Last active
February 7, 2019 00:38
-
-
Save WinstonCampeau/1d71eace809fc9a61c60f110bd3c3a5f to your computer and use it in GitHub Desktop.
tRNA DAMBE check in R
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
md <- read.csv(file.choose(), header=T) #This is not working, need to use FILE, IMPORT DATASET, FROM TEXT(BASE), then select csv, DESELECT "Strings as Factors", IMPORT | |
#removes leading and trailing numbers from sequences | |
for(i in 1:nrow(md)){ | |
md[i,] <- substr(md[i,], 3, nchar(md[i,])-2) | |
} | |
#Check for even length stem | |
trna_len_list <- c() | |
for(i in 1:nrow(md)){ | |
checkstem <- nchar(md[i,])-3 ## subtract 3 to account for anticodon | |
trna_len_list[i] <- checkstem | |
if(checkstem%%2 != 0){ | |
cat("tRNA", md[i,], "at row id", i, "has asymmetry\n\n") | |
} | |
} | |
#Get anticodon, then complement | |
anticodons <- c() | |
to_codon <- c() | |
codons <- c() | |
for(i in 1:nrow(md)){ | |
anticodons[i] <- substr(md[i,], (trna_len_list[i]/2)+1, (trna_len_list[i]/2)+3) | |
to_codon[i] <- strsplit(anticodons[i], "") | |
for(j in 1:3){ | |
if(to_codon[[i]][j] == "G"){ | |
to_codon[[i]][j] <- sub("G", "C", to_codon[[i]][j]) | |
} else | |
if(to_codon[[i]][j] == "C"){ | |
to_codon[[i]][j] <- sub("C", "G", to_codon[[i]][j]) | |
} else | |
if(to_codon[[i]][j] == "A"){ | |
to_codon[[i]][j] <- sub("A", "U", to_codon[[i]][j]) | |
} else | |
if(to_codon[[i]][j] == "U"){ | |
to_codon[[i]][j] <- sub("U", "A", to_codon[[i]][j]) | |
} | |
} | |
codons[i] <- paste(rev(to_codon[[i]]), collapse='') | |
} | |
for(i in 1:nrow(test)){ | |
print(codons[i] == test[i,]) | |
} | |
#Check stem complimentarity | |
#substr(md[1,], 0, (nchar(md[1,])/2)-1) | |
#substr(md[1,], (nchar(md[1,])/2)+5, nchar(md[,1])) | |
right_list <- c() | |
left_list <- c() | |
original_left <- c() | |
check_list <- c() | |
for(i in 1:nrow(md)){ | |
left <- strsplit(substr(md[i,], 0, (nchar(md[i,])/2)-3), "") | |
original_left[i] <- substr(md[i,], 0, (nchar(md[i,])/2)-3) | |
right_list[i] <- substr(md[i,], (nchar(md[i,])/2)+5, nchar(md[i,])) | |
for(j in 1:length(left[[1]])){ | |
if(left[[1]][j] == "G"){ | |
left[[1]][j] <- sub("G", "C", left[[1]][j]) | |
} else | |
if(left[[1]][j] == "C"){ | |
left[[1]][j] <- sub("C", "G", left[[1]][j]) | |
} else | |
if(left[[1]][j] == "A"){ | |
left[[1]][j] <- sub("A", "U", left[[1]][j]) | |
} else | |
if(left[[1]][j] == "U"){ | |
left[[1]][j] <- sub("U", "A", left[[1]][j]) | |
} | |
} | |
left_list[i] <- paste(rev(left[[1]]), collapse="") | |
check_list[i] <- left_list[i] == right_list[i] | |
} | |
output <- data.frame(tRNA=md[,1], ANTICODON=anticodons, LEFT.STEM=original_left, RIGHT.STEM=right_list, LEFT.COMPLEMENT=left_list, LC.RS.EQUIVALENCY=check_list) | |
output |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment