-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathGAMBLR_examples_output.log
More file actions
824 lines (665 loc) · 49.6 KB
/
Copy pathGAMBLR_examples_output.log
File metadata and controls
824 lines (665 loc) · 49.6 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
[1] "=== STARTED AT 2026-07-27 10:56:01 ==="
[1] "=== RUNNING devtools::run_examples() ==="
── Running 75 example files ──────────────────────────────── GAMBLR.results ──
> my_metadata = suppressMessages(get_gambl_metadata())
> some_coding_ssm = get_coding_ssm(these_samples_metadata = my_metadata,
+ projection = "grch37", this_seq_type = "genome") %>% dplyr::filter(Hugo_Symbol %in%
+ c("EZH2", "MEF2B", "MYD88", "KMT2D")) %>% dplyr::arrange(Hugo_Symbol)
> dplyr::select(some_coding_ssm, 1:10, 37) %>% head()
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol Entrez_Gene_Id Center NCBI_Build Chromosome Start_Position End_Position Strand Variant_Classification Variant_Type HGVSp_Short
1 EZH2 0 . GRCh37 7 148504773 148504773 + Missense_Mutation SNP p.Y741H
2 EZH2 0 . GRCh37 7 148504791 148504791 + Missense_Mutation SNP p.Q735K
3 EZH2 0 . GRCh37 7 148504802 148504802 + Splice_Region SNP <NA>
4 EZH2 0 . GRCh37 7 148506215 148506215 + Missense_Mutation SNP p.I715F
5 EZH2 0 . GRCh37 7 148506437 148506437 + Missense_Mutation SNP p.A692V
6 EZH2 0 . GRCh37 7 148506437 148506437 + Missense_Mutation SNP p.A692V
> hot_ssms = annotate_hotspots(some_coding_ssm)
> hot_ssms %>% dplyr::filter(!is.na(hot_spot)) %>% dplyr::select(1:10,
+ 37, hot_spot)
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol Entrez_Gene_Id Center NCBI_Build Chromosome Start_Position End_Position Strand Variant_Classification Variant_Type HGVSp_Short hot_spot
1 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
2 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
3 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
4 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
5 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
6 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
7 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
8 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
9 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
10 EZH2 0 . GRCh37 7 148508727 148508727 + Missense_Mutation SNP p.Y646F TRUE
> maf <- get_coding_ssm(projection = "grch37") %>% head(n = 500)
> dplyr::select(maf, 1:12) %>% head()
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol Entrez_Gene_Id Center NCBI_Build Chromosome Start_Position End_Position Strand Variant_Classification Variant_Type Reference_Allele Tumor_Seq_Allele1
1 AL627309.1 0 . GRCh37 1 138626 138626 + Silent SNP T T
2 AL627309.1 0 . GRCh37 1 138972 138973 + Frame_Shift_Ins INS - -
3 RP11-206L10.9 0 . GRCh37 1 730845 730845 + Splice_Region SNP G G
4 FAM87B 0 . GRCh37 1 753589 753589 + Splice_Region SNP A A
5 SAMD11 0 . GRCh37 1 865610 865610 + Missense_Mutation SNP A A
6 SAMD11 0 . GRCh37 1 871158 871158 + Silent SNP C C
> maf_anno <- annotate_maf_triplet(maf)
> dplyr::select(maf_anno, 1:12, seq) %>% head()
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol Entrez_Gene_Id Center NCBI_Build Chromosome Start_Position End_Position Strand Variant_Classification Variant_Type Reference_Allele Tumor_Seq_Allele1 seq
1 AL627309.1 0 . GRCh37 1 138626 138626 + Silent SNP T T ATG
2 AL627309.1 0 . GRCh37 1 138972 138973 + Frame_Shift_Ins INS - - NA
3 RP11-206L10.9 0 . GRCh37 1 730845 730845 + Splice_Region SNP G G CGT
4 FAM87B 0 . GRCh37 1 753589 753589 + Splice_Region SNP A A AAA
5 SAMD11 0 . GRCh37 1 865610 865610 + Missense_Mutation SNP A A CAG
6 SAMD11 0 . GRCh37 1 871158 871158 + Silent SNP C C ACG
> my_maf <- get_coding_ssm() %>% dplyr::filter(Hugo_Symbol ==
+ "BCL2") %>% dplyr::arrange(Chromosome, Start_Position, Tumor_Sample_Barcode) %>%
+ head()
> annotated = annotate_ssm_motif_context(maf = my_maf,
+ motif = "WRCY")
> dplyr::select(annotated, 1, 5, 6, 11, 13, 16, seq,
+ WRCY)
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol Chromosome Start_Position Reference_Allele Tumor_Seq_Allele2 Tumor_Sample_Barcode seq WRCY
1 BCL2 18 60795859 C T CAR_126_PreCART CTTCACT FALSE
2 BCL2 18 60795894 A T 08-13706T GCAAGCT MOTIF
3 BCL2 18 60795911 A G 00-15336_CLC01491 CCAAACT MOTIF
4 BCL2 18 60795911 A G 00-15336_CLC02290 CCAAACT MOTIF
5 BCL2 18 60795947 C G FL1010T2 AATCAAA FALSE
6 BCL2 18 60985305 GTG AAT SP192988 CAAGTGCAC FALSE
> meta = suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(pathology == "MCL")
> mut_freq = calc_mutation_frequency_bin_region(these_samples_metadata = meta,
+ region = "11:69455000-69459900", slide_by = 10, window_size = 10000)
> head(mut_freq)
# A tibble: 6 × 3
sample_id bin mutation_count
<chr> <chr> <int>
1 01-11817T 11_69455000 5
2 01-11817T 11_69455010 5
3 01-11817T 11_69455020 5
4 01-11817T 11_69455030 5
5 01-11817T 11_69455040 5
6 01-11817T 11_69455050 5
> capture_metadata = get_gambl_metadata(dna_seq_type_priority = "capture") %>%
+ dplyr::filter(seq_type == "capture")
> capture_collated_everything = collate_results(these_samples_metadata = capture_metadata,
+ from_cache = TRUE, write_to_file = FALSE)
[[1]]
/projects/nhl_meta_analysis_scratch/gambl/results_local/shared/gambl_capture_results.tsv
> my_metadata = get_gambl_metadata() %>% dplyr::filter(seq_type !=
+ "mrna")
> fl_metadata = dplyr::filter(my_metadata, pathology ==
+ "FL")
> fl_collated = collate_results(these_samples_metadata = fl_metadata,
+ write_to_file = FALSE, from_cache = TRUE)
[[1]]
/projects/nhl_meta_analysis_scratch/gambl/results_local/shared/gambl_genome_results.tsv
[[2]]
/projects/nhl_meta_analysis_scratch/gambl/results_local/shared/gambl_capture_results.tsv
> my_meta = suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(sample_id == "HTMCP-01-06-00422-01A-01D", seq_type ==
+ "genome")
> outputs = estimate_purity(these = my_meta, show_plots = TRUE,
+ projection = "grch37")
> outputs$sample_purity_estimation
[1] 1
> my_meta = suppressMessages(get_gambl_metadata())
> maf_all_seqtype = get_all_coding_ssm(my_meta)
> table(maf_all_seqtype$maf_seq_type)
capture genome
978167 241982
> dplyr::group_by(maf_all_seqtype, Hugo_Symbol, Variant_Classification) %>%
+ dplyr::count() %>% dplyr::arrange(desc(n))
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol Variant_Classification n
1 IGHV2-70 Missense_Mutation 3481
2 IGLV3-1 Missense_Mutation 3431
3 IGLL5 Missense_Mutation 2873
4 BCL2 Missense_Mutation 2815
5 TTN Missense_Mutation 2706
6 IGHV1-69 Missense_Mutation 1841
7 PIM1 Missense_Mutation 1830
8 MYC Missense_Mutation 1395
9 MUC16 Missense_Mutation 1367
10 CREBBP Missense_Mutation 1188
> DLBCL_genome_meta = get_gambl_metadata() %>% dplyr::filter(pathology ==
+ "DLBCL")
> some_regions = GAMBLR.utils::create_bed_data(GAMBLR.data::grch37_ashm_regions,
+ fix_names = "concat", concat_cols = c("gene", "region"),
+ sep = "-") %>% dplyr::filter(grepl("PAX5", name))
> pax5_matrix <- get_ashm_count_matrix(regions_bed = some_regions,
+ this_seq_type = "genome", these_samples_metadata = DLBCL_genome_meta)
> head(pax5_matrix)
PAX5-distal-enhancer-1 PAX5-distal-enhancer-2 PAX5-distal-enhancer-3 PAX5-intron-1 PAX5-TSS-1
00-14595_tumorC 4 0 3 12 2
00-15201_tumorA 0 0 3 7 0
00-15201_tumorB 0 0 0 1 0
00-17960_CLC01670 0 2 0 11 0
FL1015T2 1 0 0 0 0
00-23442_tumorB 0 0 2 0 0
> colMeans(pax5_matrix)
PAX5-distal-enhancer-1 PAX5-distal-enhancer-2 PAX5-distal-enhancer-3 PAX5-intron-1 PAX5-TSS-1
0.6367347 0.7115646 1.3401361 2.0503401 0.4775510
> capture_metadata <- suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(seq_type == "capture") %>% head()
> capture_segments_hg38 <- get_cn_segments(these_samples_metadata = capture_metadata,
+ projection = "hg38")
> print(capture_segments_hg38)
SEG Data Object
Genome Build: hg38
Showing first 10 rows:
ID chrom start end LOH_flag log.ratio seg_seq_type CN
1 00-22011_tumorB chr1 10001 69372 NA 0.0000 capture 2.00000
2 00-22011_tumorB chr1 69373 10335564 NA 1.0000 capture 4.00000
3 00-22011_tumorB chr1 10335564 12723042 NA 0.0000 capture 2.00000
4 00-22011_tumorB chr1 12723043 13184564 NA 0.0000 capture 2.00000
5 00-22011_tumorB chr1 13184565 33302847 NA 0.0000 capture 2.00000
6 00-22011_tumorB chr1 33302847 33309697 NA 2.5453 capture 11.67459
7 00-22011_tumorB chr1 33309697 40850005 NA 0.0000 capture 2.00000
8 00-22011_tumorB chr1 40850005 40922631 NA 2.8912 capture 14.83775
9 00-22011_tumorB chr1 40922631 47396477 NA 0.0000 capture 2.00000
10 00-22011_tumorB chr1 47396477 47439416 NA 2.0000 capture 8.00000
> genome_metadata <- suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(seq_type == "genome")
> mixed_seq_type_meta <- dplyr::bind_rows(capture_metadata,
+ genome_metadata)
> all_seq_type_segs <- get_cn_segments(these_samples_metadata = mixed_seq_type_meta)
> dplyr::group_by(all_seq_type_segs, seg_seq_type) %>%
+ dplyr::count()
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
seg_seq_type n
1 capture 1120
2 genome 441137
> all_types_meta = suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(pathology == "BL")
> dplyr::group_by(all_types_meta, seq_type) %>% dplyr::summarize(n = dplyr::n())
# A tibble: 3 × 2
seq_type n
<chr> <int>
1 capture 150
2 genome 257
3 mrna 280
> genes_and_cn_threshs = data.frame(gene_id = c("MYC",
+ "MIR17HG", "CCND3", "ID3", "DDX3X", "SYNCRIP"), cn_thresh = c(3,
+ 3, 2, 2, 2, 1))
> genome_cnv_ssm_status = suppressMessages(get_cnv_and_ssm_status(genes_and_cn_threshs,
+ dplyr::filter(all_types_meta, seq_type == "genome"), only_cnv = "MIR17HG"))
> print(dim(genome_cnv_ssm_status))
[1] 257 6
> head(genome_cnv_ssm_status)
MYC MIR17HG CCND3 ID3 DDX3X SYNCRIP
LyCA0278_DNA 1 0 0 0 1 0
BLGSP-71-06-00001-01A-11D 0 0 1 1 1 0
BLGSP-71-06-00002-01C-01D 1 0 0 1 0 0
BLGSP-71-06-00004-01A-11D 0 0 1 1 1 0
BLGSP-71-06-00005-01A-21D 0 0 1 1 0 0
BLGSP-71-06-00007-01A-11D 1 0 1 1 0 0
> colSums(genome_cnv_ssm_status)
MYC MIR17HG CCND3 ID3 DDX3X SYNCRIP
184 47 76 119 122 13
> all_seq_type_status = suppressMessages(get_cnv_and_ssm_status(genes_and_cn_threshs,
+ all_types_meta, only_cnv = "MIR17HG"))
> print(dim(all_seq_type_status))
[1] 407 6
> head(all_seq_type_status)
MYC MIR17HG CCND3 ID3 DDX3X SYNCRIP
LyCA0278_DNA 1 0 0 0 1 0
BLGSP-71-06-00001-01A-11D 0 0 1 1 1 0
BLGSP-71-06-00002-01C-01D 1 0 0 1 0 0
BLGSP-71-06-00004-01A-11D 0 0 1 1 1 0
BLGSP-71-06-00005-01A-21D 0 0 1 1 0 0
BLGSP-71-06-00007-01A-11D 1 0 1 1 0 0
> colSums(all_seq_type_status)
MYC MIR17HG CCND3 ID3 DDX3X SYNCRIP
283 63 118 194 186 21
> maf_genome = get_coding_ssm()
> nrow(maf_genome)
[1] 323660
> dplyr::select(maf_genome, 1, 4, 5, 6, 9, maf_seq_type)
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol NCBI_Build Chromosome Start_Position Variant_Classification maf_seq_type
1 AL627309.1 GRCh37 1 138626 Silent genome
2 AL627309.1 GRCh37 1 138972 Frame_Shift_Ins genome
3 RP11-206L10.9 GRCh37 1 730845 Splice_Region genome
4 FAM87B GRCh37 1 753589 Splice_Region genome
5 SAMD11 GRCh37 1 865610 Missense_Mutation genome
6 SAMD11 GRCh37 1 871158 Silent genome
7 SAMD11 GRCh37 1 871192 Missense_Mutation genome
8 SAMD11 GRCh37 1 874416 Splice_Region genome
9 SAMD11 GRCh37 1 874467 Missense_Mutation genome
10 SAMD11 GRCh37 1 874467 Missense_Mutation genome
> maf_exome_hg38 = get_coding_ssm(this_seq_type = "capture",
+ projection = "hg38")
> dplyr::select(maf_exome_hg38, 1, 4, 5, 6, 9, maf_seq_type)
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
Hugo_Symbol NCBI_Build Chromosome Start_Position Variant_Classification maf_seq_type
1 OR4F5 GRCh38 chr1 69594 Silent capture
2 OR4F5 GRCh38 chr1 69634 Missense_Mutation capture
3 OR4F5 GRCh38 chr1 69644 Missense_Mutation capture
4 FO538757.2 GRCh38 chr1 183189 Missense_Mutation capture
5 FO538757.2 GRCh38 chr1 183937 Missense_Mutation capture
6 FO538757.1 GRCh38 chr1 186356 Nonsense_Mutation capture
7 FO538757.1 GRCh38 chr1 186385 Missense_Mutation capture
8 FO538757.1 GRCh38 chr1 186404 Missense_Mutation capture
9 FO538757.1 GRCh38 chr1 186440 Missense_Mutation capture
10 FO538757.1 GRCh38 chr1 186440 Missense_Mutation capture
> genes = dplyr::filter(GAMBLR.data::lymphoma_genes,
+ FL_Tier == 1) %>% dplyr::pull(Gene)
> fl_meta = suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(pathology == "FL", cohort != "FL_Crouch", seq_type !=
+ "mrna")
> table(fl_meta$seq_type)
capture genome
391 533
> coding_tabulated_df = get_coding_ssm_status(gene_symbols = genes,
+ include_hotspots = FALSE, genome_build = "hg38", these_samples_metadata = fl_meta)
> length(genes)
[1] 54
> dim(coding_tabulated_df)
[1] 924 55
> head(colnames(coding_tabulated_df))
[1] "sample_id" "TNFRSF14" "ARID1A" "RRAGC" "BCL10" "CTSS"
> maf_data = get_all_coding_ssm(these_samples_metadata = fl_meta,
+ projection = "grch37")
> coding_tabulated2 = get_coding_ssm_status(gene_symbols = genes,
+ these_samples_metadata = fl_meta, maf_data = maf_data, include_hotspots = FALSE)
> dim(coding_tabulated2)
[1] 924 55
> head(colnames(coding_tabulated2))
[1] "sample_id" "TNFRSF14" "ARID1A" "RRAGC" "BCL10" "CTSS"
> coding_tabulated3 = get_coding_ssm_status(gene_symbols = c("MYD88",
+ "CREBBP", "KMT2D"), these_samples_metadata = fl_meta, maf_data = maf_data,
+ include_hotspots = TRUE, genes_of_interest = c("MYD88", "CREBBP")) %>%
+ tibble::column_to_rownames("sample_id")
> print(colSums(coding_tabulated3))
KMT2D CREBBP MYD88 CREBBPHOTSPOT MYD88HOTSPOT
545 189 7 344 6
> all_sv <- get_combined_sv()
> dplyr::select(all_sv, 1:14)
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
CHROM_A START_A END_A CHROM_B START_B END_B manta_name SCORE STRAND_A STRAND_B tumour_sample_id normal_sample_id VAF_tumour DP
1 1 9894 10014 16 69889 69998 MantaBND:10:1901:1907:0:0:0:1 NA - + 00-14595_tumorD 00-14595_normal 0.400 10
2 1 10176 10711 11 134946192 134946783 MantaBND:23:3075:4071:0:0:0:1 NA + + 14-14094T 14-11247N 0.186 59
3 1 10269 10794 16 59726 60283 MantaBND:3:3538:3557:0:0:0:1 NA + - 07-13339T 14-11247N 0.175 40
4 1 10287 10688 15 102521012 102521550 MantaBND:13192:0:1:0:0:0:0 NA + + 835-02-03TD 14-11247Normal 0.312 32
5 1 10308 10837 12 95037 95505 MantaBND:1:6049:6050:1:0:0:0 NA + + 4687-03-01BD 14-11247Normal 0.250 52
6 1 10418 10600 8 146301336 146301470 MantaBND:12:4736:4739:0:0:0:0 NA + + LyCA1414_DNA BM15-8383 0.163 49
7 1 10437 10438 8 146301390 146301391 MantaBND:2:7221:7224:0:1:0:1 NA + + 102-01-01TD 14-11247Normal 0.520 25
8 1 10437 10438 8 146301390 146301391 MantaBND:2:1723:1728:0:0:0:0 NA + + 102-0202-1DVT 14-11247Normal 0.630 27
9 1 10455 10456 12 94998 94999 MantaBND:9:480:2022:1:4:0:1 NA + + 00-12637_CLC02086 FL1011N 0.064 621
10 1 10456 10839 12 94872 95291 MantaBND:3:26317:26320:0:0:0:1 NA + + 4690-03-01BD 14-11247Normal 0.333 18
> cohort_meta = suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(cohort == "DLBCL_cell_lines")
> some_sv <- get_combined_sv(these_samples_metadata = cohort_meta)
> dplyr::select(some_sv, 1:14)
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
CHROM_A START_A END_A CHROM_B START_B END_B manta_name SCORE STRAND_A STRAND_B tumour_sample_id normal_sample_id VAF_tumour DP
1 1 1482283 1482284 4 183461608 183461609 MantaBND:57556:1:2:0:1:0:0 NA - + TMD8-WGS H040_N_WGS 0.19600000 56
2 1 1826839 1826841 1 1833712 1833714 MantaBND:14359:0:1:0:0:0:1 NA + + SU-DHL-4 14-11247N 0.21300000 94
3 1 1827338 1827339 1 8741628 8741629 MantaBND:14359:0:2:0:0:0:0 NA - - SU-DHL-4 14-11247N 0.30000000 80
4 1 6438168 6438173 1 6445895 6445900 MantaDEL:16045:0:1:0:0:0_bp1 NA + - HT 14-11247N 0.24700000 81
5 1 9121442 9121445 14 93713176 93713179 MantaBND:129287:0:2:0:0:0:0 NA + + TMD8-WGS H040_N_WGS 0.17300000 81
6 1 9121448 9121453 14 93712481 93712486 MantaBND:129287:1:2:0:0:0:0 NA - - TMD8-WGS H040_N_WGS 0.36800000 76
7 1 9830863 9830864 1 10124723 10124724 MantaDEL:323891:0:1:0:0:0_bp1 NA + - TMD8-WGS H040_N_WGS 0.32800000 67
8 1 12102613 12102730 7 54736352 54736578 MantaBND:157822:0:2:0:0:0:0 NA - - RL-WGS H040_N_WGS 0.20000000 25
9 1 12962179 12962180 6 33030302 33030303 MantaBND:15384:0:1:0:1:0:0 NA - - SU-DHL-4 14-11247N 0.28900000 38
10 1 13178581 13178582 18 9168651 9168652 <NA> 273 - - TMD8-WGS H040_N_WGS 0.04797048 271
> nrow(some_sv)
[1] 1939
> myc_region_hg38 = "chr8:127710883-127761821"
> myc_region_grch37 = "8:128723128-128774067"
> hg38_myc_locus_sv <- get_combined_sv(region = myc_region_hg38,
+ projection = "hg38")
> dplyr::select(hg38_myc_locus_sv, 1:14)
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
CHROM_A START_A END_A CHROM_B START_B END_B manta_name SCORE STRAND_A STRAND_B tumour_sample_id normal_sample_id VAF_tumour DP
1 chr1 6803016 6803030 chr8 127731317 127731331 <NA> 208.20 - + 01-12047_tumorA 01-12047_normal 0.10396040 202
2 chr1 8253139 8253144 chr8 127756470 127756475 <NA> 308.00 - + BLGSP-71-30-00665-01A-01E BLGSP-71-30-00665-10A-01D 0.08870968 124
3 chr1 50392925 50392927 chr8 127747754 127747756 <NA> 253.09 - + BLGSP-71-30-00678-01A-01E BLGSP-71-06-00286-99A-01D 0.05128205 195
4 chr1 100041646 100041649 chr8 127753200 127753203 <NA> 211.34 - + BLGSP-71-30-00656-01A-01E BLGSP-71-06-00286-99A-01D 0.05241935 248
5 chr1 149968016 149968030 chr8 127720533 127720547 <NA> 335.95 - + 13-38657_tumorB 13-38657_normal 0.10800000 250
6 chr1 180261380 180261390 chr8 127747224 127747234 MantaBND:2:133568:133570:0:2:0:0 NA - + 11-12873_tumorC 11-12873_normal 0.05900000 102
7 chr1 182119529 182119530 chr8 127747267 127747268 <NA> 226.75 + - BLGSP-71-30-00655-01A-01E BLGSP-71-06-00286-99A-01D 0.05555556 198
8 chr1 202928006 202928020 chr8 127747224 127747238 <NA> 419.03 + - 14-11777_tumorB 14-11777N 0.03921569 459
9 chr1 207726976 207727002 chr8 127724887 127724913 <NA> 204.27 - + BLGSP-71-30-00661-01A-01E BLGSP-71-06-00286-99A-01D 0.07253886 193
10 chr1 209800781 209800785 chr8 127753804 127753808 MantaBND:0:549563:738680:0:1:0:0 NA + - BLGSP-71-30-00647-01A-01E BLGSP-71-06-00286-99A-01D 0.13200000 38
> nrow(hg38_myc_locus_sv)
[1] 703
> incorrect_myc_locus_sv <- get_combined_sv(region = myc_region_grch37,
+ projection = "hg38")
> dplyr::select(incorrect_myc_locus_sv, 1:14)
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
CHROM_A START_A END_A CHROM_B START_B END_B manta_name SCORE STRAND_A STRAND_B tumour_sample_id normal_sample_id VAF_tumour DP
1 chr1 182655283 182655290 chr8 128767396 128767403 MantaBND:203817:0:1:0:0:0:0 NA - - 12-23835_tumorA 12-23835_normal 0.0530000 114
2 chr1 233914485 233914492 chr8 128773743 128773750 MantaBND:306088:0:1:0:0:0:0 NA + - 05-16093_tumorA 05-16093_normal 0.0780000 77
3 chr11 73459284 73459290 chr8 128758908 128758914 <NA> 259.43 - + 01-23117_tumorB 01-23117_normal 0.1383929 224
4 chr11 93629111 93629307 chr8 128726629 128726825 MantaBND:202456:0:1:0:0:0:1 NA + - 00-12637_CLC02086 FL1011N 0.0980000 61
5 chr11 93629111 93629647 chr8 128726343 128727380 MantaBND:28037:1:9:0:0:0:1 NA + - 01-20774T 14-11247N 0.2800000 25
6 chr11 93629111 93629641 chr8 128726295 128727325 MantaBND:0:278162:278290:0:0:0:1 NA + - CLC03336 14-11247N 0.2570000 179
7 chr11 93629111 93629613 chr8 128726323 128727499 MantaBND:170141:0:1:0:0:0:1 NA + - CLC03338 14-11247N 0.1150000 139
8 chr11 93629111 93629568 chr8 128726370 128727275 MantaBND:157518:0:3:0:0:0:0 NA + - CLC03455 14-11247N 0.2680000 97
9 chr11 93629111 93629568 chr8 128726368 128727133 MantaBND:191300:0:1:0:0:0:1 NA + - CLC03456 14-11247N 0.1850000 151
10 chr11 93629111 93629572 chr8 128726364 128727288 MantaBND:5:122305:122306:0:0:0:1 NA + - CLC03457 14-11247N 0.2540000 63
> nrow(incorrect_myc_locus_sv)
[1] 47
> annotated_myc_hg38 = suppressMessages(GAMBLR.utils::annotate_sv(hg38_myc_locus_sv,
+ genome_build = "hg38"))
> head(annotated_myc_hg38)
chrom1 start1 end1 chrom2 start2 end2 name score strand1 strand2 tumour_sample_id gene partner fusion
1: 18 63123493 63123497 8 127728389 127728393 . 1742.36 + - SU-DHL-10 BCL2 <NA> NA-BCL2
2: 18 63195263 63195266 8 127744561 127744564 . NA - - SP194216 BCL2 <NA> NA-BCL2
3: 2 28983232 28983241 8 127711263 127711272 . NA - - 02-14764_tumorB ALK <NA> NA-ALK
4: 3 70834666 70834671 8 127750318 127750323 . 249.44 - + BLGSP-71-30-00661-01A-01E FOXP1 <NA> NA-FOXP1
5: 3 101756651 101756656 8 127724888 127724893 . 261.80 + - BLGSP-71-30-00676-01A-01E NFKBIZ <NA> NA-NFKBIZ
6: 3 187747200 187747205 8 127744763 127744768 . NA + - 17-33848_tumorB BCL6 <NA> NA-BCL6
> table(annotated_myc_hg38$partner)
BCL6 CCNL1 DMD IGH IGK IGL LINC00578 LRMP PAX5 RFTN1 ZEB2
6 1 2 385 5 8 2 3 11 1 1
> annotated_myc_incorrect = suppressMessages(GAMBLR.utils::annotate_sv(incorrect_myc_locus_sv,
+ genome_build = "hg38"))
> head(annotated_myc_incorrect)
chrom1 start1 end1 chrom2 start2 end2 name score strand1 strand2 tumour_sample_id gene partner fusion
1: 8 127313080 127313571 8 128746007 128746587 . NA + - PD26401c MYC <NA> NA-MYC
2: 8 128738977 128738983 8 128752583 128752589 . NA + - 04-14093_tumorA MYC <NA> NA-MYC
3: 8 128738977 128738983 8 128752583 128752589 . NA + - 04-14093_tumorB MYC <NA> NA-MYC
4: 8 128738980 128738981 8 128752584 128752585 . NA + - BLGSP-71-17-00357-01B-09E MYC <NA> NA-MYC
5: 8 128738980 128738981 8 128752584 128752585 . NA + - BLGSP-71-27-00424-01A-01E MYC <NA> NA-MYC
6: 8 128738980 128738981 8 128752584 128752585 . NA + - SMZL-UK-T3 MYC <NA> NA-MYC
> table(annotated_myc_incorrect$partner)
< table of extent 0 >
> my_metadata = suppressMessages(get_gambl_metadata())
> dplyr::group_by(my_metadata, pathology, seq_type) %>%
+ dplyr::count()
# A tibble: 106 × 3
# Groups: pathology, seq_type [106]
pathology seq_type n
<chr> <chr> <int>
1 AILT_DLBCEBV capture 1
2 AILT_DLBCEBV mrna 1
3 AILT_NS1 capture 1
4 AILT_NS1 mrna 1
5 AITL capture 73
6 AITL genome 7
7 AITL mrna 50
8 AITL_DLBCEBV capture 1
9 AITL_DLBCEBV mrna 1
10 AITL_PTCL capture 1
# ℹ 96 more rows
> all_fusions = get_gene_fusions()
> onco_fusions = get_gene_fusions(keep_genes = c("BCL2",
+ "MYC", "BCL6"))
> print(head(onco_fusions))
# A tibble: 6 × 13
sample_id CHROM_A START_A END_A CHROM_B START_B END_B gene1 gene2 SCORE STRAND_A STRAND_B FLAGS
<chr> <chr> <dbl> <dbl> <chr> <dbl> <dbl> <chr> <chr> <dbl> <chr> <chr> <chr>
1 01-14875T 3 187463198 187463199 14 106322322 106322323 BCL6 IGH@ 0 - - known,oncogene,chimer2,chimer4seq,cancer,tumor,oncokb,mitelman,t1
2 01-15092T 18 60793477 60793478 14 106330466 106330467 BCL2 IGH@ 0 - - known,oncogene,chimer2,cancer,tumor,oncokb,mitelman,ccle,t1,reciprocal
3 01-17838T 14 106070093 106070094 8 128748830 128748831 IGH@ MYC 0 + + known,oncogene,chimer2,cancer,tumor,oncokb,mitelman,ccle,t9
4 01-19969T 18 60794689 60794690 14 106312010 106312011 BCL2 IGH@ 0 - - known,oncogene,chimer2,cancer,tumor,oncokb,mitelman,ccle
5 01-20260T 18 60891187 60891188 14 106209410 106209411 BCL2 IGH@ 0 - - known,oncogene,chimer2,cancer,tumor,m78,oncokb,mitelman,ccle,reciprocal
6 01-20260T 14 106209408 106209409 18 60833799 60833800 IGH@ BCL2 0 + - known,oncogene,chimer2,cancer,tumor,m1,multi,oncokb,mitelman,ccle,reciprocal
> my_meta = get_gambl_metadata()
> lymphgen_all <- get_lymphgen(flavour = "no_cnvs.no_sv.with_A53",
+ these = my_meta, keep_original_columns = TRUE)
> head(lymphgen_all$features[, c(1:14)])
# A tibble: 6 × 14
sample_id BCL2 EZH2 TNFRSF14 CREBBP KMT2D SOCS1 EP300 IRF8 MEF2B BTG2 PIM2 TBL1XR1 KLHL14
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 00-12637_CLC02086 1 1 1 1 1 0 0 0 0 1 0 0 0
2 00-14595_tumorA 1 1 0 1 0 1 0 0 0 1 1 0 0
3 00-14595_tumorB 1 1 0 1 0 1 0 0 0 1 0 1 0
4 00-14595_tumorC 1 1 0 1 0 1 0 0 0 1 0 1 0
5 00-14595_tumorD 1 1 0 0 0 0 0 0 0 1 1 0 1
6 00-15201_tumorA 0 0 0 0 1 0 0 0 0 1 0 0 0
> head(lymphgen_all$lymphgen[, c(1:14)])
# A tibble: 6 × 14
sample_id Copy.Number BCL2.Translocation BCL6.Translocation Model Confidence.BN2 Confidence.EZB Confidence.MCD Confidence.N1 Confidence.ST2 BN2.Feature.Count EZB.Feature.Count MCD.Feature.Count N1.Feature.Count
<chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 00-12637_CLC02086 Not Available Not Available Not Available NoFusCGH 0.08 0.99 0 0.07 0 1 5 1 0
2 00-14595_tumorA Not Available Not Available Not Available NoFusCGH 0.35 0.99 0 0.07 0.21 2 4 2 0
3 00-14595_tumorB Not Available Not Available Not Available NoFusCGH 0.35 0.99 0 0.07 0.21 2 4 2 0
4 00-14595_tumorC Not Available Not Available Not Available NoFusCGH 0.35 0.99 0 0.07 0.21 2 4 2 0
5 00-14595_tumorD Not Available Not Available Not Available NoFusCGH 0.35 0.94 0.01 0.07 0.02 2 2 3 0
6 00-15201_tumorA Not Available Not Available Not Available NoFusCGH 0.25 0.05 0.02 0.07 0.15 2 1 3 0
> all_sv <- get_manta_sv()
[1] "no metadata provided, fetching all samples..."
[1] "dropping capture samples because manta results\n are only available for genome seq_type"
[1] "No Manta SVs found for 711 samples and 18 cohorts"
[1] "DLBCL_LSARP_Trios" "tFL_LSARP_Trios" "pFL_LSARP_Trios" "MOHCCN" "FL_FOLL_BR" "DLBCL_TFRI_DarkZone" "PMBCL_Rai" "DLBCL_Pasqualucci" "DLBCL_montreal" "DLBCL_Jain" "DLBCL_cell_lines" "PMBCL_Schleussner" "MCL_CellLines" "cHL_Maura" "PMBCL_cell_lines" "MM_mmsanger" "SMZL_Strefford" "Baylor_TXCRB"
> dplyr::select(all_sv, 1:14) %>% head()
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
CHROM_A START_A END_A CHROM_B START_B END_B manta_name SCORE STRAND_A STRAND_B tumour_sample_id normal_sample_id VAF_tumour DP
1 1 10286 10286 8 146301391 146301391 MantaBND:5:1923:1927:0:0:0 46 + + 09-41114T 14-11247N 0.118 110
2 1 10309 10837 12 95038 95505 MantaBND:1:6049:6050:1:0:0 52 + + 4687-03-01BD 14-11247Normal 0.250 52
3 1 10347 10630 15 102520227 102520676 MantaBND:11:3940:4135:0:0:0 58 - - 12-34927T 14-11247N 0.135 104
4 1 10438 10438 8 146301391 146301391 MantaBND:2:7221:7224:0:1:0 84 + + 102-01-01TD 14-11247Normal 0.520 25
5 1 10438 10438 8 146301391 146301391 MantaBND:2:1723:1728:0:0:0 81 + + 102-0202-1DVT 14-11247Normal 0.630 27
6 1 10457 10839 12 94873 95291 MantaBND:3:26317:26320:0:0:0 56 + + 4690-03-01BD 14-11247Normal 0.333 18
> cohort_meta = suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(cohort == "DLBCL_cell_lines")
> some_sv <- get_manta_sv(these_samples_metadata = cohort_meta,
+ verbose = FALSE)
> dplyr::select(some_sv, 1:14) %>% head()
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
CHROM_A START_A END_A CHROM_B START_B END_B manta_name SCORE STRAND_A STRAND_B tumour_sample_id normal_sample_id VAF_tumour DP
1 1 963851 963870 1 964461 964461 MantaDEL:14848:0:0:0:0:0 144 + - Toledo 14-11247N 0.923 26
2 1 1142719 1142719 1 1143140 1143140 MantaDEL:14306:0:0:0:0:0 94 + - HBL-1 14-11247N 0.300 100
3 1 1142719 1142719 1 1143140 1143140 MantaDEL:14173:0:0:0:0:0 81 + - SU-DHL-4 14-11247N 0.256 78
4 1 1142719 1142719 1 1143140 1143140 MantaDEL:11910:0:0:0:0:0 55 + - SU-DHL-9 14-11247N 0.183 60
5 1 1161716 1161716 1 1161780 1161780 MantaDEL:15361:0:0:0:0:0 48 + - HT 14-11247N 0.273 44
6 1 1161716 1161716 1 1161780 1161780 MantaDEL:11880:0:0:0:0:0 58 + - MD903 14-11247N 0.471 34
> nrow(some_sv)
[1] 21216
> myc_region_hg38 = "chr8:127710883-127761821"
> myc_region_grch37 = "8:128723128-128774067"
> hg38_myc_locus_sv <- get_manta_sv(region = myc_region_hg38,
+ projection = "hg38", verbose = FALSE)
> dplyr::select(hg38_myc_locus_sv, 1:14) %>% head()
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
CHROM_A START_A END_A CHROM_B START_B END_B manta_name SCORE STRAND_A STRAND_B tumour_sample_id normal_sample_id VAF_tumour DP
1 chr2 9700440 9700440 chr8 127726024 127726024 MantaBND:80035:1:8:0:0:0 103 + + BLGSP-71-06-00252-01A-01D BLGSP-71-06-00252-10A-01D 0.194 252
2 chr2 28983233 28983240 chr8 127711264 127711271 MantaBND:3:52907:52908:0:3:0 43 - - 02-14764_tumorB 02-14764_normal 0.109 55
3 chr2 88858802 88858802 chr8 127744262 127744262 MantaBND:279432:0:1:0:0:0 148 + + SP59344 SP59342 0.386 88
4 chr2 88860304 88860306 chr8 127751936 127751938 MantaBND:194837:0:1:0:0:0:0 102 + + BLGSP-71-27-00414-01A-01E BLGSP-71-27-00414-10A-01D 0.171 280
5 chr2 88860417 88860417 chr8 127751955 127751955 MantaBND:194837:0:1:0:0:0:0 73 - - BLGSP-71-27-00414-01A-01E BLGSP-71-27-00414-10A-01D 0.117 230
6 chr2 88861500 88861500 chr8 127748752 127748752 MantaBND:1102030:0:1:0:0:0 89 + + BLGSP-71-30-00647-01A-01E BLGSP-71-06-00286-99A-01D 0.283 46
> nrow(hg38_myc_locus_sv)
[1] 457
> incorrect_myc_locus_sv <- get_manta_sv(region = myc_region_grch37,
+ projection = "hg38", verbose = FALSE)
> dplyr::select(incorrect_myc_locus_sv, 1:14) %>% head()
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
CHROM_A START_A END_A CHROM_B START_B END_B manta_name SCORE STRAND_A STRAND_B tumour_sample_id normal_sample_id VAF_tumour DP
1 chr4 77227094 77227100 chr8 128767241 128767247 MantaBND:658884:1:2:0:0:0 42 - - 14-33798_tumorB 14-33798_normal 0.136 44
2 chr8 1287381 1287381 chr8 1287384 1287384 MantaINS:1063533:0:0:0:4:0 51 + - 97-28459_tumorB FL3006N 0.308 26
3 chr8 128726344 128727379 chr11 93629113 93629647 MantaBND:28037:1:9:0:0:0 66 - + 01-20774T 14-11247N 0.280 25
4 chr8 128726820 128726820 chr8 128726825 128726825 MantaINS:242009:0:0:0:3:0 76 + - PD26403a PD26403b 0.400 105
5 chr8 128726820 128726820 chr8 128726825 128726825 MantaINS:226876:7:7:1:3:0 84 + - PD26403c PD26403b 0.407 113
6 chr8 128738979 128738983 chr8 128752584 128752588 MantaDEL:1407936:0:1:0:0:0 118 + - 04-14093_tumorA 04-14093_normal 0.442 43
> nrow(incorrect_myc_locus_sv)
[1] 28
> annotated_myc_hg38 = suppressMessages(GAMBLR.utils::annotate_sv(hg38_myc_locus_sv,
+ genome_build = "hg38"))
> head(annotated_myc_hg38)
chrom1 start1 end1 chrom2 start2 end2 name score strand1 strand2 tumour_sample_id gene partner fusion
1: 2 28983233 28983240 8 127711264 127711271 . 43 - - 02-14764_tumorB ALK <NA> NA-ALK
2: 3 187747202 187747205 8 127744764 127744767 . 79 + - 17-33848_tumorB BCL6 <NA> NA-BCL6
3: 3 187811601 187811601 8 127745649 127745649 . 106 - + FL1008T2 BCL6 <NA> NA-BCL6
4: 3 188074182 188074327 8 127749381 127749593 . 92 + - 140127-PL02 BCL6 <NA> NA-BCL6
5: 4 1746419 1746421 8 127723483 127723485 . 77 - - 09-41114T WHSC1 <NA> NA-WHSC1
6: 8 127226860 127226862 8 127759782 127759784 . 56 + + SP13307 MYC <NA> NA-MYC
> table(annotated_myc_hg38$partner)
BCL6 CCNL1 DMD IGH IGK IGL LRMP PAX5 RFTN1
3 1 2 293 5 6 1 5 1
> annotated_myc_incorrect = suppressMessages(GAMBLR.utils::annotate_sv(incorrect_myc_locus_sv,
+ genome_build = "hg38"))
> head(annotated_myc_incorrect)
chrom1 start1 end1 chrom2 start2 end2 name score strand1 strand2 tumour_sample_id gene partner fusion
1: 8 128726344 128727379 11 93629113 93629647 . 66 - + 01-20774T MYC <NA> NA-MYC
2: 8 128726820 128726820 8 128726825 128726825 . 76 + - PD26403a MYC <NA> NA-MYC
3: 8 128726820 128726820 8 128726825 128726825 . 84 + - PD26403c MYC <NA> NA-MYC
4: 8 128738979 128738983 8 128752584 128752588 . 118 + - 04-14093_tumorA MYC <NA> NA-MYC
5: 8 128738979 128738983 8 128752584 128752588 . 127 + - 04-14093_tumorB MYC <NA> NA-MYC
6: 8 128738981 128738981 8 128752584 128752584 . 126 + - 05-24065T MYC <NA> NA-MYC
> table(annotated_myc_incorrect$partner)
< table of extent 0 >
> test_meta = suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(cohort %in% c("DLBCL_GenomeCanada", "DLBCL_cell_lines"),
+ seq_type != "mrna")
> test_genes = c("EZH2", "KMT2D", "MYD88", "ID3", "FOXO1")
> test_maf = get_ssm_by_genes(genes = test_genes, these_samples_metadata = test_meta)
> dplyr::count(test_maf, Hugo_Symbol, sort = TRUE)
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol n
1 FOXO1 94
2 EZH2 62
3 KMT2D 50
4 MYD88 22
5 ID3 16
> hist_maf = get_ssm_by_genes(genes = "HIST1H1C", these_samples_metadata = test_meta,
+ projection = "hg38")
> dplyr::count(hist_maf, Hugo_Symbol, sort = TRUE)
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
Hugo_Symbol n
1 HIST1H1C 28
> genomes = get_gambl_metadata() %>% dplyr::filter(seq_type %in%
+ "genome")
> my_mutations = GAMBLR.results:::get_ssm_by_region(region = "chr8:128723128-128774067",
+ these_samples_metadata = genomes)
> bcl2_all_details = GAMBLR.results:::get_ssm_by_region(region = "chr18:60796500-60988073",
+ these_samples_metadata = genomes, basic_columns = FALSE)
> regions_bed = GAMBLR.utils::create_bed_data(GAMBLR.data::grch37_ashm_regions,
+ fix_names = "concat", concat_cols = c("gene", "region"),
+ sep = "-") %>% head(20)
> DLBCL_meta = suppressMessages(get_gambl_metadata()) %>%
+ dplyr::filter(pathology == "DLBCL", seq_type == "genome")
> ashm_MAF = get_ssm_by_regions(regions_bed = regions_bed,
+ these_samples_metadata = DLBCL_meta, streamlined = FALSE)
> ashm_MAF %>% dplyr::arrange(Start_Position, Tumor_Sample_Barcode) %>%
+ dplyr::select(Hugo_Symbol, Tumor_Sample_Barcode, Chromosome,
+ Start_Position, Reference_Allele, Tumor_Seq_Allele2)
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
Hugo_Symbol Tumor_Sample_Barcode Chromosome Start_Position Reference_Allele Tumor_Seq_Allele2
1 KLHL21 CLC05009 1 6661536 C A
2 KLHL21 13-26835_tumorA 1 6661537 A T
3 KLHL21 13-26835_tumorB 1 6661537 A T
4 KLHL21 13-26835_tumorD 1 6661537 A T
5 KLHL21 SP193546 1 6661538 C G
6 KLHL21 HTMCP-01-06-00497-01A-01D 1 6661563 G C
7 KLHL21 17-40409_tumorA 1 6661575 C T
8 KLHL21 17-40409_tumorB 1 6661575 C T
9 KLHL21 HTMCP-01-06-00136-01A-01D 1 6661604 G C
10 KLHL21 15-26538T 1 6661607 G A
> maf_samp = GAMBLR.results:::get_ssm_by_sample(get_gambl_metadata() %>%
+ dplyr::filter(sample_id == "13-27975_tumorA"), augmented = FALSE)
> nrow(maf_samp)
[1] 4705
> maf_samp_aug = GAMBLR.results:::get_ssm_by_sample(get_gambl_metadata() %>%
+ dplyr::filter(sample_id == "13-27975_tumorA"), augmented = TRUE)
> nrow(maf_samp_aug)
[1] 6118
> some_maf = GAMBLR.results:::get_ssm_by_sample(these_samples_metadata = get_gambl_metadata() %>%
+ dplyr::filter(sample_id == "HTMCP-01-06-00485-01A-01D", seq_type ==
+ "genome"), projection = "hg38")
> dplyr::select(some_maf, 1:10)
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
Hugo_Symbol Entrez_Gene_Id Center NCBI_Build Chromosome Start_Position End_Position Strand Variant_Classification Variant_Type
1 Unknown 0 . GRCh38 chr1 5446963 5446963 + IGR SNP
2 CAMTA1 0 . GRCh38 chr1 7244319 7244319 + Intron SNP
3 PER3 0 . GRCh38 chr1 7828459 7828459 + Intron SNP
4 TNFRSF9 0 . GRCh38 chr1 7911008 7911008 + 3'Flank SNP
5 ENSR00000000893 0 . GRCh38 chr1 8181883 8181883 + IGR SNP
6 PIK3CD 0 . GRCh38 chr1 9726972 9726972 + Missense_Mutation SNP
7 CASZ1 0 . GRCh38 chr1 10720942 10720942 + Intron SNP
8 CELA2A 0 . GRCh38 chr1 15454068 15454068 + 5'Flank SNP
9 PLA2G2A 0 . GRCh38 chr1 19975558 19975559 + 3'UTR DEL
10 PLA2G2C 0 . GRCh38 chr1 20172387 20172387 + Intron SNP
> nonsyn_maf = GAMBLR.results:::get_ssm_by_sample(get_gambl_metadata() %>%
+ dplyr::filter(sample_id == "13-27975_tumorA"), variant_classification_filter = GAMBLR.helpers::vc_nonSynonymous)
> my_meta = get_gambl_metadata() %>% dplyr::filter(sample_id %in%
+ c("HTMCP-01-06-00485-01A-01D", "14-35472_tumorA", "14-35472_tumorB"))
> sample_ssms = get_ssm_by_samples(these_samples_metadata = my_meta)
> hg38_ssms = get_ssm_by_samples(projection = "hg38",
+ these_samples_metadata = my_meta)
> dplyr::group_by(hg38_ssms, Tumor_Sample_Barcode) %>%
+ dplyr::count()
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
Tumor_Sample_Barcode n
1 14-35472_tumorA 5265
2 14-35472_tumorB 7966
3 HTMCP-01-06-00485-01A-01D 2160
> hg38_ssms_no_aug = get_ssm_by_samples(projection = "hg38",
+ these_samples_metadata = my_meta, augmented = FALSE)
> dplyr::group_by(hg38_ssms_no_aug, Tumor_Sample_Barcode) %>%
+ dplyr::count()
genomic_data Object
Genome Build: hg38
Showing first 10 rows:
Tumor_Sample_Barcode n
1 14-35472_tumorA 4001
2 14-35472_tumorB 7470
3 HTMCP-01-06-00485-01A-01D 2160
> myc_grch37 <- GAMBLR.utils::create_bed_data(GAMBLR.data::grch37_lymphoma_genes_bed) %>%
+ dplyr::filter(name == "MYC")
> print(myc_grch37)
genomic_data Object
Genome Build: grch37
Showing first 10 rows:
chrom start end name
1 8 128747680 128753674 MYC
> genomes <- get_gambl_metadata() %>% dplyr::filter(seq_type ==
+ "genome")
> genome_maf <- get_ssm_by_regions(regions_bed = myc_grch37,
+ these_samples_metadata = genomes, streamlined = FALSE, basic_columns = TRUE)
> maf_to_custom_track(maf_data = genome_maf, output_file = "myc_genome_hg19.bed")
> my_region = "8:128747680-128753674"
> captures <- get_gambl_metadata() %>% dplyr::filter(seq_type ==
+ "capture")
> capture_maf <- get_ssm_by_regions(regions_list = my_region,
+ these_samples_metadata = captures, projection = "grch37",
+ streamlined = FALSE, basic_columns = TRUE)
> maf_to_custom_track(maf_data = capture_maf, this_seq_type = "capture",
+ output_file = "myc_capture_hg19.bed")
[1] "=== COMPLETED AT 2026-07-27 11:10:53 ==="