)
calc_patterns = np.unique(pattern_array, return_counts=True)
d = {n: calc_patterns[1][i] for i, n in enumerate(calc_patterns[0])}
# total counts
AAAA = d.get(0, 0) + d.get(240, 0) # FFFF TTTT 240 and 0
BAAA = d.get(112, 0) + d.get(128, 0) # FTTT + TFFF 112 and 128
ABAA = d.get(176, 0) + d.get(64, 0) # TFTT + FTFF 176 and 64
AABA = d.get(208, 0) + d.get(32, 0) # TTFT + FFTF 208 and 32
BBAA = d.get(48, 0) + d.get(192, 0) # FFTT + TTFF 48 and 192
ABBA = d.get(144, 0) + d.get(96, 0) # TFFT + FTTF 144 and 96
BABA = d.get(80, 0) + d.get(160, 0) # FTFT + TFTF 80 and 160
BBBA = d.get(224, 0) + d.get(16, 0) # FFFT + TTTF 224 and 16
# t1t2 calc
t1, t2 = calct1t2(AAAA, BAAA, ABAA, AABA, BBAA, ABBA, BABA, BBBA)
t1t2dict["t1"].append(t1)
t1t2dict["t2"].append(t2)
# windows
windict[permute] = (pos_sub, pattern_array)
permute += 1
return(t1t2dict, windict)
def windowPattern(windict, size, chrom):
"""
"""
print("printing patterns to file...")
patterndict = defaultdict(list)
# windowT1 = defaultdict(list)
# windowT2 = defaultdict(list)
for k in windict.keys():
start = 0
step = size
end = start + size
try:
pos_array = windict[k][0]
last = pos_array[-1]
except IndexError:
continue
while end < last:
start_ix = bisect.bisect_left(pos_array, start)
end_ix = bisect.bisect_left(pos_array, end)
try:
pattern_array = windict[k][1][start_ix:end_ix]
calc_patterns = np.unique(pattern_array, return_counts=True)
d = {n: calc_patterns[1][i] for i, n in enumerate(calc_patterns[0])}
# total counts
AAAA = d.get(0, 0) + d.get(240, 0) # FFFF TTTT 240 and 0
BAAA = d.get(112, 0) + d.get(128, 0) # FTTT + TFFF 112 and 128
ABAA = d.get(176, 0) + d.get(64, 0) # TFTT + FTFF 176 and 64
AABA = d.get(208, 0) + d.get(32, 0) # TTFT + FFTF 208 and 32
BBAA = d.get(48, 0) + d.get(192, 0) # FFTT + TTFF 48 and 192
ABBA = d.get(144, 0) + d.get(96, 0) # TFFT + FTTF 144 and 96
BABA = d.get(80, 0) + d.get(160, 0) # FTFT + TFTF 80 and 160
BBBA = d.get(224, 0) + d.get(16, 0) # FFFT + TTTF 224 and 16
# t1, t2 = calct1t2(AAAA, BAAA, ABAA, AABA, BBAA, ABBA, BABA, BBBA)
except IndexError:
pattern_array = windict[k][1][start_ix:]
calc_patterns = np.unique(pattern_array, return_counts=True)
d = {n: calc_patterns[1][i] for i, n in enumerate(calc_patterns[0])}
# total counts
AAAA = d.get(0, 0) + d.get(240, 0) # FFFF TTTT 240 and 0
BAAA = d.get(112, 0) + d.get(128, 0) # FTTT + TFFF 112 and 128
ABAA = d.get(176, 0) + d.get(64, 0) # TFTT + FTFF 176 and 64
AABA = d.get(208, 0) + d.get(32, 0) # TTFT + FFTF 208 and 32
BBAA = d.get(48, 0) + d.get(192, 0) # FFTT + TTFF 48 and 192
ABBA = d.get(144, 0) + d.get(96, 0) # TFFT + FTTF 144 and 96
BABA = d.get(80, 0) + d.get(160, 0) # FTFT + TFTF 80 and 160
BBBA = d.get(224, 0) + d.get(16, 0) # FFFT + TTTF 224 and 16
# t1, t2 = calct1t2(AAAA, BAAA, ABAA, AABA, BBAA, ABBA, BABA, BBBA)
# windowT1[end].append(t1)
# windowT2[end].append(t2)
patterndict[end].append((AAAA, BAAA, ABAA, AABA, BBAA, ABBA, BABA, BBBA))
start += step
end += step
# write to file
wfile = open("dfoil.tbl", 'w')
headers = ['AAAA', 'AABA', 'ABAA', 'ABBA',
'BAAA', 'BABA', 'BBAA', 'BBBA']
# headers = ["ABC", "BCA", "ACB", "AB", "BC", "AC"]
wfile.write("chrom\tpos\t{}\n".format('\t'.join(headers)))
ordered_keys = sorted(list(patterndict.keys()))
for pos in ordered_keys:
count_mean = np.mean(list(zip(*patterndict[pos])), axis=1)
wfile.write("{}\t{}\t{}\n".format(chrom, pos, "\t".join(map(str, count_mean))))
wfile.close()
return(None)
def countPatternDFOIL(callset, sample_ix, outgroup):
"""Count patterns for all samples
"""
print("counting patterns in file...")
gt = allel.GenotypeArray(callset['calldata/GT'])
pos = allel.SortedIndex(callset['variants/POS'])
# remove any sites where outgroup is ./. or 0/1
keep = gt[:, outgroup].is_hom() & gt.count_alleles().is_biallelic()
gt = gt.compress(keep, axis=0)
pos = pos[keep]
windict = {}
permute = 1
g1, g2, g3, g4 = sample_ix
quartet = list(product(g1, g2, g3, g4))
print("total number of combinations: {}".format(len(quartet)))
for quart in quartet:
print("permutation number {}".format(permute))
i, j, k, m = quart
gt_sub = gt.take([i, j, k, m, outgroup], axis=1)
keep = gt_sub.is_hom().all(axis=1)
gt_sub = gt_sub.compress(keep, axis=0)
pos_sub = pos[keep]
count_array = gt_sub.is_hom_alt()
pattern_array = np.packbits(count_array, axis=1)
# windows
windict[permute] = (pos_sub, pattern_array)
permute += 1
return(windict)
def windowPatternDFOIL(windict, size, chrom):
"""
"""
print("printing patterns to file...")
patterndict = defaultdict(list)
# windowT1 = defaultdict(list)
# windowT2 = defaultdict(list)
for k in windict.keys():
start = 0
step = size
end = start + size
try:
pos_array = windict[k][0]
last = pos_array[-1]
except IndexError:
continue
if size == 0:
pattern_array = windict[k][1]
calc_patterns = np.unique(pattern_array, return_counts=True)
d = {n: calc_patterns[1][i] for i, n in enumerate(calc_patterns[0])}
# total counts
n_AAAAA = d.get(0, 0) + d.get(248, 0) # FFFFF TTTTT
n_AAABA = d.get(16, 0) + d.get(232, 0) # FFFTF TTTFT
n_AABAA = d.get(32, 0) + d.get(216, 0) # FFTFF TTFTT
n_AABBA = d.get(48, 0) + d.get(200, 0) # FFTTF TTFFT
n_ABAAA = d.get(64, 0) + d.get(184, 0) # FTFFF TFTTT
n_ABABA = d.get(80, 0) + d.get(168, 0) # FTFTF TFTFT
n_ABBAA = d.get(96, 0) + d.get(152, 0) # FTTFF TFFTT
n_ABBBA = d.get(112, 0) + d.get(136, 0) # FTTTF TFFFT
n_BAAAA = d.get(128, 0) + d.get(120, 0) # TFFFF FTTTT
n_BAABA = d.get(144, 0) + d.get(104, 0) # TFFTF FTTFT
n_BABAA = d.get(160, 0) + d.get(88, 0) # TFTFF FTFTT
n_BABBA = d.get(176, 0) + d.get(72, 0) # TFTTF FTFFT
n_BBAAA = d.get(192, 0) + d.get(56, 0) # TTFFF FFTTT
n_BBABA = d.get(208, 0) + d.get(40, 0) # TTFTF FFTFT
n_BBBAA = d.get(224, 0) + d.get(24, 0) # TTTFF FFFTT
n_BBBBA = d.get(8, 0) + d.get(240, 0) # FFFFT TTTTF
patterndict[end].append((n_AAAAA, n_AAABA, n_AABAA, n_AABBA,
n_ABAAA, n_ABABA, n_ABBAA, n_ABBBA,
n_BAAAA, n_BAABA, n_BABAA, n_BABBA,
n_BBAAA, n_BBABA, n_BBBAA, n_BBBBA))
else:
while end < last:
start_ix = bisect.bisect_left(pos_array, start)
end_ix = bisect.bisect_left(pos_array, end)
try:
pattern_array = windict[k][1][start_ix:end_ix]
calc_patterns = np.unique(pattern_array, return_counts=True)
d = {n: calc_patterns[1][i] for i, n in enumerate(calc_patterns[0])}
# total counts
n_AAAAA = d.get(0, 0) + d.get(248, 0) # FFFFF TTTTT
n_AAABA = d.get(16, 0) + d.get(232, 0) # FFFTF TTTFT
n_AABAA = d.get(32, 0) + d.get(216, 0) # FFTFF TTFTT
n_AABBA = d.get(48, 0) + d.get(200, 0) # FFTTF TTFFT
n_ABAAA = d.get(64, 0) + d.get(184, 0) # FTFFF TFTTT
n_ABABA = d.get(80, 0) + d.get(168, 0) # FTFTF TFTFT
n_ABBAA = d.get(96, 0) + d.get(152, 0) # FTTFF TFFTT
n_ABBBA = d.get(112, 0) + d.get(136, 0) # FTTTF TFFFT
n_BAAAA = d.get(128, 0) + d.get(120, 0) # TFFFF FTTTT
n_BAABA = d.get(144, 0) + d.get(104, 0) # TFFTF FTTFT
n_BABAA = d.get(160, 0) + d.get(88, 0) # TFTFF FTFTT
n_BABBA = d.get(176, 0) + d.get(72, 0) # TFTTF FTFFT
n_BBAAA = d.get(192, 0) + d.get(56, 0) # TTFFF FFTTT
n_BBABA = d.get(208, 0) + d.get(40, 0) # TTFTF FFTFT
n_BBBAA = d.get(224, 0) + d.get(24, 0) # TTTFF FFFTT
n_BBBBA = d.get(8, 0) + d.get(240, 0) # FFFFT TTTTF
except IndexError:
pattern_array = windict[k][1][start_ix:]
calc_patterns = np.unique(pattern_array, return_counts=True)
d = {n: calc_patterns[1][i] for i, n in enumerate(calc_patterns[0])}
# total counts
n_AAAAA = d.get(0, 0) + d.get(248, 0) # FFFFF TTTTT
n_AAABA = d.get(16, 0) + d.get(232, 0) # FFFTF TTTFT
n_AABAA = d.get(32, 0) + d.get(216, 0) # FFTFF TTFTT
n_AABBA = d.get(48, 0) + d.get(200, 0) # FFTTF TTFFT
n_ABAAA = d.get(64, 0) + d.get(184, 0) # FTFFF TFTTT
n_ABABA = d.get(80, 0) + d.get(168, 0) # FTFTF TFTFT
n_ABBAA = d.get(96, 0) + d.get(152, 0) # FTTFF TFFTT
n_ABBBA = d.get(112, 0) + d.get(136, 0) # FTTTF TFFFT
n_BAAAA = d.get(128, 0) + d.get(120, 0) # TFFFF FTTTT
n_BAABA = d.get(144, 0) + d.get(104, 0) # TFFTF FTTFT
n_BABAA = d.get(160, 0) + d.get(88, 0) # TFTFF FTFTT
n_BABBA = d.get(176, 0) + d.get(72, 0) # TFTTF FTFFT
n_BBAAA = d.get(192, 0) + d.get(56, 0) # TTFFF FFTTT
n_BBABA = d.get(208, 0) + d.get(40, 0) # TTFTF FFTFT
n_BBBAA = d.get(224, 0) + d.get(24, 0) # TTTFF FFFTT
n_BBBBA = d.get(8, 0) + d.get(240, 0) # FFFFT TTTTF
patterndict[end].append((n_AAAAA, n_AAABA, n_AABAA, n_AABBA,
n_ABAAA, n_ABABA, n_ABBAA, n_ABBBA,
n_BAAAA, n_BAABA, n_BABAA, n_BABBA,
n_BBAAA, n_BBABA, n_BBBAA, n_BBBBA))
start += step
end += step
# write to file
wfile = open("dfoil.tbl", 'w')
headers = ['AAAAA', 'AAABA', 'AABAA', 'AABBA',
'ABAAA', 'ABABA', 'ABBAA', 'ABBBA',
'BAAAA', 'BAABA', 'BABAA', 'BABBA',
'BBAAA', 'BBABA', 'BBBAA', 'BBBBA']
wfile.write("#chrom\tpos\t{}\n".format('\t'.join(headers)))
ordered_keys = sorted(list(patterndict.keys()))
for pos in ordered_keys:
count_mean = np.round(np.mean(list(zip(*patterndict[pos])), axis=1))
count_mean2 = map(int, count_mean)
wfile.write("{}\t{}\t{}\n".format(chrom, pos, "\t".join(map(str, count_mean2))))
wfile.close()
return(None)
if __name__ == "__main__":
groups = args.groups
quart_ix = [list(map(int, x)) for x in groups]
outgroup_ix = int(args.outgroup)
vcfFile = args.vcfFile
size = args.size
callset, chrom = loadvcf(vcfFile)
if len(quart_ix) > 3:
windict = countPatternDFOIL(callset, quart_ix, outgroup_ix)
windowPatternDFOIL(windict, size, chrom)
else:
t1t2dict, windict = countPattern(callset, quart_ix, outgroup_ix)
i, j, k = list(zip(*t1t2dict["t1"]))
m, n, p = list(zip(*t1t2dict["t2"]))
print("(AB)C: {}".format(np.mean(i)))
print("(BC)A: {}".format(np.mean(j)))
print("(AC)B: {}".format(np.mean(k)))
print("AB: {}".format(np.mean(m)))
print("BC: {}".format(np.mean(n)))
print("AC: {}".format(np.mean(p)))
windowPattern(windict, size, chrom)