101 lines
3.5 KiB
R
101 lines
3.5 KiB
R
library(Biostrings)
|
|
library(parallel)
|
|
|
|
parse_data <- function(file) {
|
|
reversed_sequences <- Biostrings::readQualityScaledDNAStringSet(file)
|
|
sequences <- Biostrings::reverseComplement(reversed_sequences)
|
|
vj_segments <- union(
|
|
readRDS("data/v_segments.rds"),
|
|
readRDS("data/j_segments_phe.rds")
|
|
)
|
|
return(list(sequences, vj_segments))
|
|
}
|
|
|
|
parse_metadata <- function(metadata) {
|
|
id_elements <- unlist(strsplit(metadata, split = " "))
|
|
v_identifier <- id_elements[2]
|
|
j_identifier <- id_elements[3]
|
|
return(list(v_id = v_identifier, j_id = j_identifier))
|
|
}
|
|
|
|
match_id_sequence <- function(names, vdj_segments, id) {
|
|
matches <- grep(names, pattern = id)
|
|
row <- matches[1]
|
|
return(as.character(vdj_segments[row]))
|
|
}
|
|
|
|
get_vj_sequence <- function(metadata, names, vdj_segments) {
|
|
identifiers <- parse_metadata(metadata)
|
|
v_sequence <- match_id_sequence(names, vdj_segments, id = identifiers["v_id"])
|
|
j_sequence <- match_id_sequence(names, vdj_segments, id = identifiers["j_id"])
|
|
return(list(v_seq = v_sequence, j_seq = j_sequence))
|
|
}
|
|
|
|
fetch_vj_sequences <- function(sequences, vdj_segments) {
|
|
vj_sequences <- sapply(names(sequences),
|
|
names(vdj_segments),
|
|
vdj_segments,
|
|
FUN = get_vj_sequence
|
|
)
|
|
results <- data.frame(t(vj_sequences))
|
|
return(results)
|
|
}
|
|
|
|
align_sequence <- function(sequence, vdj_segment) {
|
|
return(Biostrings::pairwiseAlignment(
|
|
subject = sequence,
|
|
pattern = vdj_segment,
|
|
type = "global-local",
|
|
gapOpening = 1
|
|
))
|
|
}
|
|
|
|
handle_indels <- function(insertion, deletion, cys, alignment) {
|
|
ins_start <- sum(Biostrings::width(deletion[start(deletion) <= cys$start]))
|
|
ins_end <- sum(Biostrings::width(deletion[end(deletion) <= cys$end]))
|
|
shift_num <- c(0, cumsum(Biostrings::width(insertion))[-length(ins_start)])
|
|
shifted_ins <- IRanges::shift(insertion, shift_num)
|
|
gaps <- sum(width(shifted_ins[end(shifted_ins) < cys$start + ins_start])) +
|
|
nchar(stringr::str_extract(alignedSubject(alignment), "^-*"))
|
|
return(list("start" = ins_start - gaps, "end" = ins_end - gaps))
|
|
}
|
|
|
|
get_cys_coordinates <- function(alignment) {
|
|
cys <- list("start" = 310, "end" = 312)
|
|
insertion <- unlist(Biostrings::insertion(alignment))
|
|
deletion <- unlist(Biostrings::deletion(alignment))
|
|
delta_coordinates <- handle_indels(insertion, deletion, cys, alignment)
|
|
cys_start <- cys$start + delta_coordinates$start
|
|
cys_end <- cys$end + delta_coordinates$end
|
|
return(list("start" = cys_start, "end" = cys_end))
|
|
}
|
|
|
|
get_hvr_sequences <- function(sequences, vdj_segments, cores = detectCores()) {
|
|
df <- fetch_vj_sequences(sequences, vdj_segments)
|
|
v_alignment <- parallel::mcmapply(sequences,
|
|
df$v_seq,
|
|
FUN = align_sequence,
|
|
mc.cores = cores
|
|
)
|
|
cys_coordinates <- parallel::mclapply(v_alignment, FUN = get_cys_coordinates)
|
|
cys_df <- as.data.frame(do.call(rbind, cys_coordinates))
|
|
remaining <- Biostrings::subseq(sequences, start = unlist(cys_df$end))
|
|
j_alignment <- parallel::mcmapply(remaining,
|
|
df$j_seq,
|
|
FUN = align_sequence,
|
|
mc.cores = cores
|
|
)
|
|
j_start <- parallel::mclapply(
|
|
j_alignment,
|
|
function(x) start(Biostrings::Views(x)),
|
|
mc.cores = cores
|
|
)
|
|
hvr_start <- unlist(cys_df$start)
|
|
hvr_end <- unlist(cys_df$start) + unlist(j_start) + 2
|
|
hvr <- Biostrings::subseq(sequences, start = hvr_start, end = hvr_end)
|
|
return(hvr)
|
|
}
|
|
|
|
data <- parse_data(file = "data/curesim_sequence.fastq")
|
|
hvr <- get_hvr_sequences(sequences = data[[1]], vdj_segments = data[[2]])
|
|
Biostrings::writeXStringSet(hvr, "data/CuReSim-HVR.fastq", format = "fastq") |