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

added ligand df in plotting

Browse source
This commit is contained in:
Tanushree Tunstall 2020-08-26 10:02:44 +01:00
parent 1a00ab614f
commit b5ad53f7d1
2 changed files with 23 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

24
scripts/plotting/plotting_data.R
View file

@ -39,7 +39,7 @@ cat(gene_match)
datadir = paste0("~/git/Data")
indir = paste0(datadir, "/", drug, "/input")
outdir = paste0("~/git/Data", "/", drug, "/output")
plotdir = paste0("~/git/Data", "/", drug, "/output/plots")
#======
# input
#======
@ -56,15 +56,19 @@ cat("Reading struct params including mcsm:", in_filename_params)
my_df = read.csv(infile_params, header = T)
cat("Input dimensions:", dim(my_df))
cat("\nInput dimensions:", dim(my_df))
# quick checks
#colnames(my_df)
#str(my_df)
###########################
# extract unique mutations
###########################
# check for duplicate mutations
if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformation)){
cat(paste0("CAUTION:", " Duplicate mutations identified"
cat(paste0("\nCAUTION:", " Duplicate mutations identified"
, "\nExtracting these..."))
dup_muts = my_df[duplicated(my_df$mutationinformation),]
dup_muts_nu = length(unique(dup_muts$mutationinformation))
@ -73,14 +77,24 @@ if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformati
, "\n\nExtracting df with unique mutations only"))
my_df_u = my_df[!duplicated(my_df$mutationinformation),]
}else{
cat(paste0("No duplicate mutations detected"))
cat(paste0("\nNo duplicate mutations detected"))
my_df_u = my_df
}
upos = unique(my_df_u$position)
cat("Dim of clean df:"); cat(dim(my_df_u))
cat("\nDim of clean df:"); cat(dim(my_df_u))
cat("\nNo. of unique mutational positions:"); cat(length(upos), "\n")
###########################
# extract mutations <10Angstroms
###########################
table(my_df_u$ligand_distance<10)
my_df_u_lig = my_df_u[my_df_u$ligand_distance <10,]
angstroms_symbol = "\u212b"
cat(paste0("There are ", nrow(my_df_u_lig), " sites lying within 10", angstroms_symbol, " of the ligand"))
########################################################################
# end of data extraction and cleaning for plots #
########################################################################