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

separted cols

Browse source
This commit is contained in:
Tanushree Tunstall 2022-08-01 14:09:46 +01:00
parent e750ee59aa
commit 0d8979dfcb
2 changed files with 129 additions and 156 deletions
Download patch file Download diff file Expand all files Collapse all files

95
scripts/plotting/mcsm_mean_stability_ensemble.R
View file

@ -53,54 +53,85 @@ all_colnames = as.data.frame(colnames(df3))
common_cols = c("mutationinformation"
, "position"
, "dst_mode"
#, "mutation_info_labels"
, "mutation_info_labels"
, "sensitivity"
, "ligand_distance")
all_colnames$`colnames(df3)`[grep("scaled", all_colnames$`colnames(df3)`)]
scaled_cols = c("duet_scaled" , "duet_stability_change"
, "deepddg_scaled" , "deepddg"
, "ddg_dynamut2_scaled" , "ddg_dynamut2"
, "foldx_scaled" , "ddg_foldx"
, "affinity_scaled" , "ligand_affinity_change"
, "mmcsm_lig_scaled" , "mmcsm_lig"
, "mcsm_ppi2_scaled" , "mcsm_ppi2_affinity"
, "mcsm_na_scaled" , "mcsm_na_affinity"
#, "consurf_scaled" , "consurf_score"
#, "snap2_scaled" , "snap2_score"
#, "provean_scaled" , "provean_score"
)
all_colnames$`colnames(df3)`[grep("outcome", all_colnames$`colnames(df3)`)]
outcome_cols_aff = c("duet_outcome"
, "deepddg_outcome"
, "ddg_dynamut2_outcome"
, "foldx_outcome"
#, "ddg_foldx", "foldx_scaled"
, "ligand_outcome"
, "mmcsm_lig_outcome"
, "mcsm_ppi2_outcome"
, "mcsm_na_outcome"
# consurf outcome doesn't exist
#,"provean_outcome"
#,"snap2_outcome"
)
#===================
# stability cols
#===================
raw_cols_stability = c("duet_stability_change"
, "deepddg"
, "ddg_dynamut2"
, "ddg_foldx")
scaled_cols_stability = c("duet_scaled"
, "deepddg_scaled"
, "ddg_dynamut2_scaled"
, "foldx_scaled")
outcome_cols_stability = c("duet_outcome"
, "deepddg_outcome"
, "ddg_dynamut2_outcome"
, "foldx_outcome")
#===================
# affinity cols
#===================
raw_cols_affinity = c("ligand_affinity_change"
, "mmcsm_lig"
, "mcsm_ppi2_affinity"
, "mcsm_na_affinity")
scaled_cols_affinity = c("affinity_scaled"
, "mmcsm_lig_scaled"
, "mcsm_ppi2_scaled"
, "mcsm_na_scaled" )
outcome_cols_affinity = c( "ligand_outcome"
, "mmcsm_lig_outcome"
, "mcsm_ppi2_outcome"
, "mcsm_na_outcome")
#===================
# conservation cols
#===================
# raw_cols_conservation = c("consurf_score"
# , "snap2_score"
# , "provean_score")
#
# scaled_cols_conservation = c("consurf_scaled"
# , "snap2_scaled"
# , "provean_scaled")
#
# # CANNOT strictly be used, as categories are not identical with conssurf missing altogether
# outcome_cols_conservation = c("provean_outcome"
# , "snap2_outcome"
# #consurf outcome doesn't exist
# )
###########################################################
cols_to_consider = colnames(df3)[colnames(df3)%in%c(common_cols
, scaled_cols
, outcome_cols)]
, raw_cols_stability
, scaled_cols_stability
, outcome_cols_stability)]
cols_to_extract = cols_to_consider[cols_to_consider%in%c(common_cols
, outcome_cols)]
, outcome_cols_stability)]
##############################################################
#####################
# Ensemble stability
# Ensemble stability: outcome_cols_stability
#####################
# extract outcome cols and map numeric values to the categories
# Destabilising == 0, and stabilising == 1, so rescaling can let -1 be destabilising
df3_plot = df3[, cols_to_extract]
# assign numeric values to outcome
df3_plot[, outcome_cols] <- sapply(df3_plot[, outcome_cols]
df3_plot[, outcome_cols_stability] <- sapply(df3_plot[, outcome_cols_stability]
, function(x){ifelse(x == "Destabilising", 0, 1)})
table(df3$duet_outcome)
table(df3_plot$duet_outcome)
@ -111,7 +142,7 @@ table(df3_plot$duet_outcome)
# column to average: ens_stability
#=====================================
cols_to_average = which(colnames(df3_plot)%in%outcome_cols)
cols_to_average = which(colnames(df3_plot)%in%outcome_cols_stability)
# ensemble average across predictors
df3_plot$ens_stability = rowMeans(df3_plot[,cols_to_average])