-
Notifications
You must be signed in to change notification settings - Fork 0
/
impute4diallel_v1.2.py
410 lines (359 loc) · 14.7 KB
/
impute4diallel_v1.2.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
401
402
403
404
405
406
407
408
409
410
#!/usr/bin/env python
from __future__ import print_function
from __future__ import division
import sys
import argparse
import textwrap
import timeit
import os
def warning(*objs):
print("WARNING: ", *objs, end='\n', file=sys.stderr)
sys.exit()
##########################################################################################
def checkFile(infile_name):
with open(infile_name, 'r') as infile:
### check the first line
line1 = infile.readline()
line1a = line1.split()
if(line1a[0] != "snpid" or line1a[1] != "chr" or line1a[2] != "pos" or line1a[3] != "major" or line1a[4] != "minor"):
warning("[dsf5 required] snpid, chr, pos, major and minor should be the first five columns in the header")
else:
print("input file header OK!")
### check the 2nd line
line2 = infile.readline()
line2array = line2.split()
for snpi in range(start, end):
if(len(str(line2array[snpi])) != 1):
warning("SNP should be coded with one latter, like:'A T C G or - +'!")
else:
print("input file coding format OK!")
#f='/Users/yangjl/Documents/Github/zmSNPtools/packages/impute4diallel/test1000_samid.dsf'
#checkFile(f)
##########################################################################################
def readPed(pedfile):
temp = []
with open(pedfile, 'r') as infile:
next(infile) # skip the header line
for line in infile:
tokens = line.split()
temp.append(tokens)
return temp
# p='/Users/yangjl/Documents/Github/zmSNPtools/packages/impute4diallel/ped.txt'
# ped = readPed(p)
def readLofD(infile_name):
templ = []
with open(infile_name, 'r') as infile:
line1 = infile.readline()
header = line1.split()
for line in infile:
tokens = line.split()
tempd = {}
for i in range(0, len(header)):
tempd[header[i]] = tokens[i] #build hash
templ.append(tempd)
return templ
#test: dsnp = readLofD(f)
##########################################################################################
def impute_raw(loci=[], ped=[]):
'''
raw type
'''
mysnp = [loci['chr'], loci['snpid'], loci['pos']]
for aped in ped:
psnp1 = loci[aped[0]]
psnp2 = loci[aped[1]]
# using original SNP coding "ATCG"
major = loci['major']
minor = loci['minor']
# probility of AA, AB and BB
if psnp1 == major and psnp2 == major:
mysnp.append('\t'.join([major, major]))
elif psnp1 == major and psnp2 == minor:
mysnp.append('\t'.join([major, minor]))
elif psnp1 == major and psnp2 == "N":
mysnp.append('\t'.join([major, 'N']))
elif psnp1 == minor and psnp2 == major:
mysnp.append('\t'.join([major, minor]))
elif psnp1 == minor and psnp2 == minor:
mysnp.append('\t'.join([minor, minor]))
elif psnp1 == minor and psnp2 == "N":
mysnp.append('\t'.join([minor, 'N']))
elif psnp1 == "N" and psnp2 == major:
mysnp.append('\t'.join([major, 'N']))
elif psnp1 == "N" and psnp2 == minor:
mysnp.append('\t'.join([minor, 'N']))
elif psnp1 == "N" and psnp2 == "N":
mysnp.append('\t'.join(['N', 'N']))
else:
warnings(loci['snpid'], "have gensel imputation error!!!")
return mysnp
def impute_gensel(aped=[], dsnp=[]):
'''
diallel imputation for GenSel: major=10, minor=-10, missing, heter=0
'''
mysnp = []
for loci in dsnp:
psnp1 = loci[aped[0]]
psnp2 = loci[aped[1]]
# major = 10, minor = -10
major = loci['major']
minor = loci['minor']
if psnp1 == major and psnp2 == major:
mysnp.append('10')
elif psnp1 == major and psnp2 == minor:
mysnp.append('0')
elif psnp1 == major and psnp2 == "N":
mysnp.append('5')
elif psnp1 == minor and psnp2 == major:
mysnp.append('0')
elif psnp1 == minor and psnp2 == minor:
mysnp.append('-10')
elif psnp1 == minor and psnp2 == "N":
mysnp.append('-5')
elif psnp1 == "N" and psnp2 == major:
mysnp.append('5')
elif psnp1 == "N" and psnp2 == minor:
mysnp.append('-5')
elif psnp1 == "N" and psnp2 == "N":
mysnp.append('0')
else:
warning(loci['snpid'], "have gensel imputation error!!!")
return mysnp
def impute_gensel_dom(aped=[], dsnp=[]):
'''
diallel imputation for GenSel: major=10, minor=-10, missing, heter=0
'''
mysnp = []
for loci in dsnp:
psnp1 = loci[aped[0]]
psnp2 = loci[aped[1]]
# major = 10, minor = -10
major = loci['major']
minor = loci['minor']
if psnp1 == major and psnp2 == major:
mysnp.append('10\t-10')
elif psnp1 == major and psnp2 == minor:
mysnp.append('0\t0')
elif psnp1 == major and psnp2 == "N":
mysnp.append('5\t-5')
elif psnp1 == minor and psnp2 == major:
mysnp.append('0\t0')
elif psnp1 == minor and psnp2 == minor:
mysnp.append('-10\t-10')
elif psnp1 == minor and psnp2 == "N":
mysnp.append('-5\t-5')
elif psnp1 == "N" and psnp2 == major:
mysnp.append('5\t-5')
elif psnp1 == "N" and psnp2 == minor:
mysnp.append('-5\t-5')
elif psnp1 == "N" and psnp2 == "N":
mysnp.append('0\t0')
else:
warning(loci['snpid'], "have gensel imputation error!!!")
return mysnp
def impute_plink(aped=[], dsnp=[]):
'''
diallel imputation for PLINK: major="MM", minor="GG", missing, heter="NN"
'''
mysnp = []
for loci in dsnp:
psnp1 = loci[aped[0]]
psnp2 = loci[aped[1]]
# using original SNP coding "ATCG"
major = loci['major']
minor = loci['minor']
if psnp1 == major and psnp2 == major:
mysnp.append(' '.join([major, major]) )
elif psnp1 == major and psnp2 == minor:
mysnp.append(' '.join([major, minor]) )
elif psnp1 == major and psnp2 == "N":
mysnp.append('0 0')
elif psnp1 == minor and psnp2 == major:
mysnp.append(' '.join([major, minor]) )
elif psnp1 == minor and psnp2 == minor:
mysnp.append(' '.join([minor, minor]) )
elif psnp1 == minor and psnp2 == "N":
mysnp.append('0 0')
elif psnp1 == "N" and psnp2 == major:
mysnp.append('0 0')
elif psnp1 == "N" and psnp2 == minor:
mysnp.append('0 0')
elif psnp1 == "N" and psnp2 == "N":
mysnp.append('0 0')
else:
warning(loci['snpid'],psnp1, psnp2, "have plink imputation error!!!")
return mysnp
def impute_snptest(loci=[], ped=[]):
'''
IMPUTE Diallel for SNPTESTv2
The next three numbers on the line should be the probabilities of the three
genotypes AA, AB and BB at the SNP for the first individual in the cohort
'''
mysnp = [loci['chr'], loci['snpid'], loci['pos'], loci['major'], loci['minor']]
for aped in ped:
psnp1 = loci[aped[0]]
psnp2 = loci[aped[1]]
# using original SNP coding "ATCG"
major = loci['major']
minor = loci['minor']
# probility of AA, AB and BB
if psnp1 == major and psnp2 == major:
mysnp.append('1 0 0')
elif psnp1 == major and psnp2 == minor:
mysnp.append('0 1 0')
elif psnp1 == major and psnp2 == "N":
mysnp.append('0.5 0.5 0')
elif psnp1 == minor and psnp2 == major:
mysnp.append('0 1 0')
elif psnp1 == minor and psnp2 == minor:
mysnp.append('0 0 1')
elif psnp1 == minor and psnp2 == "N":
mysnp.append('0 0.5 0.5')
elif psnp1 == "N" and psnp2 == major:
mysnp.append('0.5 0.5 0')
elif psnp1 == "N" and psnp2 == minor:
mysnp.append('0 0.5 0.5')
elif psnp1 == "N" and psnp2 == "N":
mysnp.append('0 0 0')
else:
warnings(loci['snpid'], "have gensel imputation error!!!")
return mysnp
##########################################################################################
def impute_write(ped=[], dsnp=[], mode=0):
outfile = open(output, 'w')
if args['header'] == "yes" and mode != 4:
outfile.write('snpid')
for loci in dsnp:
outfile.write('\t' + loci['snpid'])
outfile.write('\n')
if args['header'] == "yes" and mode == 4:
outfile.write('snpid')
for loci in dsnp:
outfile.write('\t' + loci['snpid'] + "_a" + '\t' + loci['snpid'] + "_d")
outfile.write('\n')
if mode == 0:
for aped in ped:
print("\r", "impute:", len(dsnp), " SNPs at mode=gensel for [ ", aped[2], " ]")
imputesnp = impute_gensel(aped=aped, dsnp=dsnp)
outfile.write(aped[2] + '\t' + '\t'.join(imputesnp) + '\n')
if mode == 1:
for aped in ped:
print("\r", "impute:", len(dsnp), " SNPs at mode=plink for [ ", aped[2], " ]")
imputesnp = impute_plink(aped=aped, dsnp=dsnp)
outfile.write('\t'.join([aped[2],'1','0','0','1','0']) + "\t")
outfile.write('\t'.join(imputesnp) + '\n')
if mode == 2:
print("impute", len(dsnp), " SNPs at mode=snptest")
for loci in dsnp:
imputesnp = impute_snptest(loci=loci, ped=ped)
outfile.write('\t'.join(imputesnp) + '\n')
if mode == 3:
print("impute", len(dsnp), " SNPs at mode=raw")
for loci in dsnp:
imputesnp = impute_snptest(loci=loci, ped=ped)
outfile.write('\t'.join(imputesnp) + '\n')
if mode == 4:
for aped in ped:
print("\r", "impute:", len(dsnp), " SNPs at mode=gensel dominant for [ ", aped[2], " ]")
imputesnp = impute_gensel_dom(aped=aped, dsnp=dsnp)
outfile.write(aped[2] + '\t' + '\t'.join(imputesnp) + '\n')
outfile.close()
def write_pheno(mode=0):
if mode == 0 or mode == 4:
outpheno = ".".join([output, "pheno"])
outfile = open(outpheno, "w")
outfile.write('\t'.join(["Genotype", "Pheno", "Fix", "$cof"]) + '\n')
for aped in ped:
outfile.write('\t'.join([aped[2], '-9', '1', '0']) + '\n')
outfile.close()
if mode == 1:
outpheno = ".".join([output, "map"])
outfile = open(outpheno, "w")
for loci in dsnp:
outfile.write('\t'.join([loci['chr'], loci['id'], '0', loci['pos'] ]) + '\n')
outfile.close()
if mode ==2:
outpheno =".".join([output, "sample"])
outfile = open(outpheno, "w")
outfile.write('\t'.join(['ID_1', 'ID_2', 'missing', 'cov1', 'cov2', 'pheno1', 'bin1' ]) +'\n')
outfile.write('\t'.join(['0', '0', '0', 'D', 'C', 'P', 'B' ]) +'\n')
for aped in ped:
outfile.write("\t".join([aped[2], '1', '0', '1', '2', '-9', '0']) + '\n')
return outpheno
def version():
v = """
################################################################################
impute4diallel version 1.0
Jinliang Yang
updated: Sep.12.2014
changes: 1.R codes tested for GenSel add, dom, SNPTEST output!
2.input changed to sdf5
--------------------------------
SNP Imputation for diallel!
################################################################################
"""
return v
def get_parser():
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description=textwrap.dedent(version())
)
# positional arguments:
#parser.add_argument('query', metavar='QUERY', type=str, nargs='*', \
# help='the question to answer')
# optional arguments:
parser.add_argument('-p', '--path', help='the path of the input files', \
nargs='?', default=os.getcwd())
parser.add_argument('-d','--diallel', help='pedigree of the diallels (p1 p2 F1)', type=str)
parser.add_argument('-i', '--dsf', help='path of the density SNP format file', type=str)
parser.add_argument('-s', '--start', help='start cols (1-based) of the genotype \
[defult: --start=4]', default=4, type=int)
parser.add_argument('-e', '--end', help='end cols (1-based) of the genotype \
[defult: --end=31]', default=31, type=int)
parser.add_argument('--header', help='print header or not [default: --header=no]', type=str,
choices=['yes','no'], default='no')
parser.add_argument('-o', '--output', help='output files, like chr1_merged', type=str)
parser.add_argument('-m','--mode',
help='''[default --mode=0];
0, for GenSel;
1, for PLINK;
2, for SNPTEST; need chr pos in the dsf file!
3, for raw;
4, for GenSel dominant model.
''',
choices=[0,1,2,3, 4], default=0, type=int)
return parser
#parser = get_parser()
#parser.print_help()
##########################################################################################
if __name__ == '__main__':
parser = get_parser()
args = vars(parser.parse_args())
if args['diallel'] or args['dsf'] is not None:
print(version())
if args['path'] is not None:
os.chdir(args['path'])
##### read in the pedigree file ######
st = timeit.default_timer()
print("Reading pedigree (F1) file ...")
ped = readPed(pedfile=args['diallel'])
print("[ ", len(ped), " ] F1 of diallels loaded.")
##### read in the density snp file ######
start = args['start'] - 1 #6
end = args['end'] #385
print("Checking dsf file ...")
checkFile(args['dsf'])
print("Reading density SNP file ...")
dsnp = readLofD(infile_name = args['dsf'])
print("[ ", len(dsnp), " ] SNPs loaded from [ ", end-start, " ] founders!")
##### start imputation ######
print("Start SNP imputation")
output = args['output']
impute_write(ped=ped, dsnp=dsnp, mode=args['mode'])
print("File output to: [ ", output, " ]")
##### output corresponding phenotype file ########
outpheno = write_pheno(mode=args['mode'])
print("Corresponding phenotype file: [ ", outpheno, " ]")
et = timeit.default_timer()
print("[ ", "%.0f" % ((et - st)/60), " ] minutes of run time!")
print("Imputation finsihed!")