-
Notifications
You must be signed in to change notification settings - Fork 1.7k
/
Controller.py
866 lines (784 loc) · 31.5 KB
/
Controller.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
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
# Copyright 2009 by Tiago Antao <tiagoantao@gmail.com>. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""
This module allows to control GenePop.
"""
import os
import re
import shutil
from Bio.Application import AbstractCommandline, _Argument
def _gp_float(tok):
"""Gets a float from a token, if it fails, returns the string.
"""
try:
return float(tok)
except ValueError:
return str(tok)
def _gp_int(tok):
"""Gets a int from a token, if it fails, returns the string.
"""
try:
return int(tok)
except ValueError:
return str(tok)
def _read_allele_freq_table(f):
l = f.readline()
while ' --' not in l:
if l == "":
raise StopIteration
if 'No data' in l:
return None, None
l = f.readline()
alleles = filter(lambda x: x != '', f.readline().rstrip().split(" "))
alleles = map(lambda x: _gp_int(x), alleles)
l = f.readline().rstrip()
table = []
while l != "":
line = filter(lambda x: x != '', l.split(" "))
try:
table.append(
(line[0],
map(lambda x: _gp_float(x), line[1:-1]),
_gp_int(line[-1])))
except ValueError:
table.append(
(line[0],
[None] * len(alleles),
0))
l = f.readline().rstrip()
return alleles, table
def _read_table(f, funs):
table = []
l = f.readline().rstrip()
while '---' not in l:
l = f.readline().rstrip()
l = f.readline().rstrip()
while '===' not in l and '---' not in l and l != "":
toks = filter(lambda x: x != "", l.split(" "))
line = []
for i in range(len(toks)):
try:
line.append(funs[i](toks[i]))
except ValueError:
line.append(toks[i]) # Could not cast
table.append(tuple(line))
l = f.readline().rstrip()
return table
def _read_triangle_matrix(f):
matrix = []
l = f.readline().rstrip()
while l != "":
matrix.append(
map(lambda x: _gp_float(x),
filter(lambda y: y != "", l.split(" "))))
l = f.readline().rstrip()
return matrix
def _read_headed_triangle_matrix(f):
matrix = {}
header = f.readline().rstrip()
if '---' in header or '===' in header:
header = f.readline().rstrip()
nlines = len(filter(lambda x:x != '', header.split(' '))) - 1
for line_pop in range(nlines):
l = f.readline().rstrip()
vals = filter(lambda x:x != '', l.split(' ')[1:])
clean_vals = []
for val in vals:
try:
clean_vals.append(_gp_float(val))
except ValueError:
clean_vals.append(None)
for col_pop in range(len(clean_vals)):
matrix[(line_pop+1, col_pop)] = clean_vals[col_pop]
return matrix
def _hw_func(stream, is_locus, has_fisher = False):
l = stream.readline()
if is_locus:
hook = "Locus "
else:
hook = " Pop : "
while l != "":
if l.startswith(hook):
stream.readline()
stream.readline()
stream.readline()
table = _read_table(stream,[str,_gp_float,_gp_float,_gp_float,_gp_float,_gp_int,str])
#loci might mean pop if hook="Locus "
loci = {}
for entry in table:
if len(entry) < 3:
loci[entry[0]] = None
else:
locus, p, se, fis_wc, fis_rh, steps = entry[:-1]
if se == "-": se = None
loci[locus] = p, se, fis_wc, fis_rh, steps
return loci
l = stream.readline()
#self.done = True
raise StopIteration
class _FileIterator:
"""Iterator which crawls over a stream of lines with a function.
The generator function is expected to yield a tuple, while
consuming input
"""
def __init__(self, func, stream, fname):
self.func = func
self.stream = stream
self.fname = fname
self.done = False
def __iter__(self):
if self.done:
self.done = True
raise StopIteration
return self
def next(self):
return self.func(self)
def __del__(self):
self.stream.close()
try:
os.remove(self.fname)
except OSError:
#Jython seems to call the iterator twice
pass
class _GenePopCommandline(AbstractCommandline):
""" Command Line Wrapper for GenePop.
"""
def __init__(self, genepop_dir=None, cmd='Genepop', **kwargs):
self.parameters = [
_Argument(["command"],
"GenePop option to be called",
is_required=True),
_Argument(["mode"],
"Should allways be batch",
is_required=True),
_Argument(["input"],
"Input file",
is_required=True),
_Argument(["Dememorization"],
"Dememorization step"),
_Argument(["BatchNumber"],
"Number of MCMC batches"),
_Argument(["BatchLength"],
"Length of MCMC chains"),
_Argument(["HWtests"],
"Enumeration or MCMC"),
_Argument(["IsolBDstatistic"],
"IBD statistic (a or e)"),
_Argument(["MinimalDistance"],
"Minimal IBD distance"),
_Argument(["GeographicScale"],
"Log or Linear"),
]
AbstractCommandline.__init__(self, cmd, **kwargs)
self.set_parameter("mode", "Mode=Batch")
def set_menu(self, option_list):
"""Sets the menu option.
Example set_menu([6,1]) = get all F statistics (menu 6.1)
"""
self.set_parameter("command", "MenuOptions="+
".".join(map(lambda x:str(x),option_list)))
def set_input(self, fname):
"""Sets the input file name.
"""
self.set_parameter("input", "InputFile="+fname)
class GenePopController(object):
def __init__(self, genepop_dir = None):
"""Initializes the controller.
genepop_dir is the directory where GenePop is.
The binary should be called Genepop (capital G)
"""
self.controller = _GenePopCommandline(genepop_dir)
def _remove_garbage(self, fname_out):
try:
if fname_out != None: os.remove(fname_out)
except OSError:
pass # safe
try:
os.remove("genepop.txt")
except OSError:
pass # safe
try:
os.remove("fichier.in")
except OSError:
pass # safe
try:
os.remove("cmdline.txt")
except OSError:
pass # safe
def _get_opts(self, dememorization, batches, iterations, enum_test=None):
opts = {}
opts["Dememorization"]=dememorization
opts["BatchNumber"]=batches
opts["BatchLength"]=iterations
if enum_test != None:
if enum_test == True:
opts["HWtests"]="Enumeration"
else:
opts["HWtests"]="MCMC"
return opts
def _run_genepop(self, extensions, option, fname, opts={}):
for extension in extensions:
self._remove_garbage(fname + extension)
self.controller.set_menu(option)
self.controller.set_input(fname)
for opt in opts:
self.controller.set_parameter(opt, opt+"="+str(opts[opt]))
self.controller() #checks error level is zero
self._remove_garbage(None)
return
def _test_pop_hz_both(self, fname, type, ext, enum_test = True,
dememorization = 10000, batches = 20, iterations = 5000):
"""Hardy-Weinberg test for heterozygote deficiency/excess.
Returns a population iterator containg
A dictionary[locus]=(P-val, SE, Fis-WC, Fis-RH, steps)
Some loci have a None if the info is not available
SE might be none (for enumerations)
"""
opts = self._get_opts(dememorization, batches, iterations, enum_test)
self._run_genepop([ext], [1, type], fname, opts)
f = open(fname + ext)
def hw_func(self):
return _hw_func(self.stream, False)
return _FileIterator(hw_func, f, fname + ext)
def _test_global_hz_both(self, fname, type, ext, enum_test = True,
dememorization = 10000, batches = 20, iterations = 5000):
"""Global Hardy-Weinberg test for heterozygote deficiency/excess.
Returns a triple with:
A list per population containg
(pop_name, P-val, SE, switches)
Some pops have a None if the info is not available
SE might be none (for enumerations)
A list per loci containg
(locus_name, P-val, SE, switches)
Some loci have a None if the info is not available
SE might be none (for enumerations)
Overall results (P-val, SE, switches)
"""
opts = self._get_opts(dememorization, batches, iterations, enum_test)
self._run_genepop([ext], [1, type], fname, opts)
def hw_pop_func(self):
return _read_table(self.stream, [str, _gp_float, _gp_float, _gp_float])
f1 = open(fname + ext)
l = f1.readline()
while "by population" not in l:
l = f1.readline()
pop_p = _read_table(f1, [str, _gp_float, _gp_float, _gp_float])
f2 = open(fname + ext)
l = f2.readline()
while "by locus" not in l:
l = f2.readline()
loc_p = _read_table(f2, [str, _gp_float, _gp_float, _gp_float])
f = open(fname + ext)
l = f.readline()
while "all locus" not in l:
l = f.readline()
f.readline()
f.readline()
f.readline()
f.readline()
l = f.readline().rstrip()
p, se, switches = tuple(map(lambda x: _gp_float(x),
filter(lambda y: y != "",l.split(" "))))
f.close()
return pop_p, loc_p, (p, se, switches)
#1.1
def test_pop_hz_deficiency(self, fname, enum_test = True,
dememorization = 10000, batches = 20, iterations = 5000):
"""Hardy-Weinberg test for heterozygote deficiency.
Returns a population iterator containg
A dictionary[locus]=(P-val, SE, Fis-WC, Fis-RH, steps)
Some loci have a None if the info is not available
SE might be none (for enumerations)
"""
return self._test_pop_hz_both(fname, 1, ".D", enum_test,
dememorization, batches, iterations)
#1.2
def test_pop_hz_excess(self, fname, enum_test = True,
dememorization = 10000, batches = 20, iterations = 5000):
"""Hardy-Weinberg test for heterozygote deficiency.
Returns a population iterator containg
A dictionary[locus]=(P-val, SE, Fis-WC, Fis-RH, steps)
Some loci have a None if the info is not available
SE might be none (for enumerations)
"""
return self._test_pop_hz_both(fname, 2, ".E", enum_test,
dememorization, batches, iterations)
#1.3 P file
def test_pop_hz_prob(self, fname, ext, enum_test = False,
dememorization = 10000, batches = 20, iterations = 5000):
"""Hardy-Weinberg test based on probability.
Returns 2 iterators and a final tuple:
1. Returns a loci iterator containing
b. A dictionary[pop_pos]=(P-val, SE, Fis-WC, Fis-RH, steps)
Some pops have a None if the info is not available
SE might be none (for enumerations)
c. Result of Fisher's test (Chi2, deg freedom, prob)
2. Returns a population iterator containg
a. A dictionary[locus]=(P-val, SE, Fis-WC, Fis-RH, steps)
Some loci have a None if the info is not available
SE might be none (for enumerations)
b. Result of Fisher's test (Chi2, deg freedom, prob)
3. (Chi2, deg freedom, prob)
"""
opts = self._get_opts(dememorization, batches, iterations, enum_test)
self._run_genepop([ext], [1, 3], fname, opts)
def hw_prob_loci_func(self):
return _hw_func(self.stream, True, True)
def hw_prob_pop_func(self):
return _hw_func(self.stream, False, True)
shutil.copyfile(fname+".P", fname+".P2")
f1 = open(fname + ".P")
f2 = open(fname + ".P2")
return _FileIterator(hw_prob_loci_func, f1, fname + ".P"), _FileIterator(hw_prob_pop_func, f2, fname + ".P2")
#1.4
def test_global_hz_deficiency(self, fname, enum_test = True,
dememorization = 10000, batches = 20, iterations = 5000):
"""Global Hardy-Weinberg test for heterozygote deficiency.
Returns a triple with:
An list per population containg
(pop_name, P-val, SE, switches)
Some pops have a None if the info is not available
SE might be none (for enumerations)
An list per loci containg
(locus_name, P-val, SE, switches)
Some loci have a None if the info is not available
SE might be none (for enumerations)
Overall results (P-val, SE, switches)
"""
return self._test_global_hz_both(fname, 4, ".DG", enum_test,
dememorization, batches, iterations)
#1.5
def test_global_hz_excess(self, fname, enum_test = True,
dememorization = 10000, batches = 20, iterations = 5000):
"""Global Hardy-Weinberg test for heterozygote excess.
Returns a triple with:
An list per population containg
(pop_name, P-val, SE, switches)
Some pops have a None if the info is not available
SE might be none (for enumerations)
An list per loci containg
(locus_name, P-val, SE, switches)
Some loci have a None if the info is not available
SE might be none (for enumerations)
Overall results (P-val, SE, switches)
"""
return self._test_global_hz_both(fname, 5, ".EG", enum_test,
dememorization, batches, iterations)
#2.1
def test_ld(self, fname,
dememorization = 10000, batches = 20, iterations = 5000):
opts = self._get_opts(dememorization, batches, iterations)
self._run_genepop([".DIS"], [2, 1], fname, opts)
def ld_pop_func(self):
current_pop = None
l = self.stream.readline().rstrip()
if l == "":
self.done = True
raise StopIteration
toks = filter(lambda x: x != "", l.split(" "))
pop, locus1, locus2 = toks[0], toks[1], toks[2]
if not hasattr(self, "start_locus1"):
start_locus1, start_locus2 = locus1, locus2
current_pop = -1
if locus1 == start_locus1 and locus2 == start_locus2:
current_pop += 1
if toks[3] == "No":
return current_pop, pop, (locus1, locus2), None
p, se, switches = _gp_float(toks[3]), _gp_float(toks[4]), _gp_int(toks[5])
return current_pop, pop, (locus1, locus2), (p, se, switches)
def ld_func(self):
l = self.stream.readline().rstrip()
if l == "":
self.done = True
raise StopIteration
toks = filter(lambda x: x != "", l.split(" "))
locus1, locus2 = toks[0], toks[2]
try:
chi2, df, p = _gp_float(toks[3]), _gp_int(toks[4]), _gp_float(toks[5])
except ValueError:
return (locus1, locus2), None
return (locus1, locus2), (chi2, df, p)
f1 = open(fname + ".DIS")
l = f1.readline()
while "----" not in l:
l = f1.readline()
shutil.copyfile(fname + ".DIS", fname + ".DI2")
f2 = open(fname + ".DI2")
l = f2.readline()
while "Locus pair" not in l:
l = f2.readline()
while "----" not in l:
l = f2.readline()
return _FileIterator(ld_pop_func, f1, fname+".DIS"), _FileIterator(ld_func, f2, fname + ".DI2")
#2.2
def create_contingency_tables(self, fname):
raise NotImplementedError
#3.1 PR/GE files
def test_genic_diff_all(self, fname,
dememorization = 10000, batches = 20, iterations = 5000):
raise NotImplementedError
#3.2 PR2/GE2 files
def test_genic_diff_pair(self, fname,
dememorization = 10000, batches = 20, iterations = 5000):
raise NotImplementedError
#3.3 G files
def test_genotypic_diff_all(self, fname,
dememorization = 10000, batches = 20, iterations = 5000):
raise NotImplementedError
#3.4 2G2 files
def test_genotypic_diff_pair(self, fname,
dememorization = 10000, batches = 20, iterations = 5000):
raise NotImplementedError
#4
def estimate_nm(self, fname):
self._run_genepop(["PRI"], [4], fname)
f = open(fname + ".PRI")
lines = f.readlines() # Small file, it is ok
f.close()
for line in lines:
m = re.search("Mean sample size: ([.0-9]+)", line)
if m != None:
mean_sample_size = _gp_float(m.group(1))
m = re.search("Mean frequency of private alleles p\(1\)= ([.0-9]+)", line)
if m != None:
mean_priv_alleles = _gp_float(m.group(1))
m = re.search("N=10: ([.0-9]+)", line)
if m != None:
mig10 = _gp_float(m.group(1))
m = re.search("N=25: ([.0-9]+)", line)
if m != None:
mig25 = _gp_float(m.group(1))
m = re.search("N=50: ([.0-9]+)", line)
if m != None:
mig50 = _gp_float(m.group(1))
m = re.search("for size= ([.0-9]+)", line)
if m != None:
mig_corrected = _gp_float(m.group(1))
os.remove(fname + ".PRI")
return mean_sample_size, mean_priv_alleles, mig10, mig25, mig50, mig_corrected
#5.1
def calc_allele_genotype_freqs(self, fname):
"""Calculates allele and genotype frequencies per locus and per sample.
Parameters:
fname - file name
Returns tuple with 2 elements:
Population iterator with
population name
Locus dictionary with key = locus name and content tuple as
Genotype List with
(Allele1, Allele2, observed, expected)
(expected homozygotes, observed hm,
expected heterozygotes, observed ht)
Allele frequency/Fis dictionary with allele as key and
(count, frequency, Fis Weir & Cockerham)
Totals as a pair
count
Fis Weir & Cockerham,
Fis Robertson & Hill
Locus iterator with
Locus name
allele list
Population list with a triple
population name
list of allele frequencies in the same order as allele list above
number of genes
Will create a file called fname.INF
"""
self._run_genepop(["INF"], [5,1], fname)
#First pass, general information
#num_loci = None
#num_pops = None
#f = open(fname + ".INF")
#l = f.readline()
#while (num_loci == None or num_pops == None) and l != '':
# m = re.search("Number of populations detected : ([0-9+])", l)
# if m != None:
# num_pops = _gp_int(m.group(1))
# m = re.search("Number of loci detected : ([0-9+])", l)
# if m != None:
# num_loci = _gp_int(m.group(1))
# l = f.readline()
#f.close()
def pop_parser(self):
if hasattr(self, "old_line"):
l = self.old_line
del self.old_line
else:
l = self.stream.readline()
loci_content = {}
while l != '':
l = l.rstrip()
if "Tables of allelic frequencies for each locus" in l:
return self.curr_pop, loci_content
match = re.match(".*Pop: (.+) Locus: (.+)", l)
if match != None:
pop = match.group(1)
locus = match.group(2)
if not hasattr(self, "first_locus"):
self.first_locus = locus
if hasattr(self, "curr_pop"):
if self.first_locus == locus:
old_pop = self.curr_pop
#self.curr_pop = pop
self.old_line = l
del self.first_locus
del self.curr_pop
return old_pop, loci_content
self.curr_pop = pop
else:
l = self.stream.readline()
continue
geno_list = []
l = self.stream.readline()
if "No data" in l: continue
while "Genotypes Obs." not in l:
l = self.stream.readline()
while l != "\n":
m2 = re.match(" +([0-9]+) , ([0-9]+) *([0-9]+) *(.+)",l)
if m2 != None:
geno_list.append((_gp_int(m2.group(1)), _gp_int(m2.group(2)),
_gp_int(m2.group(3)), _gp_float(m2.group(4))))
else:
l = self.stream.readline()
continue
l = self.stream.readline()
while "Expected number of ho" not in l:
l = self.stream.readline()
expHo = _gp_float(l[38:])
l = self.stream.readline()
obsHo = _gp_int(l[38:])
l = self.stream.readline()
expHe = _gp_float(l[38:])
l = self.stream.readline()
obsHe = _gp_int(l[38:])
l = self.stream.readline()
while "Sample count" not in l:
l = self.stream.readline()
l = self.stream.readline()
freq_fis={}
overall_fis = None
while "----" not in l:
vals = filter(lambda x: x!='',
l.rstrip().split(' '))
if vals[0]=="Tot":
overall_fis = _gp_int(vals[1]), \
_gp_float(vals[2]), _gp_float(vals[3])
else:
freq_fis[_gp_int(vals[0])] = _gp_int(vals[1]), \
_gp_float(vals[2]), _gp_float(vals[3])
l = self.stream.readline()
loci_content[locus] = geno_list, \
(expHo, obsHo, expHe, obsHe), \
freq_fis, overall_fis
self.done = True
raise StopIteration
def locus_parser(self):
l = self.stream.readline()
while l != "":
l = l.rstrip()
match = re.match(" Locus: (.+)", l)
if match != None:
locus = match.group(1)
alleles, table = _read_allele_freq_table(self.stream)
return locus, alleles, table
l = self.stream.readline()
self.done = True
raise StopIteration
popf = open(fname + ".INF")
shutil.copyfile(fname + ".INF", fname + ".IN2")
locf = open(fname + ".IN2")
pop_iter = _FileIterator(pop_parser, popf, fname + ".INF")
locus_iter = _FileIterator(locus_parser, locf, fname + ".IN2")
return (pop_iter, locus_iter)
def _calc_diversities_fis(self, fname, ext):
self._run_genepop([ext], [5,2], fname)
f = open(fname + ext)
l = f.readline()
while l != "":
l = l.rstrip()
if l.startswith("Statistics per sample over all loci with at least two individuals typed"):
avg_fis = _read_table(f, [str, _gp_float, _gp_float, _gp_float])
avg_Qintra = _read_table(f, [str, _gp_float])
l = f.readline()
f.close()
def fis_func(self):
l = self.stream.readline()
while l != "":
l = l.rstrip()
m = re.search("Locus: (.+)", l)
if m != None:
locus = m.group(1)
self.stream.readline()
if "No complete" in self.stream.readline(): return locus, None
self.stream.readline()
fis_table = _read_table(self.stream, [str, _gp_float, _gp_float, _gp_float])
self.stream.readline()
avg_qinter, avg_fis = tuple(map (lambda x: _gp_float(x),
filter(lambda y:y != "", self.stream.readline().split(" "))))
return locus, fis_table, avg_qinter, avg_fis
l = self.stream.readline()
self.done = True
raise StopIteration
dvf = open(fname + ext)
return _FileIterator(fis_func, dvf, fname + ext), avg_fis, avg_Qintra
#5.2
def calc_diversities_fis_with_identity(self, fname):
return self._calc_diversities_fis(fname, ".DIV")
#5.3
def calc_diversities_fis_with_size(self, fname):
raise NotImplementedError
#6.1 Less genotype frequencies
def calc_fst_all(self, fname):
"""Executes GenePop and gets Fst/Fis/Fit (all populations)
Parameters:
fname - file name
Returns:
(multiLocusFis, multiLocusFst, multiLocus Fit),
Iterator of tuples
(Locus name, Fis, Fst, Fit, Qintra, Qinter)
Will create a file called fname.FST .
This does not return the genotype frequencies.
"""
self._run_genepop([".FST"], [6,1], fname)
f = open(fname + ".FST")
l = f.readline()
while l != '':
if l.startswith(' All:'):
toks=filter(lambda x:x!="", l.rstrip().split(' '))
try:
allFis = _gp_float(toks[1])
except ValueError:
allFis = None
try:
allFst = _gp_float(toks[2])
except ValueError:
allFst = None
try:
allFit = _gp_float(toks[3])
except ValueError:
allFit = None
l = f.readline()
f.close()
f = open(fname + ".FST")
def proc(self):
if hasattr(self, "last_line"):
l = self.last_line
del self.last_line
else:
l = self.stream.readline()
locus = None
fis = None
fst = None
fit = None
qintra = None
qinter = None
while l != '':
l = l.rstrip()
if l.startswith(' Locus:'):
if locus != None:
self.last_line = l
return locus, fis, fst, fit, qintra, qinter
else:
locus = l.split(':')[1].lstrip()
elif l.startswith('Fis^='):
fis = _gp_float(l.split(' ')[1])
elif l.startswith('Fst^='):
fst = _gp_float(l.split(' ')[1])
elif l.startswith('Fit^='):
fit = _gp_float(l.split(' ')[1])
elif l.startswith('1-Qintra^='):
qintra = _gp_float(l.split(' ')[1])
elif l.startswith('1-Qinter^='):
qinter = _gp_float(l.split(' ')[1])
return locus, fis, fst, fit, qintra, qinter
l = self.stream.readline()
if locus != None:
return locus, fis, fst, fit, qintra, qinter
self.stream.close()
self.done = True
raise StopIteration
return (allFis, allFst, allFit), _FileIterator(proc , f, fname + ".FST")
#6.2
def calc_fst_pair(self, fname):
self._run_genepop([".ST2", ".MIG"], [6,2], fname)
f = open(fname + ".ST2")
l = f.readline()
while l != "":
l = l.rstrip()
if l.startswith("Estimates for all loci"):
avg_fst = _read_headed_triangle_matrix(f)
l = f.readline()
f.close()
def loci_func(self):
l = self.stream.readline()
while l != "":
l = l.rstrip()
m = re.search(" Locus: (.+)", l)
if m != None:
locus = m.group(1)
matrix = _read_headed_triangle_matrix(self.stream)
return locus, matrix
l = self.stream.readline()
self.done = True
raise StopIteration
stf = open(fname + ".ST2")
os.remove(fname + ".MIG")
return _FileIterator(loci_func, stf, fname + ".ST2"), avg_fst
#6.3
def calc_rho_all(self, fname):
raise NotImplementedError
#6.4
def calc_rho_pair(self, fname):
raise NotImplementedError
def _calc_ibd(self, fname, sub, stat="a", scale="Log", min_dist=0.00001):
"""Calculates isolation by distance statistics
"""
self._run_genepop([".GRA", ".MIG", ".ISO"], [6,sub],
fname, opts = {
"MinimalDistance" : min_dist,
"GeographicScale" : scale,
"IsolBDstatistic" : stat,
})
f = open(fname + ".ISO")
f.readline()
f.readline()
f.readline()
f.readline()
estimate = _read_triangle_matrix(f)
f.readline()
f.readline()
distance = _read_triangle_matrix(f)
f.readline()
match = re.match("a = (.+), b = (.+)", f.readline().rstrip())
a = _gp_float(match.group(1))
b = _gp_float(match.group(2))
f.readline()
f.readline()
match = re.match(" b=(.+)", f.readline().rstrip())
bb = _gp_float(match.group(1))
match = re.match(".*\[(.+) ; (.+)\]", f.readline().rstrip())
bblow = _gp_float(match.group(1))
bbhigh = _gp_float(match.group(2))
f.close()
os.remove(fname + ".MIG")
os.remove(fname + ".GRA")
os.remove(fname + ".ISO")
return estimate, distance, (a, b), (bb, bblow, bbhigh)
#6.5
def calc_ibd_diplo(self, fname, stat="a", scale="Log", min_dist=0.00001):
"""Calculates isolation by distance statistics for diploid data.
See _calc_ibd for parameter details.
Note that each pop can only have a single individual and
the individual name has to be the sample coordinates.
"""
return self._calc_ibd(fname, 5, stat, scale, min_dist)
#6.6
def calc_ibd_haplo(self, fname, stat="a", scale="Log", min_dist=0.00001):
"""Calculates isolation by distance statistics for haploid data.
See _calc_ibd for parameter details.
Note that each pop can only have a single individual and
the individual name has to be the sample coordinates.
"""
return self._calc_ibd(fname, 6, stat, scale, min_dist)