.Rhistory

tmp$X1 <- gsub(":.*","", tmp$X1)
tmp$X2 <- gsub(":.*","", tmp$X2)
idx <- rep(1:nrow(tmp), rowSums(tmp[,c(1,2)]!=""))
tmp2 <- tmp[idx,]
tmp2[duplicated(tmp2$bed.ID_caller),]$X1 <- tmp2[duplicated(tmp2$bed.ID_caller),]$X2
tmp3 <- tmp2[,-2]
tmp3 <- cbind(tmp3, stringr::str_split_fixed(tmp3$X1,"",2))
colnames(tmp3) <- c("strands","ID_caller","strand1","strand2")
strand1 <- tmp3$strand1
strand2 <- tmp3$strand2
#bed <- bed[match(tmp3$ID_caller, bed$ID),]
#bed$strand1 <- tmp3$strand1
#bed$strand2 <- tmp3$strand2
}
if(sum(!is.na(bed$INFO_CT)) != 0){
strand1 <- rep(NA, nrow(bed)); strand2 <- rep(NA, nrow(bed))
strand1[bed$INFO_CT=="3to5"] <- "+"; strand2[bed$INFO_CT=="3to5"] <- "-"
strand1[bed$INFO_CT=="5to3"] <- "-"; strand2[bed$INFO_CT=="5to3"] <- "+"
strand1[bed$INFO_CT=="3to3"] <- "+"; strand2[bed$INFO_CT=="3to3"] <- "+"
strand1[bed$INFO_CT=="5to5"] <- "-"; strand2[bed$INFO_CT=="5to5"] <- "-"
strand1[bed$INFO_CT=="NtoN"] <- NA; strand2[bed$INFO_CT=="NtoN"] <- NA
}
if(sum(!is.na(bed$INFO_INV5)) !=0){
strand1 <- rep(NA, nrow(bed)); strand2 <- rep(NA, nrow(bed))
strand1[bed$INFO_INV5] <- "-";strand2[bed$INFO_INV5] <- "-"
strand1[bed$INFO_INV3] <- "+";strand2[bed$INFO_INV3] <- "+"
}
ALT <- bed$ALT
tmp <- gsub("\\:.*",'', ALT[grepl('\\[',ALT) | grepl('\\]',ALT)])
tmp1 <- gsub(".*\\[",'', tmp)
tmp2 <- gsub(".*\\]",'', tmp1)
chrom1 = as.character(bed$CHROM)
chrom2 <- chrom1
chrom2[grepl('\\[',ALT) | grepl('\\]',ALT)] <- tmp2
tmp <- gsub(".*\\:",'', ALT[grepl('\\[',ALT) | grepl('\\]',ALT)])
tmp1 <- gsub("\\[.*",'', tmp)
tmp2 <- gsub("\\].*",'', tmp1)
pos2 <- bed$INFO_END
pos2[grepl('\\[',ALT) | grepl('\\]',ALT)] <- tmp2
pos2[is.na(pos2)] <- bed$POS[is.na(pos2)] ###if no POS2 then use #CHROM in VCF
bedpe <- data.frame(chrom1=bed$CHROM,
pos1=bed$POS,
chrom2=paste0(tolower(substring(chrom2,1,3)), substring(chrom2,4,nchar(chrom2))),
pos2=pos2,
ALT=ALT,
stringsAsFactors = FALSE)
bedpe <- data.frame(bedpe, bed[,!(colnames(bed) %in% c("CHROM","POS","INFO_END","ALT"))])
colnames(bedpe) <- c("chrom1", "pos1","chrom2","pos2","ALT", colnames(bed)[!(colnames(bed) %in% c("CHROM","POS","INFO_END","ALT"))])
return(bedpe)
}
vcf_file <- system.file("extdata", "lumpy_SVEngine_TumorSV2.60x_NormalSV1.60x_0.5.vcf", package = "ShinySoSV2")
bed <- vcf_to_bed(vcf_file)
head(bed)
tail(bed)
bedpe <- bed_to_bedpe(bed)
head(bedpe)
tail(bedpe)
vcf_file <- system.file("extdata",
"GRIDSS_SVEngine_TumorSV2.60x_NormalSV1.60x_0.5_somatic_PASS_annotated.vcf",
package = "ShinySoSV2")
bed <- vcf_to_bed(vcf_file)
bed_test <- data.frame(CHROM = bed$CHROM,
POS = bed$POS,
ALT = bed$ALT)
usethis::use_data(bed_test,overwrite = TRUE)
vcf_file <- system.file("extdata",
"lumpy_SVEngine_TumorSV2.60x_NormalSV1.60x_0.5_TumorminSU4.vcf",
package = "ShinySoSV2")
CallerA_bed <- simple_SVTYPE_classification(bed = vcf_to_bed(vcf_file), "CallerA")
#' Convert strands into standard form
#'
#' This function read bed format
#'
#' @param bed dataframe
#' @return data frame
#' @export
strands_standardisation <- function(bed){
if(length(bed$ID_caller) == 0){bed$ID_caller = c(1:nrow(bed))}
strand1 <- rep(NA, nrow(bed)); strand2 <- rep(NA, nrow(bed))
if(sum(!is.na(bed$INFO_STRANDS))!=0){
tmp <- data.frame(stringr::str_split_fixed(bed$INFO_STRANDS,",",2), bed$ID_caller)
tmp$X1 <- gsub(":.*","", tmp$X1)
tmp$X2 <- gsub(":.*","", tmp$X2)
idx <- rep(1:nrow(tmp), rowSums(tmp[,c(1,2)]!=""))
tmp2 <- tmp[idx,]
tmp2[duplicated(tmp2$bed.ID_caller),]$X1 <- tmp2[duplicated(tmp2$bed.ID_caller),]$X2
tmp3 <- tmp2[,-2]
tmp3 <- cbind(tmp3, stringr::str_split_fixed(tmp3$X1,"",2))
colnames(tmp3) <- c("strands","ID_caller","strand1","strand2")
}else if(sum(!is.na(bed$INFO_CT)) != 0){
tmp <- data.frame(bed$INFO_CT, ID_caller = bed$ID_caller)
strand1[tmp$INFO_CT=="3to5"] <- "+"; strand2[tmp$INFO_CT=="3to5"] <- "-"
strand1[tmp$INFO_CT=="5to3"] <- "-"; strand2[tmp$INFO_CT=="5to3"] <- "+"
strand1[tmp$INFO_CT=="3to3"] <- "+"; strand2[tmp$INFO_CT=="3to3"] <- "+"
strand1[tmp$INFO_CT=="5to5"] <- "-"; strand2[tmp$INFO_CT=="5to5"] <- "-"
strand1[tmp$INFO_CT=="NtoN"] <- NA; strand2[tmp$INFO_CT=="NtoN"] <- NA
tmp3 <- cbind(tmp, strand1, strand2)
}else if(sum(!is.na(bed$INFO_INV5)) !=0){
tmp <- data.frame(bed$INFO_INV5, bed$INFO_INV3, ID_caller = bed$ID_caller)
strand1[bed$INFO_INV5] <- "-";strand2[bed$INFO_INV5] <- "-"
strand1[bed$INFO_INV3] <- "+";strand2[bed$INFO_INV3] <- "+"
tmp3 <- cbind(tmp, strand1, strand2)
}else{
tmp3 <- cbind(bed, strand1, strand2)
}
bed2 <- bed[match(tmp3$ID_caller, bed$ID_caller),]
bed2$strand1 <- tmp3$strand1
bed2$strand2 <- tmp3$strand2
if((sum(bed2$INFO_SVTYPE %in% c("DEL","DUP")) != 0) & sum(is.na(bed2$strand1))!=0){
bed2[is.na(bed2$strand1) & bed2$INFO_SVTYPE == "DEL",]$strand1 <- "+"
bed2[is.na(bed2$strand2) & bed2$INFO_SVTYPE == "DEL",]$strand2 <- "-"
bed2[is.na(bed2$strand1) & bed2$INFO_SVTYPE == "DUP",]$strand1 <- "-"
bed2[is.na(bed2$strand2) & bed2$INFO_SVTYPE == "DUP",]$strand2 <- "+"
}
return(bed2)
}
#' Convert bed format to bedpe format
#'
#' This function read bed format
#'
#' @param bed data frame
#' @return data frame
#' @export
bed_to_bedpe <- function(bed){
bed <- strands_standardisation(bed)
ALT <- bed$ALT
tmp <- gsub("\\:.*",'', ALT[grepl('\\[',ALT) | grepl('\\]',ALT)])
tmp1 <- gsub(".*\\[",'', tmp)
tmp2 <- gsub(".*\\]",'', tmp1)
chrom1 = as.character(bed$CHROM)
chrom2 <- chrom1
chrom2[grepl('\\[',ALT) | grepl('\\]',ALT)] <- tmp2
tmp <- gsub(".*\\:",'', ALT[grepl('\\[',ALT) | grepl('\\]',ALT)])
tmp1 <- gsub("\\[.*",'', tmp)
tmp2 <- gsub("\\].*",'', tmp1)
pos2 <- bed$INFO_END
pos2[grepl('\\[',ALT) | grepl('\\]',ALT)] <- tmp2
pos2[is.na(pos2)] <- bed$POS[is.na(pos2)] ###if no POS2 then use #CHROM in VCF
strand1 <- bed$strand1; strand2 <- bed$strand2
###[p[t
strand1[grepl('\\[', bed$ALT) & substr(bed$ALT,1,1) == "["] <- "-"
strand2[grepl('\\[', bed$ALT) & substr(bed$ALT,1,1) == "["] <- "-"
###t[p[
strand1[grepl('\\[', bed$ALT) & substr(bed$ALT,1,1) != "["] <- "+"
strand2[grepl('\\[', bed$ALT) & substr(bed$ALT,1,1) != "["] <- "-"
###t]p]
strand1[grepl(']', bed$ALT) & substr(bed$ALT,1,1) != "]"] <- "+"
strand2[grepl(']', bed$ALT) & substr(bed$ALT,1,1) != "]"] <- "+"
###]p]t
strand1[grepl(']', bed$ALT) & substr(bed$ALT,1,1) == "]"] <- "-"
strand2[grepl(']', bed$ALT) & substr(bed$ALT,1,1) == "]"] <- "+"
bedpe <- data.frame(chrom1=bed$CHROM,
pos1=bed$POS,
chrom2=paste0(tolower(substring(chrom2,1,3)), substring(chrom2,4,nchar(chrom2))),
pos2=pos2,
strand1 = strand1,
strand2 = strand2,
ALT=ALT,
stringsAsFactors = FALSE)
bedpe <- data.frame(bedpe, bed[,!(colnames(bed) %in% c("CHROM","POS","INFO_END","ALT","strand1","strand2"))])
colnames(bedpe) <- c("chrom1", "pos1","chrom2","pos2","strand1","strand2","ALT",
colnames(bed)[!(colnames(bed) %in% c("CHROM","POS","INFO_END","ALT","strand1","strand2"))])
return(bedpe)
}
vcf_file <- system.file("extdata",
"lumpy_SVEngine_TumorSV2.60x_NormalSV1.60x_0.5_TumorminSU4.vcf",
package = "ShinySoSV2")
CallerA_bed <- simple_SVTYPE_classification(bed = vcf_to_bed(vcf_file), "CallerA")
#' Classify SV types based on VCF
#'
#' This function read bed format
#'
#' @param bed datafame of bed format
#' @param caller_name name of caller to be used in ID
#' @return data frame
#' @export
simple_SVTYPE_classification <- function(bed, caller_name){
bedpe <- bed_to_bedpe(bed)
if(length(bedpe$ID_caller)!=0){
bedpe <- bedpe[is.na(match(bedpe$ID_caller, bedpe$INFO_MATEID_caller)) | ### either don't have mate (i.e. not BND)
(c(1:nrow(bedpe)) < match(bedpe$ID_caller, bedpe$INFO_MATEID_caller)),] ###  or present first as BND
}
SV_index <- c(1:nrow(bedpe))
event_index <- SV_index
SVTYPE <- bedpe$INFO_SVTYPE
SVTYPE[(bedpe$strand1 == "+") & (bedpe$strand2 == "-") & (bedpe$chrom1 == bedpe$chrom2)] <- "DEL"
SVTYPE[(bedpe$strand1 == "-") & (bedpe$strand2 == "+") & (bedpe$chrom1 == bedpe$chrom2)] <- "DUP"
SVTYPE[(bedpe$strand1 == bedpe$strand2) & (bedpe$chrom1 == bedpe$chrom2)] <- "INV"
SVTYPE[(bedpe$chrom1 != bedpe$chrom2)] <- "TRA"
SVTYPE[is.na(bedpe$strand1)] <- "INS"
standard_bedpe <- data.frame(chrom1 = as.character(bedpe$chrom1),
pos1 = as.integer(bedpe$pos1),
chrom2 = as.character(bedpe$chrom2),
pos2 = as.integer(bedpe$pos2),
SVTYPE = SVTYPE,
strand1 = bedpe$strand1,
strand2 = bedpe$strand2,
ID = paste0(caller_name,"_",SV_index,"_1_",event_index),
ID_mate = paste0(caller_name,"_",SV_index,"_2_",event_index),
#ALT = bedpe$ALT,
stringsAsFactors = FALSE)
bedpe_SVTYPE_classified <- data.frame(standard_bedpe, bedpe[,!(colnames(bedpe) %in% c("chrom1","chrom2","pos1","pos2","strand1","strand2"))])
colnames(bedpe_SVTYPE_classified) <- c("chrom1", "pos1","chrom2","pos2","SVTYPE",
"strand1","strand2",
"ID","ID_mate",
colnames(bedpe)[!(colnames(bedpe) %in% c("chrom1","chrom2","pos1","pos2","strand1","strand2"))])
return(bedpe_SVTYPE_classified)
}
#' Convert VCF format to bed format
#'
#' This function read vcf file and convert it to bed format
#'
#' @param vcf_file names of vcf file
#' @return data frame
#' @export
vcf_to_bed <- function(vcf_file){
vcf <- VariantAnnotation::readVcf(vcf_file)
fixed_df <- vcf@fixed
gr <- vcf@rowRanges
info <- vcf@info
for(field in c("SVLEN","END", "STRANDS","CT","INV5","INV3","MATEID")){
tmp <- eval(parse(text=paste0("info$", field)))
if (length(tmp) == 0){
assign(paste0("INFO_", field), NA)
}else{
idx <- !(sapply(tmp, length))
tmp[idx] <- NA
if(field == "STRANDS"){
assign(paste0("INFO_", field), sapply(tmp, paste, collapse = ","))
}else{
assign(paste0("INFO_", field), unlist(tmp))
}
}
}
bed <- data.frame(CHROM = gr@seqnames,
POS = gr@ranges@start,
ID_caller = gr@ranges@NAMES,
REF = as.character(fixed_df$REF),
ALT = data.frame(fixed_df$ALT)$value,
QUAL = fixed_df$QUAL,
FILTER = fixed_df$FILTER,
INFO_END,
INFO_SVTYPE = info$SVTYPE,
INFO_SVLEN,
INFO_STRANDS,
INFO_CT = INFO_CT,
INFO_INV5 = INFO_INV5,
INFO_INV3 = INFO_INV3,
INFO_MATEID_caller = INFO_MATEID,
stringsAsFactors = FALSE
)
return(bed)
}
#' Classify SV types based on VCF
#'
#' This function read bed format
#'
#' @param bed datafame of bed format
#' @param caller_name name of caller to be used in ID
#' @return data frame
#' @export
simple_SVTYPE_classification <- function(bed, caller_name){
bedpe <- bed_to_bedpe(bed)
if(length(bedpe$ID_caller)!=0){
bedpe <- bedpe[is.na(match(bedpe$ID_caller, bedpe$INFO_MATEID_caller)) | ### either don't have mate (i.e. not BND)
(c(1:nrow(bedpe)) < match(bedpe$ID_caller, bedpe$INFO_MATEID_caller)),] ###  or present first as BND
}
SV_index <- c(1:nrow(bedpe))
event_index <- SV_index
SVTYPE <- bedpe$INFO_SVTYPE
SVTYPE[(bedpe$strand1 == "+") & (bedpe$strand2 == "-") & (bedpe$chrom1 == bedpe$chrom2)] <- "DEL"
SVTYPE[(bedpe$strand1 == "-") & (bedpe$strand2 == "+") & (bedpe$chrom1 == bedpe$chrom2)] <- "DUP"
SVTYPE[(bedpe$strand1 == bedpe$strand2) & (bedpe$chrom1 == bedpe$chrom2)] <- "INV"
SVTYPE[(bedpe$chrom1 != bedpe$chrom2)] <- "TRA"
SVTYPE[is.na(bedpe$strand1)] <- "INS"
standard_bedpe <- data.frame(chrom1 = as.character(bedpe$chrom1),
pos1 = as.integer(bedpe$pos1),
chrom2 = as.character(bedpe$chrom2),
pos2 = as.integer(bedpe$pos2),
SVTYPE = SVTYPE,
strand1 = bedpe$strand1,
strand2 = bedpe$strand2,
ID = paste0(caller_name,"_",SV_index,"_1_",event_index),
ID_mate = paste0(caller_name,"_",SV_index,"_2_",event_index),
#ALT = bedpe$ALT,
stringsAsFactors = FALSE)
bedpe_SVTYPE_classified <- data.frame(standard_bedpe, bedpe[,!(colnames(bedpe) %in% c("chrom1","chrom2","pos1","pos2","strand1","strand2"))])
colnames(bedpe_SVTYPE_classified) <- c("chrom1", "pos1","chrom2","pos2","SVTYPE",
"strand1","strand2",
"ID","ID_mate",
colnames(bedpe)[!(colnames(bedpe) %in% c("chrom1","chrom2","pos1","pos2","strand1","strand2"))])
return(bedpe_SVTYPE_classified)
}
#' Convert strands into standard form
#'
#' This function read bed format
#'
#' @param bed dataframe
#' @return data frame
#' @export
strands_standardisation <- function(bed){
if(length(bed$ID_caller) == 0){bed$ID_caller = c(1:nrow(bed))}
strand1 <- rep(NA, nrow(bed)); strand2 <- rep(NA, nrow(bed))
if(sum(!is.na(bed$INFO_STRANDS))!=0){
tmp <- data.frame(stringr::str_split_fixed(bed$INFO_STRANDS,",",2), bed$ID_caller)
tmp$X1 <- gsub(":.*","", tmp$X1)
tmp$X2 <- gsub(":.*","", tmp$X2)
idx <- rep(1:nrow(tmp), rowSums(tmp[,c(1,2)]!=""))
tmp2 <- tmp[idx,]
tmp2[duplicated(tmp2$bed.ID_caller),]$X1 <- tmp2[duplicated(tmp2$bed.ID_caller),]$X2
tmp3 <- tmp2[,-2]
tmp3 <- cbind(tmp3, stringr::str_split_fixed(tmp3$X1,"",2))
colnames(tmp3) <- c("strands","ID_caller","strand1","strand2")
}else if(sum(!is.na(bed$INFO_CT)) != 0){
tmp <- data.frame(bed$INFO_CT, ID_caller = bed$ID_caller)
strand1[tmp$INFO_CT=="3to5"] <- "+"; strand2[tmp$INFO_CT=="3to5"] <- "-"
strand1[tmp$INFO_CT=="5to3"] <- "-"; strand2[tmp$INFO_CT=="5to3"] <- "+"
strand1[tmp$INFO_CT=="3to3"] <- "+"; strand2[tmp$INFO_CT=="3to3"] <- "+"
strand1[tmp$INFO_CT=="5to5"] <- "-"; strand2[tmp$INFO_CT=="5to5"] <- "-"
strand1[tmp$INFO_CT=="NtoN"] <- NA; strand2[tmp$INFO_CT=="NtoN"] <- NA
tmp3 <- cbind(tmp, strand1, strand2)
}else if(sum(!is.na(bed$INFO_INV5)) !=0){
tmp <- data.frame(bed$INFO_INV5, bed$INFO_INV3, ID_caller = bed$ID_caller)
strand1[bed$INFO_INV5] <- "-";strand2[bed$INFO_INV5] <- "-"
strand1[bed$INFO_INV3] <- "+";strand2[bed$INFO_INV3] <- "+"
tmp3 <- cbind(tmp, strand1, strand2)
}else{
tmp3 <- cbind(bed, strand1, strand2)
}
bed2 <- bed[match(tmp3$ID_caller, bed$ID_caller),]
bed2$strand1 <- tmp3$strand1
bed2$strand2 <- tmp3$strand2
if((sum(bed2$INFO_SVTYPE %in% c("DEL","DUP")) != 0) & sum(is.na(bed2$strand1))!=0){
bed2[is.na(bed2$strand1) & bed2$INFO_SVTYPE == "DEL",]$strand1 <- "+"
bed2[is.na(bed2$strand2) & bed2$INFO_SVTYPE == "DEL",]$strand2 <- "-"
bed2[is.na(bed2$strand1) & bed2$INFO_SVTYPE == "DUP",]$strand1 <- "-"
bed2[is.na(bed2$strand2) & bed2$INFO_SVTYPE == "DUP",]$strand2 <- "+"
}
return(bed2)
}
#' Convert bed format to bedpe format
#'
#' This function read bed format
#'
#' @param bed data frame
#' @return data frame
#' @export
bed_to_bedpe <- function(bed){
bed <- strands_standardisation(bed)
ALT <- bed$ALT
tmp <- gsub("\\:.*",'', ALT[grepl('\\[',ALT) | grepl('\\]',ALT)])
tmp1 <- gsub(".*\\[",'', tmp)
tmp2 <- gsub(".*\\]",'', tmp1)
chrom1 = as.character(bed$CHROM)
chrom2 <- chrom1
chrom2[grepl('\\[',ALT) | grepl('\\]',ALT)] <- tmp2
tmp <- gsub(".*\\:",'', ALT[grepl('\\[',ALT) | grepl('\\]',ALT)])
tmp1 <- gsub("\\[.*",'', tmp)
tmp2 <- gsub("\\].*",'', tmp1)
pos2 <- bed$INFO_END
pos2[grepl('\\[',ALT) | grepl('\\]',ALT)] <- tmp2
pos2[is.na(pos2)] <- bed$POS[is.na(pos2)] ###if no POS2 then use #CHROM in VCF
strand1 <- bed$strand1; strand2 <- bed$strand2
###[p[t
strand1[grepl('\\[', bed$ALT) & substr(bed$ALT,1,1) == "["] <- "-"
strand2[grepl('\\[', bed$ALT) & substr(bed$ALT,1,1) == "["] <- "-"
###t[p[
strand1[grepl('\\[', bed$ALT) & substr(bed$ALT,1,1) != "["] <- "+"
strand2[grepl('\\[', bed$ALT) & substr(bed$ALT,1,1) != "["] <- "-"
###t]p]
strand1[grepl(']', bed$ALT) & substr(bed$ALT,1,1) != "]"] <- "+"
strand2[grepl(']', bed$ALT) & substr(bed$ALT,1,1) != "]"] <- "+"
###]p]t
strand1[grepl(']', bed$ALT) & substr(bed$ALT,1,1) == "]"] <- "-"
strand2[grepl(']', bed$ALT) & substr(bed$ALT,1,1) == "]"] <- "+"
bedpe <- data.frame(chrom1=bed$CHROM,
pos1=bed$POS,
chrom2=paste0(tolower(substring(chrom2,1,3)), substring(chrom2,4,nchar(chrom2))),
pos2=pos2,
strand1 = strand1,
strand2 = strand2,
ALT=ALT,
stringsAsFactors = FALSE)
bedpe <- data.frame(bedpe, bed[,!(colnames(bed) %in% c("CHROM","POS","INFO_END","ALT","strand1","strand2"))])
colnames(bedpe) <- c("chrom1", "pos1","chrom2","pos2","strand1","strand2","ALT",
colnames(bed)[!(colnames(bed) %in% c("CHROM","POS","INFO_END","ALT","strand1","strand2"))])
return(bedpe)
}
usethis::use_data(CallerA_bed,overwrite = TRUE)
CallerA_bed <- simple_SVTYPE_classification(bed = vcf_to_bed(vcf_file), "CallerA")
usethis::use_data(CallerA_bed,overwrite = TRUE)
vcf_file <- system.file("extdata",
"manta_SVEngine_TumorSV2.60x_NormalSV1.60x_0.5.T.PASS.recode.vcf",
package = "ShinySoSV2")
CallerB_bed <- simple_SVTYPE_classification(bed = vcf_to_bed(vcf_file), "CallerB")
usethis::use_data(CallerB_bed,overwrite = TRUE)
vcf_file <- system.file("extdata",
"GRIDSS_SVEngine_TumorSV2.60x_NormalSV1.60x_0.5_somatic_PASS_annotated.vcf",
package = "ShinySoSV2")
CallerC_bed <- simple_SVTYPE_classification(bed = vcf_to_bed(vcf_file), "CallerC")
usethis::use_data(CallerC_bed,overwrite = TRUE)
devtools::document()
?use_data
devtools::document()
set.seed(1)
input_SV_count <- data.frame(sampleID = paste0("sample_",c(1:100)),
DEL = sample.int(300, 100, replace = TRUE),
DUP = sample.int(300, 100, replace = TRUE),
INS = sample.int(100, 100, replace = TRUE),
INV = sample.int(300, 100, replace = TRUE),
TRA = sample.int(300, 100, replace = TRUE))
usethis::use_data(input_SV_count, overwrite = TRUE)
devtools::document()
devtools::install_github("tgong1/ShinySoSV2")
library(ShinySoSV2)
setwd("~/Desktop/work_at_home/HRPCa_SV_method_paper/TEST_R_script2")
install.packages("devtools")
install.packages("devtools")
install.packages("remotes")
devtools::install_github("tgong1/ShinySoSV2")
library(ShinySoSV2)
setwd("~/Desktop/work_at_home/HRPCa_SV_method_paper/TEST_R_script2")
remove.packages("curl")
remove.packages("httr")
install.packages("curl")
install.packages("curl")
install.packages("httr")
devtools::install_github("tgong1/ShinySoSV2")
options(download.file.method = "libcurl")
devtools::install_github("tgong1/ShinySoSV2")
options(download.file.method = "wininet")
devtools::install_github("tgong1/ShinySoSV2")
?options
options(download.file.method = "curl")
devtools::install_github("tgong1/ShinySoSV2")
set.seed(1)
input_SV_count <- data.frame(sampleID = paste0("sample_",c(1:100)),
DEL = sample.int(300, 100, replace = TRUE),
DUP = sample.int(300, 100, replace = TRUE),
INS = sample.int(100, 100, replace = TRUE),
INV = sample.int(300, 100, replace = TRUE),
TRA = sample.int(300, 100, replace = TRUE))
usethis::use_data(input_SV_count, overwrite = TRUE)
devtools::document()
###Test data for CNV integration, currently use sample UP2003 in HRPCa project
SCNV <- read.table(system.file("extdata",
"UP2003-T.final.call.threshold.cns",
package = "ShinySoSV2"), header = TRUE)
CNV_bed <- SCNV[,c(1,2,3,6)]
View(CNV_bed)
usethis::use_data(CNV_bed, overwrite = TRUE)
SCNV <- read.table(system.file("extdata",
"UP2003_Manta_GRIDSS_intersect_both_high_confidence.bedpe",
package = "ShinySoSV2"), header = TRUE)
SV_bed <- bedpe[,c(1:10)]
bedpe <- read.table(system.file("extdata",
"UP2003_Manta_GRIDSS_intersect_both_high_confidence.bedpe",
package = "ShinySoSV2"), header = TRUE)
View(bedpe)
SV_bed <- bedpe[,c(1:10)]
usethis::use_data(SV_bed, overwrite = TRUE)
devtools::install_github("tgong1/ShinySoSV2")
library(ShinySoSV2)
ShinySoSV2::Spectrum_SV_type()
load("/Users/tingtinggong/Desktop/work_at_home/HRPCa_SV_method_paper/ShinySoSV2/data/input_SV_bed.rds")
All_sampleID <- paste0("sample_",c(1:100))
All_input_df_name <- paste0(All_sampleID, "_df")
input_SV_count <- Summary_SV_type(All_sampleID, All_input_df_name)
head(input_SV_count)
data("input_SV_count")
hyper_SV <- Spectrum_SV_type(input_SV_count,threshold_total = 500, threshold_relative_freq = 0.5)
data()
data(SV_bed)
SV_bed
head(SV_bed)
data(CNV_bed)
head(CNV_bed)
data(CallerA_bed)
gene_bed <- load(system.file("extdata", "gene_bed.Rdata", package = "ShinySoSV2"))
system.file("extdata",
"GRIDSS_SVEngine_TumorSV2.60x_NormalSV1.60x_0.5_somatic_PASS_annotated.vcf",
package = "ShinySoSV2")
library(ShinySoSV2)
system.file("extdata",
"GRIDSS_SVEngine_TumorSV2.60x_NormalSV1.60x_0.5_somatic_PASS_annotated.vcf",
package = "ShinySoSV2")
gene_bed <- load(system.file("extdata", "gene_bed.Rdata", package = "ShinySoSV2"))
system.file("extdata", "gene_bed.Rdata", package = "ShinySoSV2")
gene_bed <- load("/Users/tingtinggong/Desktop/work_at_home/HRPCa_SV_method_paper/ShinySoSV2/gene_bed.Rdata")
gene_bed <- load("/Users/tingtinggong/Desktop/work_at_home/HRPCa_SV_method_paper/ShinySoSV2/inst/extdata/gene_bed.Rdata")
usethis::use_data(gene_bed, overwrite = TRUE)
gene_bed
gene_bed <- load("/Users/tingtinggong/Desktop/work_at_home/HRPCa_SV_method_paper/ShinySoSV2/inst/extdata/gene_bed.Rdata")
?load
load("/Users/tingtinggong/Desktop/work_at_home/HRPCa_SV_method_paper/ShinySoSV2/inst/extdata/gene_bed.Rdata")
devtools::document()
devtools::document()
data(CallerA_bed)
load(system.file("extdata", "gene_bed.Rdata", package = "ShinySoSV2"))
bedtools_dir = "/opt/homebrew/bin/bedtools"
CallerA_bed_GeneAnnotated <- SV_bedpe_gene_annotation(input_df_name = "CallerA_bed", gene_bed, bedtools_dir)
usethis::use_data(CallerA_bed_GeneAnnotated, overwrite = TRUE)
df_All_gene_fusions_ensembl <- read.csv("/Users/tingtinggong/Desktop/work_at_home/HYPER-DUP/SomaticSV_MantaGRIDSS/All_gene_fusions.csv")
usethis::use_data(df_All_gene_fusions_ensembl, overwrite = TRUE)
df_All_gene_fusions <- read.csv("/Users/tingtinggong/Desktop/work_at_home/HYPER-DUP/SomaticSV_MantaGRIDSS/All_gene_fusions.csv")
df_All_gene_fusions <- df_All_gene_fusions[!(df_All_gene_fusions$sampleID %in% c("16599-1159140", "10651-1042378","UP2063","UP2037","UP2041")),]
df_All_gene_fusions$sampleID<- gsub('-.*','',as.character(df_All_gene_fusions$sampleID))
df_All_gene_fusions$SVTYPE[df_All_gene_fusions$SVTYPE=="TRA_INV"] <- "TRA"
ProstateCancer_SV_bed_GeneAnnotated <- df_All_gene_fusions[,c(1:11,18,19)]
View(ProstateCancer_SV_bed_GeneAnnotated)
usethis::use_data(ProstateCancer_SV_bed_GeneAnnotated, overwrite = TRUE)
devtools::document()