File size: 3,518 Bytes
fe8e241 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | args <- commandArgs(trailingOnly = FALSE)
script_arg <- grep("^--file=", args, value = TRUE)
if (length(script_arg) > 0) {
script_path <- normalizePath(sub("^--file=", "", script_arg[1]))
setwd(normalizePath(file.path(dirname(script_path), "..")))
}
library(caret)
pep_mat_local <- function(pep) {
do.call(rbind, strsplit(as.character(pep), split = ""))
}
one_hot <- function(y, num_classes = 2) {
y <- as.integer(as.character(y))
out <- matrix(0, nrow = length(y), ncol = num_classes)
out[cbind(seq_along(y), y + 1)] <- 1
out
}
load("model/BLOSUM62_with_deletion.Rdata")
pep_encode_blosum <- function(pep) {
bl62_prob <- BLOSUM62
p_mat <- pep_mat_local(pep)
n_peps <- length(pep)
l_peps <- nchar(pep[1])
l_enc <- ncol(bl62_prob)
o_tensor <- array(data = NA, dim = c(n_peps, l_peps, l_enc))
for (i in 1:n_peps) {
pep_i_residues <- p_mat[i, ]
pep_img <- bl62_prob[pep_i_residues, ]
o_tensor[i, , ] <- pep_img
}
o_tensor
}
all <- read.delim("model/CNN/all_ab_pre_post.txt", sep = "\t", header = TRUE, stringsAsFactors = FALSE)
set.seed(42)
all <- all[sample(nrow(all)), ]
max_k <- max(nchar(all$CDR3K))
max_h <- max(nchar(all$CDR3H))
all$paddedh <- gsub("\\s", "-", format(all$CDR3H, width = max_h))
all$paddedk <- gsub("\\s", "-", format(all$CDR3K, width = max_k))
all$lengthh <- nchar(all$CDR3H)
all$lengthk <- nchar(all$CDR3K)
all$padded <- paste0(all$paddedk, all$paddedh)
all <- all[order(all$padded, -all$post), ]
all2 <- all[!duplicated(all$padded), ]
all2$enriched <- ifelse((all2$fc >= 1.8 & all2$post >= 0.01), 1,
ifelse(all2$fc < 1 & all2$pre >= 0.01, 0, "ambi"))
all2 <- all2[all2$enriched != "ambi", ]
all2$enriched <- as.integer(all2$enriched)
split_train_test <- function(antigenx) {
mini <- all2[all2$antigen == antigenx, ]
set.seed(22)
trainIndex <- createDataPartition(mini$enriched, p = .8, list = FALSE, times = 1)
list(train = mini[trainIndex, ], test = mini[-trainIndex, ])
}
c1 <- split_train_test("CTLA-4")
p1 <- split_train_test("PD-1")
saveRDS(c1, file = "model/CNN/c1.RDS")
saveRDS(p1, file = "model/CNN/p1.RDS")
c1_train <- pep_encode_blosum(c1$train$padded)
c1_test <- pep_encode_blosum(c1$test$padded)
p1_train <- pep_encode_blosum(p1$train$padded)
p1_test <- pep_encode_blosum(p1$test$padded)
c1_train <- array(c1_train, dim = c(dim(c1_train), 1))
c1_test <- array(c1_test, dim = c(dim(c1_test), 1))
p1_train <- array(p1_train, dim = c(dim(p1_train), 1))
p1_test <- array(p1_test, dim = c(dim(p1_test), 1))
c1_train_y <- one_hot(c1$train$enriched)
c1_test_y <- one_hot(c1$test$enriched)
p1_train_y <- one_hot(p1$train$enriched)
p1_test_y <- one_hot(p1$test$enriched)
saveRDS(p1_train, file = "model/CNN/p1_train.RDS")
saveRDS(p1_test, file = "model/CNN/p1_test.RDS")
saveRDS(p1_train_y, file = "model/CNN/p1_train_y.RDS")
saveRDS(p1_test_y, file = "model/CNN/p1_test_y.RDS")
saveRDS(c1_train, file = "model/CNN/c1_train.RDS")
saveRDS(c1_test, file = "model/CNN/c1_test.RDS")
saveRDS(c1_train_y, file = "model/CNN/c1_train_y.RDS")
saveRDS(c1_test_y, file = "model/CNN/c1_test_y.RDS")
seq_all <- readRDS("model/GAN/seq_all.RDS")
encoded <- vector("list", 15)
names(encoded) <- names(seq_all)
for (i in 1:15) {
seq_encoded <- pep_encode_blosum(seq_all[[i]])
encoded[[i]] <- array(seq_encoded, dim = c(dim(seq_encoded), 1))
}
saveRDS(encoded, file = "model/GAN/seq_all_encoded.RDS")
print("prepare data OK")
print(dim(c1_train))
print(dim(p1_train))
print(names(encoded))
|