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

repurposing corr_data.R into a function to allow required params to be passed in

Browse source
This commit is contained in:
Tanushree Tunstall 2022-01-29 17:24:15 +00:00
parent 7317156bba
commit 5346431256
4 changed files with 126 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

64
scripts/plotting/corr_data.R
View file

@ -2,6 +2,7 @@
#########################################################
# TASK: Script to format data for corr plots
#########################################################
#library(dplyr)
#=================================================
# Data for Corrplots
@ -12,6 +13,10 @@ cat("\n=========================================="
# use data
#merged_df2
geneL_normal = c("pnca")
geneL_na_dy = c("gid")
geneL_na = c("rpob")
geneL_ppi2 = c("alr", "embb", "katg", "rpob")
#----------------------------
# columns for corr plots:PS
@ -19,11 +24,55 @@ cat("\n=========================================="
# NOTE: you can add mcsm_ppi column as well, and it will only select what it can find!
big_df_colnames = data.frame(names(merged_df2))
corr_cols_select <- c("mutationinformation", drug, "mutation_info_labels"
, "duet_stability_change", "ligand_affinity_change", "ddg_foldx", "asa", "rsa"
, "rd_values", "kd_values", "log10_or_mychisq", "neglog_pval_fisher","af"
, "deepddg", "ddg_dynamut", "ddg_dynamut2", "mcsm_na_affinity"
, "ddg_encom", "dds_encom", "ddg_mcsm", "ddg_sdm", "ddg_duet", "ligand_distance")
core_cols = c("mutationinformation", drug, "mutation_info_labels"
, "duet_stability_change", "ligand_affinity_change", "ddg_foldx", "asa", "rsa"
, "rd_values", "kd_values", "log10_or_mychisq", "neglog_pval_fisher","af"
, "deepddg" , "ddg_dynamut2"
, "consurf_score"
#, "consurf_scaled"
, "snap2_score"
#, "snap2_scaled", "snap2_accuracy_pc"
, "ligand_distance")
if (tolower(gene)%in%geneL_normal){
corr_cols_select = core_cols
}
if (tolower(gene)%in%geneL_na_dy){
additional_cols = c("mcsm_na_affinity"
, "ddg_dynamut"
, "ddg_encom", "dds_encom"
, "ddg_mcsm", "ddg_sdm"
, "ddg_duet"
#, "mcsm_na_scaled"
#, "ddg_dynamut_scaled"
#, "ddg_encom_scaled", "dds_encom_scaled"
#, "ddg_mcsm_scaled", "ddg_sdm_scaled"
#, "ddg_duet_scaled"
)
corr_cols_select = c(core_cols, additional_cols)
}
if (tolower(gene)%in%geneL_na){
additional_cols = c("mcsm_na_affinity"
#, "mcsm_na_scaled"
)
corr_cols_select = c(core_cols, additional_cols)
}
if (tolower(gene)%in%geneL_ppi2){
additional_cols = c("mcsm_ppi2_affinity")
corr_cols_select = c(core_cols, additional_cols)
}
# corr_cols_select <- c("mutationinformation", drug, "mutation_info_labels"
# , "duet_stability_change", "ligand_affinity_change", "ddg_foldx", "asa", "rsa"
# , "rd_values", "kd_values", "log10_or_mychisq", "neglog_pval_fisher","af"
# , "deepddg", "ddg_dynamut", "ddg_dynamut2", "mcsm_na_affinity"
# , "ddg_encom", "dds_encom", "ddg_mcsm", "ddg_sdm", "ddg_duet", "ligand_distance")
#===========================
# Corr data for plots: PS
@ -36,9 +85,8 @@ corr_df_m2 = merged_df2[,colnames(merged_df2)%in%corr_cols_select]
# formatting: some cols
# Add pretty colnames
#-----------------------
corr_df_m2_f <- corr_df_m2 %>%
rename(
DUET = duet_stability_change
corr_df_m2_f <- corr_df_m2 %>% dplyr::rename(
'DUET' = duet_stability_change
, 'mCSM-lig' = ligand_affinity_change
, FoldX = ddg_foldx
, DeepDDG = deepddg