diff --git a/src/repertoire.r b/src/repertoire.r index 8904ad7..e9d3115 100644 --- a/src/repertoire.r +++ b/src/repertoire.r @@ -11,17 +11,17 @@ generate_repertoire <- function(number_of_sequences) { } save_data <- function(data, reads) { - Biostrings::writeXStringSet(data$sequence, "data/sequence.fasta") vdj_sequences <- data[-1] amplified_vdj <- vdj_sequences[rep(seq_len(nrow(vdj_sequences)), reads), ] - write.csv(amplified_vdj, "data/vdj_metadata.csv", row.names = FALSE) + Biostrings::writeXStringSet(data$sequence, "data/sequence.fasta") } process_data <- function(repertoire, reads) { - columns <- c("sequence", "junction", "v_call", "j_call") + columns <- c("sequence", "v_call", "j_call") data <- repertoire[, columns] dna_sequence <- Biostrings::DNAStringSet(data$sequence) data$sequence <- Biostrings::reverseComplement(dna_sequence) + names(data$sequence) <- paste(rownames(data), data$v_call, data$j_call) save_data(data, reads) }