168 lines
5 KiB
R
Executable file
168 lines
5 KiB
R
Executable file
getwd()
|
|
setwd("~/git/LSHTM_analysis/scripts/plotting")
|
|
getwd()
|
|
|
|
#########################################################
|
|
# TASK: output barplot by position with each bar coloured by
|
|
# its stability value and NO coloured positions indicated
|
|
#########################################################
|
|
#=======================================================================
|
|
|
|
############################################################
|
|
# 1: Installing and loading required packages and functions
|
|
#############################################################
|
|
|
|
#source("~/git/LSHTM_analysis/scripts/Header_TT.R")
|
|
library(ggplot2)
|
|
library(data.table)
|
|
source("barplot_colour_function.R")
|
|
source("plotting_data.R")
|
|
|
|
# should return the following dfs, directories and variables
|
|
# mut_pos_cols
|
|
# my_df
|
|
# my_df_u
|
|
# my_df_u_lig
|
|
# dup_muts
|
|
|
|
cat(paste0("Directories imported:"
|
|
, "\ndatadir:", datadir
|
|
, "\nindir:", indir
|
|
, "\noutdir:", outdir
|
|
, "\nplotdir:", plotdir))
|
|
|
|
cat(paste0("Variables imported:"
|
|
, "\ndrug:", drug
|
|
, "\ngene:", gene
|
|
, "\ngene_match:", gene_match
|
|
, "\nLength of upos:", length(upos)
|
|
, "\nAngstrom symbol:", angstroms_symbol))
|
|
|
|
# clear excess variable
|
|
rm(my_df, upos, dup_muts, my_df_u_lig)
|
|
########################################################
|
|
|
|
#=======
|
|
# output
|
|
#=======
|
|
print(paste0("plot will be in:", plotdir))
|
|
bp_subcols_duet = "barplot_coloured_PS.svg"
|
|
plot_bp_subcols_duet = paste0(plotdir, "/", bp_subcols_duet)
|
|
|
|
#===================
|
|
# Data for plots
|
|
#===================
|
|
# REASSIGNMENT as necessary
|
|
df = my_df_u
|
|
|
|
# sanity checks
|
|
str(df)
|
|
upos = unique(df$position)
|
|
|
|
# should be a factor
|
|
if (is.factor(df$duet_outcome)){
|
|
print("duet_outcome is factor")
|
|
}else{
|
|
print("convert duet_outcome to factor")
|
|
df$duet_outcome = as.factor(df$duet_outcome)
|
|
}
|
|
|
|
is.factor(df$duet_outcome)
|
|
|
|
table(df$duet_outcome)
|
|
|
|
# should be -1 and 1
|
|
min(df$duet_scaled)
|
|
max(df$duet_scaled)
|
|
|
|
tapply(df$duet_scaled, df$duet_outcome, min)
|
|
tapply(df$duet_scaled, df$duet_outcome, max)
|
|
|
|
#******************
|
|
# generate plot
|
|
#******************
|
|
#==========================
|
|
# Barplot with scores (unordered)
|
|
# corresponds to duet_outcome
|
|
# Stacked Barplot with colours: duet_outcome @ position coloured by
|
|
# stability scores. This is a barplot where each bar corresponds
|
|
# to a SNP and is coloured by its corresponding DUET stability value.
|
|
# Normalised values (range between -1 and 1 ) to aid visualisation
|
|
# NOTE: since barplot plots discrete values, colour = score, so number of
|
|
# colours will be equal to the no. of unique normalised scores
|
|
# rather than a continuous scale
|
|
# will require generating the colour scale separately.
|
|
#============================
|
|
|
|
# My colour FUNCTION: based on group and subgroup
|
|
# in my case;
|
|
# df = df
|
|
# group = duet_outcome
|
|
# subgroup = normalised score i.e duet_scaled
|
|
|
|
# check unique values in normalised data
|
|
u = unique(df$duet_scaled)
|
|
|
|
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
# Run this section if rounding is to be used
|
|
n = 3
|
|
df$duet_scaledR = round(df$duet_scaled, n)
|
|
ur = unique(df$duet_scaledR)
|
|
|
|
# create an extra column called group which contains the "gp name and score"
|
|
# so colours can be generated for each unique values in this column
|
|
|
|
#my_grp = df$duet_scaledR # rounding
|
|
my_grp = df$duet_scaled # no rounding
|
|
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
df$group <- paste0(df$duet_outcome, "_", my_grp, sep = "")
|
|
|
|
# Call the function to create the palette based on the group defined above
|
|
colours <- ColourPalleteMulti(df, "duet_outcome", "my_grp")
|
|
print(paste0("Colour palette generated for: ", length(colours), " colours"))
|
|
my_title = "Protein stability (DUET)"
|
|
|
|
# axis label size
|
|
my_xaxls = 13
|
|
my_yaxls = 15
|
|
|
|
# axes text size
|
|
my_xaxts = 15
|
|
my_yaxts = 15
|
|
|
|
#******************
|
|
# generate plot: NO axis colours
|
|
#******************
|
|
print(paste0("plot name:", plot_bp_subcols_duet))
|
|
|
|
svg(plot_bp_subcols_duet, width = 26, height = 4)
|
|
|
|
g = ggplot(df, aes(factor(position, ordered = T)))
|
|
outPlot = g +
|
|
geom_bar(aes(fill = group), colour = "grey") +
|
|
scale_fill_manual( values = colours
|
|
, guide = "none") +
|
|
theme( axis.text.x = element_text(size = my_xaxls
|
|
, angle = 90
|
|
, hjust = 1
|
|
, vjust = 0.4)
|
|
, axis.text.y = element_text(size = my_yaxls
|
|
, angle = 0
|
|
, hjust = 1
|
|
, vjust = 0)
|
|
, axis.title.x = element_text(size = my_xaxts)
|
|
, axis.title.y = element_text(size = my_yaxts ) ) +
|
|
labs(title = ""
|
|
#title = my_title
|
|
, x = "position"
|
|
, y = "Frequency")
|
|
|
|
print(outPlot)
|
|
dev.off()
|
|
# for sanity and good practice
|
|
rm(df)
|
|
#======================= end of plot
|
|
# axis colours labels
|
|
# https://stackoverflow.com/questions/38862303/customize-ggplot2-axis-labels-with-different-colors
|
|
# https://stackoverflow.com/questions/56543485/plot-coloured-boxes-around-axis-label
|