# HAP40 library(readr) #################################################################### ## Data import from ConSurf ####### #################################################################### data_con <- read_delim( "Consurf AA Conservation Scores modified.csv", ";", escape_double = FALSE, trim_ws = TRUE ) #################################################################### ## Caculation of conservation score for each domain #### #################################################################### #' Function to average conservation scorce for certain protein region #' Scores obtained by ConSturf method) #' #' @param data: R dataframe containing postions and scores #' @param pos: vector with start and end position of protein region #' #' @return: vector with elements pos, mean, SEM conservation <- function(data, pos) { data <- as.data.frame(data) # Loading of conservation scores data.sub <- as.vector(data[pos, 3]) # Subsetting of data frame mean.conservation <- mean(data.sub) # calculation of mean SEM.conservation <- sd(data.sub)/sqrt(length(pos)) # calculation of SEM # Defining output of function output <-c( mean.conservation, SEM.conservation) names(output) <- c("mean", "SEM") return(output) } ##################################################################### ## List defining start and end point of the corresponding domains ### ## Note: in this case: notation in Guo et al. 2018 + 6 ### ##################################################################### # Positions regions <- list(1:216,217:258,259:371) ## Name of regions names(regions) <- c( "N-terminal domain", "central", "C-terminal domain" ) ########################################################################### ## Repetition of function conservation for each element of list regions ### ########################################################################### x <- sapply(regions,FUN = conservation,data=data_con) library(readr) #################################################################### ## Data import from ConSurf ####### #################################################################### data_con <- read_delim( "Consurf AA Conservation Scores modified.csv", ";", escape_double = FALSE, trim_ws = TRUE ) #################################################################### ## Caculation of conservation score for each domain #### #################################################################### #' Function to average conservation scorce for certain protein region #' Scores obtained by ConSturf method) #' #' @param data: R dataframe containing postions and scores #' @param pos: vector with start and end position of protein region #' #' @return: vector with elements pos, mean, SEM conservation <- function(data, pos) { data <- as.data.frame(data) # Loading of conservation scores data.sub <- as.vector(data[pos, 2]) # Subsetting of data frame mean.conservation <- mean(data.sub) # calculation of mean SEM.conservation <- sd(data.sub)/sqrt(length(pos)) # calculation of SEM # Defining output of function output <-c( mean.conservation, SEM.conservation) names(output) <- c("mean", "SEM") return(output) } ##################################################################### ## List defining start and end point of the corresponding domains ### ## Note: in this case: notation in Guo et al. 2018 + 6 ### ##################################################################### # Positions C_HEAT.1 <- c(2098:2126,2463:2515,2670:3104) # Positions of C-HEAT without insertions N_HEAT.1 <- c(97:405,691:1690) regions <- list(97:1690,1690:2097,2098:3104,2127:2462,2516:2669,C_HEAT.1,406:680,N_HEAT.1) ## Name of regions names(regions) <- c( "N-HEAT", "bridge", "C-HEAT", "C-Insertion_1", "C-Insertion_2", "C-HEAT without Insertions", "N-Insertion", "N-HEAT without Insertion" ) ########################################################################### ## Repetition of function conservation for each element of list regions ### ########################################################################### x <- sapply(regions,FUN = conservation,data=data_con)