Compare commits
No commits in common. "36eb73b458656567cd2e7192bd72b6eb8e514de5" and "5afe040592cdb943b955022ed452e5bbb863c919" have entirely different histories.
36eb73b458
...
5afe040592
@ -18,5 +18,4 @@ prefix="curesim_"
|
|||||||
|
|
||||||
Rscript src/repertoire.r "$sequences" "$number_of_reads" &&
|
Rscript src/repertoire.r "$sequences" "$number_of_reads" &&
|
||||||
java -jar tools/CuReSim.jar -f "$data_directory$filename$fastq" -o "$data_directory$prefix$filename$fastq"
|
java -jar tools/CuReSim.jar -f "$data_directory$filename$fastq" -o "$data_directory$prefix$filename$fastq"
|
||||||
Rscript src/alignment.r
|
|
||||||
rm "$data_directory/log.txt"
|
rm "$data_directory/log.txt"
|
||||||
|
@ -70,32 +70,31 @@ get_cys_coordinates <- function(alignment) {
|
|||||||
return(list("start" = cys_start, "end" = cys_end))
|
return(list("start" = cys_start, "end" = cys_end))
|
||||||
}
|
}
|
||||||
|
|
||||||
get_hvr_sequences <- function(sequences, vdj_segments, cores = detectCores()) {
|
# TODO Refactor this mess
|
||||||
|
get_hvr_sequences <- function(sequences, vdj_segments) {
|
||||||
df <- fetch_vj_sequences(sequences, vdj_segments)
|
df <- fetch_vj_sequences(sequences, vdj_segments)
|
||||||
v_alignment <- parallel::mcmapply(sequences,
|
v_alignment <- parallel::mcmapply(sequences, df$v_seq, FUN = align_sequence)
|
||||||
df$v_seq,
|
j_alignment <- parallel::mcmapply(sequences, df$j_seq, FUN = align_sequence)
|
||||||
FUN = align_sequence,
|
|
||||||
mc.cores = cores
|
|
||||||
)
|
|
||||||
cys_coordinates <- parallel::mclapply(v_alignment, FUN = get_cys_coordinates)
|
cys_coordinates <- parallel::mclapply(v_alignment, FUN = get_cys_coordinates)
|
||||||
cys_df <- as.data.frame(do.call(rbind, cys_coordinates))
|
cys_df <- as.data.frame(do.call(rbind, cys_coordinates))
|
||||||
remaining <- Biostrings::subseq(sequences, start = unlist(cys_df$end))
|
|
||||||
j_alignment <- parallel::mcmapply(remaining,
|
|
||||||
df$j_seq,
|
|
||||||
FUN = align_sequence,
|
|
||||||
mc.cores = cores
|
|
||||||
)
|
|
||||||
j_start <- parallel::mclapply(
|
j_start <- parallel::mclapply(
|
||||||
j_alignment,
|
j_alignment,
|
||||||
function(x) start(Biostrings::Views(x)),
|
function(x) start(Biostrings::Views(x))
|
||||||
mc.cores = cores
|
)
|
||||||
|
hvr <- Biostrings::subseq(sequences,
|
||||||
|
start = unlist(cys_df$start),
|
||||||
|
end = unlist(j_start) + 2
|
||||||
)
|
)
|
||||||
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)
|
return(hvr)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
save_data <- function(data) {
|
||||||
|
Biostrings::writeXStringSet(data, "data/CuReSim-HVR.fastq", format = "fastq")
|
||||||
|
}
|
||||||
|
|
||||||
data <- parse_data(file = "data/curesim_sequence.fastq")
|
data <- parse_data(file = "data/curesim_sequence.fastq")
|
||||||
hvr <- get_hvr_sequences(sequences = data[[1]], vdj_segments = data[[2]])
|
hvr <- get_hvr_sequences(
|
||||||
|
sequences = data[[1]],
|
||||||
|
vdj_segments = data[[2]]
|
||||||
|
)
|
||||||
Biostrings::writeXStringSet(hvr, "data/CuReSim-HVR.fastq", format = "fastq")
|
Biostrings::writeXStringSet(hvr, "data/CuReSim-HVR.fastq", format = "fastq")
|
Loading…
Reference in New Issue
Block a user