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

added rpob plot scripts

Browse source
This commit is contained in:
Tanushree Tunstall 2022-08-29 23:26:43 +01:00
parent 8f97ab7cc8
commit 7c2e4b898e
8 changed files with 109 additions and 48 deletions
Download patch file Download diff file Expand all files Collapse all files

6
config/rpob.R
View file

@ -72,3 +72,9 @@ tile_map=data.frame(tile=c("RFP"),
#### ####
chain_suffix = ".C" chain_suffix = ".C"
print(toString(paste0(aa_pos_drug, chain_suffix))) print(toString(paste0(aa_pos_drug, chain_suffix)))
# # equivalent resiudes on 5uhc:
# active_aa_pos_5uhc = active_aa_pos+6
# active_aa_pos_5uhc
# print(toString(paste0(active_aa_pos_5uhc, chain_suffix)))

11
scripts/functions/corr_plot_data.R
View file

@ -45,7 +45,7 @@ corr_data_extract <- function(df
) )
display_common_colnames = c( drug, "dst_mode" display_common_colnames = c( drug, "dst_mode"
, "DUET" , "FoldX" , "DeepDDG", "Dynamut2" , "mCSM-DUET" , "FoldX" , "DeepDDG", "Dynamut2"
, "ASA" , "RSA" , "KD" , "RD" , "ASA" , "RSA" , "KD" , "RD"
# previously MAF # previously MAF
, "Log10(MAF)" , "Log10(OR)" , "-Log10(P)" , "Log10(MAF)" , "Log10(OR)" , "-Log10(P)"
@ -80,12 +80,13 @@ corr_data_extract <- function(df
# SPECIAL case for rpob as it exists in both ppi and na # SPECIAL case for rpob as it exists in both ppi and na
if (tolower(gene)%in%c("rpob")){ if (tolower(gene)%in%c("rpob")){
colnames_to_extract = c(common_colnames colnames_to_extract = c(common_colnames
, "mcsm_ppi2_affinity", ppi2Dist_colname , "mcsm_na_affinity", naDist_colname
, "mcsm_na_affinity", naDist_colname) , "mcsm_ppi2_affinity", ppi2Dist_colname)
display_colnames = c(display_common_colnames display_colnames = c(display_common_colnames
,"mCSM-PPI2", "PPI-Dist" ,"mCSM-NA", "NA-Dist"
,"mCSM-NA", "NA-Dist" ) ,"mCSM-PPI2", "PPI-Dist")
corr_df = df[,colnames_to_extract] corr_df = df[,colnames_to_extract]
colnames(corr_df) = display_colnames colnames(corr_df) = display_colnames

16
scripts/functions/dm_om_data.R
View file

@ -83,10 +83,10 @@ dm_om_wf_lf_data <- function(df
if (tolower(gene)%in%geneL_both){ if (tolower(gene)%in%geneL_both){
additional_dfL = list( additional_dfL = list(
wf_mcsm_ppi2 = data.frame(), wf_mcsm_ppi2 = data.frame(),
lf_mcsm_ppi2 = data.frame(), lf_mcsm_ppi2 = data.frame(),
wf_mcsm_na = data.frame(), wf_mcsm_na = data.frame(),
lf_mcsm_na = data.frame() lf_mcsm_na = data.frame()
) )
wf_lf_dataL = c(common_dfsL, additional_dfL) wf_lf_dataL = c(common_dfsL, additional_dfL)
} }
@ -98,7 +98,7 @@ dm_om_wf_lf_data <- function(df
# display names # display names
stability_suffix <- paste0(delta_symbol, delta_symbol, "G") stability_suffix <- paste0(delta_symbol, delta_symbol, "G")
duet_dn = paste0("DUET ", stability_suffix); duet_dn duet_dn = paste0("mCSM-DUET ", stability_suffix); duet_dn
foldx_dn = paste0("FoldX ", stability_suffix); foldx_dn foldx_dn = paste0("FoldX ", stability_suffix); foldx_dn
deepddg_dn = paste0("Deepddg " , stability_suffix); deepddg_dn deepddg_dn = paste0("Deepddg " , stability_suffix); deepddg_dn
dynamut2_dn = paste0("Dynamut2 " , stability_suffix); dynamut2_dn dynamut2_dn = paste0("Dynamut2 " , stability_suffix); dynamut2_dn
@ -119,8 +119,7 @@ dm_om_wf_lf_data <- function(df
lig_dist_dn = paste0("Lig Dist(", angstroms_symbol, ")"); lig_dist_dn lig_dist_dn = paste0("Lig Dist(", angstroms_symbol, ")"); lig_dist_dn
mcsm_lig_dn = paste0("mCSM-lig"); mcsm_lig_dn mcsm_lig_dn = paste0("mCSM-lig"); mcsm_lig_dn
mmcsm_lig_dn2 = paste0("mmCSM-lig"); mmcsm_lig_dn2 mmcsm_lig_dn2 = paste0("mmCSM-lig"); mmcsm_lig_dn2
na_dist_dn = paste0("Dist to NA (", angstroms_symbol, ")"); na_dist_dn na_dist_dn = paste0("Dist to NA (", angstroms_symbol, ")"); na_dist_dn
mcsm_na_dn = paste0("mCSM-NA ", stability_suffix); mcsm_na_dn mcsm_na_dn = paste0("mCSM-NA ", stability_suffix); mcsm_na_dn
@ -240,8 +239,8 @@ dm_om_wf_lf_data <- function(df
} }
if (tolower(gene)%in%geneL_na){ if (tolower(gene)%in%geneL_na){
colnames_to_extract = c(common_colnames ,"mcsm_na_affinity" , "mcsm_na_scaled" , "mcsm_na_outcome" , naDist_colname) colnames_to_extract = c(common_colnames ,"mcsm_na_affinity" , "mcsm_na_scaled" , "mcsm_na_outcome" , naDist_colname)
display_colnames = c(display_common_colnames, "mcsm_na_affinity" , mcsm_na_dn , "mcsm_na_outcome" , na_dist_dn) display_colnames = c(display_common_colnames , "mcsm_na_affinity" , mcsm_na_dn , "mcsm_na_outcome" , na_dist_dn)
comb_df_sl = df[, colnames_to_extract] comb_df_sl = df[, colnames_to_extract]
# Rename cols: display names # Rename cols: display names
@ -282,7 +281,7 @@ dm_om_wf_lf_data <- function(df
colnames(comb_df_sl) = display_colnames colnames(comb_df_sl) = display_colnames
comb_df_sl_ppi2 = comb_df_sl[comb_df_sl[[ppi2_dist_dn]]<DistCutOff,] comb_df_sl_ppi2 = comb_df_sl[comb_df_sl[[ppi2_dist_dn]]<DistCutOff,]
comb_df_sl_na = comb_df_sl[comb_df_sl[[na_dist_dn]]<DistCutOff,] comb_df_sl_na = comb_df_sl[comb_df_sl[[na_dist_dn]]<DistCutOff,]
static_cols_end = c(na_dist_dn, static_cols_end_common) static_cols_end = c(ppi2_dist_dn, na_dist_dn, static_cols_end_common)
} }
@ -348,7 +347,6 @@ dm_om_wf_lf_data <- function(df
colnames(wf_dist_gen) colnames(wf_dist_gen)
colnames(lf_dist_gen) colnames(lf_dist_gen)
# Assign them to the output list # Assign them to the output list
wf_lf_dataL[['wf_dist_gen']] = wf_dist_gen wf_lf_dataL[['wf_dist_gen']] = wf_dist_gen
wf_lf_dataL[['lf_dist_gen']] = lf_dist_gen wf_lf_dataL[['lf_dist_gen']] = lf_dist_gen

4
scripts/plotting/plotting_thesis/rpob/basic_barplots_rpob.R
View file

@ -7,8 +7,8 @@
#============= #=============
# Data: Input # Data: Input
#============== #==============
source("~/git/LSHTM_analysis/config/rpob.R") #source("~/git/LSHTM_analysis/config/rpob.R")
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R") #source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
#cat("\nSourced plotting cols as well:", length(plotting_cols)) #cat("\nSourced plotting cols as well:", length(plotting_cols))

15
scripts/plotting/plotting_thesis/rpob/basic_barplots_rpob_layout.R
View file

@ -4,7 +4,22 @@
source("~/git/LSHTM_analysis/config/rpob.R") source("~/git/LSHTM_analysis/config/rpob.R")
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R") source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
#cat("\nSourced plotting cols as well:", length(plotting_cols)) #cat("\nSourced plotting cols as well:", length(plotting_cols))
##############################################################
nrow(merged_df3)
table(merged_df3$sensitivity)
df3_lig = merged_df3[merged_df3$ligand_distance<10,]
nrow(df3_lig)
table(df3_lig$sensitivity)
df3_na = merged_df3[merged_df3$nca_distance<10,]
nrow(df3_na)
table(df3_na$sensitivity)
df3_ppi2 = merged_df3[merged_df3$interface_dist<10,]
nrow(df3_ppi2)
table(df3_ppi2$sensitivity)
#############################################################
#======= #=======
# output # output
#======= #=======

22
scripts/plotting/plotting_thesis/rpob/dm_om_plots_layout_rpob.R
View file

@ -1,5 +1,6 @@
# source dm_om_plots.R # source dm_om_plots.R
source("/home/tanu/git/LSHTM_analysis/scripts/plotting/plotting_thesis/dm_om_plots.R") source("/home/tanu/git/LSHTM_analysis/scripts/plotting/plotting_thesis/rpob/dm_om_plots_rpob.R")
# source("/home/tanu/git/LSHTM_analysis/scripts/plotting/plotting_thesis/dm_om_plots.R")
##### plots to combine #### ##### plots to combine ####
duetP duetP
@ -14,6 +15,8 @@ mcsmligP
mcsmlig2P mcsmlig2P
mcsmppi2P mcsmppi2P
mcsmnaP mcsmnaP
distanceP_ppi2
distanceP_na
# Plot labels # Plot labels
tit1 = "Stability changes" tit1 = "Stability changes"
@ -105,18 +108,17 @@ OutPlot_dm_om = function(x){
), ),
NULL, NULL,
cowplot::plot_grid(pt3, cowplot::plot_grid(pt3,
cowplot::plot_grid( #distanceP cowplot::plot_grid(distanceP_lig
distanceP_lig
#, distanceP_ppi2
, distanceP_na , distanceP_na
, distanceP_ppi2
, nrow = 1 , nrow = 1
, labels = c("F", "G") , labels = c("F", "G","H")
, label_size = my_label_size) , label_size = my_label_size)
, ncol = 1 , ncol = 1
, rel_heights = relH_tp , rel_heights = relH_tp
), ),
nrow = 1, nrow = 1,
rel_widths = c(2/7, 0.1/7, 0.5/7, 0.1/7, 1/7) rel_widths = c(4/8, 0.1/8, 1/8, 0.1/8, 3/8)
) )
#---------------- #----------------
@ -126,7 +128,7 @@ OutPlot_dm_om = function(x){
cowplot::plot_grid(pt4, cowplot::plot_grid(pt4,
cowplot::plot_grid(consurfP, proveanP, snap2P cowplot::plot_grid(consurfP, proveanP, snap2P
, nrow = 1 , nrow = 1
, labels = c("H", "I", "J") , labels = c("I", "J", "K")
, label_size = my_label_size) , label_size = my_label_size)
, ncol = 1 , ncol = 1
, rel_heights =relH_tp , rel_heights =relH_tp
@ -134,16 +136,16 @@ OutPlot_dm_om = function(x){
cowplot::plot_grid(pt5, cowplot::plot_grid(pt5,
cowplot::plot_grid(mcsmligP cowplot::plot_grid(mcsmligP
, mcsmlig2P , mcsmlig2P
, mcsmppi2P
, mcsmnaP , mcsmnaP
, mcsmppi2P
, nrow = 1 , nrow = 1
, labels = c("K", "L", "M") , labels = c("L", "M", "N", "O")
, label_size = my_label_size) , label_size = my_label_size)
, ncol = 1 , ncol = 1
, rel_heights = relH_tp , rel_heights = relH_tp
),NULL, ),NULL,
nrow = 1, nrow = 1,
rel_widths = c(3/6,0.1/6,3/6, 0.1/6 ) rel_widths = c(3/7,0.1/7,4/7, 0.1/7 )
) )
#------------------------------- #-------------------------------

14
scripts/plotting/plotting_thesis/rpob/gg_pairs_all_rpob.R
View file

@ -1,5 +1,5 @@
source("~/git/LSHTM_analysis/config/rpob.R") #source("~/git/LSHTM_analysis/config/rpob.R")
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R") #source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
#======= #=======
# output # output
@ -48,6 +48,7 @@ DistCutOff = 10
geneL_normal = c("pnca") geneL_normal = c("pnca")
geneL_na = c("gid", "rpob") geneL_na = c("gid", "rpob")
geneL_ppi2 = c("alr", "embb", "katg", "rpob") geneL_ppi2 = c("alr", "embb", "katg", "rpob")
geneL_both = c("rpob")
merged_df3 = as.data.frame(merged_df3) merged_df3 = as.data.frame(merged_df3)
@ -58,7 +59,7 @@ corr_plotdf = corr_data_extract(merged_df3
aff_dist_cols = colnames(corr_plotdf)[grep("Dist", colnames(corr_plotdf))] aff_dist_cols = colnames(corr_plotdf)[grep("Dist", colnames(corr_plotdf))]
static_cols = c("Log10(MAF)" static_cols = c("Log10(MAF)"
, "Log10(OR)" #, "Log10(OR)"
) )
############################################################ ############################################################
#============================================= #=============================================
@ -90,7 +91,7 @@ unmasked_vals
# Stability # Stability
#================ #================
corr_ps_colnames = c(static_cols corr_ps_colnames = c(static_cols
, "DUET" , "mCSM-DUET"
, "FoldX" , "FoldX"
, "DeepDDG" , "DeepDDG"
, "Dynamut2" , "Dynamut2"
@ -138,6 +139,11 @@ if (tolower(gene)%in%geneL_na){
aff_colnames = c(common_aff_colnames, "mCSM-NA") aff_colnames = c(common_aff_colnames, "mCSM-NA")
} }
if (tolower(gene)%in%geneL_both){
aff_colnames = c(common_aff_colnames, "mCSM-NA", "mCSM-PPI2")
}
# building ffinal affinity colnames for correlation # building ffinal affinity colnames for correlation
corr_aff_colnames = c(static_cols corr_aff_colnames = c(static_cols
, aff_colnames , aff_colnames

69
scripts/plotting/plotting_thesis/rpob/rpob_appendix_tables.R
View file

@ -1,7 +1,6 @@
#!/usr/bin/env Rscript #!/usr/bin/env Rscript
#source("~/git/LSHTM_analysis/config/gid.R")
source("~/git/LSHTM_analysis/config/gid.R") #source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
#======= #=======
# output # output
@ -13,7 +12,7 @@ cat("\nOutput dir for stats:", outdir_stats)
geneL_normal = c("pnca") geneL_normal = c("pnca")
#geneL_na = c("gid", "rpob") #geneL_na = c("gid", "rpob")
geneL_na_v2 = c("gid") geneL_na_v2 = c("gid")
geneL_nca = c("alr", "embb", "katg", "rpob") geneL_ppi2 = c("alr", "embb", "katg", "rpob")
geneL_both = c("rpob") geneL_both = c("rpob")
@ -21,10 +20,15 @@ if (tolower(gene)%in%geneL_na_v2) {
gene_colnames = c("mcsm_na_affinity", "mcsm_na_outcome") gene_colnames = c("mcsm_na_affinity", "mcsm_na_outcome")
} }
if (tolower(gene)%in%geneL_nca) { if (tolower(gene)%in%geneL_na) {
gene_colnames = c("mcsm_nca_affinity", "mcsm_nca_outcome") gene_colnames = c("mcsm_nca_affinity", "mcsm_nca_outcome")
} }
if (tolower(gene)%in%geneL_both) {
gene_colnames = c("mcsm_na_affinity", "mcsm_na_outcome"
, "mcsm_ppi2_affinity", "mcsm_ppi2_outcome")
}
#from plotting_globals() #from plotting_globals()
LigDist_colname LigDist_colname
@ -36,6 +40,9 @@ angstroms_symbol
cat("\nAffinity Distance colnames:", length(affinity_dist_colnames) cat("\nAffinity Distance colnames:", length(affinity_dist_colnames)
, "\nThese are:", affinity_dist_colnames) , "\nThese are:", affinity_dist_colnames)
affinity_dist_colnames = c("ligand_distance","nca_distance","interface_dist") # for consistency
#=========== #===========
# Data used # Data used
#=========== #===========
@ -50,7 +57,7 @@ cols_to_output = c("position"
, "mmcsm_lig" , "mmcsm_lig"
, "mmcsm_lig_outcome" , "mmcsm_lig_outcome"
, affinity_dist_colnames[2] , affinity_dist_colnames[2]
# #, affinity_dist_colnames[3] , affinity_dist_colnames[3]
# , "mcsm_na_affinity" # , "mcsm_na_affinity"
# , "mcsm_na_outcome" # , "mcsm_na_outcome"
# #, "mcsm_nca_affinity" # #, "mcsm_nca_affinity"
@ -148,8 +155,13 @@ colsNames_to_output_lig = c("position"
colnames(Out_df_ligS) = colsNames_to_output_lig colnames(Out_df_ligS) = colsNames_to_output_lig
head(Out_df_ligS) head(Out_df_ligS)
# ADD: active site annot
nrow(Out_df_ligS)
Out_df_ligS$drug_site = ifelse(Out_df_ligS$position%in%aa_pos_drug, "drug", "no")
table(Out_df_ligS$drug_site)
#-------------------- #--------------------
# write output file: KS test within grpup # write output file: lig
#---------------------- #----------------------
Out_ligT = paste0(outdir_stats Out_ligT = paste0(outdir_stats
, tolower(gene) , tolower(gene)
@ -172,7 +184,9 @@ cols_to_output_nca = c("position"
, "sensitivity" , "sensitivity"
, "mutationinformation" , "mutationinformation"
, naDist_colname , naDist_colname
, gene_colnames , "mcsm_na_affinity"
, "mcsm_na_outcome"
# , gene_colnames
, "maf_percent" , "maf_percent"
, "or_mychisq" , "or_mychisq"
, "pval_fisher" , "pval_fisher"
@ -201,8 +215,14 @@ colsNames_to_output_nca = c("position"
colnames(Out_df_ncaS) = colsNames_to_output_nca colnames(Out_df_ncaS) = colsNames_to_output_nca
Out_df_ncaS Out_df_ncaS
# ADD: active site annot
nrow(Out_df_ncaS)
Out_df_ncaS$drug_site = ifelse(Out_df_ncaS$position%in%aa_pos_drug, "drug", "no")
table(Out_df_ncaS$drug_site)
#-------------------- #--------------------
# write output file: KS test within grpup # write output file: na
#---------------------- #----------------------
Out_ncaT = paste0(outdir_stats Out_ncaT = paste0(outdir_stats
, tolower(gene) , tolower(gene)
@ -223,9 +243,9 @@ cols_to_output_ppi2 = c("position"
, "sensitivity" , "sensitivity"
, "mutationinformation" , "mutationinformation"
, ppi2Dist_colname , ppi2Dist_colname
#, "mcsm_ppi2_affinity" , "mcsm_ppi2_affinity"
#, "mcsm_ppi2_outcome" , "mcsm_ppi2_outcome"
, gene_colnames #, gene_colnames
, "maf_percent" , "maf_percent"
, "or_mychisq" , "or_mychisq"
, "pval_fisher" , "pval_fisher"
@ -254,8 +274,14 @@ colsNames_to_output_ppi2 = c("position"
colnames(Out_df_ppi2S) = colsNames_to_output_ppi2 colnames(Out_df_ppi2S) = colsNames_to_output_ppi2
Out_df_ppi2S Out_df_ppi2S
# ADD: active site annot
nrow(Out_df_ppi2S)
Out_df_ppi2S$drug_site = ifelse(Out_df_ppi2S$position%in%aa_pos_drug, "drug", "no")
table(Out_df_ppi2S$drug_site)
#-------------------- #--------------------
# write output file: KS test within grpup # write output file: ppi2
#---------------------- #----------------------
Out_ppi2T = paste0(outdir_stats Out_ppi2T = paste0(outdir_stats
, tolower(gene) , tolower(gene)
@ -270,7 +296,7 @@ write.csv(Out_df_ppi2S, Out_ppi2T, row.names = FALSE)
########################################################## ##########################################################
# higest or/maf and stability effects # higest or/maf and stability effects
########################################################### ###########################################################
# convert to percet # convert to percent
df3$maf_percent = df3$maf*100 df3$maf_percent = df3$maf*100
cols_to_output_effects = c("position" cols_to_output_effects = c("position"
@ -282,6 +308,7 @@ cols_to_output_effects = c("position"
, "avg_lig_affinity" , "avg_lig_affinity"
, "avg_lig_affinity_outcome" , "avg_lig_affinity_outcome"
, affinity_dist_colnames[2] , affinity_dist_colnames[2]
, affinity_dist_colnames[3]
, gene_colnames , gene_colnames
, "maf_percent" , "maf_percent"
, "or_mychisq" , "or_mychisq"
@ -402,7 +429,7 @@ if (tolower(gene)%in%geneL_both ){
# add cols: PPI2 # add cols: PPI2
mut_h_ppi2_dd$mutational_effect = "Most Destabilising for PPI affinity" mut_h_ppi2_dd$mutational_effect = "Most Destabilising for PPI affinity"
mut_h_ppi2_dd$mutational_effect = "Most Stabilising for PPI affinity" mut_h_ppi2_ss$mutational_effect = "Most Stabilising for PPI affinity"
if (identical(colnames(mut_h_ppi2_dd), colnames(mut_h_ppi2_ss)) ){ if (identical(colnames(mut_h_ppi2_dd), colnames(mut_h_ppi2_ss)) ){
cat("\nPass 1: ppi2") cat("\nPass 1: ppi2")
@ -417,7 +444,7 @@ if (tolower(gene)%in%geneL_both ){
} }
# combine BOTH: NA and PPI2 # combine BOTH: NA and PPI2
gene_aff_combined = rbind(mut_h_na_dd, mut_h_na_ss) gene_aff_combined = rbind(mut_h_na_dd, mut_h_na_ss, mut_h_ppi2_dd, mut_h_ppi2_ss)
} }
#=============== #===============
@ -447,10 +474,11 @@ colsNames_combined_table = c("position"
, "Ligand affinity outcome" , "Ligand affinity outcome"
, paste0("NA-Dist (", angstroms_symbol, ")") , paste0("NA-Dist (", angstroms_symbol, ")")
, paste0("PPI-Dist (", angstroms_symbol, ")")
, paste0("mCSM-NA (", delta_symbol,delta_symbol,"G)") , paste0("mCSM-NA (", delta_symbol,delta_symbol,"G)")
, "mCSM-NA outcome" , "mCSM-NA outcome"
, paste0("PPI-Dist (", angstroms_symbol, ")")
, paste0("mCSM-PPI (", delta_symbol,delta_symbol,"G)") , paste0("mCSM-PPI (", delta_symbol,delta_symbol,"G)")
, "mCSM-PPI outcome" , "mCSM-PPI outcome"
@ -469,8 +497,13 @@ if ( length(colnames(combined_table)) == length(colsNames_combined_table) ) {
stop("\nAbort: No. of cols mismatch. Cannot assign pretty colnames for output") stop("\nAbort: No. of cols mismatch. Cannot assign pretty colnames for output")
} }
# ADD: active site annot
nrow(combined_table)
combined_table$drug_site = ifelse(combined_table$position%in%aa_pos_drug, "drug", "no")
table(combined_table$drug_site)
#-------------------- #--------------------
# write output file: KS test within grpup # write output file: extreme effects
#---------------------- #----------------------
Out_combined_effectsT = paste0(outdir_stats Out_combined_effectsT = paste0(outdir_stats
, tolower(gene) , tolower(gene)