182 lines
5.4 KiB
R
Executable file
182 lines
5.4 KiB
R
Executable file
#!/usr/bin/env Rscript
|
|
#########################################################
|
|
# TASK: Barplots for mCSM DUET, ligand affinity, and foldX
|
|
# basic barplots with count of mutations
|
|
# basic barplots with frequency of count of mutations
|
|
#########################################################
|
|
# working dir
|
|
setwd("~/git/LSHTM_analysis/scripts/plotting")
|
|
getwd()
|
|
|
|
|
|
# load libraries
|
|
#source("Header_TT.R")
|
|
library(ggplot2)
|
|
library(data.table)
|
|
library(dplyr)
|
|
require("getopt", quietly = TRUE) # cmd parse arguments
|
|
|
|
# load functions
|
|
source("../functions/plotting_globals.R")
|
|
source("../functions/plotting_data.R")
|
|
source("../functions/stability_count_bp.R")
|
|
source("../functions/position_count_bp.R")
|
|
#############################################################
|
|
# command line args
|
|
#********************
|
|
# !!!FUTURE TODO!!!
|
|
# Can pass additional params of output/plot dir by user.
|
|
# Not strictly required for my workflow since it is optimised
|
|
# to have a streamlined input/output flow without filename worries.
|
|
#********************
|
|
spec = matrix(c(
|
|
"drug" ,"d", 1, "character",
|
|
"gene" ,"g", 1, "character",
|
|
"data" ,"f", 2, "character"
|
|
), byrow = TRUE, ncol = 4)
|
|
|
|
opt = getopt(spec)
|
|
|
|
#FIXME: detect if script running from cmd, then set these
|
|
drug = opt$drug
|
|
gene = opt$gene
|
|
infile = opt$data
|
|
|
|
# hardcoding when not using cmd
|
|
#drug = "streptomycin"
|
|
#gene = "gid"
|
|
|
|
if(is.null(drug)|is.null(gene)) {
|
|
stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
|
|
}
|
|
#########################################################
|
|
# call functions with relevant args
|
|
#***********************************
|
|
# import_dirs(): returns
|
|
# datadir
|
|
# indir
|
|
# outdir
|
|
# plotdir
|
|
# dr_muts_col
|
|
# other_muts_col
|
|
# resistance_col
|
|
#***********************************
|
|
import_dirs(drug, gene)
|
|
#***********************************
|
|
# plotting_data(): returns
|
|
# my_df
|
|
# my_df_u
|
|
# my_df_u_lig
|
|
# dup_muts
|
|
#***********************************
|
|
#infile = "/home/tanu/git/Data/streptomycin/output/gid_comb_stab_struc_params.csv"
|
|
#infile = ""
|
|
|
|
#if (!exists("infile") && exists("gene")){
|
|
if (!is.character(infile) && exists("gene")){
|
|
#in_filename_params = paste0(tolower(gene), "_all_params.csv")
|
|
in_filename_params = paste0(tolower(gene), "_comb_stab_struc_params.csv") # part combined for gid
|
|
infile = paste0(outdir, "/", in_filename_params)
|
|
cat("\nInput file not specified, assuming filename: ", infile, "\n")
|
|
}
|
|
|
|
# Get the DFs out of plotting_data()
|
|
pd_df = plotting_data(infile)
|
|
my_df = pd_df[[1]]
|
|
my_df_u = pd_df[[2]]
|
|
my_df_u_lig = pd_df[[3]]
|
|
dup_muts = pd_df[[4]]
|
|
|
|
cat(paste0("Directories imported:"
|
|
, "\ndatadir:", datadir
|
|
, "\nindir:", indir
|
|
, "\noutdir:", outdir
|
|
, "\nplotdir:", plotdir))
|
|
|
|
cat(paste0("\nVariables imported:"
|
|
, "\ndrug:", drug
|
|
, "\ngene:", gene
|
|
, "\n"))
|
|
#=======================================================================
|
|
#=======
|
|
# output
|
|
#=======
|
|
cat("plots will output to:", plotdir)
|
|
#=======================================================================
|
|
# begin plots
|
|
|
|
# ------------------------------
|
|
# barplot for mscm stability
|
|
# ------------------------------
|
|
basic_bp_duet = paste0(tolower(gene), "_basic_barplot_PS.svg")
|
|
plot_basic_bp_duet = paste0(plotdir,"/", basic_bp_duet)
|
|
|
|
svg(plot_basic_bp_duet)
|
|
print(paste0("plot filename:", basic_bp_duet))
|
|
|
|
# function only
|
|
stability_count_bp(plotdf = my_df_u
|
|
, df_colname = "duet_outcome"
|
|
, leg_title = "DUET outcome")
|
|
|
|
dev.off()
|
|
|
|
# ------------------------------
|
|
# barplot for ligand affinity
|
|
# ------------------------------
|
|
basic_bp_ligand = paste0(tolower(gene), "_basic_barplot_LIG.svg")
|
|
plot_basic_bp_ligand = paste0(plotdir, "/", basic_bp_ligand)
|
|
|
|
svg(plot_basic_bp_ligand)
|
|
print(paste0("plot filename:", basic_bp_ligand))
|
|
|
|
# function only
|
|
stability_count_bp(plotdf = my_df_u_lig
|
|
, df_colname = "ligand_outcome"
|
|
, leg_title = "Ligand outcome"
|
|
, bp_plot_title = "Sites < 10 Ang of ligand")
|
|
|
|
dev.off()
|
|
# ------------------------------
|
|
# barplot for foldX
|
|
# ------------------------------
|
|
basic_bp_foldx = paste0(tolower(gene), "_basic_barplot_foldx.svg")
|
|
plot_basic_bp_foldx = paste0(plotdir,"/", basic_bp_foldx)
|
|
|
|
svg(plot_basic_bp_foldx)
|
|
print(paste0("plot filename:", plot_basic_bp_foldx))
|
|
|
|
stability_count_bp(plotdf = my_df_u
|
|
, df_colname = "foldx_outcome"
|
|
, leg_title = "FoldX outcome")
|
|
dev.off()
|
|
#===============================================================
|
|
# ------------------------------
|
|
# barplot for nssnp site count: all
|
|
# ------------------------------
|
|
pos_count_duet = paste0(tolower(gene), "_position_count_PS.svg")
|
|
plot_pos_count_duet = paste0(plotdir, "/", pos_count_duet)
|
|
|
|
svg(plot_pos_count_duet)
|
|
print(paste0("plot filename:", plot_pos_count_duet))
|
|
|
|
# function only
|
|
site_snp_count_bp(plotdf = my_df_u
|
|
, df_colname = "position")
|
|
|
|
dev.off()
|
|
# ------------------------------
|
|
# barplot for nssnp site count: within 10 Ang
|
|
# ------------------------------
|
|
pos_count_ligand = paste0(tolower(gene), "_position_count_LIG.svg")
|
|
plot_pos_count_ligand = paste0(plotdir, "/", pos_count_ligand)
|
|
|
|
svg(plot_pos_count_ligand)
|
|
print(paste0("plot filename:", plot_pos_count_ligand))
|
|
|
|
# function only
|
|
site_snp_count_bp(plotdf = my_df_u_lig
|
|
, df_colname = "position")
|
|
|
|
dev.off()
|
|
#===============================================================
|