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
|
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mut_matrix_stranded.R
\name{mut_matrix_stranded}
\alias{mut_matrix_stranded}
\title{Make mutation count matrix of 96 trinucleotides with
strand information}
\usage{
mut_matrix_stranded(
vcf_list,
ref_genome,
ranges,
mode = "transcription",
extension = 1
)
}
\arguments{
\item{vcf_list}{GRangesList or GRanges object.}
\item{ref_genome}{BSgenome reference genome object}
\item{ranges}{GRanges object with the genomic ranges of:
1. (transcription mode) the gene bodies with strand (+/-) information, or
2. (replication mode) the replication strand with 'strand_info' metadata}
\item{mode}{"transcription" or "replication", default = "transcription"}
\item{extension}{The number of bases, that's extracted upstream and
downstream of the base substitutions. (Default: 1).}
}
\value{
192 mutation count matrix (96 X 2 strands)
}
\description{
Make a mutation count matrix with 192 features: 96 trinucleotides and 2 strands,
these can be transcription or replication strand
}
\examples{
## See the 'read_vcfs_as_granges()' example for how we obtained the
## following data:
grl <- readRDS(system.file("states/read_vcfs_as_granges_output.rds",
package = "MutationalPatterns"
))
## Load the corresponding reference genome.
ref_genome <- "BSgenome.Hsapiens.UCSC.hg19"
library(ref_genome, character.only = TRUE)
## Transcription strand analysis:
## You can obtain the known genes from the UCSC hg19 dataset using
## Bioconductor:
# BiocManager::install("TxDb.Hsapiens.UCSC.hg19.knownGene")
library("TxDb.Hsapiens.UCSC.hg19.knownGene")
genes_hg19 <- genes(TxDb.Hsapiens.UCSC.hg19.knownGene)
mut_mat_s <- mut_matrix_stranded(grl, ref_genome, genes_hg19,
mode = "transcription"
)
## You can also use a longer context
mut_mat_s <- mut_matrix_stranded(grl, ref_genome, genes_hg19,
mode = "transcription", extension = 2
)
## Replication strand analysis:
## Read example bed file with replication direction annotation
repli_file <- system.file("extdata/ReplicationDirectionRegions.bed",
package = "MutationalPatterns"
)
repli_strand <- read.table(repli_file, header = TRUE)
repli_strand_granges <- GRanges(
seqnames = repli_strand$Chr,
ranges = IRanges(
start = repli_strand$Start + 1,
end = repli_strand$Stop
),
strand_info = repli_strand$Class
)
## UCSC seqlevelsstyle
seqlevelsStyle(repli_strand_granges) <- "UCSC"
# The levels determine the order in which the features
# will be countend and plotted in the downstream analyses
# You can specify your preferred order of the levels:
repli_strand_granges$strand_info <- factor(
repli_strand_granges$strand_info,
levels = c("left", "right")
)
mut_mat_s_rep <- mut_matrix_stranded(grl, ref_genome, repli_strand_granges,
mode = "replication"
)
}
\seealso{
\code{\link{read_vcfs_as_granges}},
\code{\link{mut_matrix}},
\code{\link{mut_strand}}
}
|
