Construct a dataframe containing the HVR region
This commit is contained in:
parent
8f5b9ee698
commit
3a10380d8c
|
@ -1,12 +1,23 @@
|
||||||
library(Biostrings)
|
library(Biostrings)
|
||||||
library(fastqcr)
|
library(parallel)
|
||||||
|
|
||||||
|
construct_dataframe <- function(data) {
|
||||||
|
vdj_string_set <- lapply(data, FUN = Biostrings::DNAStringSet)
|
||||||
|
vdj_dataframe <- as.data.frame(vdj_string_set)
|
||||||
|
vdj_dataframe$hvr_region <- paste(vdj_dataframe$v_sequence,
|
||||||
|
vdj_dataframe$d_sequence, vdj_dataframe$j_sequence,
|
||||||
|
sep = ""
|
||||||
|
)
|
||||||
|
return(vdj_dataframe)
|
||||||
|
}
|
||||||
|
|
||||||
parse_data <- function(files) {
|
parse_data <- function(files) {
|
||||||
reversed_sequences <- Biostrings::readQualityScaledDNAStringSet(files[1])
|
reversed_sequences <- Biostrings::readQualityScaledDNAStringSet(files[1])
|
||||||
sequences <- Biostrings::reverseComplement(reversed_sequences)
|
sequences <- Biostrings::reverseComplement(reversed_sequences)
|
||||||
vdj_alignment <- read.csv(files[2])
|
vdj_alignment <- read.csv(files[2])
|
||||||
vdj_string_set <- lapply(vdj_alignment, FUN = Biostrings::DNAStringSet)
|
vdj_dataframe <- construct_dataframe(vdj_alignment)
|
||||||
return(list(sequences, vdj_string_set))
|
return(list(sequences, vdj_dataframe))
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
align_sequences <- function(sequences, vdj_segments) {
|
align_sequences <- function(sequences, vdj_segments) {
|
||||||
|
|
Loading…
Reference in New Issue