-
Notifications
You must be signed in to change notification settings - Fork 0
/
coverageAnalysis.py
1161 lines (1066 loc) · 44.8 KB
/
coverageAnalysis.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
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
#================================================================================
#NOTICE
#================================================================================
'''
'''
#================================================================================
#MODULES
#================================================================================
import re
import sys
import subprocess
import argparse
import os.path
import getpass
#================================================================================
#CLASS
#================================================================================
class Subject:
def __init__(self, name):
self.name = name
self.noCover = None
def breadth_append(self, breadth):
self.breadth = breadth
def no_cover_file_append(self, noCover):
self.noCover = noCover
def depth_at_each_pos_file_append(self, depth_at_each_pos_outputFile):
self.depth_at_each_pos = depth_at_each_pos_outputFile
def plot_depth_append(self, plotDepth):
self.plotDepth = plotDepth
class Region:
def __init__(self,chr,start,end):
self.chr = chr
self.start = start
self.end = end
self.txNcExIn = {}
self.dicOfSubject = {}
self.utrStart = 0
self.utrEnd = 0
def chr_append(self, chr):
self.chr = chr
def start_append(self, start):
self.start = start
def end_append(self, end):
self.end = end
def gene_append(self, gene):
self.gene = gene
def txNcExIn_append(self, txNc, exIn):
self.txNcExIn[txNc] = exIn
def dicOfSubject_append(self,name):
self.dicOfSubject[str(name)] = Subject(name)
def utr_append(self, utrStart,utrEnd):
self.utrStart = utrStart
self.utrEnd = utrEnd
#================================================================================
#FUNCTIONS
#================================================================================
def remove_tmp_file(tmpFileName):
'''
remove the given temporary file with bash command rm
'''
command = "rm {0}".format(tmpFileName)
subprocess.call(command, shell= True)
return
def min_region(listOfRegions,what):
min = 99999999999
if what == "start":
for region in listOfRegions:
if region.start < min:
min = region.start
elif what == "end":
for region in listOfRegions:
if region.end < min:
min = region.end
else:
print "error min_region"
return min
def max_region(listOfRegions,what):
max = 0
if what == "start":
for region in listOfRegions:
if region.start > max:
max = region.start
elif what == "end":
for region in listOfRegions:
if region.end > max:
max = region.end
else:
print "error min_region"
return max
def convert_position_into_listOfRegions(position, ref_hgtable):
'''
from the position string CHR:FROM-TO or CHR:POS given in argument
return a proper python list [CHR, FROM, TO] or [CHR, POS, POS+1]
interrupt the program if the position string is no conform
'''
listOfRegions = []
pattern1=re.compile("^chr.*[0-9]+-[0-9]+$")
pattern2=re.compile("^chr.*[0-9]+$")
if pattern1.match(position):
posSplit = re.split(":|-", position)
tmpChr = posSplit[0]
tmpStart = int(posSplit[1])
tmpEnd = int(posSplit[2])
elif pattern2.match(position):
posSplit = position.split(":")
tmpChr = posSplit[0]
tmpStart = int(posSplit[1])
tmpEnd = tmpStart+1
else:
print "WARNING position format CHR:START-END or CHR:POSITION expected"
sys.exit()
#get features
tmp_grep_chr = "tmp_grep_chr"
command = "grep {0} {1} > {2}".format(tmpChr, ref_hgtable, tmp_grep_chr)
subprocess.call(command, shell = True)
with open(tmp_grep_chr, 'r') as ref_hg:
in_tx = 0
for ligne in ref_hg.readlines():
splitLigne = ligne.split()
txStart = int(splitLigne[4])
txEnd = int(splitLigne[5])
if(tmpEnd >= txStart and tmpStart <= txEnd):
in_tx=1
geneName = splitLigne[0]
txName = splitLigne[1]
exonAllStart = splitLigne[9].split(",")[:-1]
exonAllEnd = splitLigne[10].split(",")[:-1]
cdsStart = int(splitLigne[6])
cdsEnd = int(splitLigne[7])
txStrand = splitLigne[3]
utr5Start = txStart
utr5End = cdsStart-1
utr3Start = cdsEnd+1
utr3End = txEnd
if txStrand != '-':
i=1
else:
i=len(exonAllStart)
if tmpEnd >= utr5Start and tmpStart <= utr5End:
#utr 5'
if txStrand != '-':
exIn = "utr_5"
else:
exIn = "utr_3"
if(utr5Start < tmpStart):
utr5Start = tmpStart
if(utr5End > tmpEnd):
utr5End = tmpEnd
region = Region(tmpChr, utr5Start, utr5End)
region.gene_append(geneName)
region.txNcExIn_append(txName, exIn)
listOfRegions.append(region)
for s, e in zip(exonAllStart, exonAllEnd):
exonStart = int(s)
exonEnd = int(e)
#est dans exon
if(tmpEnd >= exonStart and tmpStart <= exonEnd):
utrStart = 0
utrEnd = 0
if (exonStart < cdsStart and exonEnd < cdsStart) or (exonStart > cdsEnd and exonEnd > cdsEnd):
exIn = "UTR"
elif exonStart < cdsStart:
exIn = "UTR"
utrStart = cdsStart
utrEnd = exonEnd
elif exonEnd > cdsEnd:
exIn = "UTR"
utrStart = exonStart
utrEnd = cdsEnd
else:
exIn = i
if(exonStart < tmpStart):
exonStart = tmpStart
if(exonEnd > tmpEnd):
exonEnd = tmpEnd
region = Region(tmpChr, exonStart, exonEnd)
region.gene_append(geneName)
region.txNcExIn_append(txName, exIn)
region.utr_append(utrStart,utrEnd)
listOfRegions.append(region)
#est dans intron
intronStart = exonEnd+1
if i < len(exonAllStart):
intronEnd = int(exonAllStart[i])-1
if (tmpEnd >= intronStart and tmpStart <= intronEnd):
if(intronStart < tmpStart):
intronStart = tmpStart
if(intronEnd > tmpEnd):
intronEnd = tmpEnd
exIn = "intron_{0}".format(i)
region = Region(tmpChr, intronStart, intronEnd)
region.gene_append(geneName)
region.txNcExIn_append(txName, exIn)
listOfRegions.append(region)
if txStrand != '-':
i+=1
else:
i-=1
if tmpEnd >= utr3Start and tmpStart <= utr3End:
#utr 3'
if txStrand != '-':
exIn = "utr_3"
else:
exIn = "utr_5"
if(utr3Start < tmpStart):
utr3Start = tmpStart
if(utr3End > tmpEnd):
utr3End = tmpEnd
region = Region(tmpChr, utr3Start, utr3End)
region.gene_append(geneName)
region.txNcExIn_append(txName, exIn)
listOfRegions.append(region)
NCListOfRegions = []
geneName = "intergenic"
if in_tx == 0:
NCStart = tmpStart
NCEnd = tmpEnd
region = Region(tmpChr, NCStart, NCEnd)
region.gene_append(geneName)
region.txNcExIn_append("nc", "nc")
NCListOfRegions.append(region)
else:
NCEnd = max_region(listOfRegions,"end")
NCStart = min_region(listOfRegions,"start")
if NCStart > tmpStart:
region = Region(tmpChr, tmpStart, NCStart)
region.gene_append(geneName)
region.txNcExIn_append("nc", "nc")
NCListOfRegions.append(region)
for region in listOfRegions:
NCListOfRegions.append(region)
if NCEnd < tmpEnd:
region = Region(tmpChr, NCEnd, tmpEnd)
region.gene_append(geneName)
region.txNcExIn_append("nc", "nc")
NCListOfRegions.append(region)
ref_hg.close()
return NCListOfRegions
def convert_gene_into_region(geneName, ref_hgtable, cdsMode):
tmp_grep_gen = "tmp_grep_gen"
command = """grep "{0}\t" {1} > {2}""".format(geneName, ref_hgtable, tmp_grep_gen)
subprocess.call(command, shell = True)
listOfRegions = []
with open(tmp_grep_gen, 'r') as ref_hg:
for ligne in ref_hg.readlines():
splitLigne = ligne.split()
txChr = splitLigne[2]
txName = splitLigne[1]
txGene = splitLigne[0]
txStart = int(splitLigne[4])
txEnd = int(splitLigne[5])
txStrand = splitLigne[3]
exonAllStart = splitLigne[9].split(",")[:-1]
exonAllEnd = splitLigne[10].split(",")[:-1]
cdsStart = int(splitLigne[6])
cdsEnd = int(splitLigne[7])
if txStrand != '-':
i=1
first_utr=5
last_utr=3
else:
i=len(exonAllStart)
first_utr=5
last_utr=3
#premier intron ou region UTR
exonStart = int(exonAllStart[0])
if cdsStart < exonStart:
region = Region(txChr, cdsStart, exonStart-1)
region.gene_append(txGene)
exIn = "intron:first"
region.txNcExIn_append(txName, exIn)
listOfRegions.append(region)
for s, e in zip(exonAllStart, exonAllEnd):
exonStart = int(s)
exonEnd = int(e)
if (exonStart < cdsStart and exonEnd < cdsStart) or (exonStart > cdsEnd and exonEnd > cdsEnd):
if cdsMode:
print "",
else:
if (exonStart < cdsStart):
exIn = "UTR{0}".format(last_utr)
else:
exIn = "UTR{0}".format(first_utr)
region = Region(txChr, exonStart,exonEnd)
region.gene_append(txGene)
region.txNcExIn_append(txName, exIn)
region.utr_append(exonStart,exonEnd)
listOfRegions.append(region)
elif exonStart < cdsStart or exonEnd > cdsEnd:
if exonStart < cdsStart:
utrStart = exonStart
utrEnd = cdsStart
else:
utrStart = cdsEnd
utrEnd = exonEnd
if cdsMode:
if exonStart < cdsStart:
exonStart = cdsStart
else:
exonEnd = cdsEnd
exIn = i
else:
print "",
if (exonStart < cdsStart):
exIn = "UTR{0}".format(last_utr)#partly
else:
exIn = "UTR{0}".format(first_utr)#partly
region = Region(txChr, exonStart,exonEnd)
region.gene_append(txGene)
region.txNcExIn_append(txName, exIn)
region.utr_append(utrStart,utrEnd)
listOfRegions.append(region)
else:
exIn = i
region = Region(txChr, exonStart,exonEnd)
region.gene_append(txGene)
region.txNcExIn_append(txName, exIn)
listOfRegions.append(region)
if txStrand != '-':
i+=1
else:
i-=1
#dernier intron ou region UTR
exonEnd = int(exonAllEnd[-1])
if cdsEnd > exonEnd:
region = Region(txChr, cdsStart, exonStart-1)
region.gene_append(txGene)
exIn = "intron_last".format(len(exonAllStart))
region.txNcExIn_append(txName, exIn)
listOfRegions.append(region)
ref_hg.close()
remove_tmp_file(tmp_grep_gen)
return listOfRegions
def add_intron_to_listOfRegions(listOfRegions):
intronListOfRegions = []
test_utr = listOfRegions[0].txNcExIn.values()[0]
if test_utr != "utr_3" and test_utr != "utr_5":
test_utr = None
base_j=1
else:
base_j=0
test_utr = 1
j = base_j
i = 0
prec_tx = listOfRegions[0].txNcExIn.keys()[0]
for exon in listOfRegions[1:]:
tx = exon.txNcExIn.keys()[0]
ex_numb = exon.txNcExIn[tx]
if tx != prec_tx:
i+=1
j = base_j
prec_tx = tx
else:
exon_prec = listOfRegions[i]
inChr = exon.chr
inStart = exon_prec.end+1
inEnd = exon.start-1
inGene = exon.gene
intron = Region(inChr, inStart, inEnd)
intron.gene_append(inGene)
intron.txNcExIn_append(tx, "intron_{0}".format(ex_numb))
j+=1
i+=1
intronListOfRegions.append(exon_prec)
if test_utr is None:
intronListOfRegions.append(intron)
intronListOfRegions.append(exon)
else:
if exon.txNcExIn[tx] != "utr_3" and exon.txNcExIn[tx] != "utr_5":
if exon_prec.txNcExIn[prec_tx] != "utr_3" and exon_prec.txNcExIn[prec_tx] != "utr_5":
intronListOfRegions.append(intron)
else:
intronListOfRegions.append(exon)
intronListOfRegions.append(listOfRegions[-1])
return intronListOfRegions
def add_utr_to_listOfRegions(listOfRegions, ref_hgtable):
tmp_grep_gen = "tmp_grep_gen"
command = """grep "{0}\t" {1} > {2}""".format(geneName, ref_hgtable, tmp_grep_gen)
subprocess.call(command, shell = True)
utrListOfRegions = []
with open(tmp_grep_gen, 'r') as ref_hg:
for ligne in ref_hg.readlines():
splitLigne = ligne.split()
txChr = splitLigne[2]
txName = splitLigne[1]
txGene = splitLigne[0]
txStart = int(splitLigne[4])
txEnd = int(splitLigne[5])
cdsStart = int(splitLigne[6])
cdsEnd = int(splitLigne[7])
txStrand = splitLigne[3]
if txStrand != '-':
utr5Start = txStart
utr5End = cdsStart-1
utr3Start = cdsEnd+1
utr3End = txEnd
utr3 = Region(txChr, utr3Start, utr3End)
utr3.gene_append(txGene)
utr3.txNcExIn_append(txName, "utr_3")
utr5 = Region(txChr, utr5Start, utr5End)
utr5.gene_append(txGene)
utr5.txNcExIn_append(txName, "utr_5")
utrListOfRegions.append(utr5)
for exon in listOfRegions:
if exon.txNcExIn.keys()[0] == txName:
utrListOfRegions.append(exon)
utrListOfRegions.append(utr3)
else:
utr5Start = cdsEnd+1
utr5End = txEnd
utr3Start = txStart
utr3End = cdsStart-1
utr3 = Region(txChr, utr3Start, utr3End)
utr3.gene_append(txGene)
utr3.txNcExIn_append(txName, "utr_3")
utr5 = Region(txChr, utr5Start, utr5End)
utr5.gene_append(txGene)
utr5.txNcExIn_append(txName, "utr_5")
utrListOfRegions.append(utr3)
for exon in listOfRegions:
if exon.txNcExIn.keys()[0] == txName:
utrListOfRegions.append(exon)
utrListOfRegions.append(utr5)
ref_hg.close()
return utrListOfRegions
def uniq_listOfRegions(listOfRegions):
uniqListOfRegions = []
for reg1 in listOfRegions:
test = 0
for reg2 in uniqListOfRegions:
if reg1.start == reg2.start and reg1.end == reg2.end:
test = 1
for key,val in reg1.txNcExIn.items():
reg2.txNcExIn_append(key,val )
break
else:
test = 0
if test != 1:
uniqListOfRegions.append(reg1)
return(uniqListOfRegions)
def print_region(listOfRegions):
for region in listOfRegions:
print region.chr, region.start, region.end, region.gene,
print "|",
for key,val in region.txNcExIn.items():
print key,val,
print "|",
for nameSubject, subject in region.dicOfSubject.items():
print nameSubject, subject.breadth
print ""
return
#------------------------------------------------------------------------------
def execute_samtools_depth(samtools, bamFile, region, tmpSamDepthFile, mapQualThreshold):
'''
get samtools path and execute samtools depth on positions given by listOfPos and bamFile
The samtools depth output is stocked in temporary file
'''
cmdBams = bamFile
cmdRegion = "{0}:{1}-{2}".format(region.chr, region.start, region.end)
command = "{0}samtools depth -Q {1} -r {2} {3} > {4} 2> /dev/null".format(samtools,mapQualThreshold ,cmdRegion, cmdBams, tmpSamDepthFile)
#print command
subprocess.call(command, shell = True)
return
def no_cover_from_samtools_depth(region, subject, tmpSamDepthFile, resultsPath):
no_cover_outputFile = resultsPath+"/no_cover_"+subject+"_"+region.gene+"_"+region.txNcExIn.keys()[0]+"_"+str(region.txNcExIn[region.txNcExIn.keys()[0]])+".cov-res"
#print no_cover_outputFile
region.dicOfSubject[subject].no_cover_file_append(no_cover_outputFile)
with open(tmpSamDepthFile, 'r') as depthFile:
with open(no_cover_outputFile, 'w') as outFile:
header = "chr\tstart\tend\tgene\ttranscript\texon\n"
outFile.write(header)
read = depthFile.readlines()
lengthRead = len(read)
pos = region.start
samPos = pos
no_coverStart = 0
no_coverEnd = 0
i=0
while pos <= region.end and no_coverEnd == 0:
if i >= lengthRead:
if pos != no_coverEnd+1:
no_coverStart = samPos+1
no_coverEnd = region.end
break
samPos = int(read[i].split()[1])
depthPos = int(read[i].split()[2])
testThresold = 0
if depthPos <= thresholdCoverage:
testThresold = 1
if samPos != pos:
if pos != no_coverEnd+1:
no_coverStart = pos
no_coverEnd = samPos
pos = samPos
elif testThresold:
if pos != no_coverEnd+1:
no_coverStart = pos
no_coverEnd = samPos
i+=1
pos+=1
else:
i+=1
pos+=1
while pos <= region.end:
if i >= lengthRead:
if pos != no_coverEnd+1:
#for tx in region.txNcExIn:
outFile.write("{0}\t".format(region.chr))
outFile.write("{0}\t".format(no_coverStart))
outFile.write("{0}\t".format(no_coverEnd))
outFile.write("{0}\t".format(region.gene))
outFile.write("{0}\t".format(region.txNcExIn.keys()[0]))
outFile.write("{0}\n".format(region.txNcExIn.values()[0]))
no_coverStart = samPos+1
no_coverEnd = region.end
break
samPos = int(read[i].split()[1])
depthPos = int(read[i].split()[2])
testThresold = 0
if depthPos <= thresholdCoverage:
testThresold = 1
if samPos != pos:
if pos != no_coverEnd+1:
#for tx in region.txNcExIn:
outFile.write("{0}\t".format(region.chr))
outFile.write("{0}\t".format(no_coverStart))
outFile.write("{0}\t".format(no_coverEnd))
outFile.write("{0}\t".format(region.gene))
outFile.write("{0}\t".format(region.txNcExIn.keys()[0]))
outFile.write("{0}\n".format(region.txNcExIn.values()[0]))
no_coverStart = pos
no_coverEnd = samPos
pos = samPos
elif testThresold:
if pos != no_coverEnd+1:
#for tx in region.txNcExIn:
outFile.write("{0}\t".format(region.chr))
outFile.write("{0}\t".format(no_coverStart))
outFile.write("{0}\t".format(no_coverEnd))
outFile.write("{0}\t".format(region.gene))
outFile.write("{0}\t".format(region.txNcExIn.keys()[0]))
outFile.write("{0}\n".format(region.txNcExIn.values()[0]))
no_coverStart = pos
no_coverEnd = samPos
i+=1
pos+=1
else:
i+=1
pos+=1
#for tx in region.txNcExIn:
outFile.write("{0}\t".format(region.chr))
outFile.write("{0}\t".format(no_coverStart))
outFile.write("{0}\t".format(no_coverEnd))
outFile.write("{0}\t".format(region.gene))
outFile.write("{0}\t".format(region.txNcExIn.keys()[0]))
outFile.write("{0}\n".format(region.txNcExIn.values()[0]))
outFile.close()
depthFile.close()
subprocess.call("uniq {0} > tmp ; mv tmp {0}".format(no_cover_outputFile), shell=True)
tmpFileName = resultsPath+"/no_cover_tmp"
with open(no_cover_outputFile, 'r') as no_coverFile:
with open(tmpFileName, 'w') as tmpFile:
read = no_coverFile.readlines()
header = read[0]
tmpFile.write(header)
lignes = read[1:]
lenLignes = len(lignes)
if lenLignes > 1:
i = 1
while i < lenLignes:
ligne1 = lignes[i-1].split()
ligne2 = lignes[i].split()
if int(ligne1[2]) == int(ligne2[1]):
tmpFile.write(
ligne1[0]+"\t"+
ligne1[1]+"\t"+
ligne2[2]+"\t"+
ligne1[3]+"\t"+
ligne1[4]+"\t"+
ligne1[5]+"\n"
)
i+=2
else:
tmpFile.write(lignes[i-1])
i+=1
else:
for ligne in lignes:
tmpFile.write(ligne)
tmpFile.close()
no_coverFile.close()
subprocess.call("mv {0} {1}".format(tmpFileName, no_cover_outputFile),shell=True)
return
def depth_at_each_pos_from_samtools_depth(tmpSamDepthFile, subject, region, resultsPath):
depth_at_each_pos_outputFile = resultsPath+"/depth_at_each_pos_"+subject+"_"+region.gene+"_"+region.txNcExIn.keys()[0]+"_"+str(region.txNcExIn[region.txNcExIn.keys()[0]])+".cov-res"
#print depth_at_each_pos_outputFile
region.dicOfSubject[subject].depth_at_each_pos_file_append(depth_at_each_pos_outputFile)
with open(tmpSamDepthFile, 'r') as depthFile:
with open(depth_at_each_pos_outputFile, 'w') as outFile:
read = depthFile.readlines()
lengthRead = len(read)
if lengthRead < 1:
for zeropos in xrange(region.start, region.end+1):
outFile.write("{0}\t".format(region.chr))
outFile.write("{0}\t".format(zeropos))
outFile.write("{0}\n".format(0))
else:
i=0
pos = region.start
samPos = pos
while pos <= region.end:
if i >= lengthRead:
for supPos in xrange(samPos, region.end):
outFile.write("{0}\t".format(region.chr))
outFile.write("{0}\t".format(supPos))
outFile.write("{0}\n".format(0))
break
samPos = int(read[i].split()[1])
if samPos != pos:
for supPos in xrange(pos, samPos):
outFile.write("{0}\t".format(region.chr))
outFile.write("{0}\t".format(supPos))
outFile.write("{0}\n".format(0))
pos = samPos
else:
depth = read[i].split()[2]
outFile.write("{0}\t".format(region.chr))
outFile.write("{0}\t".format(pos))
outFile.write("{0}\n".format(depth))
i+=1
pos+=1
outFile.close()
depthFile.close()
return
def breadth_from_samtools_depth(listOfRegions, resultsPath, thresholdCoverage, samtools, subjectBams, mapQualThreshold):
tmpSamDepthFile = "{0}/tmp_sam_depth".format(resultsPath)
for region in listOfRegions:
for s in subjectBams:
execute_samtools_depth(samtools, subjectBams[s], region, tmpSamDepthFile, mapQualThreshold)
with open(tmpSamDepthFile, 'r') as depthFile:
read = depthFile.readlines()
lengthRead = len(read)
nbNoCoverPos = 0
i=0
pos = region.start
samPos = pos
while pos <= region.end:
if i >= lengthRead:
nbNoCoverPos+=(region.end-samPos+1)
break
samPos = int(read[i].split()[1])
depthPos = int(read[i].split()[2])
testThresold = 0
if depthPos <= thresholdCoverage:
testThresold = 1
if samPos != pos:
nbNoCoverPos+=(samPos-pos)
pos = samPos
elif testThresold:
nbNoCoverPos+=1
i+=1
pos+=1
else:
i+=1
pos+=1
size = region.end-region.start+1
if size < 1:
print size
print region.end
print region.start
breadth = float(size-nbNoCoverPos)/float(size)
breadth = round(breadth, 2)
region.dicOfSubject_append(s)
region.dicOfSubject[s].breadth_append(breadth)
#no_cover
depthFile.close()
if breadth < 1:
no_cover_from_samtools_depth(region, s, tmpSamDepthFile, resultsPath)
depth_at_each_pos_from_samtools_depth(tmpSamDepthFile, s, region, resultsPath)
#execute_plot_depth(region, thresholdCoverage, s, resultsPath)
os.remove(tmpSamDepthFile)
return
#------------------------------------------------------------------------------
def get_bamFile_from_subject_name(subjectName, bamsPath):
command = "find {0} -name {1}*bam".format(bamsPath, subjectName)
process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=None)
output = process.communicate()
bamFile = str(output[0])[:-1]
if output[1] is not None:
print "WARNING : {0} is not in the subjects list".format(subjectName)
sys.exit()
return bamFile
def exon_from_listOfRegions(listOfRegions, exon):
exonlistOfRegions = []
for reg in listOfRegions:
for key,val in reg.txNcExIn.items():
if val == exon or val == (str(exon)+"u") or val == (str(exon)+"U"):
exonlistOfRegions.append(reg)
return exonlistOfRegions
def parse_exon_args(args_exon):
if args_exon is None:
return None
try:
exon = int(args_exon)
except ValueError:
print "WARNING : exon is not a number"
sys.exit()
if exon < 0:
print "WARNING : exon is not a positive number"
sys.exit()
return exon
def check_is_file(testFile):
if os.path.isfile(testFile):
return 1
else:
print "WARNING : {0} is not a file".format(testFile)
return None
def check_is_dir(testDir):
if os.path.isdir(testDir):
return 1
else:
print "WARNING : {0} is not a directory".format(testDir)
return None
def check_is_bamFile(bamFile):
patternBamFile=re.compile("^.*\.bam$")
if patternBamFile.match(bamFile):
return 1
else:
return None
#================================================================================
#ARGUMENTS
#================================================================================
parser = argparse.ArgumentParser(description='depth coverage')
parser.add_argument("-o","--output", type=str)
#select region
parser.add_argument("-p","--position",type=str)
parser.add_argument("-gene","--geneName",type=str)
parser.add_argument("-cds","--cds_regions", action='store_true')
parser.add_argument("-add_utr","--add_utr_regions", action='store_true')
parser.add_argument("-add_intron","--add_intron_regions", action='store_true')
#select subject
parser.add_argument("-bams","--bamsPath",type=str)
parser.add_argument("-subject","--subject_list",type=str)
#select coverage thresholds
parser.add_argument("-cov","--coverage_threshold", type=int, default=5)
parser.add_argument("-mapqual","--mapQuality_threshold", type=int, default=20)
#generate additional file(s)
parser.add_argument("-covout", "--cover_output", action='store_true')
parser.add_argument("-track", "--track_no_cover_UCSC_output", action='store_true')
#external
parser.add_argument("-ref","--refPath",type=str)
parser.add_argument("-samtools","--samtoolsPath",type=str)
#================================================================================
#MAIN
#================================================================================
args = parser.parse_args()
resultsPath = args.output
position = args.position
geneName = args.geneName
ref_hgtable = args.refPath
samtools = args.samtoolsPath
bamsPath = args.bamsPath
subject = args.subject_list
thresholdCoverage = args.coverage_threshold
utrAdd = args.add_utr_regions
intronAdd = args.add_intron_regions
cdsMode = args.cds_regions
mapQualThreshold = args.mapQuality_threshold
coverOutputMode = args.cover_output
trackNoCoverUCSC = args.track_no_cover_UCSC_output
print "Checking arguments..."
#--------------------------------------------------------------------------------
#CHECK ARGS
#--------------------------------------------------------------------------------
#check genome reference file
if check_is_file(ref_hgtable) is None:
sys.exit()
#check samtools pathway
if check_is_dir(samtools) is None:
sys.exit()
#check output pathway
if check_is_dir(resultsPath) is None:
sys.exit()
#check BAMS pathway
if check_is_dir(bamsPath) is None:
sys.exit()
if subject is not None:
subjectBams = {}
#removedSubject = []
listOfSubject = []
for s in subject.split(","):
bamFile = get_bamFile_from_subject_name(s, bamsPath)
if check_is_bamFile(bamFile) is not None:
subjectBams[s]=bamFile
listOfSubject.append(s)
else:
print "WARNING : No .BAM file found for the {0} subject in {1}".format(s,bamsPath)
print "However the {0} subject has been remove from the list of subjects".format(s)
#removedSubject.append(s)
else:
print "WARNING : no subject argument"
sys.exit()
#print subjectBams
print "Done"
print "Parsing reference..."
#--------------------------------------------------------------------------------
#PARSE QUERY GENOME POSITIONS
#--------------------------------------------------------------------------------
typeOfQuery = ""
if position:
#region position
typeOfQuery = "region {0}".format(position)
listOfRegions = convert_position_into_listOfRegions(position, ref_hgtable)
elif geneName:
typeOfQuery = "all CDS ONLY exonic regions in gene {0}".format(geneName)
exon = None
listOfRegions = convert_gene_into_region(geneName, ref_hgtable, cdsMode)
if utrAdd:
typeOfQuery = typeOfQuery + " and UTR regions"
listOfRegions = add_utr_to_listOfRegions(listOfRegions, ref_hgtable)
if intronAdd:
typeOfQuery = typeOfQuery + " and intronic regions"
listOfRegions = add_intron_to_listOfRegions(listOfRegions)
else:
print "WARNING : no position/gene arguments"
sys.exit()
listOfRegions = uniq_listOfRegions(listOfRegions)
#print_region(listOfRegions)
print "Done"
print "Coverage analysis..."
#--------------------------------------------------------------------------------
#COVERAGE DEPTH ANALYSIS
#--------------------------------------------------------------------------------
breadth_from_samtools_depth(listOfRegions, resultsPath, thresholdCoverage, samtools, subjectBams, mapQualThreshold)
#print_region(listOfRegions)
print "Done"
print "Generate results..."
#--------------------------------------------------------------------------------
#GENERATE TABLE RESULTS
#--------------------------------------------------------------------------------
tableOutput = str(resultsPath)+"/"+str(getpass.getuser())
if position:
tableOutput += "_position_" + str(position)
else:
tableOutput += "_gene_" + str(geneName)
if cdsMode:
tableOutput += "_cds"
else:
tableOutput += "_cds_add_utr"
if utrAdd:
tableOutput += "_add_utr"
if intronAdd:
tableOutput += "_add_intron"
tableOutput += "_cov_" + str(thresholdCoverage)
tableOutput += "_qual_" + str(mapQualThreshold)
if coverOutputMode:
tableCoverOutput = tableOutput + "_covered.table"
tableOutput += "_uncovered.table"
with open(tableOutput,"w") as tableOutputFile:
tableOutputFile.write("chrom\tuncovered_start\tuncovered_end\tsubject\tgene\ttranscript\texon_numb\tuncovered_length\n")
tableOutputFile.close()
listOfRegions.sort(key = lambda region : region.start, reverse = False)
for nameSubject in listOfSubject:
for region in listOfRegions:
subject = region.dicOfSubject[nameSubject]
if subject.noCover is not None:
region_no_cover = subject.noCover
with open(region_no_cover, "r") as noCoverFile:
#print "coucou"+nameSubject+subject.noCover
read = noCoverFile.readlines()[1:]
if len(read) > 0:
with open(tableOutput,"a") as tableOutputFile:
for ligne in read:
ligneSplit = ligne[:-1].split("\t")
chromosome = ligneSplit[0]
start = int(ligneSplit[1])
end = int(ligneSplit[2])
gene = ligneSplit[3]
tx = ligneSplit[4]
exon = ligneSplit[5]
if exon[-1] == "u":
#print start,end
#print region.utrStart,region.utrEnd
if end < region.utrStart:
exon = exon[:-1]
elif start > region.utrEnd:
exon = exon[:-1]
else:
exon = exon
tableOutputFile.write("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\t{6}\t{7}\n".format(
chromosome,
start,
end,
nameSubject,
gene,
tx,
exon,
((end-start)+1)
))
tableOutputFile.close()
noCoverFile.close()
subprocess.call("uniq {0} > tmp ; mv tmp {0}".format(tableOutput), shell=True)
#subprocess.call("rm {0}/*.pdf".format(resultsPath, htmlPage), shell=True)
print "Done"
if coverOutputMode:
with open(tableCoverOutput,'w') as coverFile:
coverFile.write("chrom\tcovered_start\tcovered_end\tsubject\tgene\ttranscript\texon_numb\tcovered_length\n")
for nameSubject in listOfSubject:
for region in listOfRegions:
subject = region.dicOfSubject[nameSubject]
if subject.noCover is not None:
region_no_cover = subject.noCover