tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

sorted combining_dfs.py with all other data files and tidied up get_plotting_dfs.R

Browse source
This commit is contained in:
Tanushree Tunstall 2021-09-10 18:16:41 +01:00
parent 4ba4ff602e
commit 5c8a9e8f00
3 changed files with 111 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

72
scripts/functions/plotting_data.R
View file

@ -16,7 +16,9 @@ library(dplyr)
## my_df_u_lig
## dup_muts
#========================================================
plotting_data <- function(df, lig_dist_colname = 'ligand_distance', lig_dist_cutoff = 10) {
plotting_data <- function(df
, lig_dist_colname = 'ligand_distance'
, lig_dist_cutoff = 10) {
my_df = data.frame()
my_df_u = data.frame()
my_df_u_lig = data.frame()
@ -38,51 +40,51 @@ cat("\nInput dimensions:", dim(df))
#==================================
#------------------------------
# adding foldx scaled values
# scale data b/w -1 and 1
#------------------------------
n = which(colnames(df) == "ddg"); n
my_min = min(df[,n]); my_min
my_max = max(df[,n]); my_max
df$foldx_scaled = ifelse(df[,n] < 0
, df[,n]/abs(my_min)
, df[,n]/my_max)
# sanity check
my_min = min(df$foldx_scaled); my_min
my_max = max(df$foldx_scaled); my_max
if (my_min == -1 && my_max == 1){
cat("\nPASS: foldx ddg successfully scaled b/w -1 and 1"
, "\nProceeding with assigning foldx outcome category")
}else{
cat("\nFAIL: could not scale foldx ddg values"
, "Aborting!\n")
}
# # adding foldx scaled values
# # scale data b/w -1 and 1
# #------------------------------
# n = which(colnames(df) == "ddg"); n
#
# my_min = min(df[,n]); my_min
# my_max = max(df[,n]); my_max
#
# df$foldx_scaled = ifelse(df[,n] < 0
# , df[,n]/abs(my_min)
# , df[,n]/my_max)
# # sanity check
# my_min = min(df$foldx_scaled); my_min
# my_max = max(df$foldx_scaled); my_max
#
# if (my_min == -1 && my_max == 1){
# cat("\nPASS: foldx ddg successfully scaled b/w -1 and 1"
# , "\nProceeding with assigning foldx outcome category")
# }else{
# cat("\nFAIL: could not scale foldx ddg values"
# , "Aborting!\n")
# }
#------------------------------
# adding foldx outcome category
# ddg<0 = "Stabilising" (-ve)
#------------------------------
c1 = table(df$ddg < 0)
df$foldx_outcome = ifelse(df$ddg < 0, "Stabilising", "Destabilising")
c2 = table(df$ddg < 0)
if ( all(c1 == c2) ){
cat("\nPASS: foldx outcome successfully created")
}else{
cat("\nFAIL: foldx outcome could not be created. Aborting!\n")
exit()
}
# c1 = table(df$ddg < 0)
# df$foldx_outcome = ifelse(df$ddg < 0, "Stabilising", "Destabilising")
# c2 = table(df$ddg < 0)
#
# if ( all(c1 == c2) ){
# cat("\nPASS: foldx outcome successfully created")
# }else{
# cat("\nFAIL: foldx outcome could not be created. Aborting!\n")
# exit()
# }
#------------------------------
# renaming foldx column from
# "ddg" --> "ddg_foldx"
#------------------------------
# change name to foldx
colnames(df)[n] <- "ddg_foldx"
# # change name to foldx
# colnames(df)[n] <- "ddg_foldx"
#==================================
# extract unique mutation entries