added corr data to get_plotting_dfs.R and generate corr plots

This commit is contained in:
Tanushree Tunstall 2021-06-28 17:25:45 +01:00
parent 2993ab722a
commit a7d26412e5
4 changed files with 252 additions and 19 deletions

View file

@ -61,12 +61,6 @@ all_plot_dfs = combining_dfs_plotting(my_df_u
, lig_dist_colname = 'ligand_distance'
, lig_dist_cutoff = 10)
cat(paste0("Directories imported:"
, "\ndatadir:", datadir
, "\nindir:", indir
@ -110,7 +104,6 @@ df_lig = merged_df2_lig
#======================
# adding log cols
#======================
df_ps$log10_or_mychisq = log10(df_ps$or_mychisq)
df_ps$neglog_pval_fisher = -log10(df_ps$pval_fisher)
@ -119,9 +112,9 @@ df_ps$neglog_pwald_kin = -log10(df_ps$pwald_kin)
#df_ps$mutation_info_labels = ifelse(df_ps$mutation_info == dr_muts_col, 1, 0)
#===========================
#===============================
# Data for Correlation plots:PS
#===========================
#===============================
# subset data to generate pairwise correlations
cols_to_select = c("mutationinformation"
, "duet_scaled"
@ -136,7 +129,7 @@ cols_to_select = c("mutationinformation"
, "or_kin"
, "neglog_pwald_kin"
, "af"
, "af_kin"
#, "af_kin"
, "duet_outcome"
, drug)
@ -176,9 +169,9 @@ offset = 1
corr_ps_df2 = corr_data_ps[start:end]
head(corr_ps_df2)
#-----------------
#--------------------------
# short_df ps: merged_df3
#-----------------
#--------------------------
corr_ps_df3 = corr_ps_df2[!duplicated(corr_ps_df2$Mutation),]
na_or = sum(is.na(corr_ps_df3$`Log (OR)`))
@ -194,9 +187,9 @@ check2 = nrow(corr_ps_df3) - na_adj_or
#}
################################################################################################
#===========================
#=================================
# Data for Correlation plots: LIG
#===========================
#=================================
table(df_lig$ligand_outcome)
df_lig$log10_or_mychisq = log10(df_lig$or_mychisq)
@ -258,7 +251,6 @@ offset = 1
corr_lig_df2 = corr_data_lig[start:end]
head(corr_lig_df2)
#-----------------
# short_df lig: merged_df3_lig
#-----------------