ydeng/bch441-work-abc-units
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Line termination change and old code.

Browse Source
This commit is contained in:
Harrison Deng 2021-11-16 00:31:48 -05:00
parent b1e00f52f7
commit affe00f6fb
86 changed files with 37873 additions and 37876 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
myScripts/ABC-INT-Mutation_impact-code.R
View File

@ -1,42 +1,25 @@
myFA <- readFASTA("data/RAB39B_HSa_coding.fa")
myFA <- rbind(myFA, readFASTA("data/PTPN5_HSa_coding.fa"))
myFA <- rbind(myFA, readFASTA("data/PTPN11_HSa_coding.fa"))
myFA <- rbind(myFA, readFASTA("data/KRAS_HSa_coding.fa"))
rownames(myFA)<-c("RAB39B", "PTPN5", "PTPN11", "KRAS") # Assign row names
gen_mutations <- function(seq, N) {
sealKey() # See: http://steipe.biochemistry.utoronto.ca/abc/index.php/BCH441_Code_submisson_instructions
stats <- c()
stats <- cbind(stats, c(0, 0, 0))
rownames(stats) <- c("silent", "missense", "nonsense")
colnames(stats) <- c("occurrences")
# Actual function
for (i in 1:217) {
# select index for mutation
working_seq <- Biostrings::DNAString(seq)
aa_seq <- Biostrings::translate(working_seq, no.init.codon = TRUE)
mut_action <- sample(c("ins", "del", "sub"), 1, TRUE)
for (i in 1:N) {
original_seq <- Biostrings::DNAString(seq)
aa_seq <- Biostrings::translate(original_seq, no.init.codon = TRUE)
mut_seq <- Biostrings::DNAString(seq)
if (mut_action == "sub") {
mut_index <- sample(1:length(working_seq), 1, replace = TRUE)
mut_index <- sample(1:length(original_seq), 1, replace = TRUE)
possible_mutations <- Biostrings::DNA_BASES
possible_mutations <- possible_mutations[possible_mutations != as.character(unlist(working_seq[mut_index]))]
mut_change <- sample(possible_mutations, 1, replace = TRUE)
mut_seq <- Biostrings::replaceLetterAt(mut_seq, mut_index, mut_change)
} else if (mut_action == "ins") {
mut_index <- sample(1:length(working_seq) - 2, 1, replace = TRUE)
possible_mutations <- Biostrings::DNA_BASES
mut_seq <- Biostrings::DNAString(paste(substring(working_seq, 1, mut_index - 1), sample(possible_mutations, 1), substring(working_seq, mut_index), sep = ""))
} else {
mut_index <- sample(1:length(working_seq), 1, replace = TRUE)
mut_seq <- mut_seq[-mut_index]
}
mut_seq <- Biostrings::DNAString(substring(mut_seq, 1, length(mut_seq) - (length(mut_seq) %% 3)))
possible_mutations <- possible_mutations[possible_mutations != as.character(unlist(original_seq[mut_index]))]
mut_seq <- Biostrings::replaceLetterAt(mut_seq, mut_index, sample(possible_mutations, 1, replace = TRUE))
mut_aa <- Biostrings::translate(mut_seq, no.init.codon = TRUE)
# Note: we need silent, nonsense, and missense
mut_aa_stop <- match("*", Biostrings::as.matrix(mut_aa))
aa_seq_stop <- match("*", Biostrings::as.matrix(aa_seq))
if (!is.na(mut_aa_stop) & (is.na(aa_seq_stop) | mut_aa_stop < aa_seq_stop)) {
term_aa <- regexpr(pattern = "\\*", aa_seq)
term_mut_aa <- as.integer(regexpr(pattern = "\\*", mut_aa))
if ((term_aa == -1 && term_mut_aa != -1) || (term_mut_aa != -1 && term_mut_aa < term_aa)) {
stats["nonsense", "occurrences"] <- 1 + stats["nonsense", "occurrences"]
} else if (mut_aa == aa_seq) {
stats["silent", "occurrences"] <- 1 + stats["silent", "occurrences"]
@ -44,11 +27,25 @@ gen_mutations <- function(seq, N) {
stats["missense", "occurrences"] <- 1 + stats["missense", "occurrences"]
}
}
sealKey()
return(stats)
}
N_test <- 1200
gen_mutations("ATGATGATGATGATGATG", N_test)
gen_mutations("CCCCCCCCCCCCCCCCCC", N_test)
gen_mutations("TATTACTATTACTATTAC", N_test)
gen_mutations("TGGTGGTGGTGGTGGTGGTGGTGG", N_test)
gen_mutations("TGTTGTTGTTGTTGTTGTTGTTGT", N_test)
gen_mutations("ATGATGATGATGATGATG", 1000)
gen_mutations("CCCCCCCCCCCCCCCCCC", 500)
gen_mutations("TATTACTATTACTATTAC", 500)
gen_mutations("TGGTGGTGGTGGTGGTGGTGGTGG", 500)
gen_mutations("TGTTGTTGTTGTTGTTGTTGTTGT", 500)
gen_mutations("TGTTGTTGTTGTTGTTGTTGTTGA", 500)
myFA <- readFASTA("data/RAB39B_HSa_coding.fa")
myFA <- rbind(myFA, readFASTA("data/PTPN5_HSa_coding.fa"))
myFA <- rbind(myFA, readFASTA("data/PTPN11_HSa_coding.fa"))
myFA <- rbind(myFA, readFASTA("data/KRAS_HSa_coding.fa"))
rownames(myFA)<-c("RAB39B", "PTPN5", "PTPN11", "KRAS") # Assign row names
gen_mutations(myFA["RAB39B", 2], 10000)
gen_mutations(myFA["PTPN5", 2], 10000)
gen_mutations(myFA["PTPN11", 2], 10000)
gen_mutations(myFA["KRAS", 2], 10000)