Skip to content

Update fitness_calculation.R #30

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
BenjaminWehnert1008 merged 1 commit into from
Mar 2, 2026
Merged

Update fitness_calculation.R #30

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
60 changes: 30 additions & 30 deletions modules/local/fitness/templates/fitness_calculation.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,13 +18,13 @@ compute_nt_hamming <- function(merged.counts, wt.seq) {
merged.counts <- cbind("nt_ham" = rep(NA, nrow(merged.counts)), merged.counts)
for (i in 1:nrow(merged.counts)){
tmp.wt <- strsplit(as.character(wt.seq), "")[[1]]
tmp.mut <- strsplit(as.character(merged.counts\$nt_seq[i]), "")[[1]]
tmp.mut <- strsplit(as.character(merged.counts$nt_seq[i]), "")[[1]]
if(length(which(tmp.mut != tmp.wt)) == 0){
merged.counts\$nt_ham[i] <- 0
merged.counts$nt_ham[i] <- 0
rm(tmp.mut, tmp.wt)
next
}else{
merged.counts\$nt_ham[i] <- length(which(tmp.mut != tmp.wt))
merged.counts$nt_ham[i] <- length(which(tmp.mut != tmp.wt))
rm(tmp.mut, tmp.wt)
next
}
Expand All @@ -34,7 +34,7 @@ compute_nt_hamming <- function(merged.counts, wt.seq) {

# translate sequences and add aa_seq
add_aa_seq <- function(merged.counts) {
merged.counts <- cbind("aa_seq" = as.character(translate(DNAStringSet(merged.counts\$nt_seq))), merged.counts)
merged.counts <- cbind("aa_seq" = as.character(translate(DNAStringSet(merged.counts$nt_seq))), merged.counts)
merged.counts
}

Expand All @@ -43,13 +43,13 @@ compute_aa_hamming <- function(merged.counts, wt.seq.aa) {
merged.counts <- cbind("aa_ham" = rep(NA, nrow(merged.counts)), merged.counts)
for (i in 1:nrow(merged.counts)){
tmp.wt <- strsplit(as.character(wt.seq.aa), "")[[1]]
tmp.mut <- strsplit(as.character(merged.counts\$aa_seq[i]), "")[[1]]
tmp.mut <- strsplit(as.character(merged.counts$aa_seq[i]), "")[[1]]
if(length(which(tmp.mut != tmp.wt)) == 0){
merged.counts\$aa_ham[i] <- 0
merged.counts$aa_ham[i] <- 0
rm(tmp.mut, tmp.wt)
next
}else{
merged.counts\$aa_ham[i] <- length(which(tmp.mut != tmp.wt))
merged.counts$aa_ham[i] <- length(which(tmp.mut != tmp.wt))
rm(tmp.mut, tmp.wt)
next
}
Expand All @@ -63,14 +63,14 @@ name_mutations <- function(merged.counts, wt.seq.aa) {
"pos" = rep(NA, nrow(merged.counts)),
"mut aa" = rep(NA, nrow(merged.counts)), merged.counts)
for (i in 1:nrow(merged.counts)){
if(merged.counts\$aa_ham[i] == 0){
if(merged.counts$aa_ham[i] == 0){
next
}else{
tmp.wt <- strsplit(as.character(wt.seq.aa), "")[[1]]
tmp.mut <- strsplit(as.character(merged.counts\$aa_seq[i]), "")[[1]]
merged.counts\$pos[i] <- which(tmp.mut != tmp.wt)
merged.counts\$`wt aa`[i] <- tmp.wt[merged.counts\$pos[i]]
merged.counts\$`mut aa`[i] <- tmp.mut[merged.counts\$pos[i]]
tmp.mut <- strsplit(as.character(merged.counts$aa_seq[i]), "")[[1]]
merged.counts$pos[i] <- which(tmp.mut != tmp.wt)
merged.counts$`wt aa`[i] <- tmp.wt[merged.counts$pos[i]]
merged.counts$`mut aa`[i] <- tmp.mut[merged.counts$pos[i]]
rm(tmp.mut, tmp.wt)
}
}
Expand All @@ -83,17 +83,17 @@ aggregate_by_aa <- function(merged.counts) {
merged.counts <- cbind(merged.counts,
"wt" = rep(NA, nrow(merged.counts)),
"stop" = rep(NA, nrow(merged.counts)))
merged.counts\$wt[which(merged.counts\$nt_ham == 0)] <- TRUE
merged.counts\$stop[which(merged.counts\$`mut aa` == "*")] <- TRUE
merged.counts$wt[which(merged.counts$nt_ham == 0)] <- TRUE
merged.counts$stop[which(merged.counts$`mut aa` == "*")] <- TRUE

## aggregate counts of variants which are identical on the aa (but not nt) level
## exception: wildtype ones
## thereby shrinking the matrix
uniq.aa.vars <- unique(merged.counts\$aa_seq)
uniq.aa.vars <- uniq.aa.vars[-which(uniq.aa.vars == merged.counts\$aa_seq[which(merged.counts\$wt == TRUE)])]
uniq.aa.vars <- unique(merged.counts$aa_seq)
uniq.aa.vars <- uniq.aa.vars[-which(uniq.aa.vars == merged.counts$aa_seq[which(merged.counts$wt == TRUE)])]
for(i in 1:length(uniq.aa.vars)){
tmp.aa_seq <- uniq.aa.vars[i]
hits <- which(as.character(merged.counts\$aa_seq) == tmp.aa_seq)
hits <- which(as.character(merged.counts$aa_seq) == tmp.aa_seq)
if(length(hits) == 1){
rm(tmp.aa_seq, hits)
next
Expand Down Expand Up @@ -129,7 +129,7 @@ density_peaks <- function(x, adjust = 1, ...) {
# 3. Raw fitness calculations ##
calc_raw_fitness <- function(merged.counts, exp.design) {
## how many fitness replicates are there
reps <- length(unique(exp.design\$experiment_replicate))
reps <- length(unique(exp.design$experiment_replicate))
for (i in 1:reps){
merged.counts <- cbind(merged.counts, rep(NA, nrow(merged.counts)))
colnames(merged.counts)[ncol(merged.counts)] <- paste0("raw_fitness_rep", i)
Expand All @@ -146,8 +146,8 @@ calc_raw_fitness <- function(merged.counts, exp.design) {
tmp.output.counts[which(tmp.output.counts == 0 & tmp.input.counts != 0)] <- 1

### take logs
tmp.wt.log.ratio <- log(tmp.output.counts[which(merged.counts\$wt == TRUE)] /
tmp.input.counts[which(merged.counts\$wt == TRUE)])
tmp.wt.log.ratio <- log(tmp.output.counts[which(merged.counts$wt == TRUE)] /
tmp.input.counts[which(merged.counts$wt == TRUE)])
tmp.fitness <- log(tmp.output.counts /
tmp.input.counts) - tmp.wt.log.ratio

Expand All @@ -174,8 +174,8 @@ rescale_and_summarize <- function(merged.counts, reps) {
colnames(merged.counts)[ncol(merged.counts)] <- paste0("rescaled_fitness_rep", i)

### fetch the key counts
tmp.wt.fitness <- merged.counts[which(merged.counts\$aa_ham == 0),ncol(merged.counts) - reps]
tmp.stop.fitness <- merged.counts[which(merged.counts\$stop == TRUE),ncol(merged.counts) - reps]
tmp.wt.fitness <- merged.counts[which(merged.counts$aa_ham == 0),ncol(merged.counts) - reps]
tmp.stop.fitness <- merged.counts[which(merged.counts$stop == TRUE),ncol(merged.counts) - reps]

### rescale
tmp.wt.fitness.med <- median(tmp.wt.fitness, na.rm = TRUE)
Expand Down Expand Up @@ -221,15 +221,15 @@ rescale_and_summarize <- function(merged.counts, reps) {

if(reps == 1){

merged.counts\$`mean fitness` <- merged.counts[,ncol(merged.counts) - 2]
merged.counts$`mean fitness` <- merged.counts[,ncol(merged.counts) - 2]

}else if(reps > 1){

merged.counts\$`mean fitness` <- apply(merged.counts[,c(ncol(merged.counts) - 1 - reps):c(ncol(merged.counts) - 2)],
merged.counts$`mean fitness` <- apply(merged.counts[,c(ncol(merged.counts) - 1 - reps):c(ncol(merged.counts) - 2)],
1,
mean,
na.rm = TRUE)
merged.counts\$`fitness sd` <- apply(merged.counts[,c(ncol(merged.counts) - 1 - reps):c(ncol(merged.counts) - 2)],
merged.counts$`fitness sd` <- apply(merged.counts[,c(ncol(merged.counts) - 1 - reps):c(ncol(merged.counts) - 2)],
1,
sd,
na.rm = TRUE)
Expand All @@ -256,8 +256,8 @@ run_fitness_estimation <- function(counts_path,
## 1. Import key files ##
#########################

merged.counts <- read.table(counts_path, sep = "\\t", header = TRUE, check.names = FALSE)
exp.design <- read.table(design_path, sep = "\\t", header = TRUE, check.names = FALSE)
merged.counts <- read.table(counts_path, sep = "\t", header = TRUE, check.names = FALSE)
exp.design <- read.table(design_path, sep = "\t", header = TRUE, check.names = FALSE)
wt.seq <- DNAString(as.character(read.table(wt_seq_path)))
wt.seq.aa <- translate(wt.seq)

Expand All @@ -282,8 +282,8 @@ run_fitness_estimation <- function(counts_path,
## 3. Raw fitness calculations ##
#################################
fitness_res <- calc_raw_fitness(merged.counts, exp.design)
merged.counts <- fitness_res\$merged.counts
reps <- fitness_res\$reps
merged.counts <- fitness_res$merged.counts
reps <- fitness_res$reps

## 4. Fitness and error refinements ##
######################################
Expand All @@ -294,7 +294,7 @@ run_fitness_estimation <- function(counts_path,

## export
write.table(merged.counts, output_path,
col.names = TRUE, row.names = FALSE, quote = FALSE, sep = "\\t", na = "")
col.names = TRUE, row.names = FALSE, quote = FALSE, sep = "\t", na = "")

invisible(merged.counts)
}
Expand Down
Loading