Newer
Older
# input:
# this trio PED file [${PED_DIR}/${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}_${KID_ID}.ped]
# individual VCF file for the trio proband [${FAMILY_ID}-gatk-haplotype-annotated.${SAMPLE_ID}.vcf.gz] ????
# G2P text output for the trio [${G2P_DIR}/${PLATE_ID}_${FAMILY_ID}_${KID_ID}_LOG_DIR/${PLATE_ID}_${FAMILY_ID}_${KID_ID}.report.txt]
# VASE output [${VASE_DIR}/${PLATE_ID}_${FAMILY_ID}_${KID_ID}.ready.denovo.vcf]
#
#
# output:
# DECIPHER formated file for the proband
# - all G2P variants
# - denovo variants marked as such
#
# checks:
# all G2P variants found in the individual VCF
# all VASE denovo variants found in the individual VCF
#
# Author: MH
# last modified: JAN 21, 2022
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
import sys
import os
import csv
import gzip
from collections import defaultdict
ASSEMBLY = 'GRCh38'
INTERGENIC = 'No'
ACCESS = 'No'
G2P_DICT = {} # key: chr:pos:ref:alt; value: 0 (if found only in G2P); 1 (if found in VCF) - for variants found in G2P output for this CHILD_ID
G2P_DATA = {} # key: chr:pos:ref:alt; value: (transcript,gene,GT)
VASE_DICT = {} # key: chr:pos:ref:alt; value: 0 (if found only in VASE); 1 (if found in VCF) - for variants found in VASE output for this CHILD_ID
NUM_UNIQ_G2P_VARS = 0
NUM_UNIQ_VASE_VARS = 0
CHILD_ID = 0
CHILD_SEX = 0
DEC_CHILD_SEX = 'unknown'
MOM_ID = 0
MOM_STAT = 0 # 1 = UNAFF, 2 = AFF
DAD_ID = 0
DAD_STAT = 0 # 1 = UNAFF, 2 = AFF
ALL_CHILD_DICT = {} # key: chr:pos:ref:alt; value: (num_ALT_reads,VAF)
ALL_MOM_DICT = {} # key: chr:pos:ref:alt; value: irrelevant
ALL_DAD_DICT = {} # key: chr:pos:ref:alt; value: irrelevant
CHILD_INHER_DICT = {} # key: chr:pos:ref:alt; value: 'Paternally inherited, constitutive in father' | 'Maternally inherited, constitutive in mother' | 'Biparental' | 'De novo constitutive' | 'Unknown'
SNAP_FLANK = 25
MAP_DICT = {} # key: family_id (aka decipher_id); value: internal (decipher) ID
TRANS_DICT = {} # key: transcriptID not found in DECIPHER; value: the chosen replacement transcriptID from those available in DECIPHER
FS_THRESH = float(60)
SOR_THRESH = float(3)
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
### call the python scrpit
#time ${PYTHON2} ${SCRIPTS_DIR}/NHS_WES_generate_DEC_IGV_trio_from_quad.py \
#${DECIPHER_ID} \
#${TRANS_MAP} \
#${PED_FILE} \
#${IN_G2P_FILE} \
#${IN_VASE_FILE} \
#${FAM_IGV_DIR} \
#${VCF_DIR} \
#${PLATE_ID} \
#${FAMILY_ID} \
#${DEC_DIR} \
#${FAM_BAM_DIR} \
#${KID_ID}
def go(dec_id,trans_map_file,ped_file,in_g2p_file,in_vase_file,fam_igv_dir,vcf_dir,plate_id,fam_id,dec_dir,fam_bam_dir,this_kid):
### # read the decipher to internal ID mapping file
### read_map_file(dec_map_file)
# set the Internal ID (called dec_id) for this Decipher ID (called fam_id)
MAP_DICT[fam_id] = dec_id
# read the transcript mapping file
read_trans_map(trans_map_file)
# read the ped file and establish CHILD_ID,CHILD_SEX,MOM_ID,DAD_ID
read_ped(ped_file)
if (CHILD_ID != 0) and (CHILD_SEX != 0) and (DEC_CHILD_SEX != 'unknown') and (MOM_ID != 0) and (MOM_STAT != 0) and (DAD_ID != 0) and (MOM_STAT != 0):
print "======================================"
print "Analyzing:"
print "CHILD_ID = %s, CHILD_SEX = %s, DEC_CHILD_SEX = %s" % (CHILD_ID,CHILD_SEX,DEC_CHILD_SEX)
print "MOM_ID = %s, MOM_STATUS = %s" % (MOM_ID,MOM_STAT)
print "DAD_ID = %s, DAD_STATUS = %s" % (DAD_ID,DAD_STAT)
print "======================================"
sys.stdout.flush()
else:
print "ERROR: problems reading the PED file = %s" % (ped_file)
raise SystemExit
# read the G2P output for this family
read_G2P(in_g2p_file)
# read the VASE output for this family
read_VASE(in_vase_file)
# now read the individual VCFs and record all the variants
child_vcf_file = '%s/%s_%s_%s.ready.%s.vcf.gz' % (vcf_dir,plate_id,fam_id,this_kid,CHILD_ID)
mom_vcf_file = '%s/%s_%s_%s.ready.%s.vcf.gz' % (vcf_dir,plate_id,fam_id,this_kid,MOM_ID)
dad_vcf_file = '%s/%s_%s_%s.ready.%s.vcf.gz' % (vcf_dir,plate_id,fam_id,this_kid,DAD_ID)
read_all_VCF_vars(child_vcf_file,ALL_CHILD_DICT)
print "Found %s unique VCF variants for CHILD (%s)" % (len(ALL_CHILD_DICT),CHILD_ID)
sys.stdout.flush()
read_all_VCF_vars(mom_vcf_file,ALL_MOM_DICT)
print "Found %s unique VCF variants for MOM (%s)" % (len(ALL_MOM_DICT),MOM_ID)
sys.stdout.flush()
read_all_VCF_vars(dad_vcf_file,ALL_DAD_DICT)
print "Found %s unique VCF variants for DAD (%s)" % (len(ALL_DAD_DICT),DAD_ID)
sys.stdout.flush()
# now go over all child variants and set the inheritance
num_child_vars_assigned = 0
for key,v in ALL_CHILD_DICT.iteritems():
if (key in ALL_MOM_DICT) and (key in ALL_DAD_DICT):
CHILD_INHER_DICT[key] = 'Biparental'
num_child_vars_assigned += 1
elif key in ALL_MOM_DICT:
CHILD_INHER_DICT[key] = 'Maternally inherited, constitutive in mother'
num_child_vars_assigned += 1
elif key in ALL_DAD_DICT:
CHILD_INHER_DICT[key] = 'Paternally inherited, constitutive in father'
num_child_vars_assigned += 1
else:
CHILD_INHER_DICT[key] = 'Unknown'
assigned_ratio = (float(num_child_vars_assigned)/float(len(ALL_CHILD_DICT)))*100.0
print "%s of the %s unique VCF variants (%.2f%%) for CHILD (%s) has been assigned to parents" % (num_child_vars_assigned,len(ALL_CHILD_DICT),assigned_ratio,CHILD_ID)
sys.stdout.flush()
# setup the DECIPHER output file
out_dec_file = '%s/%s_DEC_FLT.csv' % (dec_dir,CHILD_ID) ################################
out_han = open(out_dec_file,'w')
out_han.write('Internal reference number or ID,Chromosome,Start,Genome assembly,Reference allele,Alternate allele,Transcript,Gene name,Intergenic,Chromosomal sex,Other rearrangements/aneuploidy,Open-access consent,Age at last clinical assessment,Prenatal age in weeks,Note,Inheritance,Pathogenicity,Phenotypes,HGVS code,Genotype,Responsible contact\n')
# setup the IGV snapshot file
out_igv_file = '%s/IGV/%s.snapshot.FLT.txt' % (dec_dir,CHILD_ID) #################################
out_igv_han = open(out_igv_file,'w')
out_igv_han.write('new\n')
out_igv_han.write('genome hg38\n')
out_igv_han.write('mkdir -p "%s"\n' % (fam_igv_dir))
out_igv_han.write('new\n')
child_bam = '%s/%s/%s-ready.bam' % (fam_bam_dir,CHILD_ID,CHILD_ID)
mom_bam = '%s/%s/%s-ready.bam' % (fam_bam_dir,MOM_ID,MOM_ID)
dad_bam = '%s/%s/%s-ready.bam' % (fam_bam_dir,DAD_ID,DAD_ID)
out_igv_han.write('load %s\n' % (child_bam))
out_igv_han.write('load %s\n' % (mom_bam))
out_igv_han.write('load %s\n' % (dad_bam))
out_igv_han.write('snapshotDirectory "%s"\n' % (fam_igv_dir))
out_igv_han.write('\n')
# now read the child VCF, check if the variant in the G2P/VASE output, if yes:
# set the value in the dict to 1
# print out to to output file
in_cntr = 0
out_cntr = 0
child_vcf_file = '%s/%s_%s_%s.ready.%s.vcf.gz' % (vcf_dir,plate_id,fam_id,this_kid,CHILD_ID)
in_han = gzip.open(child_vcf_file,'r')
for line in in_han:
if line.startswith('#'):
continue
in_cntr += 1
data = [x.strip() for x in line.strip().split('\t')]
chr = data[0]
pos = int(data[1])
ref = data[3]
alt = data[4]
# extract FS and SOR
FS = ''
SOR = ''
infos = [y.strip() for y in data[7].strip().split(';')]
for info in infos:
if info.startswith('FS='):
tag,FS = info.split('=')
FS = float(FS)
elif info.startswith('SOR='):
tag,SOR = info.split('=')
SOR = float(SOR)
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
VCF_VAR = data[9]
key = '%s:%s:%s:%s' % (chr,pos,ref,alt)
inher_stat = CHILD_INHER_DICT[key]
##############################################################
# different processing depending on being a SNP, INS, or DEL #
##############################################################
if len(ref) == len(alt): # SNP
if len(ref) != 1:
print "ERROR: MNPs are not supported!"
print line
raise SystemExit
key_to_match = '%s:%s:%s:%s' % (chr,pos,ref,alt)
is_denovo = False
if key_to_match in VASE_DICT:
VASE_DICT[key_to_match] = 1
is_denovo = True
if key_to_match in G2P_DICT:
G2P_DICT[key_to_match] = 1
trans = G2P_DATA[key_to_match][0]
gene = G2P_DATA[key_to_match][1]
GT = G2P_DATA[key_to_match][2]
if is_denovo:
if inher_stat == 'Unknown':
inher_stat = 'De novo constitutive'
else:
print "ERROR: %s is both VASE denovo and %s from VCF" % (key,inher_stat)
raise SystemExit
if (chr != 'chrX') and (chr != 'chrY'):
if GT == 'HET':
genotype = 'Heterozygous'
elif GT == 'HOM':
genotype = 'Homozygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
elif (chr == 'chrX') or (chr == 'chrY'):
if DEC_CHILD_SEX == '46XX': # a girl
if GT == 'HET':
genotype = 'Heterozygous'
elif GT == 'HOM':
genotype = 'Homozygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
elif DEC_CHILD_SEX == '46XY': # a boy
if GT == 'HET':
genotype = 'Heterozygous'
print " WARNING: HET variant on chrX/Y for a boy (%s): %s\t%s\t%s\t%s\t%s" % (CHILD_ID,chr,pos,ref,alt,VCF_VAR)
elif GT == 'HOM':
genotype = 'Hemizygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
else:
print "ERROR: unknown sex for this proband = %s" % (DEC_CHILD_SEX)
raise SystemExit
else:
print "ERROR: unknown chr"
print line
raise SystemExit
# write to the DECIPHER file
gene_id_idx = gene.find('(')
if gene_id_idx == -1:
gene_id_idx = len(gene)
gene_id = gene[0:gene_id_idx]
int_ID = MAP_DICT[fam_id]
if trans in TRANS_DICT: # if the transcriptID is to be replaced
safe_trans = TRANS_DICT[trans]
else:
safe_trans = trans
to_write = '%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,,%s,,,,"%s",,,,%s,\n' % (int_ID,chr[3:],pos,ASSEMBLY,ref,alt,safe_trans,gene_id,INTERGENIC,DEC_CHILD_SEX,ACCESS,inher_stat,genotype)
out_cntr += 1
out_han.write(to_write)
# write to the IGV file
i_s = pos - SNAP_FLANK
i_e = pos + SNAP_FLANK
# check if above FS/SOR_THRESH to include in the snapshot name
if (FS == '') or (SOR == ''):
flag = 'NA'
elif (FS >= FS_THRESH) and (SOR >= SOR_THRESH):
flag = 'FS_%.1f_SOR_%.1f' % (FS,SOR)
else:
flag = 'OK'
i_name = '%s_%s_%s_%s_%s_%s.png' % (CHILD_ID,chr,pos,ref,alt,flag)
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
out_igv_han.write('goto %s:%s-%s\n' % (chr,i_s,i_e))
out_igv_han.write('sort strand\n')
out_igv_han.write('squish\n')
out_igv_han.write('snapshot %s\n' % (i_name))
out_igv_han.write('\n')
elif len(ref) > len(alt): # DEL
if len(alt) != 1:
print "ERROR with a deletion"
print line
raise SystemExit
G2P_key_to_match = '%s:%s:%s:-' % (chr,pos+1,ref[1:])
VASE_key_to_match = '%s:%s:%s:%s' % (chr,pos,ref,alt)
is_denovo = False
if VASE_key_to_match in VASE_DICT:
VASE_DICT[VASE_key_to_match] = 1
is_denovo = True
if G2P_key_to_match in G2P_DICT:
G2P_DICT[G2P_key_to_match] = 1
trans = G2P_DATA[G2P_key_to_match][0]
gene = G2P_DATA[G2P_key_to_match][1]
GT = G2P_DATA[G2P_key_to_match][2]
if is_denovo:
if inher_stat == 'Unknown':
inher_stat = 'De novo constitutive'
else:
print "ERROR: %s is both VASE denovo and %s from VCF" % (key,inher_stat)
raise SystemExit
if (chr != 'chrX') and (chr != 'chrY'):
if GT == 'HET':
genotype = 'Heterozygous'
elif GT == 'HOM':
genotype = 'Homozygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
elif (chr == 'chrX') or (chr == 'chrY'):
if DEC_CHILD_SEX == '46XX': # a girl
if GT == 'HET':
genotype = 'Heterozygous'
elif GT == 'HOM':
genotype = 'Homozygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
elif DEC_CHILD_SEX == '46XY': # a boy
if GT == 'HET':
genotype = 'Heterozygous'
print " WARNING: HET variant on chrX/Y for a boy (%s): %s\t%s\t%s\t%s\t%s" % (CHILD_ID,chr,pos,ref,alt,VCF_VAR)
elif GT == 'HOM':
genotype = 'Hemizygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
else:
print "ERROR: unknown sex for this proband = %s" % (DEC_CHILD_SEX)
raise SystemExit
else:
print "ERROR: unknown chr"
print line
raise SystemExit
# write to the DECIPHER file
gene_id_idx = gene.find('(')
if gene_id_idx == -1:
gene_id_idx = len(gene)
gene_id = gene[0:gene_id_idx]
int_ID = MAP_DICT[fam_id]
if trans in TRANS_DICT: # if the transcriptID is to be replaced
safe_trans = TRANS_DICT[trans]
else:
safe_trans = trans
to_write = '%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,,%s,,,,"%s",,,,%s,\n' % (int_ID,chr[3:],pos,ASSEMBLY,ref,alt,safe_trans,gene_id,INTERGENIC,DEC_CHILD_SEX,ACCESS,inher_stat,genotype)
out_cntr += 1
out_han.write(to_write)
# write to the IGV file
i_s = pos - SNAP_FLANK
i_e = pos + SNAP_FLANK
# check if above FS/SOR_THRESH to include in the snapshot name
if (FS == '') or (SOR == ''):
flag = 'NA'
elif (FS >= FS_THRESH) and (SOR >= SOR_THRESH):
flag = 'FS_%.1f_SOR_%.1f' % (FS,SOR)
else:
flag = 'OK'
i_name = '%s_%s_%s_%s_%s_%s.png' % (CHILD_ID,chr,pos,ref,alt,flag)
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
out_igv_han.write('goto %s:%s-%s\n' % (chr,i_s,i_e))
out_igv_han.write('sort strand\n')
out_igv_han.write('squish\n')
out_igv_han.write('snapshot %s\n' % (i_name))
out_igv_han.write('\n')
elif len(ref) < len(alt): # INS
if len(ref) != 1:
print "ERROR with an insertion"
print line
raise SystemExit
G2P_key_to_match = '%s:%s:-:%s' % (chr,pos+1,alt[1:])
VASE_key_to_match = '%s:%s:%s:%s' % (chr,pos,ref,alt)
is_denovo = False
if VASE_key_to_match in VASE_DICT:
VASE_DICT[VASE_key_to_match] = 1
is_denovo = True
if G2P_key_to_match in G2P_DICT:
G2P_DICT[G2P_key_to_match] = 1
trans = G2P_DATA[G2P_key_to_match][0]
gene = G2P_DATA[G2P_key_to_match][1]
GT = G2P_DATA[G2P_key_to_match][2]
if is_denovo:
if inher_stat == 'Unknown':
inher_stat = 'De novo constitutive'
else:
print "ERROR: %s is both VASE denovo and %s from VCF" % (key,inher_stat)
raise SystemExit
if (chr != 'chrX') and (chr != 'chrY'):
if GT == 'HET':
genotype = 'Heterozygous'
elif GT == 'HOM':
genotype = 'Homozygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
elif (chr == 'chrX') or (chr == 'chrY'):
if DEC_CHILD_SEX == '46XX': # a girl
if GT == 'HET':
genotype = 'Heterozygous'
elif GT == 'HOM':
genotype = 'Homozygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
elif DEC_CHILD_SEX == '46XY': # a boy
if GT == 'HET':
genotype = 'Heterozygous'
print " WARNING: HET variant on chrX/Y for a boy (%s): %s\t%s\t%s\t%s\t%s" % (CHILD_ID,chr,pos,ref,alt,VCF_VAR)
elif GT == 'HOM':
genotype = 'Hemizygous'
else:
print "ERROR: Cannot understand GT = %s" % (GT)
raise SystemExit
else:
print "ERROR: unknown sex for this proband = %s" % (DEC_CHILD_SEX)
raise SystemExit
else:
print "ERROR: unknown chr"
print line
raise SystemExit
# write to the DECIPHER file
gene_id_idx = gene.find('(')
if gene_id_idx == -1:
gene_id_idx = len(gene)
gene_id = gene[0:gene_id_idx]
int_ID = MAP_DICT[fam_id]
if trans in TRANS_DICT: # if the transcriptID is to be replaced
safe_trans = TRANS_DICT[trans]
else:
safe_trans = trans
to_write = '%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,,%s,,,,"%s",,,,%s,\n' % (int_ID,chr[3:],pos,ASSEMBLY,ref,alt,safe_trans,gene_id,INTERGENIC,DEC_CHILD_SEX,ACCESS,inher_stat,genotype)
out_cntr += 1
out_han.write(to_write)
# write to the IGV file
i_s = pos - SNAP_FLANK
i_e = pos + SNAP_FLANK
# check if above FS/SOR_THRESH to include in the snapshot name
if (FS == '') or (SOR == ''):
flag = 'NA'
elif (FS >= FS_THRESH) and (SOR >= SOR_THRESH):
flag = 'FS_%.1f_SOR_%.1f' % (FS,SOR)
else:
flag = 'OK'
i_name = '%s_%s_%s_%s_%s_%s.png' % (CHILD_ID,chr,pos,ref,alt,flag)
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
out_igv_han.write('goto %s:%s-%s\n' % (chr,i_s,i_e))
out_igv_han.write('sort strand\n')
out_igv_han.write('squish\n')
out_igv_han.write('snapshot %s\n' % (i_name))
out_igv_han.write('\n')
else:
print "Cannot establish the type of this VCF variant"
print line
raise SystemExit
in_han.close()
out_han.close()
out_igv_han.close()
### check if all G2P and VASE variants were found/matched in the proband's VCF
found_all_G2P = True
found_all_VASE = True
for k,v in G2P_DICT.iteritems():
if int(v) == 0:
print k
found_all_G2P = False
break
for k,v in VASE_DICT.iteritems():
if int(v) == 0:
print k
found_all_VASE = False
break
if found_all_G2P:
print "OK: Found all %s G2P variants in the proband's VCF file" % (len(G2P_DICT))
else:
print "ERROR: Could not find all G2P variants in the probands VCF file"
raise SystemExit
if found_all_VASE:
print "OK: Found all %s VASE variants in the proband's VCF file" % (len(VASE_DICT))
else:
print "ERROR: Could not find all VASE variants in the probands VCF file"
raise SystemExit
### check if all G2P variants are written out
if out_cntr == NUM_UNIQ_G2P_VARS:
print "OK: All G2P vars are recorded in the output DECIPHER file"
else:
print "ERROR: *NOT* all G2P vars are recorded in the G2P VCF file"
print "Wrote %s variants in outfile = %s" % (out_cntr,out_dec_file)
print "The batch snapshot file = %s" % (out_igv_file)
sys.stdout.flush()
def read_all_VCF_vars(in_vcf_file,THIS_DICT):
in_han = gzip.open(in_vcf_file,'r')
for line in in_han:
if line.startswith('#'):
continue
data = [x.strip() for x in line.strip().split('\t')]
chr = data[0]
pos = int(data[1])
ref = data[3]
alt = data[4]
# did the splitting and normalizing - should not have multiallelic variants
if alt.find(',') != -1:
print "ERROR: found multiallelic variant"
print line
raiseSystemExit
key = '%s:%s:%s:%s' % (chr,pos,ref,alt)
if key not in THIS_DICT:
THIS_DICT[key] = 1
else:
print "ERROR: duplicate key = %s in %s" % (key,in_vcf_file)
raise SystemExit
in_han.close()
def read_VASE(in_file):
global NUM_UNIQ_VASE_VARS
in_han = open(in_file,'r')
for line in in_han:
# ignore header lines
if line.startswith('#'):
continue
data = [x.strip() for x in line.strip().split('\t')]
chr = data[0]
pos = data[1]
ref = data[3]
alt = data[4]
key = '%s:%s:%s:%s' % (chr,pos,ref,alt)
if key not in VASE_DICT:
VASE_DICT[key] = 0
else:
print "ERROR: duplicate VASE variant key = %s" % (key)
raise SystemExit
in_han.close()
NUM_UNIQ_VASE_VARS = len(VASE_DICT)
print "Found %s unique VASE denovo variants for CHILD (%s)" % (NUM_UNIQ_VASE_VARS,CHILD_ID)
sys.stdout.flush()
def read_G2P(in_file):
global NUM_UNIQ_G2P_VARS
#.# known_OBS_states = ['monoallelic','biallelic','hemizygous','x-linked dominant','x-linked over-dominance']
known_OBS_states = ['monoallelic_autosomal','biallelic_autosomal','monoallelic_X_hem','monoallelic_X_het']
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
# first, read the G2P variants on canonical transcripts for each of the family members
CHILD_DICT = defaultdict(dict) # 1st level key: OBS state; 2nd level key: chr:start:end:ref:alt; value: (ZYG,gene,trans)
MOM_DICT = defaultdict(dict) # 1st level key: OBS state; 2nd level key: chr:start:end:ref:alt; value: (ZYG,gene,trans)
DAD_DICT = defaultdict(dict) # 1st level key: OBS state; 2nd level key: chr:start:end:ref:alt; value: (ZYG,gene,trans)
in_han = open(in_file,'r')
for line in in_han:
data = [x.strip() for x in line.strip().split('\t')]
# get the individual_id
sam_id = data[0]
# ignore variants not on canonical transcripts
is_canon = data[3]
if is_canon != 'is_canonical':
continue
# split the variants based on the gene's OBS model of inheritance
inher_model = data[4]
aaa,OBS_state = inher_model.split('=')
if OBS_state not in known_OBS_states:
print "ERROR: unknown OBS state = %s in %s" % (OBS_state,in_file)
raise SystemExit
# get the gene name in format ENSG00000165899(C12orf64,OTOGL)
gene_name = data[1]
# get the transcript name in format ENST00000238647
transcript = data[2]
# this is a list of variants (n>=1) on a canonical transcript in a gene being considered under any OBS state
var_list = [y.strip() for y in data[6].split(';')]
for v in var_list:
v_details = [z.strip() for z in v.split(':')]
chr = v_details[0]
start = int(v_details[1])
end = int(v_details[2])
ref = v_details[3]
alt = v_details[4]
GT = v_details[5]
second_key = '%s:%s:%s:%s:%s' % (chr,start,end,ref,alt)
if sam_id == CHILD_ID:
# check for duplication
if OBS_state not in CHILD_DICT:
CHILD_DICT[OBS_state][second_key] = (GT,gene_name,transcript)
elif second_key not in CHILD_DICT[OBS_state]:
CHILD_DICT[OBS_state][second_key] = (GT,gene_name,transcript)
else: # already recorded this variant
# if we have refseq recorded and this is ensembl --> replace
if not CHILD_DICT[OBS_state][second_key][1].startswith('ENSG'): # recorded is refseq
if gene_name.startswith('ENSG'): # this is ensembl
CHILD_DICT[OBS_state][second_key] = (GT,gene_name,transcript) # replace
else: # this is refseq again, ignore
pass
else: # recorded is ensembl, ignore
pass
elif sam_id == MOM_ID:
# check for duplication
if OBS_state not in MOM_DICT:
MOM_DICT[OBS_state][second_key] = (GT,gene_name,transcript)
elif second_key not in MOM_DICT[OBS_state]:
MOM_DICT[OBS_state][second_key] = (GT,gene_name,transcript)
else: # already recorded this variant
# if we have refseq recorded and this is ensembl --> replace
if not MOM_DICT[OBS_state][second_key][1].startswith('ENSG'): # recorded is refseq
if gene_name.startswith('ENSG'): # this is ensembl
MOM_DICT[OBS_state][second_key] = (GT,gene_name,transcript) # replace
else: # this is refseq again, ignore
pass
else: # recorded is ensembl, ignore
pass
elif sam_id == DAD_ID:
# check for duplication
if OBS_state not in DAD_DICT:
DAD_DICT[OBS_state][second_key] = (GT,gene_name,transcript)
elif second_key not in DAD_DICT[OBS_state]:
DAD_DICT[OBS_state][second_key] = (GT,gene_name,transcript)
else: # already recorded this variant
# if we have refseq recorded and this is ensembl --> replace
if not DAD_DICT[OBS_state][second_key][1].startswith('ENSG'): # recorded is refseq
if gene_name.startswith('ENSG'): # this is ensembl
DAD_DICT[OBS_state][second_key] = (GT,gene_name,transcript) # replace
else: # this is refseq again, ignore
pass
else: # recorded is ensembl, ignore
pass
else:
print "ERROR: cannot identify the person for this variant"
print line
raise SystemExit
in_han.close()
### print out the number of unique G2P variants in CHILD ###
child_mono = 0
child_bi = 0
child_hem = 0
child_het = 0
if 'monoallelic_autosomal' in CHILD_DICT:
child_mono = len(CHILD_DICT['monoallelic_autosomal'])
if 'biallelic_autosomal' in CHILD_DICT:
child_bi = len(CHILD_DICT['biallelic_autosomal'])
if 'monoallelic_X_hem' in CHILD_DICT:
child_hem = len(CHILD_DICT['monoallelic_X_hem'])
if 'monoallelic_X_het' in CHILD_DICT:
child_het = len(CHILD_DICT['monoallelic_X_het'])
print "CHILD (%s): number of unique G2P variants on canon transcript in the following OBS states" % (CHILD_ID)
print " monoallelic_autosomal: %s" % (child_mono)
print " biallelic_autosomal: %s" % (child_bi)
print " monoallelic_X_hem: %s" % (child_hem)
print " monoallelic_X_het: %s" % (child_het)
### print out the number of unique G2P variants in MOM ###
mom_mono = 0
mom_bi = 0
mom_hem = 0
mom_het = 0
if 'monoallelic_autosomal' in MOM_DICT:
mom_mono = len(MOM_DICT['monoallelic_autosomal'])
if 'biallelic_autosomal' in MOM_DICT:
mom_bi = len(MOM_DICT['biallelic_autosomal'])
if 'monoallelic_X_hem' in MOM_DICT:
mom_hem = len(MOM_DICT['monoallelic_X_hem'])
if 'monoallelic_X_het' in MOM_DICT:
mom_het = len(MOM_DICT['monoallelic_X_het'])
print "MOM (%s): number of unique G2P variants on canon transcript in the following OBS states" % (MOM_ID)
print " monoallelic_autosomal: %s" % (mom_mono)
print " biallelic_autosomal: %s" % (mom_bi)
print " monoallelic_X_hem: %s" % (mom_hem)
print " monoallelic_X_het: %s" % (mom_het)
### print out the number of unique G2P variants in DAD ###
dad_mono = 0
dad_bi = 0
dad_hem = 0
dad_het = 0
if 'monoallelic_autosomal' in DAD_DICT:
dad_mono = len(DAD_DICT['monoallelic_autosomal'])
if 'biallelic_autosomal' in DAD_DICT:
dad_bi = len(DAD_DICT['biallelic_autosomal'])
if 'monoallelic_X_hem' in DAD_DICT:
dad_hem = len(DAD_DICT['monoallelic_X_hem'])
if 'monoallelic_X_het' in DAD_DICT:
dad_het = len(DAD_DICT['monoallelic_X_het'])
print "DAD (%s): number of unique G2P variants on canon transcript in the following OBS states" % (DAD_ID)
print " monoallelic_autosomal: %s" % (dad_mono)
print " biallelic_autosomal: %s" % (dad_bi)
print " monoallelic_X_hem: %s" % (dad_hem)
print " monoallelic_X_het: %s" % (dad_het)
sys.stdout.flush()
######################################################################################################
#### Dominant filtering ####
#### if the gene has been considered under the dominant model (OBS == monoallelic_autosomal) ####
#### exclude child variants seen in UNAFFECTED mother/father, regardless of GT ####
######################################################################################################
print "=== monoallelic autosomal (DOMINANT) filtering ==="
for key in CHILD_DICT['monoallelic_autosomal']: # this the second key: chr:start:end:ref:alt; value: (ZYG,gene,trans)
CHILD_GT = CHILD_DICT['monoallelic_autosomal'][key][0]
CHILD_GENE = CHILD_DICT['monoallelic_autosomal'][key][1]
CHILD_TRANS = CHILD_DICT['monoallelic_autosomal'][key][2]
if (key in MOM_DICT['monoallelic_autosomal']) and (MOM_STAT == "UNAFFECTED"):
MOM_GT = MOM_DICT['monoallelic_autosomal'][key][0]
print "***[DOMINANT model]*** Excluded CHILD var %s in gene = %s, CHILD_GT = %s, MOM_GT = %s, MOM_STAT = %s" % (key,CHILD_GENE,CHILD_GT,MOM_GT,MOM_STAT)
if (key in DAD_DICT['monoallelic_autosomal']) and (DAD_STAT == "UNAFFECTED"):
DAD_GT = DAD_DICT['monoallelic_autosomal'][key][0]
print "***[DOMINANT model]*** Excluded CHILD var %s in gene = %s, CHILD_GT = %s, DAD_GT = %s, DAD_STAT = %s" % (key,CHILD_GENE,CHILD_GT,DAD_GT,DAD_STAT)
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
continue
# if a non-normalized INDEL in child G2P - must adjust (should not happen really, we split, normalized and left-aligned the family VCF before sending it to VEP+G2P)
chr,start,end,ref,alt = key.split(":")
if len(ref) > 1 and len(alt) > 1: # an INDEL - not normalized
if len(ref) < len(alt): # an INS
orig_start = start
orig_ref = ref
orig_alt = alt
start = orig_start
ref = '-'
alt = orig_alt[len(orig_ref):]
print " WARNING: original INS = %s:%s:%s:%s:%s --> replaced with INS = %s:%s:%s:%s" % (chr,orig_start,end,orig_ref,orig_alt,chr,start,ref,alt)
else: # a DEL
print "ERROR: At the momemnt, cannot deal with this non-normalized deletion"
print line
raise SystemExit
new_key = '%s:%s:%s:%s' % (chr,start,ref,alt)
# record the data for CHILD G2P variants (for OBS=monoallelic)
if new_key not in G2P_DICT:
G2P_DICT[new_key] = 0
else:
# print "ERROR: duplicate G2P variant new_key = %s" % (new_key)
# raise SystemExit
# this will happen if a gene is e.g. hemizygous,x-linked dominant - there will be two separate lines in the output for each req
pass
# and record the required data (CHILD_TRANS,CHILD_GENE,CHILD_GT) in G2P_DATA
if new_key not in G2P_DATA:
G2P_DATA[new_key] = (CHILD_TRANS,CHILD_GENE,CHILD_GT)
else:
# print "ERROR: duplicate G2P variant new_key = %s" % (new_key)
# raise SystemExit
# this will happen if a gene is e.g. hemizygous,x-linked dominant - there will be two separate lines in the output for each req
pass
NUM_UNIQ_G2P_VARS = len(G2P_DICT)
print "Found %s unique G2P variants in CHILD (%s) after considering MONOALLELIC genes" % (NUM_UNIQ_G2P_VARS,CHILD_ID)
sys.stdout.flush()
print ""
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
##############################################################################################################
#### Recessive filtering ####
#### under the recessive model (OBS == biallelic_autosomal) - consider ALL variants per gene ####
#### must all be HET in CHILD, GT in parent does not matter ####
#### all of them must *clearly* come from only one of the parents (maternally/paternally + biparental) ####
#### and this parent must be unaffected ####
#### if all these: then exclude all child variants in this gene ####
##############################################################################################################
print ""
print "=== biallelic autosomal (RECESSIVE) filtering ==="
GENE_KEY_GT = defaultdict(dict) # for child - 1st level key: gene_name; 2nd level key: chr:start:end:ref:alt; value: (GT,trans)
# process all variants in biallelic genes in child
for key in CHILD_DICT['biallelic_autosomal']: # this the second key: chr:start:end:ref:alt; value: (ZYG,gene,trans)
b_GT = CHILD_DICT['biallelic_autosomal'][key][0]
b_gene = CHILD_DICT['biallelic_autosomal'][key][1]
b_trans = CHILD_DICT['biallelic_autosomal'][key][2]
GENE_KEY_GT[b_gene][key] = (b_GT,b_trans)
# iterate over genes in GENE_KEY_GT
for g in GENE_KEY_GT: # this is the biallelic gene name
all_HET = True
# iterate over variants in this gene
for kx in GENE_KEY_GT[g]: # this the second key: chr:start:end:ref:alt
if GENE_KEY_GT[g][kx][0] == 'HOM': # there is a HOM variant in the child - NO filtering
all_HET = False
break
if all_HET: # for this gene
# all variants in this gene in the CHILD are HET, check if all come from a single unaffected parent
# if yes, filter out and write a message to the log file
# if not, to be added to G2P_DICT and G2P_DATA for further processing
all_from_one_parent = True
# iterate again over the variants in this gene
VAR_SOURCE_LIST = {} # key: chr:start:end:ref:alt in child; value: (NONE) or (MOM or DAD or BOTH and the parent is UNAFFECTED)
for ky in GENE_KEY_GT[g]: # this the second key: chr:start:end:ref:alt
this_var_status = 'NONE'
if ((ky in MOM_DICT['biallelic_autosomal']) or (ky in MOM_DICT['monoallelic_autosomal'])) and (MOM_STAT == "UNAFFECTED"):
this_var_status = 'MOM'
if ((ky in DAD_DICT['biallelic_autosomal']) or (ky in DAD_DICT['monoallelic_autosomal'])) and (DAD_STAT == "UNAFFECTED"):
if this_var_status == 'NONE':
this_var_status = 'DAD'
elif this_var_status == 'MOM':
this_var_status = 'BOTH'
VAR_SOURCE_LIST[ky] = this_var_status
# have collected the parent source for all variants in this gene
tot_num_vars = len(VAR_SOURCE_LIST)