sv_df <- sigrap::chord_mantavcf2df(sv_vcf) # prepare SV VCF as data.frame
res <- sigrap::chord_run(
vcf.snv = snvindel_vcf,
df.sv = sv_df,
sv.caller = "manta",
# vcf.sv = sv_vcf, # alternative
sample.name = "sample_A",
ref.genome = "hg38",
verbose = TRUE
)
#>
#> #====== Loading variants from vcfs ======#
#>
#> ## SNVs
#> Warning in fun(libname, pkgname):
#> No reference genome loaded. Please install and load a BSgenome.
#> For example:
#> install.packages('BiocManager')
#> BiocManager::install('BSgenome.Hsapiens.UCSC.hg19')
#> library('BSgenome.Hsapiens.UCSC.hg19')
#>
#> Then specify the BSgenome to the ref.genome arguemnts to the relevant functions.
#> For example:
#> extractSigsSnv(..., ref.genome=BSgenome.Hsapiens.UCSC.hg19)
#> Reading in vcf file...
#> Converting chrom name style to style in ref.genome...
#> Loading required package: BiocGenerics
#>
#> Attaching package: 'BiocGenerics'
#> The following objects are masked from 'package:dplyr':
#>
#> combine, intersect, setdiff, union
#> The following objects are masked from 'package:stats':
#>
#> IQR, mad, sd, var, xtabs
#> The following objects are masked from 'package:base':
#>
#> anyDuplicated, aperm, append, as.data.frame, basename, cbind,
#> colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
#> get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,
#> match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
#> Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,
#> table, tapply, union, unique, unsplit, which.max, which.min
#> Loading required package: S4Vectors
#> Loading required package: stats4
#>
#> Attaching package: 'S4Vectors'
#> The following objects are masked from 'package:dplyr':
#>
#> first, rename
#> The following objects are masked from 'package:base':
#>
#> expand.grid, I, unname
#>
#> Attaching package: 'IRanges'
#> The following objects are masked from 'package:dplyr':
#>
#> collapse, desc, slice
#>
#> ## Indels
#> vcf file is the same for both SNVs and indels. Skipping reading vcf for indels
#>
#> ## SVs
#>
#> #====== Counting mutation contexts ======#
#>
#> ## Single base substitutions
#> Loading variants...
#> Initializing SNV signature output vector...
#> Removing rows with multiple ALT sequences...
#> Subsetting for SNVs...
#> Getting SNV trinucleotide contexts...
#> Converting trinucleotide contexts to substitution contexts...
#> Counting substitution context occurrences...
#> Returning context counts...
#>
#> ## Indel contexts (types x lengths)
#> Loading variants...
#> Removing rows with multiple ALT sequences...
#> Determining indel type...
#> Initializing indel signature output vector...
#> Determining indel length and sequence...
#> Determining the start/end positions for the left/right flanks of each indel...
#> Retrieving flanking sequences...
#> Calculating the number of copies of the indel sequence are present in the 3' flanking sequence...
#> Calculating the (max) number of bases that are homologous to the 5'/3' flanking sequence...
#> Determining indel contexts...
#> Counting indel context occurrences...
#> Returning indel context counts...
#>
#> ## SV contexts (types x lengths)
#> Creating SV type/length lookup table...
#> Counting DEL, DUP, and INV context occurrences...
#> Counting TRA occurrences...
#> Returning SV contexts...
#>
#> #====== Exporting output =========#
#> output.path not specified. Directly returning output
#>