get_ashm_count_matrix.RdPrepare a matrix with one row per sample and one column per region using a set of hypermutated regions.
get_ashm_count_matrix(
regions_bed,
maf_data,
these_samples_metadata,
seq_type,
from_indexed_flatfile = TRUE
)A bed file with one row for each region.
Optionally provide a data frame in the MAF format, otherwise the database will be used.
This is used to complete your matrix. All GAMBL samples will be used by default. Provide a data frame with at least sample_id for all samples if you are using non-GAMBL data.
The seq type to return results for.
Boolean parameter set to TRUE per default.
A matrix.
Values are the number of mutations in that patient in the region.
regions_bed = dplyr::mutate(GAMBLR.data::somatic_hypermutation_locations_GRCh37_v_latest, name = paste(gene, region, sep = "_"))
matrix = get_ashm_count_matrix(regions_bed = regions_bed,
seq_type = "genome")
#> [1] "chr1:6661482-6662702" "chr1:23885584-23885835"
#> [3] "chr1:150550814-150552135" "chr1:203274698-203275778"
#> [5] "chr1:226864857-226873452" "chr1:226920563-226927885"
#> [7] "chr1:226921088-226927982" "chr2:60773789-60783486"
#> [9] "chr2:96808901-96811913" "chr2:111874854-111882174"
#> [11] "chr2:136874728-136875461" "chr3:16546433-16556786"
#> [13] "chr3:32020518-32024930" "chr3:71104986-71119518"
#> [15] "chr3:71176427-71180960" "chr3:71350633-71357665"
#> [17] "chr3:71503103-71504870" "chr3:71550753-71551478"
#> [19] "chr3:71626341-71635648" "chr3:101546669-101547704"
#> [21] "chr3:101568239-101569274" "chr3:183269360-183274139"
#> [23] "chr3:186739628-186740875" "chr3:186782522-186784438"
#> [25] "chr3:187458526-187464632" "chr3:187771678-187801626"
#> [27] "chr3:187801627-187813568" "chr3:187813569-187955254"
#> [29] "chr3:187955255-187969220" "chr3:188377178-188401951"
#> [31] "chr3:188401952-188461879" "chr3:188461880-188474683"
#> [33] "chr3:188474684-188491248" "chr4:40193105-40204231"
#> [35] "chr5:88131209-88174373" "chr5:88174374-88182243"
#> [37] "chr5:88182244-88206620" "chr5:131823933-131826458"
#> [39] "chr5:149790977-149792349" "chr5:158500476-158532769"
#> [41] "chr6:390572-394093" "chr6:14118026-14120025"
#> [43] "chr6:31548325-31550717" "chr6:37138104-37139804"
#> [45] "chr6:90981034-91016134" "chr6:134487960-134499859"
#> [47] "chr6:159237903-159240216" "chr7:5568297-5570856"
#> [49] "chr8:11347723-11355318" "chr8:128748352-128749427"
#> [51] "chr9:37023396-37027663" "chr9:37029849-37037154"
#> [53] "chr9:37192080-37207549" "chr9:37275952-37306152"
#> [55] "chr9:37312655-37328260" "chr9:37329706-37340398"
#> [57] "chr9:37369209-37372160" "chr9:37382267-37385854"
#> [59] "chr9:37395932-37409239" "chr9:37423010-37425279"
#> [61] "chr10:127578912-127591133" "chr11:9595246-9599502"
#> [63] "chr11:35156769-35164248" "chr11:60223385-60225310"
#> [65] "chr11:65190369-65192380" "chr11:65265237-65268359"
#> [67] "chr11:102188170-102190077" "chr11:111248078-111250224"
#> [69] "chr11:128339774-128345731" "chr11:128388492-128394163"
#> [71] "chr12:11796001-11812968" "chr12:25204045-25213569"
#> [73] "chr12:92537999-92539598" "chr12:113492311-113497546"
#> [75] "chr12:122456912-122464036" "chr13:46957278-46963342"
#> [77] "chr14:69257848-69259739" "chr14:94940587-94942549"
#> [79] "chr14:96179535-96180366" "chr15:59658991-59671152"
#> [81] "chr16:10970795-10975465" "chr16:11347512-11350007"
#> [83] "chr16:27322895-27329423" "chr16:85931918-85933977"
#> [85] "chr17:3597616-3599572" "chr17:56407732-56410140"
#> [87] "chr17:75424734-75440956" "chr17:75443766-75451177"
#> [89] "chr17:75453203-75471471" "chr17:79478289-79479959"
#> [91] "chr18:60796984-60814103" "chr18:60982728-60988342"
#> [93] "chr19:10340142-10341764" "chr19:16434978-16439011"
#> [95] "chr19:19279635-19281441" "chr20:46128611-46138099"
#> [97] "chr20:49120482-49140477" "chr21:26934372-26937651"
#> [99] "chr22:23229554-23232042" "chrX:12993308-12994511"
#> [101] "chrX:48774756-48776255"
#> Joining with `by = join_by(sample_id, region_name)`