Compare commits

...

1 Commits

Author SHA1 Message Date
coolneng 04415310c6
Remove redundant sequencing runs argument 2021-03-29 20:33:39 +02:00
2 changed files with 12 additions and 26 deletions

View File

@ -20,5 +20,5 @@ filename="sequence"
prefix="curesim_" prefix="curesim_"
Rscript src/repertoire.r "$sequences" "$sequencing_runs" Rscript src/repertoire.r "$sequences" "$sequencing_runs"
java -jar tools/CuReSim.jar -m "$read_mean_size" -sd "$read_variance_size" -f "$data_directory$filename$fasta" -o "$data_directory$prefix$filename$fastq" java -jar tools/CuReSim.jar -n "$sequencing_runs" -m "$read_mean_size" -sd "$read_variance_size" -f "$data_directory$filename$fasta" -o "$data_directory$prefix$filename$fastq"
rm "$data_directory/log.txt" rm "$data_directory/log.txt"

View File

@ -10,44 +10,30 @@ generate_repertoire <- function(number_of_sequences) {
)) ))
} }
amplify_rows <- function(data, column, factor) {
if (column == "sequence") {
dna_string <- Biostrings::DNAStringSet(data)
reverse_complement <- Biostrings::reverseComplement(dna_string)
return(rep(reverse_complement, factor))
}
return(rep(data, factor))
}
save_data <- function(data) { save_data <- function(data) {
Biostrings::writeXStringSet(data$sequence, "data/sequence.fasta") Biostrings::writeXStringSet(data$sequence, "data/sequence.fasta")
vdj_sequences <- data[-1] vdj_sequences <- data[-1]
write.csv(vdj_sequences, "data/vdj_alignment.csv", row.names = FALSE) write.csv(vdj_sequences, "data/vdj_alignment.csv", row.names = FALSE)
} }
process_data <- function(repertoire, sequencing_runs) { process_data <- function(repertoire) {
columns <- c( columns <- c(
"sequence", "v_sequence_alignment", "sequence", "v_sequence_alignment",
"d_sequence_alignment", "j_sequence_alignment" "d_sequence_alignment", "j_sequence_alignment"
) )
data <- repertoire[, columns] data <- repertoire[, columns]
amplified_data <- mapply(data, names(data), data$sequence <- Biostrings::reverseComplement(data$sequence)
sequencing_runs, save_data(data)
FUN = amplify_rows
)
save_data(amplified_data)
} }
parse_cli_arguments <- function(args) { parse_cli_arguments <- function() {
if (length(args) != 2) { args <- commandArgs(trailingOnly = TRUE)
stop("usage: repertoire.r <number of sequences> <sequencing_runs>") if (length(args) != 1) {
stop("usage: repertoire.r <number of sequences>")
} }
return(c(args[1], args[2])) return(args[1])
} }
args <- commandArgs(trailingOnly = TRUE) arguments <- parse_cli_arguments(commandArgs(trailing))
arguments <- parse_cli_arguments(args) repertoire <- generate_repertoire(number_of_sequences = arguments[1])
number_of_sequences <- as.integer(arguments[1]) process_data(repertoire)
sequencing_runs <- as.integer(arguments[2])
repertoire <- generate_repertoire(number_of_sequences)
process_data(repertoire, sequencing_runs)