forked from ryanlayer/samplot
-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathsamplot_vcf.py
More file actions
1343 lines (1193 loc) · 37.4 KB
/
Copy pathsamplot_vcf.py
File metadata and controls
1343 lines (1193 loc) · 37.4 KB
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
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Create samplot vcf commands to execute and generate
companion HTML image browser.
Note: additional arguments are passed through to samplot plot
"""
from __future__ import print_function
import argparse
import operator
import os
import random
import sys
import re
import pysam
from jinja2 import Environment, FileSystemLoader, select_autoescape
try:
from shlex import quote
except ImportError:
from pipes import quote
from .samplot import add_plot
cmp_lookup = {
">": operator.gt, # e.g. DHFC < 0.5
"<": operator.lt,
"<=": operator.le,
">=": operator.ge,
"==": operator.eq,
"contains": operator.contains, # e.g. CSQ contains HIGH
"exists": lambda a, b: True, # e.g. exists smoove_gene
}
class Sample(object):
__slots__ = [
"family_id",
"id",
"paternal_id",
"maternal_id",
"mom",
"dad",
"kids",
"i",
]
def __init__(self, line):
toks = line.rstrip().split()
self.family_id = toks[0]
self.id = toks[1]
self.paternal_id = toks[2]
self.maternal_id = toks[3]
self.kids = []
self.i = -1 # index in the vcf.
def __repr__(self):
return "Sample(id:{id},paternal_id:{pid},maternal_id:{mid})".format(
id=self.id, pid=self.paternal_id, mid=self.maternal_id
)
def flatten(value, sep=","):
"""
>>> flatten([1,2,3,4])
'1,2,3,4'
>>> flatten((5,6))
'5,6'
>>> flatten(0.987654321)
'0.987654'
>>> flatten(7)
'7'
>>> flatten("flatten")
'flatten'
"""
flat = None
# tuple or list
if isinstance(value, tuple) or isinstance(value, list):
flat = sep.join([str(i) for i in value])
# reformats long float values
elif isinstance(value, float):
flat = "%.6f" % (value,)
# string and int
else:
flat = str(value)
return flat
def get_format_fields(ids, variant):
"""
args:
ids (list) - list of FORMAT field IDs, e.g. ['AS', 'AP', 'DHFFC']
variant (pysam.libcbcf.VariantRecord)
returns:
list
"""
sample_format = []
for i, sample_fields in enumerate(variant.samples.values()):
for field_id in ids:
sample_field_val = flatten(sample_fields.get(field_id, ""))
if sample_field_val:
if len(sample_format) < i + 1:
sample_format.append("")
else:
sample_format[i] += " "
sample_format[i] += "{}={}".format(field_id, sample_field_val)
return sample_format
def get_format_title(samples, ids, variant):
"""
args:
samples (list) - list of sample IDs in order of VCF annotations
ids (list) - list of FORMAT field IDs, e.g. ['AS', 'AP', 'DHFFC']
variant (pysam.libcbcf.VariantRecord)
returns:
dict
"""
fields = get_format_fields(ids, variant)
return dict(zip(samples, fields))
def make_plot_titles(samples, attr_values):
"""
keeping this method separate in the event we add more things to the title
args:
samples (list) - list of sample IDs
attr_values (str) - string of VCF FORMAT values
returns:
dict
>>> make_plot_titles(
['s1', 's2', 's3'],
{
's1': 'AS=0 AP=0',
's2': 'AS=0 AP=1',
's3': 'AS=1 AP=1'
}
)
{
's1': "'s1 AS=0 AP=0'",
's2': "'s2 AS=0 AP=1'",
's3': "'s3 AS=1 AP=1'"
}
"""
plot_titles = dict()
for sample in samples:
if sample in attr_values:
plot_titles[sample] = quote("%s %s" % (sample, attr_values[sample]))
return plot_titles
def get_overlap(
tabix,
chrom,
start,
end,
priority=["exon", "gene", "transcript", "cds"],
no_hit="intergenic",
fix_chr=True,
):
"""
args:
tabix (pysam.libctabix.TabixFile) - open TabixFile
chrom (str)
start (int)
end (int)
priority (Optional[list]) - order of preferred region annotation
no_hit (Optional[str]) - use this annotation if no matches among priority
fix_chr (Optional[bool]) - try to fetch a region using both
non-'chr' and 'chr' prefix on failures
returns:
str
"""
overlaps = None
try:
overlaps = set(
[i.split("\t")[2].lower() for i in tabix.fetch(chrom, start, end)]
)
except IndexError:
# probably not a gff3
print("Invalid annotation file specified for --gff3")
overlaps = None
except ValueError:
if fix_chr:
# try removing chr
if chrom.startswith("chr"):
overlaps = get_overlap(
tabix, chrom[3:], start, end, priority, no_hit, False
)
# or adding chr
else:
overlaps = get_overlap(
tabix,
"chr{chrom}".format(chrom=chrom),
start,
end,
priority,
no_hit,
False,
)
except:
# bad regions
print(
"Error fetching {chrom}:{start}-{end}".format(
chrom=chrom, start=start, end=end
)
)
overlaps = None
overlap = ""
if overlaps:
for feature in priority:
if feature in overlaps:
overlap = feature
break
else:
# fetching overlaps failed
overlap = "unknown"
if not overlap and no_hit:
overlap = no_hit
return overlap
def parse_ped(path, vcf_samples=None):
if path is None:
return {}
samples = []
look = {}
for line in open(path):
samples.append(Sample(line))
look[samples[-1].id] = samples[-1]
for s in samples:
s.dad = look.get(s.paternal_id)
if s.dad is not None:
s.dad.kids.append(s)
s.mom = look.get(s.maternal_id)
if s.mom is not None:
s.mom.kids.append(s)
# match these samples to the ones in the VCF.
if vcf_samples is not None:
result = []
for i, variant_sample in enumerate(vcf_samples):
if variant_sample not in look:
continue
result.append(next(s for s in samples if s.id == variant_sample))
result[-1].i = i
samples = result
return {s.id: s for s in samples}
def get_names_to_bams(bams, name_list=None):
"""
get mapping from names (read group samples) to bam paths)
this is useful because the VCF has the names and we'll want the bam paths
for those samples
if name_list is passed in as a parameter those will be used instead
"""
names = {}
if name_list:
if len(name_list) != len(bams):
sys.exit("List of sample IDs does not match list of alignment files.")
for i, p in enumerate(bams):
names[name_list[i]] = p
else:
for p in bams:
b = pysam.AlignmentFile(p)
try:
names[b.header["RG"][0]["SM"]] = p
except:
sys.exit(
"No RG field in alignment file "
+ p
+ ". \nInclude ordered list of sample IDs to avoid this error"
)
return names
def tryfloat(v):
try:
return float(v)
except:
return v
def to_exprs(astr):
"""
an expr is just a 3-tuple of "name", fn, value"
e.g. "DHFFC", operator.lt, 0.7"
>>> to_exprs("DHFFC < 0.5 & SVTYPE == 'DEL'")
[('DHFFC', <built-in function lt>, 0.5), ('SVTYPE', <built-in function eq>, 'DEL')]
>>> to_exprs("CSQ contains 'HIGH'")
[('CSQ', <built-in function contains>, 'HIGH')]
"""
astr = (x.strip() for x in astr.strip().split("&"))
result = []
for a in astr:
a = [x.strip() for x in a.split()]
if len(a) == 2:
assert a[1] == "exists", ("bad expression", a)
a.append("extra_arg")
assert len(a) == 3, ("bad expression", a)
assert a[1] in cmp_lookup, (
"comparison:"
+ a[1]
+ " not supported. must be one of:"
+ ",".join(cmp_lookup.keys())
)
result.append((a[0], cmp_lookup[a[1]], tryfloat(a[2].strip("'").strip('"'))))
return result
def check_expr(vdict, expr):
"""
>>> check_expr({"CSQ": "asdfHIGHasdf"},
to_exprs("CSQ contains 'HIGH'"))
True
>>> check_expr({"CSQ": "asdfHIGHasdf", "DHFC": 1.1},
to_exprs("CSQ contains 'HIGH' & DHFC < 0.5"))
False
>>> check_expr({"CSQ": "asdfHIGHasdf", "DHFC": 1.1},
to_exprs("CSQ contains 'HIGH' & DHFC < 1.5"))
True
>>> check_expr({"smoove_gene": "asdf"},
to_exprs("smoove_gene exists"))
True
>>> check_expr({"smooe_gene": "asdf"},
to_exprs("smoove_gene exists"))
False
>>> check_expr({"smoove_gene": ""},
to_exprs("smoove_gene exists"))
True
"""
# a single set of exprs must be "anded"
for name, fcmp, val in expr:
# NOTE: asking for a missing annotation will return false.
if name not in vdict:
return False
if not fcmp(vdict[name], val):
return False
return True
def make_single(vdict):
"""
>>> d = {"xx": (1,)}
>>> make_single(d)
{'xx': 1}
"""
for k in vdict.keys():
if isinstance(vdict[k], tuple) and len(vdict[k]) == 1:
vdict[k] = vdict[k][0]
return vdict
def get_dn_row(ped_samples):
for s in ped_samples.values():
if s.mom is not None and s.dad is not None:
return '{title:"de novo", field:"dn"}'
return ""
def read_important_regions(bedfilename):
if not bedfilename:
return None
important_regions = {}
with open(bedfilename, "r") as bedfile:
for line in bedfile:
pos_fields = line.strip().split()
region_string = "_".join(pos_fields[1:3])
if pos_fields[0] not in important_regions:
important_regions[pos_fields[0]] = []
important_regions[pos_fields[0]].append(region_string)
return important_regions
def var_in_important_regions(important_regions, chrom, start, end, svtype, debug):
if not important_regions:
# if no important regions are set all locations are valid
return True
if chrom in important_regions:
for region in important_regions[chrom]:
region_st, region_end = [int(x) for x in region.split("_")]
if (
region_st <= start <= region_end
or region_st <= end <= region_end
or start <= region_st <= end
):
return True
if debug:
print(
"Skipping {} at {}:{}-{}, outside important_regions coordinates".format(
svtype, chrom, start, end
),
file=sys.stderr,
)
return False
def cram_input(bams):
for bam in bams:
if bam.endswith(".cram"):
return True
return False
def above_call_rate(gts, sample_count, min_call_rate, svtype, chrom, start, end, debug):
"""
skips variants with call rate below min_call_rate if set
"""
if not min_call_rate:
return True
call_rate = (sample_count - sum(None in g for g in gts)) / sample_count
if min_call_rate and (call_rate < min_call_rate):
if debug:
print(
(
"Skipping {} at {}:{}-{}, call rate of variant "
+ "({}) below min_call_rate"
).format(svtype, chrom, start, end, call_rate),
file=sys.stderr,
)
return False
return True
def below_max_hets(gts, max_hets, svtype, chrom, start, end, debug):
"""
skips variants with more than max_hets heterozygotes
if max_hets is set
"""
if not max_hets:
return False
# requisite hets/hom-alts
het_count = sum(sum(x) >= 1 for x in gts if None not in x)
if het_count > max_hets:
if debug:
print(
"Skipping {} at {}:{}-{}, more than max_hets heterozygotes".format(
svtype, chrom, start, end
),
file=sys.stderr,
)
return False
return True
def no_variant_found(gts, svtype, chrom, start, end, debug):
"""
skips variants with no non-ref samples
"""
if not any(sum(x) > 0 for x in gts if None not in x):
if debug:
print(
"Skipping {} at {}:{}-{}, no samples have non-ref genotypes".format(
svtype, chrom, start, end
),
file=sys.stderr,
)
return True
return False
def get_plottable_samples(
gts, variant, plot_all, filters, svtype, chrom, start, end, debug,
):
"""
gets the samples and indices for all those which need to be plotted,
which means passing filters and, if not plot_all, having a nonref genotype
"""
if plot_all:
test_idxs = [i for i, gt in enumerate(gts)]
if len(test_idxs) == 0 and debug:
print(
"No samples found for {} at {}:{}-{}".format(svtype, chrom, start, end),
file=sys.stderr,
)
else:
test_idxs = [i for i, gt in enumerate(gts) if None not in gt and sum(gt) > 0]
if len(test_idxs) == 0 and debug:
print(
"No non-reference samples found for {} at {}:{}-{}".format(
svtype, chrom, start, end
),
file=sys.stderr,
)
test_samples = [s for i, s in enumerate(variant.samples.values()) if i in test_idxs]
# apply filters if set
if len(filters) == 0:
idxs = test_idxs
else:
idxs = []
odict = make_single(dict(variant.info.items()))
for i, ts in enumerate(test_samples):
vdict = odict.copy()
vdict.update(make_single(dict(ts.items())))
if any(check_expr(vdict, fs) for fs in filters):
idxs.append(test_idxs[i])
if len(idxs) == 0 and debug:
print(
"No samples pass filters for {} at {}:{}-{}".format(
svtype, chrom, start, end
),
file=sys.stderr,
)
return idxs, test_samples
def get_variant_samples(
idxs, vcf_samples, names_to_bams, svtype, chrom, start, end, debug,
):
"""
gets the samples that need to be plotted and have alignment files assigned
"""
variant_samples = []
for i in idxs:
if vcf_samples[i] in names_to_bams:
variant_samples.append(vcf_samples[i])
if len(variant_samples) == 0:
if debug:
print(
(
"Skipping {} at {}:{}-{}, no plottable samples "
+ "with matched alignment files"
).format(svtype, chrom, start, end),
file=sys.stderr,
)
return variant_samples
def get_denovos(
denovo_row,
test_samples,
variant_samples,
ped_samples,
svtype,
chrom,
start,
end,
dn_only,
debug,
):
"""
we call it a de novo if the sample passed the filters but the mom and
dad had homref genotypes before filtering.
so stringent filtering on the kid and lenient on parents.
"""
denovo_svs = []
if denovo_row != "":
test_sample_names = {s.name for s in test_samples}
for variant_sample in variant_samples:
sample = ped_samples[variant_sample]
if sample.mom is None or sample.dad is None:
continue
if (
sample.mom.id not in test_sample_names
and sample.dad.id not in test_sample_names
):
denovo_svs.append(sample.id)
if len(denovo_svs) <= 0 and dn_only:
if debug:
print(
"Skipping {} at {}:{}-{}, dn_only selected and no de novos found".format(
svtype, chrom, start, end
),
file=sys.stderr,
)
return denovo_svs
def get_family_controls(
ped,
denovo_svs,
variant_samples,
ped_samples,
max_hets,
bams,
names_to_bams,
vcf_samples_set,
):
"""
tries to find family members to use as controls for putative de novos
"""
# do DN samples first so we can see parents.
# TODO also need to do the non-denovos as they seem to have been forgotten
for variant_sample in denovo_svs + [
x for x in variant_samples if x not in denovo_svs
]:
sample = ped_samples.get(variant_sample)
if sample is None:
continue
if (
sample.mom is not None
and sample.mom.id not in variant_samples
and sample.mom.id in vcf_samples_set
):
variant_samples.append("mom-of-%s[%s]" % (variant_sample, sample.mom.id))
bams.append(names_to_bams[sample.mom.id])
if (
sample.dad is not None
and sample.dad.id not in variant_samples
and sample.dad.id in vcf_samples_set
):
variant_samples.append("dad-of-%s[%s]" % (variant_sample, sample.dad.id))
bams.append(names_to_bams[sample.dad.id])
for kid in sample.kids:
if kid.id not in variant_samples and kid.id in vcf_samples_set:
variant_samples.append("kid-of-%s[%s]" % (variant_sample, kid.id))
bams.append(names_to_bams[kid.id])
if max_hets:
if len(bams) > 1.5 * max_hets:
break
if max_hets:
if len(bams) > 1.5 * max_hets:
break
return variant_samples, bams
def get_nonfamily_controls(
gts, vcf_samples, variant_samples, names_to_bams, min_entries, bams
):
# extend with some controls:
hom_ref_idxs = [
i for i, gt in enumerate(gts) if len(gt) == 2 and gt[0] == 0 and gt[1] == 0
]
if len(hom_ref_idxs) > 3:
random.shuffle(hom_ref_idxs)
hom_ref_samples = []
for i in hom_ref_idxs:
if vcf_samples[i] in names_to_bams:
hom_ref_samples.append(vcf_samples[i])
to_add_count = min_entries - len(bams)
bams.extend(names_to_bams[s] for s in hom_ref_samples[:to_add_count])
variant_samples += ["control-sample:" + s for s in hom_ref_samples[:to_add_count]]
return variant_samples, bams
def create_metadata(
variant,
translocation_chrom,
svtype,
sample_str,
n_samples,
annotations,
denovo_row,
denovo_svs,
):
"""
creates a dict with the info about the SV
that will be used in the website
"""
data_dict = {
"chrom": variant.chrom,
"chrom2": translocation_chrom,
"start": variant.start,
"end": variant.stop,
"svtype": svtype,
"svlength": variant.stop - variant.start,
"samples": sample_str,
"nsamples": n_samples,
}
if annotations:
data_dict["overlaps"] = get_overlap(
annotations, variant.chrom, variant.start, variant.stop
)
if denovo_row != "":
data_dict["dn"] = ",".join(denovo_svs)
return data_dict
def format_template(
variant,
data_dict,
max_entries,
bams,
variant_samples,
plot_titles,
out_dir,
output_type,
svtype,
downsample,
pass_through_args,
):
"""
formates the template string for generation of the final command
"""
if data_dict["chrom2"] is None:
figname_template = "{svtype}_{chrom}_{start}_{end}.{itype}"
else:
figname_template = "{svtype}_{chrom}_{start}_{chrom2}_{end}.{itype}"
fig_path = os.path.join(
out_dir, figname_template.format(itype=output_type, **data_dict),
)
if "CIPOS" in variant.info:
v = variant.info["CIPOS"]
cipos = "--start_ci '%s,%s'" % (abs(int(v[0])), abs(int(v[1])))
else:
cipos = ""
if "CIEND" in variant.info:
v = variant.info["CIEND"]
ciend = "--end_ci '%s,%s'" % (abs(int(v[0])), abs(int(v[1])))
else:
ciend = ""
# dynamically set Z to speed drawing and remove noise for larger events
z = 3
if variant.stop - variant.start > 2000:
z = 4
if variant.stop - variant.start > 10000:
z = 6
if variant.stop - variant.start > 20000:
z = 9
if max_entries:
bams = bams[:max_entries]
variant_samples = variant_samples[:max_entries]
# update titles based on FORMAT fields requested
title_list = list()
for variant_sample in variant_samples:
if variant_sample in plot_titles:
title_list.append(plot_titles[variant_sample])
else:
title_list.append(variant_sample)
start = variant.start
stop = variant.stop
start2 = None
stop2 = None
if data_dict["chrom2"] is None:
template = (
"samplot plot {extra_args} -z {z} -n {titles} "
+ "{cipos} {ciend} {svtype} -c {chrom} -s {start} "
+ "-e {end} -o {fig_path} -d {downsample} -b {bams}"
)
else:
template = (
"samplot plot {extra_args} -z {z} -n {titles} "
+ "{cipos} {ciend} {svtype} -c {chrom} -s {start}"
+ "-e {end} -o {fig_path} -d {downsample} -b {bams}"
)
template += " -c {chrom2} -s {start2} -e {end2}"
start2 = stop
stop2 = start2 + 1
stop = start + 1
command = template.format(
extra_args=" ".join(pass_through_args),
bams=" ".join(bams),
titles=" ".join(title_list),
z=z,
cipos=cipos,
ciend=ciend,
svtype="-t " + svtype if svtype != "SV" else "",
fig_path=fig_path,
chrom=variant.chrom,
start=start,
end=stop,
downsample=downsample,
chrom2=data_dict["chrom2"],
start2=start2,
end2=stop2,
) + "\n"
return command
def write_site(table_data, out_dir, output_type, annotations, denovo_row):
# grab the template
env = Environment(
loader=FileSystemLoader(os.path.join(os.path.dirname(__file__), "templates")),
autoescape=select_autoescape(["html"]),
)
html_template = env.get_template("samplot_vcf.html")
# write index.html
with open("{out_dir}/index.html".format(out_dir=out_dir), "w") as fh:
print(
html_template.render(
data=table_data,
plot_type=output_type,
gff3="true" if annotations else "false",
denovo="true" if denovo_row else "false",
),
file=fh,
)
def is_simply_skippable(
variant,
vcf_samples,
gts,
important_regions,
max_mb,
min_bp,
min_call_rate,
max_hets,
plot_all,
translocation_chrom,
debug,
):
"""
checks several basic terms that could filter this variant out
specifically, if the variant type is INS,
or fails the important regions,
max_mb, min_bp, min_call_rate, or max_hets filters
"""
svtype = variant.info.get("SVTYPE", "SV")
# skips variants outside important regions if those are set
if not var_in_important_regions(
important_regions, variant.chrom, variant.start, variant.stop, svtype, debug,
):
return True
# skips insertions
if svtype in ("INS"):
if debug:
print(
"Skipping {} at {}:{}-{}, INS type not supported".format(
svtype, variant.chrom, variant.start, variant.stop
),
file=sys.stderr,
)
return True
# skips variants over max_mb length, if set
if max_mb and (variant.stop - variant.start > max_mb * 1000000):
if debug:
print(
"Skipping {} at {}:{}-{}, variant length greater than max_mb".format(
svtype, variant.chrom, variant.start, variant.stop
),
file=sys.stderr,
)
return True
# skips variants under min_bp, if set
if (variant.stop - variant.start < min_bp) and translocation_chrom is None:
if debug:
print(
"Skipping {} at {}:{}-{}, variant length shorter than min_bp".format(
svtype, variant.chrom, variant.start, variant.stop
),
file=sys.stderr,
)
return True
# skips variants if the call rate is below min_call_rate, if set
if not above_call_rate(
gts,
len(vcf_samples),
min_call_rate,
svtype,
variant.chrom,
variant.start,
variant.stop,
debug,
):
return True
# skips variants if there are more hets than max_hets, if set
if below_max_hets(
gts, max_hets, svtype, variant.chrom, variant.start, variant.stop, debug
):
return True
# skips variants where no sample is non-ref, if plot_all is not set
if not plot_all:
if no_variant_found(
gts, svtype, variant.chrom, variant.start, variant.stop, debug
):
return True
return False
def generate_commands(
vcf,
plot_all,
max_mb,
min_bp,
min_call_rate,
max_hets,
dn_only,
ped,
important_regions,
format_field_ids,
min_entries,
max_entries,
out_dir,
output_type,
downsample,
filters,
ped_samples,
denovo_row,
names_to_bams,
annotations,
pass_through_args,
debug,
):
"""
for every variant in vcf, process and output plot
command - if and only if it passes filters
"""
commands = []
table_data = []
vcf_samples = vcf.header.samples
vcf_samples_set = set(vcf_samples)
vcf_samples_list = list(vcf_samples)
for var_count, variant in enumerate(vcf):
translocation_chrom = None
svtype = variant.info.get("SVTYPE", "SV")
# get genotypes
gts = [s.get("GT", (None, None)) for s in variant.samples.values()]
# handle translocations
if svtype in ["BND", "TRA"]:
try:
# TODO add specific exception
translocation_chrom = variant.info.get("CHR2x")
# translocation_chrom = variant.info.get("CHR2")
except:
pass
if is_simply_skippable(
variant,
vcf_samples,
gts,
important_regions,
max_mb,
min_bp,
min_call_rate,
max_hets,
plot_all,
translocation_chrom,
debug,
):
continue
# gets the list of samples to plot
# skips ref samples if plot_all isn't set
# and applies user-defined filters
idxs, test_samples = get_plottable_samples(
gts,
variant,
plot_all,
filters,
svtype,
variant.chrom,
variant.start,
variant.stop,
debug,
)
if len(idxs) == 0:
continue
# matches alignment files to variant samples
variant_samples = get_variant_samples(
idxs,
vcf_samples,
names_to_bams,
svtype,
variant.chrom,
variant.start,
variant.stop,
debug,
)