added pnca plot dir to generate plots that weren#t covered in the paper
This commit is contained in:
parent
1dacebbaf6
commit
2cec743ae0
8 changed files with 1391 additions and 0 deletions
364
scripts/plotting/plotting_thesis/pnca/basic_barplots_pnca.R
Normal file
364
scripts/plotting/plotting_thesis/pnca/basic_barplots_pnca.R
Normal file
|
|
@ -0,0 +1,364 @@
|
|||
#!/usr/bin/env Rscript
|
||||
#########################################################
|
||||
# TASK: Barplots
|
||||
# basic barplots with outcome
|
||||
# basic barplots with frequency of count of mutations
|
||||
#########################################################
|
||||
#=============
|
||||
# Data: Input
|
||||
#==============
|
||||
#source("~/git/LSHTM_analysis/config/pnca.R")
|
||||
#source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
|
||||
|
||||
#cat("\nSourced plotting cols as well:", length(plotting_cols))
|
||||
|
||||
####################################################
|
||||
class(merged_df3)
|
||||
|
||||
df3 = subset(merged_df3, select = -c(pos_count))
|
||||
|
||||
#=======
|
||||
# output
|
||||
#=======
|
||||
outdir_images = paste0("~/git/Writing/thesis/images/results/", tolower(gene), "/")
|
||||
cat("plots will output to:", outdir_images)
|
||||
|
||||
##########################################################
|
||||
# blue, red bp
|
||||
sts = 8
|
||||
lts = 8
|
||||
ats = 8
|
||||
als = 8
|
||||
ltis = 8
|
||||
geom_ls = 2.2
|
||||
|
||||
#pos_count
|
||||
subtitle_size = 8
|
||||
geom_ls_pc = 2.2
|
||||
leg_text_size = 8
|
||||
axis_text_size = 8
|
||||
axis_label_size = 8
|
||||
|
||||
###########################################################
|
||||
#------------------------------
|
||||
# plot default sizes
|
||||
#------------------------------
|
||||
#=========================
|
||||
# Affinity outcome
|
||||
# check this var: outcome_cols_affinity
|
||||
# get from preformatting or put in globals
|
||||
#==========================
|
||||
DistCutOff
|
||||
LigDist_colname # = "ligand_distance" # from globals
|
||||
ppi2Dist_colname
|
||||
naDist_colname
|
||||
|
||||
###########################################################
|
||||
# get plotting data within the distance
|
||||
df3_lig = df3[df3[[LigDist_colname]]<DistCutOff,]
|
||||
df3_ppi2 = df3[df3[[ppi2Dist_colname]]<DistCutOff,]
|
||||
df3_na = df3[df3[[naDist_colname]]<DistCutOff,]
|
||||
common_bp_title = paste0("Sites <", DistCutOff, angstroms_symbol)
|
||||
|
||||
#------------------------------
|
||||
# barplot for ligand affinity:
|
||||
# <10 Ang of ligand
|
||||
#------------------------------
|
||||
mLigP = stability_count_bp(plotdf = df3_lig
|
||||
, df_colname = "ligand_outcome"
|
||||
#, leg_title = "mCSM-lig"
|
||||
#, bp_plot_title = paste(common_bp_title, "ligand")
|
||||
, yaxis_title = "Number of nsSNPs"
|
||||
, leg_position = "none"
|
||||
, subtitle_text = "mCSM\nLig"
|
||||
, bar_fill_values = c("#F8766D", "#00BFC4")
|
||||
, subtitle_colour= "black"
|
||||
, sts = sts
|
||||
, lts = lts
|
||||
, ats = ats
|
||||
, als = als
|
||||
, ltis = ltis
|
||||
, geom_ls = geom_ls
|
||||
)
|
||||
mLigP
|
||||
#------------------------------
|
||||
# barplot for ligand affinity:
|
||||
# <10 Ang of ligand
|
||||
# mmCSM-lig: will be the same no. of sites but the effect will be different
|
||||
#------------------------------
|
||||
mmLigP = stability_count_bp(plotdf = df3_lig
|
||||
, df_colname = "mmcsm_lig_outcome"
|
||||
#, leg_title = "mmCSM-lig"
|
||||
#, label_categories = labels_mmlig
|
||||
#, bp_plot_title = paste(common_bp_title, "ligand")
|
||||
|
||||
, yaxis_title = ""
|
||||
, leg_position = "none"
|
||||
, subtitle_text = "mmCSM\nLig"
|
||||
, bar_fill_values = c("#F8766D", "#00BFC4")
|
||||
, subtitle_colour= "black"
|
||||
, sts = sts
|
||||
, lts = lts
|
||||
, ats = ats
|
||||
, als = als
|
||||
, ltis = ltis
|
||||
, geom_ls = geom_ls
|
||||
)
|
||||
mmLigP
|
||||
#------------------------------
|
||||
# barplot for ppi2 affinity
|
||||
# <10 Ang of interface
|
||||
#------------------------------
|
||||
if (tolower(gene)%in%geneL_ppi2){
|
||||
ppi2P = stability_count_bp(plotdf = df3_ppi2
|
||||
, df_colname = "mcsm_ppi2_outcome"
|
||||
#, leg_title = "mCSM-ppi2"
|
||||
#, label_categories = labels_ppi2
|
||||
#, bp_plot_title = paste(common_bp_title, "PP-interface")
|
||||
|
||||
, yaxis_title = "Number of nsSNPs"
|
||||
, leg_position = "none"
|
||||
, subtitle_text = "mCSM\nPPI2"
|
||||
, bar_fill_values = c("#F8766D", "#00BFC4")
|
||||
, subtitle_colour= "black"
|
||||
, sts = sts
|
||||
, lts = lts
|
||||
, ats = ats
|
||||
, als = als
|
||||
, ltis = ltis
|
||||
, geom_ls = geom_ls
|
||||
)
|
||||
ppi2P
|
||||
}
|
||||
#----------------------------
|
||||
# barplot for ppi2 affinity
|
||||
# <10 Ang of interface
|
||||
#------------------------------
|
||||
if (tolower(gene)%in%geneL_na){
|
||||
nca_distP = stability_count_bp(plotdf = df3_na
|
||||
, df_colname = "mcsm_na_outcome"
|
||||
#, leg_title = "mCSM-NA"
|
||||
#, label_categories =
|
||||
#, bp_plot_title = paste(common_bp_title, "Dist to NA")
|
||||
|
||||
, yaxis_title = "Number of nsSNPs"
|
||||
, leg_position = "none"
|
||||
, subtitle_text = "mCSM\nNA"
|
||||
, bar_fill_values = c("#F8766D", "#00BFC4")
|
||||
, subtitle_colour= "black"
|
||||
, sts = sts
|
||||
, lts = lts
|
||||
, ats = ats
|
||||
, als = als
|
||||
, ltis = ltis
|
||||
, geom_ls = geom_ls
|
||||
)
|
||||
nca_distP
|
||||
}
|
||||
|
||||
#####################################################################
|
||||
# ------------------------------
|
||||
# bp site site count: mCSM-lig
|
||||
# < 10 Ang ligand
|
||||
# ------------------------------
|
||||
common_bp_title = paste0("Sites <", DistCutOff, angstroms_symbol)
|
||||
|
||||
posC_lig = site_snp_count_bp(plotdf = df3_lig
|
||||
, df_colname = "position"
|
||||
, xaxis_title = "Number of nsSNPs"
|
||||
, yaxis_title = "Number of Sites"
|
||||
, subtitle_colour = "chocolate4"
|
||||
, subtitle_text = ""
|
||||
, subtitle_size = subtitle_size
|
||||
, geom_ls = geom_ls_pc
|
||||
, leg_text_size = leg_text_size
|
||||
, axis_text_size = axis_text_size
|
||||
, axis_label_size = axis_label_size)
|
||||
|
||||
posC_lig
|
||||
#------------------------------
|
||||
# bp site site count: ppi2
|
||||
# < 10 Ang interface
|
||||
#------------------------------
|
||||
if (tolower(gene)%in%geneL_ppi2){
|
||||
posC_ppi2 = site_snp_count_bp(plotdf = df3_ppi2
|
||||
, df_colname = "position"
|
||||
, xaxis_title = "Number of nsSNPs"
|
||||
, yaxis_title = "Number of Sites"
|
||||
, subtitle_colour = "chocolate4"
|
||||
, subtitle_text = ""
|
||||
, subtitle_size = subtitle_size
|
||||
, geom_ls = geom_ls_pc
|
||||
, leg_text_size = leg_text_size
|
||||
, axis_text_size = axis_text_size
|
||||
, axis_label_size = axis_label_size)
|
||||
posC_ppi2
|
||||
}
|
||||
|
||||
#------------------------------
|
||||
# bp site site count: NCA dist
|
||||
# < 10 Ang nca
|
||||
#------------------------------
|
||||
if (tolower(gene)%in%geneL_na){
|
||||
posC_nca = site_snp_count_bp(plotdf = df3_na
|
||||
, df_colname = "position"
|
||||
, xaxis_title = "Number of nsSNPs"
|
||||
, yaxis_title = "Number of Sites"
|
||||
, subtitle_colour = "chocolate4"
|
||||
, subtitle_text = ""
|
||||
, subtitle_size = subtitle_size
|
||||
, geom_ls = geom_ls_pc
|
||||
, leg_text_size = leg_text_size
|
||||
, axis_text_size = axis_text_size
|
||||
, axis_label_size = axis_label_size)
|
||||
posC_nca
|
||||
}
|
||||
#===============================================================
|
||||
#------------------------------
|
||||
# bp site site count: ALL
|
||||
# <10 Ang ligand
|
||||
#------------------------------
|
||||
posC_all = site_snp_count_bp(plotdf = df3
|
||||
, df_colname = "position"
|
||||
, xaxis_title = "Number of nsSNPs"
|
||||
, yaxis_title = "Number of Sites"
|
||||
, subtitle_colour = "chocolate4"
|
||||
, subtitle_text = "All mutations sites"
|
||||
, subtitle_size = subtitle_size
|
||||
, geom_ls = geom_ls_pc
|
||||
, leg_text_size = leg_text_size
|
||||
, axis_text_size = axis_text_size
|
||||
, axis_label_size = axis_label_size)
|
||||
posC_all
|
||||
##################################################################
|
||||
consurfP = stability_count_bp(plotdf = df3
|
||||
, df_colname = "consurf_outcome"
|
||||
#, leg_title = "ConSurf"
|
||||
#, label_categories = labels_consurf
|
||||
, yaxis_title = "Number of nsSNPs"
|
||||
, leg_position = "top"
|
||||
, subtitle_text = "ConSurf"
|
||||
, bar_fill_values = consurf_colours # from globals
|
||||
, subtitle_colour= "black"
|
||||
, sts = sts
|
||||
, lts = lts
|
||||
, ats = ats
|
||||
, als = als
|
||||
, ltis = ltis
|
||||
, geom_ls = geom_ls)
|
||||
|
||||
consurfP
|
||||
|
||||
##############################################################
|
||||
sts_so = 10
|
||||
lts_so = 10
|
||||
ats_so = 10
|
||||
als_so = 10
|
||||
ltis_so = 10
|
||||
geom_ls_so = 2.5
|
||||
#===================
|
||||
# Stability
|
||||
#===================
|
||||
# duetP
|
||||
duetP = stability_count_bp(plotdf = df3
|
||||
, df_colname = "duet_outcome"
|
||||
, leg_title = "mCSM-DUET"
|
||||
#, label_categories = labels_duet
|
||||
, yaxis_title = "Number of nsSNPs"
|
||||
, leg_position = "none"
|
||||
, subtitle_text = "mCSM-DUET"
|
||||
, bar_fill_values = c("#F8766D", "#00BFC4")
|
||||
, subtitle_colour= "black"
|
||||
, sts = sts_so
|
||||
, lts = lts_so
|
||||
, ats = ats_so
|
||||
, als = als_so
|
||||
, ltis = ltis_so
|
||||
, geom_ls = geom_ls_so)
|
||||
duetP
|
||||
|
||||
# foldx
|
||||
foldxP = stability_count_bp(plotdf = df3
|
||||
, df_colname = "foldx_outcome"
|
||||
#, leg_title = "FoldX"
|
||||
#, label_categories = labels_foldx
|
||||
, yaxis_title = ""
|
||||
, leg_position = "none"
|
||||
, subtitle_text = "FoldX"
|
||||
, bar_fill_values = c("#F8766D", "#00BFC4")
|
||||
, sts = sts_so
|
||||
, lts = lts_so
|
||||
, ats = ats_so
|
||||
, als = als_so
|
||||
, ltis = ltis_so
|
||||
, geom_ls = geom_ls_so)
|
||||
foldxP
|
||||
|
||||
# deepddg
|
||||
deepddgP = stability_count_bp(plotdf = df3
|
||||
, df_colname = "deepddg_outcome"
|
||||
#, leg_title = "DeepDDG"
|
||||
#, label_categories = labels_deepddg
|
||||
, yaxis_title = ""
|
||||
, leg_position = "none"
|
||||
, subtitle_text = "DeepDDG"
|
||||
, bar_fill_values = c("#F8766D", "#00BFC4")
|
||||
, sts = sts_so
|
||||
, lts = lts_so
|
||||
, ats = ats_so
|
||||
, als = als_so
|
||||
, ltis = ltis_so
|
||||
, geom_ls = geom_ls_so)
|
||||
deepddgP
|
||||
|
||||
# deepddg
|
||||
dynamut2P = stability_count_bp(plotdf = df3
|
||||
, df_colname = "ddg_dynamut2_outcome"
|
||||
#, leg_title = "Dynamut2"
|
||||
#, label_categories = labels_ddg_dynamut2_outcome
|
||||
, yaxis_title = ""
|
||||
, leg_position = "none"
|
||||
, subtitle_text = "Dynamut2"
|
||||
, bar_fill_values = c("#F8766D", "#00BFC4")
|
||||
, sts = sts_so
|
||||
, lts = lts_so
|
||||
, ats = ats_so
|
||||
, als = als_so
|
||||
, ltis = ltis_so
|
||||
, geom_ls = geom_ls_so)
|
||||
dynamut2P
|
||||
|
||||
# provean
|
||||
proveanP = stability_count_bp(plotdf = df3
|
||||
, df_colname = "provean_outcome"
|
||||
#, leg_title = "PROVEAN"
|
||||
#, label_categories = labels_provean
|
||||
, yaxis_title = "Number of nsSNPs"
|
||||
, leg_position = "none" # top
|
||||
, subtitle_text = "PROVEAN"
|
||||
, bar_fill_values = c("#D01C8B", "#F1B6DA") # light pink and deep
|
||||
, sts = sts_so
|
||||
, lts = lts_so
|
||||
, ats = ats_so
|
||||
, als = als_so
|
||||
, ltis = ltis_so
|
||||
, geom_ls = geom_ls_so)
|
||||
proveanP
|
||||
|
||||
# snap2
|
||||
snap2P = stability_count_bp(plotdf = df3
|
||||
, df_colname = "snap2_outcome"
|
||||
#, leg_title = "SNAP2"
|
||||
#, label_categories = labels_snap2
|
||||
, yaxis_title = ""
|
||||
, leg_position = "none" # top
|
||||
, subtitle_text = "SNAP2"
|
||||
, bar_fill_values = c("#D01C8B", "#F1B6DA") # light pink and deep
|
||||
, sts = sts_so
|
||||
, lts = lts_so
|
||||
, ats = ats_so
|
||||
, als = als_so
|
||||
, ltis = ltis_so
|
||||
, geom_ls = geom_ls_so)
|
||||
snap2P
|
||||
#####################################################################################
|
||||
|
|
@ -0,0 +1,261 @@
|
|||
#=============
|
||||
# Data: Input
|
||||
#==============
|
||||
#source("~/git/LSHTM_analysis/config/pnca.R")
|
||||
#source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
|
||||
|
||||
source("/home/tanu/git/LSHTM_analysis/scripts/plotting/plotting_thesis/pnca/basic_barplots_pnca.R")
|
||||
source("/home/tanu/git/LSHTM_analysis/scripts/plotting/plotting_thesis/pnca/pe_sens_site_count_pnca.R")
|
||||
|
||||
if ( tolower(gene)%in%c("pnca") ){
|
||||
cat("\nPlots available for layout are:")
|
||||
|
||||
duetP
|
||||
foldxP
|
||||
deepddgP
|
||||
dynamut2P
|
||||
proveanP
|
||||
snap2P
|
||||
|
||||
mLigP
|
||||
mmLigP
|
||||
posC_lig
|
||||
|
||||
#ppi2P
|
||||
#posC_ppi2
|
||||
|
||||
peP2
|
||||
sens_siteP
|
||||
peP # not used
|
||||
sensP # not used
|
||||
}
|
||||
|
||||
|
||||
#========================
|
||||
# Common title settings
|
||||
#=========================
|
||||
theme_georgia <- function(...) {
|
||||
theme_gray(base_family = "sans", ...) +
|
||||
theme(plot.title = element_text(face = "bold"))
|
||||
}
|
||||
title_theme <- calc_element("plot.title", theme_georgia())
|
||||
|
||||
###############################################################
|
||||
common_bp_title = paste0("Sites <", DistCutOff, angstroms_symbol)
|
||||
|
||||
# extract common legends
|
||||
# lig affinity
|
||||
common_legend_outcome = get_legend(mLigP +
|
||||
guides(color = guide_legend(nrow = 1)) +
|
||||
theme(legend.position = "top"))
|
||||
|
||||
# stability
|
||||
common_legend_outcome = get_legend(duetP +
|
||||
guides(color = guide_legend(nrow = 1)) +
|
||||
theme(legend.position = "top"))
|
||||
# conservation
|
||||
cons_common_legend_outcome = get_legend(snap2P +
|
||||
guides(color = guide_legend(nrow = 1)) +
|
||||
theme(legend.position = "top"))
|
||||
###################################################################
|
||||
#==================================
|
||||
# Stability+Conservation: COMBINE
|
||||
#==================================
|
||||
tt_size = 10
|
||||
#----------------------------
|
||||
# stability and consv title
|
||||
#----------------------------
|
||||
tt_stab = ggdraw() +
|
||||
draw_label(
|
||||
paste0("Stability outcome"),
|
||||
fontfamily = title_theme$family,
|
||||
fontface = title_theme$face,
|
||||
#size = title_theme$size
|
||||
size = tt_size
|
||||
)
|
||||
|
||||
tt_cons = ggdraw() +
|
||||
draw_label(
|
||||
paste0("Conservation outcome"),
|
||||
fontfamily = title_theme$family,
|
||||
fontface = title_theme$face,
|
||||
size = tt_size
|
||||
)
|
||||
|
||||
#----------------------
|
||||
# Output plot
|
||||
#-----------------------
|
||||
stab_cons_CLP = paste0(outdir_images
|
||||
,tolower(gene)
|
||||
,"_stab_cons_BP_CLP.png")
|
||||
|
||||
print(paste0("plot filename:", stab_cons_CLP))
|
||||
png(stab_cons_CLP, units = "in", width = 10, height = 5, res = 300 )
|
||||
|
||||
cowplot::plot_grid(
|
||||
cowplot::plot_grid(
|
||||
cowplot::plot_grid(
|
||||
tt_stab,
|
||||
common_legend_outcome,
|
||||
nrow = 2
|
||||
),
|
||||
cowplot::plot_grid(
|
||||
duetP,
|
||||
foldxP,
|
||||
deepddgP,
|
||||
dynamut2P,
|
||||
nrow = 1,
|
||||
labels = c("A", "B", "C", "D"),
|
||||
label_size = 12),
|
||||
nrow = 2,
|
||||
rel_heights=c(1,10)
|
||||
),
|
||||
NULL,
|
||||
cowplot::plot_grid(
|
||||
cowplot::plot_grid(
|
||||
cowplot::plot_grid(
|
||||
tt_cons,
|
||||
cons_common_legend_outcome,
|
||||
nrow = 2
|
||||
),
|
||||
cowplot::plot_grid(
|
||||
proveanP,
|
||||
snap2P,
|
||||
nrow=1,
|
||||
labels = c("E", "F"),
|
||||
align = "hv"),
|
||||
nrow = 2,
|
||||
rel_heights = c(1, 10),
|
||||
label_size = 12),
|
||||
nrow=1
|
||||
),
|
||||
rel_widths = c(2,0.15,1),
|
||||
nrow=1
|
||||
)
|
||||
|
||||
dev.off()
|
||||
|
||||
#################################################################
|
||||
#=======================================
|
||||
# Affinity barplots: COMBINE ALL four
|
||||
#========================================
|
||||
ligT = paste0(common_bp_title, " ligand")
|
||||
lig_affT = ggdraw() +
|
||||
draw_label(
|
||||
ligT,
|
||||
fontfamily = title_theme$family,
|
||||
fontface = title_theme$face,
|
||||
#size = title_theme$size
|
||||
size = 8
|
||||
)
|
||||
|
||||
p1 = cowplot::plot_grid(cowplot::plot_grid(lig_affT
|
||||
, common_legend_outcome
|
||||
, nrow=2),
|
||||
cowplot::plot_grid(mLigP, mmLigP, posC_lig
|
||||
, nrow = 1
|
||||
, rel_widths = c(1,0.65,1.8)
|
||||
, align = "h"),
|
||||
nrow = 2,
|
||||
rel_heights = c(1,8)
|
||||
|
||||
)
|
||||
p1
|
||||
|
||||
#### Combine p1 ####
|
||||
w = 11.79
|
||||
h = 3.5
|
||||
mut_impact_CLP = paste0(outdir_images
|
||||
,tolower(gene)
|
||||
,"_mut_impactCLP.png")
|
||||
|
||||
#svg(affP, width = 20, height = 5.5)
|
||||
print(paste0("plot filename:", mut_impact_CLP))
|
||||
png(mut_impact_CLP, units = "in", width = w, height = h, res = 300 )
|
||||
|
||||
cowplot::plot_grid(p1,
|
||||
nrow = 1,
|
||||
labels = "AUTO",
|
||||
label_size = 12,
|
||||
rel_widths = c(2.5,2,2)
|
||||
#, rel_heights = c(1)
|
||||
)
|
||||
|
||||
dev.off()
|
||||
w = 11.79
|
||||
h = 3.5
|
||||
mut_impact_CLP = paste0(outdir_images
|
||||
,tolower(gene)
|
||||
,"_mut_impactCLP.png")
|
||||
|
||||
#svg(affP, width = 20, height = 5.5)
|
||||
print(paste0("plot filename:", mut_impact_CLP))
|
||||
png(mut_impact_CLP, units = "in", width = w, height = h, res = 300 )
|
||||
|
||||
cowplot::plot_grid(p1,
|
||||
nrow = 1,
|
||||
labels = "AUTO",
|
||||
label_size = 12,
|
||||
rel_widths = c(2.5,2,2)
|
||||
#, rel_heights = c(1)
|
||||
)
|
||||
|
||||
dev.off()
|
||||
|
||||
##################################################
|
||||
sensP
|
||||
consurfP
|
||||
#=================
|
||||
#### Combine sensitivity + ConSurf ####
|
||||
# or ConSurf
|
||||
#=================
|
||||
w = 3
|
||||
h = 3
|
||||
# sens_conP = paste0(outdir_images
|
||||
# ,tolower(gene)
|
||||
# ,"_sens_cons_CLP.png")
|
||||
#
|
||||
# print(paste0("plot filename:", sens_conP))
|
||||
# png(sens_conP, units = "in", width = w, height = h, res = 300 )
|
||||
#
|
||||
# cowplot::plot_grid(sensP, consurfP,
|
||||
# nrow = 2,
|
||||
# rel_heights = c(1, 1.5)
|
||||
# )
|
||||
#
|
||||
# dev.off()
|
||||
|
||||
conCLP = paste0(outdir_images
|
||||
,tolower(gene)
|
||||
,"_consurf_BP.png")
|
||||
|
||||
print(paste0("plot filename:", conCLP))
|
||||
png(conCLP, units = "in", width = w, height = h, res = 300 )
|
||||
consurfP
|
||||
|
||||
dev.off()
|
||||
#================================
|
||||
# Sensitivity mutation numbers: geom_tile
|
||||
#================================
|
||||
sensCLP = paste0(outdir_images
|
||||
,tolower(gene)
|
||||
,"_sensN_tile.png")
|
||||
|
||||
print(paste0("plot filename:", sensCLP))
|
||||
png(sensCLP, units = "in", width = 1, height = 1, res = 300 )
|
||||
sensP
|
||||
dev.off()
|
||||
#================================
|
||||
# Sensitivity SITE numbers: geom_tile
|
||||
#================================
|
||||
sens_siteCLP = paste0(outdir_images
|
||||
,tolower(gene)
|
||||
,"_sens_siteC_tile.png")
|
||||
|
||||
print(paste0("plot filename:", sens_siteCLP))
|
||||
png(sens_siteCLP, units = "in", width = 1.2, height = 1, res = 300 )
|
||||
sens_siteP
|
||||
dev.off()
|
||||
|
||||
###########################################################
|
||||
|
||||
165
scripts/plotting/plotting_thesis/pnca/lineage_bp_dist.R
Normal file
165
scripts/plotting/plotting_thesis/pnca/lineage_bp_dist.R
Normal file
|
|
@ -0,0 +1,165 @@
|
|||
#!/usr/bin/env Rscript
|
||||
|
||||
#########################################################
|
||||
# TASK: Lineage plots [merged_df2]
|
||||
# Count
|
||||
# Diversity
|
||||
# Average stability dist
|
||||
# Avergae affinity dist: optional
|
||||
#########################################################
|
||||
#=======
|
||||
# output
|
||||
#=======
|
||||
# outdir_images = paste0("~/git/Writing/thesis/images/results/"
|
||||
# , tolower(gene), "/")
|
||||
# cat("plots will output to:", outdir_images)
|
||||
#########################################################
|
||||
|
||||
#===============
|
||||
#Quick numbers checks
|
||||
#===============
|
||||
nsample_lin = merged_df2[merged_df2$lineage%in%c("L1", "L2", "L3", "L4"),]
|
||||
|
||||
if ( all(table(nsample_lin$sensitivity)== table(nsample_lin$mutation_info_labels)) ){
|
||||
cat("\nTotal no. of samples belonging to L1-l4 for", gene,":", nrow(nsample_lin)
|
||||
, "\nCounting R and S samples")
|
||||
if( sum(table(nsample_lin$sensitivity)) == nrow(nsample_lin) ){
|
||||
cat("\nPASSNumbers cross checked:")
|
||||
print(table(nsample_lin$sensitivity))
|
||||
}
|
||||
}else{
|
||||
stop("Abort: Numbers mismatch. Please check")
|
||||
}
|
||||
########################################################################
|
||||
###################################################
|
||||
# Lineage barplots #
|
||||
###################################################
|
||||
my_xats = 8 # x axis text size # were 25
|
||||
my_yats = 8# y axis text sized_lab_size
|
||||
my_xals = 8 # x axis label size
|
||||
my_yals = 8 # y axis label size
|
||||
my_lls = 8 # legend label size
|
||||
d_lab_size = 2.3
|
||||
#===============================
|
||||
# lineage sample and SNP count
|
||||
#===============================
|
||||
lin_countP = lin_count_bp(lf_data = lineage_dfL[['lin_lf']]
|
||||
, all_lineages = F
|
||||
, x_categ = "sel_lineages"
|
||||
, y_count = "p_count"
|
||||
, use_lineages = c("L1", "L2", "L3", "L4")
|
||||
, bar_fill_categ = "count_categ"
|
||||
, display_label_col = "p_count"
|
||||
, bar_stat_stype = "identity"
|
||||
, d_lab_size = d_lab_size
|
||||
, d_lab_col = "black"
|
||||
, my_xats = my_xats # x axis text size
|
||||
, my_yats = my_yats # y axis text sized_lab_size
|
||||
, my_xals = my_xals # x axis label size
|
||||
, my_yals = my_yals # y axis label size
|
||||
, my_lls = my_lls # legend label size
|
||||
, bar_col_labels = c("nsSNPs", "Total Samples")
|
||||
, bar_col_values = c("grey50", "gray75")
|
||||
, bar_leg_name = ""
|
||||
, leg_location = "top"
|
||||
, y_log10 = F
|
||||
, y_scale_percent = FALSE
|
||||
, y_label = c("Count")
|
||||
)
|
||||
lin_countP
|
||||
#===============================
|
||||
# lineage SNP diversity count
|
||||
#===============================
|
||||
lin_diversityP = lin_count_bp_diversity(lf_data = lineage_dfL[['lin_wf']]
|
||||
, x_categ = "sel_lineages"
|
||||
, y_count = "snp_diversity"
|
||||
#, all_lineages = F
|
||||
, use_lineages = c("L1", "L2", "L3", "L4")
|
||||
, display_label_col = "snp_diversity_f"
|
||||
, bar_stat_stype = "identity"
|
||||
, x_lab_angle = 90
|
||||
, d_lab_size = d_lab_size
|
||||
, my_xats = my_xats # x axis text size
|
||||
, my_yats = my_yats # y axis text sized_lab_size
|
||||
, my_xals = my_xals # x axis label size
|
||||
, my_yals = my_yals # y axis label size
|
||||
, my_lls = my_lls # legend label size
|
||||
, y_log10 = F
|
||||
, y_scale_percent = F
|
||||
, leg_location = "top"
|
||||
, y_label = "Percent" #"SNP diversity"
|
||||
, bp_plot_title = "nsSNP diversity"
|
||||
, title_colour = "black" #"chocolate4"
|
||||
, subtitle_text = NULL
|
||||
, sts = 10
|
||||
, subtitle_colour = "#350E20FF")
|
||||
lin_diversityP
|
||||
|
||||
|
||||
###################################################
|
||||
# Stability dist #
|
||||
###################################################
|
||||
# scaled_cols_stability = c("duet_scaled"
|
||||
# , "deepddg_scaled"
|
||||
# , "ddg_dynamut2_scaled"
|
||||
# , "foldx_scaled"
|
||||
# , "avg_stability_scaled")
|
||||
|
||||
my_ats = 8 # x axis text size # were 25
|
||||
my_als = 8# y axis text sized_lab_size
|
||||
my_leg_ts = 8 # x axis label size
|
||||
my_leg_title = 8 # y axis label size
|
||||
my_strip_ts = 8 #
|
||||
|
||||
|
||||
my_xlabel = paste0("Average stability ", "(", stability_suffix, ")"); my_xlabel
|
||||
#plotdf = merged_df2[merged_df2$lineage%in%c("L1", "L2", "L3", "L4"),]
|
||||
|
||||
linP_dm_om = lineage_distP(merged_df2
|
||||
, with_facet = F
|
||||
, x_axis = "avg_stability_scaled"
|
||||
, y_axis = "lineage_labels"
|
||||
, x_lab = my_xlabel
|
||||
, use_lineages = c("L1", "L2", "L3", "L4")
|
||||
#, fill_categ = "mutation_info_orig", fill_categ_cols = c("#E69F00", "#999999")
|
||||
, fill_categ = "sensitivity"
|
||||
, fill_categ_cols = c("red", "blue")
|
||||
, label_categories = c("Resistant", "Sensitive")
|
||||
, leg_label = "Mutation group"
|
||||
, my_ats = my_ats # axis text size
|
||||
, my_als = my_als # axis label size
|
||||
, my_leg_ts = my_leg_ts
|
||||
, my_leg_title = my_leg_title
|
||||
, my_strip_ts = my_strip_ts
|
||||
, alpha = 0.56
|
||||
)
|
||||
|
||||
linP_dm_om
|
||||
|
||||
###################################################
|
||||
# Affinity dist [OPTIONAL] #
|
||||
###################################################
|
||||
# scaled_cols_affinity = c("affinity_scaled"
|
||||
# , "mmcsm_lig_scaled"
|
||||
# , "mcsm_ppi2_scaled"
|
||||
# , "mcsm_na_scaled"
|
||||
# , "avg_lig_affinity_scaled")
|
||||
|
||||
# lineage_distP(merged_df2
|
||||
# , with_facet = F
|
||||
# , x_axis = "avg_lig_affinity_scaled"
|
||||
# , y_axis = "lineage_labels"
|
||||
# , x_lab = my_xlabel
|
||||
# , use_lineages = c("L1", "L2", "L3", "L4")
|
||||
# #, fill_categ = "mutation_info_orig", fill_categ_cols = c("#E69F00", "#999999")
|
||||
# , fill_categ = "sensitivity"
|
||||
# , fill_categ_cols = c("red", "blue")
|
||||
# , label_categories = c("Resistant", "Sensitive")
|
||||
# , leg_label = "Mutation group"
|
||||
# , my_ats = 22 # axis text size
|
||||
# , my_als = 22 # axis label size
|
||||
# , my_leg_ts = 22
|
||||
# , my_leg_title = 22
|
||||
# , my_strip_ts = 22
|
||||
# , alpha = 0.56
|
||||
# )
|
||||
|
|
@ -0,0 +1,62 @@
|
|||
#!/usr/bin/env Rscript
|
||||
source("/home/tanu/git/LSHTM_analysis/scripts/plotting/plotting_thesis/pnca/lineage_bp_dist.R")
|
||||
|
||||
#=======
|
||||
# output
|
||||
#=======
|
||||
#outdir_images = paste0("~/git/Writing/thesis/images/results/", tolower(gene), "/")
|
||||
#cat("plots will output to:", outdir_images)
|
||||
###########################################
|
||||
# TASK: generate plots for lineage
|
||||
# Individual plots in
|
||||
#lineage_bp_both.R
|
||||
#linage_dist_ens_stability.R
|
||||
###########################################
|
||||
# svg
|
||||
# linPlots_combined = paste0(outdir_images
|
||||
# , tolower(gene)
|
||||
# ,"_linP_combined.svg")
|
||||
#
|
||||
# cat("\nOutput plot:", linPlots_combined)
|
||||
# svg(linPlots_combined, width = 18, height = 12)
|
||||
#
|
||||
# cowplot::plot_grid(
|
||||
# cowplot::plot_grid(lin_countP, lin_diversityP
|
||||
# , nrow = 2
|
||||
# , rel_heights = c(1.2,1)
|
||||
# , labels = "AUTO"
|
||||
# , label_size = my_label_size),
|
||||
# NULL,
|
||||
# linP_dm_om,
|
||||
# nrow = 1,
|
||||
# labels = c("", "", "C"),
|
||||
# label_size = my_label_size,
|
||||
# rel_widths = c(35, 3, 52)
|
||||
# )
|
||||
# dev.off()
|
||||
|
||||
# png
|
||||
my_label_size = 12
|
||||
linPlots_combined = paste0(outdir_images
|
||||
, tolower(gene)
|
||||
,"_linP_combined.png")
|
||||
|
||||
cat("\nOutput plot:", linPlots_combined)
|
||||
png(linPlots_combined, width = 9, height = 6, units = "in" ,res = 300)
|
||||
|
||||
cowplot::plot_grid(
|
||||
cowplot::plot_grid(lin_countP, lin_diversityP,
|
||||
nrow = 2,
|
||||
rel_heights = c(1.2,1),
|
||||
labels = "AUTO",
|
||||
label_size = my_label_size),
|
||||
NULL,
|
||||
linP_dm_om,
|
||||
nrow = 1,
|
||||
labels = c("", "", "C"),
|
||||
label_size = my_label_size,
|
||||
rel_widths = c(35, 3, 52)
|
||||
)
|
||||
dev.off()
|
||||
|
||||
|
||||
173
scripts/plotting/plotting_thesis/pnca/pe_sens_site_count_pnca.R
Normal file
173
scripts/plotting/plotting_thesis/pnca/pe_sens_site_count_pnca.R
Normal file
|
|
@ -0,0 +1,173 @@
|
|||
source("/home/tanu/git/LSHTM_analysis/scripts/plotting/plotting_thesis/pnca/prominent_effects_pnca.R")
|
||||
source("/home/tanu/git/LSHTM_analysis/scripts/plotting/plotting_thesis/pnca/sensitivity_count_pnca.R")
|
||||
|
||||
##############################################################
|
||||
# PE count
|
||||
#pe_colour_map = c("DD_lig" = "#f0e68c" # khaki
|
||||
# , "SS_lig" = "#ffd700" # gold
|
||||
|
||||
# , "DD_nucleic_acid"= "#d2b48c" # sandybrown
|
||||
# , "SS_nucleic_acid"= "#a0522d" # sienna
|
||||
|
||||
# , "DD_ppi2" = "#da70d6" # orchid
|
||||
# , "SS_ppi2" = "#ff1493" # deeppink
|
||||
|
||||
# , "DD_stability" = "#f8766d" # red
|
||||
# , "SS_stability" = "#00BFC4") # blue
|
||||
table(str_df_plot_cols$pe_effect_outcome)
|
||||
##############################################################
|
||||
#===========
|
||||
#PE count:
|
||||
# lig, ppi2, stability
|
||||
#===========
|
||||
rects <- data.frame(x=1:6,
|
||||
colors = c("#f0e68c" ,
|
||||
"#ffd700" ,
|
||||
|
||||
"#da70d6" ,
|
||||
"#ff1493" ,
|
||||
|
||||
"#f8766d" ,
|
||||
"#00BFC4")
|
||||
)
|
||||
|
||||
rects$text = c("-ve Lig"
|
||||
, "+ve Lig"
|
||||
|
||||
, "-ve PPI2"
|
||||
, "+ve PPI2"
|
||||
|
||||
, "-ve stability"
|
||||
, "+ve stability"
|
||||
)
|
||||
|
||||
cell1 = table(str_df_plot_cols$pe_effect_outcome)[["DD_lig"]]
|
||||
cell2 = 0
|
||||
|
||||
#cell3 = table(str_df_plot_cols$pe_effect_outcome)[["DD_nucleic_acid"]]
|
||||
#cell4 = table(str_df_plot_cols$pe_effect_outcome)[["SS_nucleic_acid"]]
|
||||
|
||||
cell5 = table(str_df_plot_cols$pe_effect_outcome)[["DD_ppi2"]]
|
||||
cell6 = table(str_df_plot_cols$pe_effect_outcome)[["SS_ppi2"]]
|
||||
|
||||
cell7 = table(str_df_plot_cols$pe_effect_outcome)[["DD_stability"]]
|
||||
cell8 = table(str_df_plot_cols$pe_effect_outcome)[["SS_stability"]]
|
||||
|
||||
|
||||
#rects$numbers = c(38, 0, 22, 9, 108, 681) #for embb
|
||||
rects$numbers = c(cell1, cell2,
|
||||
#cell3, cell4,
|
||||
cell5, cell6,
|
||||
cell7, cell8)
|
||||
|
||||
rects$num_labels = paste0("n=", rects$numbers)
|
||||
|
||||
rects
|
||||
#------
|
||||
# Plot
|
||||
#------
|
||||
#https://stackoverflow.com/questions/47986055/create-a-rectangle-filled-with-text
|
||||
peP = ggplot(rects, aes(x, y = 0, fill = colors, label = paste0(text,"\n", num_labels))) +
|
||||
geom_tile(width = 1, height = 1) + # make square tiles
|
||||
geom_text(color = "black", size = 1.7) + # add white text in the middle
|
||||
scale_fill_identity(guide = "none") + # color the tiles with the colors in the data frame
|
||||
coord_fixed() + # make sure tiles are square
|
||||
coord_flip()+ scale_x_reverse() +
|
||||
# theme_void() # remove any axis markings
|
||||
theme_nothing() # remove any axis markings
|
||||
peP
|
||||
|
||||
#------
|
||||
# Plot: this one is better
|
||||
#------
|
||||
peP2 = ggplot(rects, aes(x, y = 0, fill = colors, label = paste0(text,"\n", num_labels))) +
|
||||
geom_tile() + # make square tiles
|
||||
geom_text(color = "black", size = 1.6) + # add white text in the middle
|
||||
scale_fill_identity(guide = "none") + # color the tiles with the colors in the data frame
|
||||
coord_fixed() + # make sure tiles are square
|
||||
theme_nothing() # remove any axis markings
|
||||
peP2
|
||||
|
||||
########################################################
|
||||
# From: script sensitivity_count per gene
|
||||
#===============================
|
||||
# Sensitivity count: SITE
|
||||
#===============================
|
||||
#--------
|
||||
# embb
|
||||
#--------
|
||||
#rsc = 54
|
||||
#ccc = 46
|
||||
#ssc = 470
|
||||
|
||||
rsc = site_Rc; rsc
|
||||
ccc = site_Cc; ccc
|
||||
ssc = site_Sc; ssc
|
||||
|
||||
rect_rs_siteC <- data.frame(x=1:3,
|
||||
colors = c("red",
|
||||
"purple",
|
||||
"blue")
|
||||
)
|
||||
|
||||
rect_rs_siteC
|
||||
rect_rs_siteC$text = c("Resistant",
|
||||
"Common",
|
||||
"Sensitive")
|
||||
|
||||
rect_rs_siteC$numbers = c(rsc,ccc,ssc)
|
||||
rect_rs_siteC$num_labels = paste0("n=", rect_rs_siteC$numbers)
|
||||
rect_rs_siteC
|
||||
|
||||
#------
|
||||
# Plot
|
||||
#------
|
||||
sens_siteP = ggplot(rect_rs_siteC, aes(x, y = 0,
|
||||
fill = colors,
|
||||
label = num_labels
|
||||
#,label = paste0(text,"\n", num_labels)
|
||||
)) +
|
||||
geom_tile(width = 1, height = 1) +
|
||||
#geom_text(color = "black", size = 1.7) +
|
||||
geom_label(color = "black", size = 1.7,fill = "white", alpha=0.7) +
|
||||
scale_fill_identity(guide = "none") +
|
||||
coord_fixed()+
|
||||
theme_nothing() # remove any axis markings
|
||||
sens_siteP
|
||||
|
||||
################################################################
|
||||
#===============================
|
||||
# Sensitivity count: Mutations
|
||||
#===============================
|
||||
table(sensP_df$sensitivity)
|
||||
muts_Rc = table(sensP_df$sensitivity)[["R"]]
|
||||
muts_Sc = table(sensP_df$sensitivity)[["S"]]
|
||||
rect_sens <- data.frame(x=1:2,
|
||||
colors = c("red",
|
||||
"blue")
|
||||
)
|
||||
|
||||
rect_sens$text = c("Resistant",
|
||||
"Sensitive")
|
||||
rect_sens$numbers = c(muts_Rc,muts_Sc)
|
||||
rect_sens$num_labels = paste0("n=", rect_sens$numbers)
|
||||
rect_sens
|
||||
#------
|
||||
# Plot
|
||||
#------
|
||||
sensP = ggplot(rect_sens, aes(x, y = 0,
|
||||
fill = colors,
|
||||
label = paste0(text,"\n", num_labels))) +
|
||||
geom_tile(width = 1, height = 1) +
|
||||
#geom_text(color = "black", size = 1.7) +
|
||||
geom_label(color = "black", size = 1.7,fill = "white", alpha=0.7) +
|
||||
scale_fill_identity(guide = "none") +
|
||||
coord_fixed()+
|
||||
theme_nothing() # remove any axis markings
|
||||
sensP
|
||||
|
||||
sensP2 = sensP +
|
||||
coord_flip() + scale_x_reverse()
|
||||
sensP2
|
||||
|
||||
|
||||
16
scripts/plotting/plotting_thesis/pnca/plot_data_pnca.R
Normal file
16
scripts/plotting/plotting_thesis/pnca/plot_data_pnca.R
Normal file
|
|
@ -0,0 +1,16 @@
|
|||
#!/usr/bin/env Rscript
|
||||
#=============
|
||||
# Data: Input
|
||||
#==============
|
||||
source("~/git/LSHTM_analysis/config/pnca.R")
|
||||
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
|
||||
####################################################
|
||||
class(merged_df3)
|
||||
|
||||
df3 = subset(merged_df3, select = -c(pos_count))
|
||||
|
||||
#=======
|
||||
# output
|
||||
#=======
|
||||
outdir_images = paste0("~/git/Writing/thesis/images/results/", tolower(gene), "/")
|
||||
cat("plots will output to:", outdir_images)
|
||||
285
scripts/plotting/plotting_thesis/pnca/prominent_effects_pnca.R
Normal file
285
scripts/plotting/plotting_thesis/pnca/prominent_effects_pnca.R
Normal file
|
|
@ -0,0 +1,285 @@
|
|||
########################################################
|
||||
pos_colname = "position"
|
||||
|
||||
#-------------
|
||||
# from ~/git/LSHTM_analysis/scripts/plotting/plotting_colnames.R
|
||||
#-------------
|
||||
length(all_stability_cols); length(raw_stability_cols)
|
||||
length(scaled_stability_cols); length(outcome_stability_cols)
|
||||
length(affinity_dist_colnames)
|
||||
|
||||
|
||||
static_cols = c("mutationinformation",
|
||||
#"position",
|
||||
pos_colname,
|
||||
"sensitivity")
|
||||
|
||||
other_cols_all = c(scaled_stability_cols, scaled_affinity_cols, affinity_dist_colnames)
|
||||
|
||||
#omit avg cols and foldx_scaled_signC cols
|
||||
other_cols = other_cols_all[grep("avg", other_cols_all, invert = T)]
|
||||
other_cols = other_cols[grep("foldx_scaled_signC",other_cols, invert = T )]
|
||||
other_cols
|
||||
|
||||
cols_to_extract = c(static_cols, other_cols)
|
||||
cat("\nExtracting cols:", cols_to_extract)
|
||||
expected_ncols = length(static_cols) + length(other_cols)
|
||||
expected_ncols
|
||||
|
||||
str_df = merged_df3[, cols_to_extract]
|
||||
|
||||
if (ncol(str_df) == expected_ncols){
|
||||
cat("\nPASS: successfully extracted cols for calculating prominent effects")
|
||||
}else{
|
||||
stop("\nAbort: Could not extract cols for calculating prominent effects")
|
||||
}
|
||||
|
||||
#=========================
|
||||
# Masking affinity columns
|
||||
#=========================
|
||||
# First make values for affinity cols 0 when their corresponding dist >10
|
||||
head(str_df)
|
||||
|
||||
# replace in place affinity values >10
|
||||
str_df[str_df["ligand_distance"]>10,"affinity_scaled"]=0
|
||||
str_df[str_df["ligand_distance"]>10,"mmcsm_lig_scaled"]=0
|
||||
|
||||
#ppi2 gene: replace in place ppi2 affinity values where ppi2 dist >10
|
||||
if (tolower(gene)%in%geneL_ppi2){
|
||||
str_df[str_df["interface_dist"]>10,"mcsm_ppi2_scaled"]=0
|
||||
}
|
||||
|
||||
# na gene: replace in place na affinity values where na dist >10
|
||||
if (tolower(gene)%in%geneL_na){
|
||||
str_df[str_df["nca_distance"]>10,"mcsm_na_scaled"]=0
|
||||
}
|
||||
|
||||
colnames(str_df)
|
||||
head(str_df)
|
||||
|
||||
scaled_cols_tc = other_cols[grep("scaled", other_cols)]
|
||||
|
||||
|
||||
################################################
|
||||
#===============
|
||||
# whole df
|
||||
#===============
|
||||
give_col=function(x,y,df=str_df){
|
||||
df[df[[pos_colname]]==x,y]
|
||||
}
|
||||
|
||||
for (i in unique(str_df[[pos_colname]]) ){
|
||||
print(i)
|
||||
#cat(length(unique(str_df[[pos_colname]])))
|
||||
|
||||
biggest = max(abs(give_col(i,scaled_cols_tc)))
|
||||
|
||||
str_df[str_df[[pos_colname]]==i,'abs_max_effect'] = biggest
|
||||
str_df[str_df[[pos_colname]]==i,'effect_type']= names(
|
||||
give_col(i,scaled_cols_tc)[which(
|
||||
abs(
|
||||
give_col(i,scaled_cols_tc)
|
||||
) == biggest, arr.ind=T
|
||||
)[, "col"]])[1]
|
||||
|
||||
effect_name = unique(str_df[str_df[[pos_colname]]==i,'effect_type'])#[1] # pick first one in case we have multiple exact values
|
||||
|
||||
# get index/rowname for value of max effect, and then use it to get the original sign
|
||||
# here
|
||||
#ind = rownames(which(abs(str_df[str_df[[pos_colname]]==i,c('position',effect_name)][effect_name])== biggest, arr.ind=T))
|
||||
ind = rownames(which(abs(str_df[str_df[[pos_colname]]==i,c(pos_colname,effect_name)][effect_name])== biggest, arr.ind=T))
|
||||
|
||||
str_df[str_df[[pos_colname]]==i,'effect_sign'] = sign(str_df[effect_name][ind,])[1]
|
||||
}
|
||||
|
||||
# ends with suffix 2 if dups
|
||||
str_df$effect_type = sub("\\.[0-9]+", "", str_df$effect_type) # cull duplicate effect types that happen when there are exact duplicate values
|
||||
colnames(str_df)
|
||||
table(str_df$effect_type)
|
||||
|
||||
# check
|
||||
str_df_check = str_df[str_df[[pos_colname]]%in%c(24, 32, 160, 303, 334),]
|
||||
|
||||
#================
|
||||
# for Plots
|
||||
#================
|
||||
str_df_short = str_df[, c("mutationinformation",
|
||||
#"position",
|
||||
pos_colname,
|
||||
"sensitivity"
|
||||
, "effect_type"
|
||||
, "effect_sign")]
|
||||
|
||||
table(str_df_short$effect_type)
|
||||
table(str_df_short$effect_sign)
|
||||
str(str_df_short)
|
||||
|
||||
# assign pe outcome
|
||||
str_df_short$pe_outcome = ifelse(str_df_short$effect_sign<0, "DD", "SS")
|
||||
table(str_df_short$pe_outcome )
|
||||
table(str_df_short$effect_sign)
|
||||
|
||||
#==============
|
||||
# group effect type:
|
||||
# lig, ppi2, nuc. acid, stability
|
||||
#==============
|
||||
affcols = c("affinity_scaled", "mmcsm_lig_scaled")
|
||||
|
||||
#lig
|
||||
table(str_df_short$effect_type)
|
||||
str_df_short$effect_grouped = ifelse(str_df_short$effect_type%in%affcols
|
||||
, "lig"
|
||||
, str_df_short$effect_type)
|
||||
table(str_df_short$effect_grouped)
|
||||
|
||||
|
||||
#stability
|
||||
str_df_short$effect_grouped = ifelse(!str_df_short$effect_grouped%in%c("lig")
|
||||
, "stability"
|
||||
, str_df_short$effect_grouped)
|
||||
|
||||
table(str_df_short$effect_grouped)
|
||||
|
||||
# create a sign as well
|
||||
str_df_short$pe_effect_outcome = paste0(str_df_short$pe_outcome, "_"
|
||||
, str_df_short$effect_grouped)
|
||||
|
||||
table(str_df_short$pe_effect_outcome)
|
||||
|
||||
#####################################################################
|
||||
# Chimera: for colouring
|
||||
####################################################################
|
||||
|
||||
#-------------------------------------
|
||||
# get df with unique position
|
||||
#--------------------------------------
|
||||
#data[!duplicated(data$x), ]
|
||||
str_df_plot = str_df_short[!duplicated(str_df[[pos_colname]]),]
|
||||
|
||||
if (nrow(str_df_plot) == length(unique(str_df[[pos_colname]]))){
|
||||
cat("\nPASS: successfully extracted df with unique positions")
|
||||
}else{
|
||||
stop("\nAbort: Could not extract df with unique positions")
|
||||
}
|
||||
|
||||
#-------------------------------------
|
||||
# generate colours for effect types
|
||||
#--------------------------------------
|
||||
str_df_plot_cols = str_df_plot[, c(pos_colname,
|
||||
"sensitivity",
|
||||
"pe_outcome",
|
||||
"effect_grouped",
|
||||
"pe_effect_outcome")]
|
||||
head(str_df_plot_cols)
|
||||
|
||||
# colour intensity based on sign
|
||||
#str_df_plot_cols$colour_hue = ifelse(str_df_plot_cols$effect_sign<0, "bright", "light")
|
||||
str_df_plot_cols$colour_hue = ifelse(str_df_plot_cols$pe_outcome=="DD", "bright", "light")
|
||||
|
||||
table(str_df_plot_cols$colour_hue); table(str_df_plot$pe_outcome)
|
||||
head(str_df_plot_cols)
|
||||
|
||||
# colour based on effect
|
||||
table(str_df_plot_cols$pe_effect_outcome)
|
||||
|
||||
pe_colour_map = c("DD_lig" = "#f0e68c" # khaki
|
||||
, "SS_lig" = "#ffd700" # gold
|
||||
|
||||
, "DD_nucleic_acid"= "#d2b48c" # sandybrown
|
||||
, "SS_nucleic_acid"= "#a0522d" # sienna
|
||||
|
||||
, "DD_ppi2" = "#da70d6" # orchid
|
||||
, "SS_ppi2" = "#ff1493" # deeppink
|
||||
|
||||
, "DD_stability" = "#f8766d" # red
|
||||
, "SS_stability" = "#00BFC4") # blue
|
||||
|
||||
#unlist(d[c('a', 'a', 'c', 'b')], use.names=FALSE)
|
||||
|
||||
#map the colours
|
||||
str_df_plot_cols$colour_map= unlist(map(str_df_plot_cols$pe_effect_outcome
|
||||
,function(x){pe_colour_map[[x]]}
|
||||
))
|
||||
head(str_df_plot_cols$colour_map)
|
||||
table(str_df_plot_cols$colour_map)
|
||||
table(str_df_plot_cols$pe_effect_outcome)
|
||||
|
||||
# str_df_plot_cols$colours = paste0(str_df_plot_cols$colour_hue
|
||||
# , "_"
|
||||
# , str_df_plot_cols$colour_map)
|
||||
# head(str_df_plot_cols$colours)
|
||||
# table(str_df_plot_cols$colours)
|
||||
#
|
||||
#
|
||||
# class(str_df_plot_cols$colour_map)
|
||||
# str(str_df_plot_cols)
|
||||
|
||||
# sort by colour
|
||||
head(str_df_plot_cols)
|
||||
str_df_plot_cols = str_df_plot_cols[order(str_df_plot_cols$colour_map), ]
|
||||
head(str_df_plot_cols)
|
||||
|
||||
#======================================
|
||||
# write file with prominent effects
|
||||
#======================================
|
||||
outdir_images = paste0("~/git/Writing/thesis/images/results/", tolower(gene), "/")
|
||||
write.csv(str_df_plot_cols, paste0(outdir_images, tolower(gene), "_prominent_effects.csv"))
|
||||
|
||||
################################
|
||||
# printing for chimera
|
||||
###############################
|
||||
chain_suffix = ".A"
|
||||
str_df_plot_cols$pos_chain = paste0(str_df_plot_cols[[pos_colname]], chain_suffix)
|
||||
table(str_df_plot_cols$colour_map)
|
||||
table(str_df_plot_cols$pe_effect_outcome)
|
||||
|
||||
#===================================================
|
||||
#-------------------
|
||||
# Ligand Affinity
|
||||
#-------------------
|
||||
# -ve Lig Aff
|
||||
dd_lig = str_df_plot_cols[str_df_plot_cols$pe_effect_outcome=="DD_lig",]
|
||||
if (nrow(dd_lig) == table(str_df_plot_cols$pe_effect_outcome)[['DD_lig']]){
|
||||
dd_lig_pos = dd_lig[[pos_colname]]
|
||||
}else{
|
||||
stop("Abort: DD affinity colour numbers mismtatch")
|
||||
}
|
||||
toString(paste0(dd_lig_pos, chain_suffix))
|
||||
|
||||
# +ve Lig Aff
|
||||
ss_lig = str_df_plot_cols[str_df_plot_cols$pe_effect_outcome=="SS_lig",]
|
||||
if (!empty(ss_lig)){
|
||||
if (nrow(ss_lig) == table(str_df_plot_cols$pe_effect_outcome)[['SS_lig']]){
|
||||
ss_lig_pos = ss_lig[[pos_colname]]
|
||||
}else{
|
||||
stop("Abort: SS affinity colour numbers mismtatch")
|
||||
}
|
||||
#put in chimera cmd
|
||||
toString(paste0(ss_lig_pos, chain_suffix))
|
||||
}
|
||||
|
||||
#=========================================================
|
||||
#------------------------
|
||||
# Stability
|
||||
#------------------------
|
||||
# -ve Stability
|
||||
dd_stability = str_df_plot_cols[str_df_plot_cols$pe_effect_outcome=="DD_stability",]
|
||||
if (nrow(dd_stability) == table(str_df_plot_cols$pe_effect_outcome)[['DD_stability']]){
|
||||
dd_stability_pos = dd_stability[[pos_colname]]
|
||||
}else{
|
||||
stop("Abort: DD Stability colour numbers mismtatch")
|
||||
}
|
||||
|
||||
# +ve Stability
|
||||
ss_stability = str_df_plot_cols[str_df_plot_cols$pe_effect_outcome=="SS_stability",]
|
||||
if (nrow(ss_stability) == table(str_df_plot_cols$pe_effect_outcome)[['SS_stability']]){
|
||||
ss_stability_pos = ss_stability[[pos_colname]]
|
||||
}else{
|
||||
stop("Abort: SS Stability colour numbers mismtatch")
|
||||
}
|
||||
|
||||
#put in chimera cmd
|
||||
toString(paste0(dd_stability_pos, chain_suffix))
|
||||
toString(paste0(ss_stability_pos, chain_suffix))
|
||||
####################################################################
|
||||
|
||||
|
|
@ -0,0 +1,65 @@
|
|||
#=========================
|
||||
# Count Sensitivity
|
||||
# Mutations and positions
|
||||
#=========================
|
||||
pos_colname_c ="position"
|
||||
|
||||
sensP_df = merged_df3[,c("mutationinformation",
|
||||
#"position",
|
||||
pos_colname_c,
|
||||
"sensitivity")]
|
||||
|
||||
head(sensP_df)
|
||||
table(sensP_df$sensitivity)
|
||||
|
||||
#---------------
|
||||
# Total unique positions
|
||||
#----------------
|
||||
tot_mut_pos = length(unique(sensP_df[[pos_colname_c]]))
|
||||
cat("\nNo of Tot muts sites:", tot_mut_pos)
|
||||
|
||||
# resistant mut pos
|
||||
sens_site_allR = sensP_df[[pos_colname_c]][sensP_df$sensitivity=="R"]
|
||||
sens_site_UR = unique(sens_site_allR)
|
||||
length(sens_site_UR)
|
||||
|
||||
# Sensitive mut pos
|
||||
sens_site_allS = sensP_df[[pos_colname_c]][sensP_df$sensitivity=="S"]
|
||||
sens_site_US = unique(sens_site_allS)
|
||||
length(sens_site_UR)
|
||||
|
||||
#---------------
|
||||
# Common Sites
|
||||
#----------------
|
||||
common_pos = intersect(sens_site_UR,sens_site_US)
|
||||
site_Cc = length(common_pos)
|
||||
cat("\nNo of Common sites:", site_Cc
|
||||
, "\nThese are:", common_pos)
|
||||
|
||||
#---------------
|
||||
# Resistant muts
|
||||
#----------------
|
||||
site_R = sens_site_UR[!sens_site_UR%in%common_pos]
|
||||
site_Rc = length(site_R)
|
||||
|
||||
if ( length(sens_site_allR) == table(sensP_df$sensitivity)[['R']] ){
|
||||
cat("\nNo of R muts:", length(sens_site_allR)
|
||||
, "\nNo. of R sites:",site_Rc
|
||||
, "\nThese are:", site_R
|
||||
)
|
||||
}
|
||||
|
||||
#---------------
|
||||
# Sensitive muts
|
||||
#----------------
|
||||
site_S = sens_site_US[!sens_site_US%in%common_pos]
|
||||
site_Sc = length(site_S)
|
||||
|
||||
if ( length(sens_site_allS) == table(sensP_df$sensitivity)[['S']] ){
|
||||
cat("\nNo of S muts:", length(sens_site_allS)
|
||||
, "\nNo. of S sites:", site_Sc
|
||||
, "\nThese are:", site_S)
|
||||
}
|
||||
|
||||
#########################
|
||||
|
||||
Loading…
Add table
Add a link
Reference in a new issue