-
Notifications
You must be signed in to change notification settings - Fork 4
Expand file tree
/
Copy pathget_align_info.py
More file actions
1568 lines (1329 loc) · 65.3 KB
/
get_align_info.py
File metadata and controls
1568 lines (1329 loc) · 65.3 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
# %%
from Bio import SeqIO
import csv
import math
#pysam: https://pysam.readthedocs.io/en/latest/usage.html
import pysam
#print(pysam.__version__)
from Bio.Seq import Seq
from Bio import pairwise2
import sys
import numpy as np
from Bio import Align
import mappy
import os
#function to get seq record from a fasta file
#seq_name: string, file_name:string with suffix
def getSeqRec(seq_name, file_name):
#fasta_file = SeqIO.parse(file_name, "fasta")
#for record in fasta_file:
# if seq_name == record.id.strip():
# return record
fasta_file = pysam.FastaFile(file_name)
seq = fasta_file.fetch(seq_name)
return seq
def getQuerySeqRec(seq_name):
seq = query_fasta_file.fetch(seq_name)
return seq
#get the most close 'interval(500)' before sv_pos
def getRefStart(sv_pos, interval):
start = math.floor(sv_pos/interval) * interval
return start
#get the most close 'interval(500)' after sv_stop
def getRefEnd(sv_stop, interval):
end = math.ceil(sv_stop/interval) * interval
return end
#lookup in a dict given a key
def lookupDict(key, dictionary):
result = dictionary.get(key)
return result
#get depth of coverage given position of a chromosome and a target bam_file
#TODO: probably will not do read-depth filtering for giab callset:
#1. they should be reliable;
#2. they are a combination of multiple sources: don't know depth;
def get_depth(ref_name, ref_pos, bam_file):
pos_str = ref_name + ':' + str(int(ref_pos) - 1) + '-' + str(ref_pos)
res = pysam.depth("-r", pos_str, bam_file)
if res=='':
return 0
start = 0
end = len(res) - 1
for i in range(len(res) - 1, -1, -1):
if res[i] == '\t':
start = i + 1
break
return int(res[start:end])
#write error cases with error messages
def write_err(output_file_name, message):
f = open(output_file_name, "a")
f.write(str(counter) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(-1) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(str(0) + "\t")
f.write(message + "\t")
f.write("\n")
f.close()
#return chr name as an integer
#X = 23, Y = 24
def get_int_chr_name(name, if_hg38):
#remove "chr"
if if_hg38:
chr_name = name[3:]
else:
chr_name = name
if chr_name.upper() == 'X':
int_name = 23
elif chr_name.upper() == 'Y':
int_name = 24
else:
int_name = int(chr_name)
return int_name
#build map
def build_map(chr_len, interval, liftover_file, if_hg38):
contig_name_list = []
contig_pos_list = []
for i in range(1, 25):
lo_length = chr_len[i-1]
#set the initial values to -1
contig_name_list.append(np.zeros(int(lo_length/interval) + 1, dtype='int16') - 1)
contig_pos_list.append(np.zeros(int(lo_length/interval) + 1, dtype='uint32'))
#build a dictionary for contig names: to avoid store too many str
contig_name_dict = dict()
with open(liftover_file) as f:
contig_name_ctr = -1
pre_contig_name = ""
for line in f:
record = line.strip().split()
int_ref_name = get_int_chr_name(record[4], if_hg38)
ref_pos = int(record[5])
contig_pos = int(record[1])
#store contig name in a dict to save memory
contig_name = record[0]
if contig_name != pre_contig_name:
#contig_name_ctr starting from 0
contig_name_ctr += 1
contig_name_dict[contig_name_ctr] = contig_name
pre_contig_name = contig_name
#chr index: 0-23
lo_list_index = int_ref_name - 1
#pos in the chr list
lo_list_pos = int(ref_pos//interval)
contig_name_list[lo_list_index][lo_list_pos] = contig_name_ctr
contig_pos_list[lo_list_index][lo_list_pos] = contig_pos
f.close()
return contig_name_list, contig_pos_list, contig_name_dict
def build_map_compress(chr_len, interval, liftover_file, if_hg38):
contig_name_list = []
contig_pos_list = []
for i in range(1, 25):
lo_length = chr_len[i-1]
#set the initial values to -1
contig_name_list.append(np.zeros(int(lo_length/interval) + 1, dtype='int16') - 1)
contig_pos_list.append(np.zeros(int(lo_length/interval) + 1, dtype='uint32'))
#build a dictionary for contig names: to avoid store too many str
contig_name_dict = dict()
with open(liftover_file) as f:
contig_name_ctr = -1
pre_contig_name = ""
for line in f:
record = line.strip().split()
int_ref_name = get_int_chr_name(record[0], if_hg38)
#store contig name in a dict to save memory
contig_name = record[1]
if contig_name != pre_contig_name:
#contig_name_ctr starting from 0
contig_name_ctr += 1
contig_name_dict[contig_name_ctr] = contig_name
pre_contig_name = contig_name
#chr index: 0-23
lo_list_index = int_ref_name - 1
lo_info = record[2].strip().split(";")
for info in lo_info[:len(lo_info)-1]:
info_list = info.strip().split(":")
ctr = int(info_list[2])
strand = info_list[3]
if strand == "+":
forward = True
elif strand == "-":
forward = False
for i in range(0, ctr):
ref_pos = int(info_list[0]) + i*interval
if forward:
contig_pos = int(info_list[1]) + i*interval
else:
contig_pos = int(info_list[1]) - i*interval
#pos in the chr list
lo_list_pos = int(ref_pos//interval)
contig_name_list[lo_list_index][lo_list_pos] = contig_name_ctr
contig_pos_list[lo_list_index][lo_list_pos] = contig_pos
f.close()
return contig_name_list, contig_pos_list, contig_name_dict
#get alignment score of given seq pair
def get_align_score(seq1, seq2):
aligner = Align.PairwiseAligner()
aligner.mode = 'global'
#aligner.mode = 'local'
aligner.match_score = 1
aligner.mismatch_score = -1
aligner.open_gap_score = -1
aligner.extend_gap_score = -0.5
#aligner.score_only = True
alignment_score = aligner.score(seq1, seq2)
return alignment_score
#invert sequence
def inversion_seq(seq):
inverted_seq = ''
for i in seq:
inverted_seq = i + inverted_seq
return inverted_seq
#get different chromosomes' tandem regions start/end index
def get_chr_tandem_shart_end_list(tandem_info, if_hg38):
start_list = [0] * 24
end_list = [0] * 24
cur_chr = tandem_info[0][0]
# print(tandem_info[chr_index_ctr][0], " start ", chr_index_ctr)
start_list[get_int_chr_name(cur_chr, if_hg38) - 1] = 0
for i, rec in enumerate(tandem_info[1:]):
if rec[0] != cur_chr:
# print(cur_chr, " end ", i-1)
end_list[get_int_chr_name(cur_chr, if_hg38) - 1] = i-1
cur_chr = rec[0]
# print(cur_chr, " start ", i)
start_list[get_int_chr_name(cur_chr, if_hg38) - 1] = i
# print(cur_chr, " end ", len(tandem_info)-1)
end_list[get_int_chr_name(cur_chr, if_hg38) - 1] = len(tandem_info)-1
return start_list, end_list
#check if in tandem repeats regions
def ol_tandem(ref_name, sv_pos, sv_stop, tandem_start_list, tandem_end_list, if_hg38, tandem_info):
if not tandem_info:
return [-1, -1]
ref_idx = get_int_chr_name(ref_name, if_hg38)
tandem_start_idx = tandem_start_list[ref_idx - 1]
tandem_end_idx = tandem_end_list[ref_idx - 1]
#index of tandem regions that contain sv start/end
tandem_region_sv_start = tandem_region_sv_end = -1
for i in range(tandem_start_idx, tandem_end_idx + 1):
if int(tandem_info[i][1]) <= sv_pos and int(tandem_info[i][2]) >= sv_pos:
tandem_region_sv_start = i
break
for i in range(tandem_start_idx, tandem_end_idx + 1):
if int(tandem_info[i][1]) <= sv_stop and int(tandem_info[i][2]) >= sv_stop:
tandem_region_sv_end = i
break
return [tandem_region_sv_start, tandem_region_sv_end]
def get_intervals(sv, cur_ref_name, ref_fasta_file, tandem_start_list, tandem_end_list, if_hg38, tandem_info, interval, memory_limit, contig_name_list, contig_pos_list, contig_name_dict, hap, ref_rec, region_len_m):
if sv.sv_type in ['INS', 'DEL', 'DUP:TANDEM', 'DUP']:
# region_len_m = 500
check_tandem = ol_tandem(sv.ref_name, sv.sv_pos, sv.sv_stop, tandem_start_list, tandem_end_list, if_hg38, tandem_info)
if check_tandem[0] != -1:
ref_start_start = max(getRefStart(int(tandem_info[check_tandem[0]][1]), interval) - region_len_m, 0)
ref_start_end = getRefStart(sv.sv_pos, interval)
else:
ref_start_start = max(getRefStart(sv.sv_pos, interval) - region_len_m, 0)
ref_start_end = getRefStart(sv.sv_pos, interval)
if check_tandem[1] != -1:
ref_end_start = getRefEnd(sv.sv_stop, interval)
ref_end_end = min(getRefEnd(int(tandem_info[check_tandem[1]][2]), interval) + region_len_m, getRefEnd(len(ref_rec), interval) - interval)
else:
ref_end_start = getRefEnd(sv.sv_stop, interval)
ref_end_end = min(getRefEnd(sv.sv_stop, interval) + region_len_m, getRefEnd(len(ref_rec), interval) - interval)
#if tandem repeat regions too large
if check_tandem[0] != -1 and check_tandem[1] != -1:
if int(tandem_info[check_tandem[1]][2]) - int(tandem_info[check_tandem[0]][1]) > memory_limit:
ref_start_start = max(getRefStart(sv.sv_pos, interval) - region_len_m, 0)
ref_start_end = getRefStart(sv.sv_pos, interval)
ref_end_start = getRefEnd(sv.sv_stop, interval)
ref_end_end = min(getRefEnd(sv.sv_stop, interval) + region_len_m, getRefEnd(len(ref_rec), interval) - interval)
#first level key: chr index as an int
int_ref_name = get_int_chr_name(sv.ref_name, if_hg38)
lo_list_index = int_ref_name - 1
first_key = lo_list_index
#second level key: ref list_pos
if sv.idx % 1000 == 0:
print(sv.idx)
min_diff_len = 100000000
ref_start_best = ref_start_start
ref_end_best = ref_end_start
query_start_best = None
query_end_best = None
start_contig_name_ctr = -1
end_contig_name_ctr = -1
neg_strand = False
for ref_end_cand in range(ref_end_start, ref_end_end, interval):
for ref_start_cand in range(ref_start_end, ref_start_start, -interval):
if ref_end_cand <= ref_start_cand:
continue
#second_key_start = str(ref_start_cand)
#second_key_end = str(ref_end_cand)
second_key_start = ref_start_cand//interval
second_key_end = ref_end_cand//interval
start_contig_name_ctr_cand = contig_name_list[first_key][second_key_start]
end_contig_name_ctr_cand = contig_name_list[first_key][second_key_end]
if start_contig_name_ctr_cand == -1 or end_contig_name_ctr_cand == -1:
#print("wrong second key")
message = "wrong_sec_key"
#write_err(output_file_name, message, g)
continue
if start_contig_name_ctr_cand != end_contig_name_ctr_cand:
#print("Not same contig")
message = "not_same_contig"
#write_err(output_file_name, message, g)
continue
query_start = contig_pos_list[first_key][second_key_start]
query_end = contig_pos_list[first_key][second_key_end]
neg_strand_tep = False
#in case: negtive strand
if query_end < query_start:
tem = query_start
query_start = query_end
query_end = tem
neg_strand_tep = True
#take the best relative length to be the optimal interval
if abs((query_end - query_start) - (ref_end_cand - ref_start_cand) - sv.length) < min_diff_len:
min_diff_len = abs((query_end - query_start) - (ref_end_cand - ref_start_cand) - sv.length)
ref_start_best = ref_start_cand
ref_end_best = ref_end_cand
query_start_best = query_start
query_end_best = query_end
start_contig_name_ctr = start_contig_name_ctr_cand
end_contig_name_ctr = end_contig_name_ctr_cand
if neg_strand_tep:
neg_strand = True
else:
neg_strand = False
if query_start_best == None or query_end_best == None:
#print("Wrong query pos")
message = "Wrong_query_pos"
#write_err(output_file_name, message, g)
return False
if ref_start_best == sv.sv_pos:
ref_start_best = ref_start_best - 1
if ref_end_best == sv.sv_stop:
ref_end_best = ref_end_best + 1
if query_end_best == query_start_best:
query_end_best += 1
if hap == 1:
sv.ref_start_best_hap1 = ref_start_best
sv.ref_end_best_hap1 = ref_end_best
sv.query_start_best_hap1 = query_start_best
sv.query_end_best_hap1 = query_end_best
sv.query_name_hap1 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap1 = neg_strand
elif hap == 2:
sv.ref_start_best_hap2 = ref_start_best
sv.ref_end_best_hap2 = ref_end_best
sv.query_start_best_hap2 = query_start_best
sv.query_end_best_hap2 = query_end_best
sv.query_name_hap2 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap2 = neg_strand
return True
#if inv, no need to use the flexible interval
#bc/ flexi int will be found by relative length
elif sv.sv_type == 'INV':
region_len = 500
check_tandem = ol_tandem(sv.ref_name, sv.sv_pos, sv.sv_stop, tandem_start_list, tandem_end_list, if_hg38, tandem_info)
if check_tandem[0] != -1:
ref_start = getRefStart(int(tandem_info[check_tandem[0]][1]), interval)
else:
ref_start = getRefStart(sv.sv_pos, interval)
if check_tandem[1] != -1:
ref_end = getRefEnd(int(tandem_info[check_tandem[1]][2]), interval)
else:
ref_end = getRefEnd(sv.sv_stop, interval)
# ref_start = getRefStart(sv_pos, interval)
# ref_end = getRefEnd(sv_stop, interval)
#first level key: chr index as an int
int_ref_name = get_int_chr_name(sv.ref_name, if_hg38)
lo_list_index = int_ref_name - 1
first_key = lo_list_index
if sv.idx % 1000 == 0:
print(sv.idx)
ref_start = ref_start-region_len
ref_end = ref_end+region_len
second_key_start = (ref_start)//interval
second_key_end = (ref_end)//interval
start_contig_name_ctr = contig_name_list[first_key][second_key_start]
end_contig_name_ctr = contig_name_list[first_key][second_key_end]
if start_contig_name_ctr == -1 or end_contig_name_ctr == -1:
#print("wrong second key")
message = "wrong_sec_key"
#write_err(output_file_name, message, g)
return False
if start_contig_name_ctr != end_contig_name_ctr:
#print("Not same contig")
message = "not_same_contig"
#write_err(output_file_name, message, g)
return False
query_start = contig_pos_list[first_key][second_key_start]
query_end = contig_pos_list[first_key][second_key_end]
neg_strand = False
#in case: negtive strand
if query_end < query_start:
tem = query_start
query_start = query_end
query_end = tem
neg_strand = True
if ref_start == sv.sv_pos:
ref_start = ref_start - 1
if ref_end == sv.sv_stop:
ref_end = ref_end + 1
if query_end == query_start:
query_end += 1
if hap == 1:
sv.ref_start_best_hap1 = ref_start
sv.ref_end_best_hap1 = ref_end
sv.query_start_best_hap1 = query_start
sv.query_end_best_hap1 = query_end
sv.query_name_hap1 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap1 = neg_strand
elif hap == 2:
sv.ref_start_best_hap2 = ref_start
sv.ref_end_best_hap2 = ref_end
sv.query_start_best_hap2 = query_start
sv.query_end_best_hap2 = query_end
sv.query_name_hap2 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap2 = neg_strand
return True
#for abn DEL only
def get_intervals_abn(sv, cur_ref_name, ref_fasta_file, tandem_start_list, tandem_end_list, if_hg38, tandem_info, interval, memory_limit, contig_name_list, contig_pos_list, contig_name_dict, hap, ref_rec, region_len_m):
if sv.sv_type in ['DEL']:
# region_len_m = 500
#if sv overlaps with tandem repeats
check_tandem = ol_tandem(sv.ref_name, sv.sv_pos - interval, sv.sv_stop + interval, tandem_start_list, tandem_end_list, if_hg38, tandem_info)
if check_tandem[0] != -1:
ref_start_start = max(getRefStart(int(tandem_info[check_tandem[0]][1]), interval) - region_len_m, 0)
ref_start_end = getRefStart(sv.sv_pos - interval, interval)
else:
ref_start_start = max(getRefStart(sv.sv_pos - interval, interval) - region_len_m, 0)
ref_start_end = getRefStart(sv.sv_pos - interval, interval)
if check_tandem[1] != -1:
ref_end_start = getRefEnd(sv.sv_stop + interval, interval)
ref_end_end = min(getRefEnd(int(tandem_info[check_tandem[1]][2]), interval) + region_len_m, getRefEnd(len(ref_rec), interval) - interval)
else:
ref_end_start = getRefEnd(sv.sv_stop + interval, interval)
ref_end_end = min(getRefEnd(sv.sv_stop + interval, interval) + region_len_m, getRefEnd(len(ref_rec), interval) - interval)
#if tandem repeat regions too large
if check_tandem[0] != -1 and check_tandem[1] != -1:
if int(tandem_info[check_tandem[1]][2]) - int(tandem_info[check_tandem[0]][1]) > memory_limit:
ref_start_start = max(getRefStart(sv.sv_pos - interval, interval) - region_len_m, 0)
ref_start_end = getRefStart(sv.sv_pos - interval, interval)
ref_end_start = getRefEnd(sv.sv_stop + interval, interval)
ref_end_end = min(getRefEnd(sv.sv_stop + interval, interval) + region_len_m, getRefEnd(len(ref_rec), interval) - interval)
#first level key: chr index as an int
int_ref_name = get_int_chr_name(sv.ref_name, if_hg38)
lo_list_index = int_ref_name - 1
first_key = lo_list_index
#second level key: ref list_pos
if sv.idx % 1000 == 0:
print(sv.idx)
min_diff_len = 100000000
ref_start_best = ref_start_start
ref_end_best = ref_end_start
query_start_best = None
query_end_best = None
start_contig_name_ctr = -1
end_contig_name_ctr = -1
neg_strand = False
#get the query interval start / end
query_key_start = getRefStart(sv.sv_pos, interval)//interval
query_key_end = getRefEnd(sv.sv_stop, interval)//interval
start_contig_name_ctr_query = contig_name_list[first_key][query_key_start]
end_contig_name_ctr_query = contig_name_list[first_key][query_key_end]
if start_contig_name_ctr_query == -1 or end_contig_name_ctr_query == -1:
#print("wrong second key")
message = "wrong_sec_key 1"
#write_err(output_file_name, message, g)
return False
if start_contig_name_ctr_query != end_contig_name_ctr_query:
#print("Not same contig")
message = "not_same_contig 1"
#write_err(output_file_name, message, g)
return False
query_int_start = contig_pos_list[first_key][query_key_start]
query_int_end = contig_pos_list[first_key][query_key_end]
#in case: negtive strand
if query_int_start < query_int_end:
tem = query_int_start
query_int_start = query_int_end
query_int_end = tem
for ref_end_cand in range(ref_end_start, ref_end_end, interval):
for ref_start_cand in range(ref_start_end, ref_start_start, -interval):
if ref_end_cand <= ref_start_cand:
continue
#second_key_start = str(ref_start_cand)
#second_key_end = str(ref_end_cand)
second_key_start = ref_start_cand//interval
second_key_end = ref_end_cand//interval
start_contig_name_ctr_cand = contig_name_list[first_key][second_key_start]
end_contig_name_ctr_cand = contig_name_list[first_key][second_key_end]
if start_contig_name_ctr_cand == -1 or end_contig_name_ctr_cand == -1:
#print("wrong second key")
message = "wrong_sec_key"
#write_err(output_file_name, message, g)
continue
if start_contig_name_ctr_cand != end_contig_name_ctr_cand:
#print("Not same contig")
message = "not_same_contig"
#write_err(output_file_name, message, g)
continue
query_start = contig_pos_list[first_key][second_key_start]
query_end = contig_pos_list[first_key][second_key_end]
neg_strand_tep = False
#in case: negtive strand
if query_end < query_start:
tem = query_start
query_start = query_end
query_end = tem
neg_strand_tep = True
#take the best relative length to be the optimal interval
if abs((query_end - query_start) - (ref_end_cand - ref_start_cand) - sv.length) < min_diff_len:
min_diff_len = abs((query_end - query_start) - (ref_end_cand - ref_start_cand) - sv.length)
ref_start_best = ref_start_cand
ref_end_best = ref_end_cand
query_start_best = query_start
query_end_best = query_end
start_contig_name_ctr = start_contig_name_ctr_cand
end_contig_name_ctr = end_contig_name_ctr_cand
if neg_strand_tep:
neg_strand = True
else:
neg_strand = False
if start_contig_name_ctr != start_contig_name_ctr_query:
message = "not_same_contig 2"
#write_err(output_file_name, message, g)
return False
if query_start_best == None or query_end_best == None:
#print("Wrong query pos")
message = "Wrong_query_pos"
#write_err(output_file_name, message, g)
return False
if ref_start_best == sv.sv_pos:
ref_start_best = ref_start_best - 1
if ref_end_best == sv.sv_stop:
ref_end_best = ref_end_best + 1
if query_end_best == query_start_best:
query_end_best += 1
if hap == 1:
sv.ref_start_best_hap1 = ref_start_best
sv.ref_end_best_hap1 = ref_end_best
sv.query_start_best_hap1 = query_start_best
sv.query_end_best_hap1 = query_end_best
sv.query_name_hap1 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap1 = neg_strand
sv.query_int_start1 = query_int_start
sv.query_int_end1 = query_int_end
elif hap == 2:
sv.ref_start_best_hap2 = ref_start_best
sv.ref_end_best_hap2 = ref_end_best
sv.query_start_best_hap2 = query_start_best
sv.query_end_best_hap2 = query_end_best
sv.query_name_hap2 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap2 = neg_strand
sv.query_int_start2 = query_int_start
sv.query_int_end2 = query_int_end
return True
#for calls large than memory_limit
def get_large_intervals(sv, cur_ref_name, ref_fasta_file, tandem_start_list, tandem_end_list, if_hg38, tandem_info, interval, memory_limit, contig_name_list, contig_pos_list, contig_name_dict, hap, ref_rec):
region_len = int(0.5 * abs(sv.length))
#region_len = 200
check_tandem = ol_tandem(sv.ref_name, sv.sv_pos, sv.sv_stop, tandem_start_list, tandem_end_list, if_hg38, tandem_info)
if check_tandem[0] != -1:
ref_start = getRefStart(int(tandem_info[check_tandem[0]][1]), interval)
else:
ref_start = getRefStart(sv.sv_pos, interval)
if check_tandem[1] != -1:
ref_end = getRefEnd(int(tandem_info[check_tandem[1]][2]), interval)
else:
ref_end = getRefEnd(sv.sv_stop, interval)
# ref_start = getRefStart(sv_pos, interval)
# ref_end = getRefEnd(sv_stop, interval)
#first level key: chr index as an int
int_ref_name = get_int_chr_name(sv.ref_name, if_hg38)
lo_list_index = int_ref_name - 1
first_key = lo_list_index
if sv.idx % 1000 == 0:
print(sv.idx)
ref_start = max(1, ref_start-region_len)
second_key_start = int((ref_start)//interval)
ref_end = min((len(contig_name_list[first_key]) - 1) * interval, ref_end+region_len)
second_key_end = int((ref_end)//interval)
start_contig_name_ctr = contig_name_list[first_key][second_key_start]
end_contig_name_ctr = contig_name_list[first_key][second_key_end]
if start_contig_name_ctr == -1 or end_contig_name_ctr == -1:
#print("wrong second key")
message = "wrong_sec_key"
#write_err(output_file_name, message, g)
return False
if start_contig_name_ctr != end_contig_name_ctr:
#print("Not same contig")
message = "not_same_contig"
#write_err(output_file_name, message, g)
return False
query_start = contig_pos_list[first_key][second_key_start]
query_end = contig_pos_list[first_key][second_key_end]
neg_strand = False
#in case: negtive strand
if query_end < query_start:
tem = query_start
query_start = query_end
query_end = tem
neg_strand = True
if ref_start == sv.sv_pos:
ref_start = ref_start - 1
if ref_end == sv.sv_stop:
ref_end = ref_end + 1
if query_end == query_start:
query_end += 1
if hap == 1:
sv.ref_start_best_hap1 = ref_start
sv.ref_end_best_hap1 = ref_end
sv.query_start_best_hap1 = query_start
sv.query_end_best_hap1 = query_end
sv.query_name_hap1 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap1 = neg_strand
elif hap == 2:
sv.ref_start_best_hap2 = ref_start
sv.ref_end_best_hap2 = ref_end
sv.query_start_best_hap2 = query_start
sv.query_end_best_hap2 = query_end
sv.query_name_hap2 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap2 = neg_strand
return True
#for calls large than memory_limit
def get_large_intervals_abn(sv, cur_ref_name, ref_fasta_file, tandem_start_list, tandem_end_list, if_hg38, tandem_info, interval, memory_limit, contig_name_list, contig_pos_list, contig_name_dict, hap, ref_rec):
region_len = int(0.5 * abs(sv.length))
#region_len = 200
check_tandem = ol_tandem(sv.ref_name, sv.sv_pos - interval, sv.sv_stop + interval, tandem_start_list, tandem_end_list, if_hg38, tandem_info)
if check_tandem[0] != -1:
ref_start = getRefStart(int(tandem_info[check_tandem[0]][1]), interval)
else:
ref_start = getRefStart(sv.sv_pos - interval, interval)
if check_tandem[1] != -1:
ref_end = getRefEnd(int(tandem_info[check_tandem[1]][2]), interval)
else:
ref_end = getRefEnd(sv.sv_stop + interval, interval)
# ref_start = getRefStart(sv_pos, interval)
# ref_end = getRefEnd(sv_stop, interval)
#first level key: chr index as an int
int_ref_name = get_int_chr_name(sv.ref_name, if_hg38)
lo_list_index = int_ref_name - 1
first_key = lo_list_index
if sv.idx % 1000 == 0:
print(sv.idx)
ref_start = max(1, ref_start-region_len)
second_key_start = int((ref_start)//interval)
ref_end = min((len(contig_name_list[first_key]) - 1) * interval, ref_end+region_len)
second_key_end = int((ref_end)//interval)
start_contig_name_ctr = contig_name_list[first_key][second_key_start]
end_contig_name_ctr = contig_name_list[first_key][second_key_end]
if start_contig_name_ctr == -1 or end_contig_name_ctr == -1:
#print("wrong second key")
message = "wrong_sec_key"
#write_err(output_file_name, message, g)
return False
if start_contig_name_ctr != end_contig_name_ctr:
#print("Not same contig")
message = "not_same_contig"
#write_err(output_file_name, message, g)
return False
query_start = contig_pos_list[first_key][second_key_start]
query_end = contig_pos_list[first_key][second_key_end]
#get the query interval start / end
query_key_start = getRefStart(sv.sv_pos, interval)//interval
query_key_end = getRefEnd(sv.sv_stop, interval)//interval
start_contig_name_ctr_query = contig_name_list[first_key][query_key_start]
end_contig_name_ctr_query = contig_name_list[first_key][query_key_end]
if start_contig_name_ctr != start_contig_name_ctr_query:
message = "not_same_contig 2"
#write_err(output_file_name, message, g)
return False
if start_contig_name_ctr_query == -1 or end_contig_name_ctr_query == -1:
#print("wrong second key")
message = "wrong_sec_key 1"
#write_err(output_file_name, message, g)
return False
if start_contig_name_ctr_query != end_contig_name_ctr_query:
#print("Not same contig")
message = "not_same_contig 1"
#write_err(output_file_name, message, g)
return False
query_int_start = contig_pos_list[first_key][query_key_start]
query_int_end = contig_pos_list[first_key][query_key_end]
#in case: negtive strand
if query_int_start < query_int_end:
tem = query_int_start
query_int_start = query_int_end
query_int_end = tem
neg_strand = False
#in case: negtive strand
if query_end < query_start:
tem = query_start
query_start = query_end
query_end = tem
neg_strand = True
if ref_start == sv.sv_pos:
ref_start = ref_start - 1
if ref_end == sv.sv_stop:
ref_end = ref_end + 1
if query_end == query_start:
query_end += 1
if hap == 1:
sv.ref_start_best_hap1 = ref_start
sv.ref_end_best_hap1 = ref_end
sv.query_start_best_hap1 = query_start
sv.query_end_best_hap1 = query_end
sv.query_name_hap1 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap1 = neg_strand
sv.query_int_start1 = query_int_start
sv.query_int_end1 = query_int_end
elif hap == 2:
sv.ref_start_best_hap2 = ref_start
sv.ref_end_best_hap2 = ref_end
sv.query_start_best_hap2 = query_start
sv.query_end_best_hap2 = query_end
sv.query_name_hap2 = contig_name_dict[start_contig_name_ctr]
sv.neg_strand_hap2 = neg_strand
sv.query_int_start1 = query_int_start
sv.query_int_end1 = query_int_end
return True
#write vali info
def write_vali_info(g, sv, hap):
g.write(str(sv.idx) + "\t")
if hap == 1:
alignment_beforeSV = sv.score_before_hap1
alignment_afterSV = sv.score_after_hap1
query_length = sv.len_query_hap1
ref_length = sv.len_ref_hap1
ref_start = sv.ref_start_best_hap1
ref_end = sv.ref_end_best_hap1
elif hap == 2:
alignment_beforeSV = sv.score_before_hap2
alignment_afterSV = sv.score_after_hap2
query_length = sv.len_query_hap2
ref_length = sv.len_ref_hap2
ref_start = sv.ref_start_best_hap2
ref_end = sv.ref_end_best_hap2
g.write(str(alignment_beforeSV) + "\t")
#g.write(str(1) + "\t")
g.write(str(alignment_afterSV) + "\t")
#g.write(str(1) + "\t")
#g.write(str(len(query_start_dic)) + "\t")
g.write(str(1) + "\t")
g.write(str(sv.sv_type) + "\t")
g.write(str(hap) + "\t")
g.write(str(query_length) + "\t")
g.write(str(ref_length) + "\t")
g.write(str(sv.length) + "\t")
#g.write(str(sv_stop-sv_pos+1) + "\t")
g.write(str(sv.ref_name) + "\t")
g.write(str(sv.sv_pos) + "\t")
g.write(str(sv.sv_stop) + "\t")
g.write(str(ref_start) + "\t")
g.write(str(ref_end) + "\t")
g.write(str(sv.sv_type) + "\t")
g.write("noerr" + "\t")
g.write("\n")
def align_before_after(output_dir, sv, query_seq, ref_seq_1, ref_seq_2):
#within length limit
if not sv.is_third_fil:
aligner = Align.PairwiseAligner()
aligner.mode = 'global'
#aligner.mode = 'local'
aligner.match_score = 1
aligner.mismatch_score = -1
aligner.open_gap_score = -1
aligner.extend_gap_score = -0.5
#aligner.score_only = True
alignment_beforeSV = aligner.score(query_seq, ref_seq_1)
alignment_afterSV = aligner.score(query_seq, ref_seq_2)
else:
h = open(output_dir+"tmp_query.fasta", "w")
h.write('>' + str(sv.idx) + "\n")
h.write(query_seq + "\n")
h.close()
# aligner = mappy.Aligner(fn_idx_in=output_dir+"tmp_query.fasta", scoring=[1,1,2,1])
aligner = mappy.Aligner(fn_idx_in=output_dir+"tmp_query.fasta")
#if not alignment: raise Exception("ERROR: failed to load/build index")
aligner_beforeSV = aligner.map(ref_seq_1, seq2=None, cs=False, MD=False)
aligner_afterSV = aligner.map(ref_seq_2, seq2=None, cs=False, MD=False)
#test
# for agt in aligner_beforeSV:
# alignment_beforeSV = len(query_seq) - (len(ref_seq_1) - agt.mlen)
# break
# for agt in aligner_afterSV:
# alignment_afterSV = len(query_seq) - (len(ref_seq_2) - agt.mlen)
# break
try:
agt_before = next(aligner_beforeSV)
except:
os.remove(output_dir+"tmp_query.fasta")
return None, None
try:
agt_after = next(aligner_afterSV)
except:
os.remove(output_dir+"tmp_query.fasta")
return None, None
alignment_beforeSV = len(query_seq) - (len(ref_seq_1) - agt_before.mlen)
alignment_afterSV = len(query_seq) - (len(ref_seq_2) - agt_after.mlen)
os.remove(output_dir+"tmp_query.fasta")
return alignment_beforeSV, alignment_afterSV
def align_before_after_abn(output_dir, sv, query_seq, ref_seq_1, query_afterSV_seq, ref_seq_2):
#within length limit
# if not sv.is_third_fil:
aligner = Align.PairwiseAligner()
aligner.mode = 'global'
#aligner.mode = 'local'
aligner.match_score = 1
aligner.mismatch_score = -1
aligner.open_gap_score = -1
aligner.extend_gap_score = -0.5
#aligner.score_only = True
alignment_beforeSV = aligner.score(query_seq, ref_seq_1)
alignment_afterSV = aligner.score(query_afterSV_seq, ref_seq_2)
return alignment_beforeSV, alignment_afterSV
#get vcf file and run score_callset on each SV record
def get_vali_info(output_dir, vcf_file, query_file, hap, ref_file, interval,
contig_name_list, contig_pos_list, contig_name_dict, memory_limit, if_hg38, chr_list,
tandem_start_list, tandem_end_list, tandem_info, sv_list, seq_resolved, region_len_m):
#query_file = query_file2
#hap = 2
name_str = "assem" + str(hap)
chromosome = "all"
output_file_name = output_dir + "align_info_" + name_str + "_chr" + chromosome + ".txt"
query_fasta_file = pysam.FastaFile(query_file)
ref_fasta_file = pysam.FastaFile(ref_file)
cur_ref_name = ""
g = open(output_file_name, "w")
for sv in sv_list:
#filtered by centromere, non-cov
if sv.is_sec_fil:
continue
if cur_ref_name != sv.ref_name:
cur_ref_name = sv.ref_name
ref_rec = ref_fasta_file.fetch(cur_ref_name)
#filtered by size
if not sv.is_third_fil:
#Search for the best second_key_start and second_key_end in the regions
if not get_intervals(sv, cur_ref_name, ref_fasta_file, tandem_start_list, tandem_end_list, if_hg38, tandem_info, interval, memory_limit, contig_name_list, contig_pos_list, contig_name_dict, hap, ref_rec, region_len_m):
continue
else:
#get the intervals, won't search
if not get_large_intervals(sv, cur_ref_name, ref_fasta_file, tandem_start_list, tandem_end_list, if_hg38, tandem_info, interval, memory_limit, contig_name_list, contig_pos_list, contig_name_dict, hap, ref_rec):
continue
if hap == 1:
query_rec = query_fasta_file.fetch(sv.query_name_hap1)
ref_start = sv.ref_start_best_hap1
ref_end = sv.ref_end_best_hap1
query_start = sv.query_start_best_hap1
query_end = sv.query_end_best_hap1
neg_strand = sv.neg_strand_hap1
elif hap == 2:
query_rec = query_fasta_file.fetch(sv.query_name_hap2)
ref_start = sv.ref_start_best_hap2
ref_end = sv.ref_end_best_hap2
query_start = sv.query_start_best_hap2
query_end = sv.query_end_best_hap2
neg_strand = sv.neg_strand_hap2
if query_start >= len(query_rec) or query_end >= len(query_rec):
message = "bad_query_pos"
#write_err(output_file_name, message, g)
continue
#case 1: DEL
if sv.sv_type == "DEL":