From a14fc4dc33b8064a2fb1891f7110f83f772e0d6f Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Fri, 11 Sep 2020 16:07:23 +0100
Subject: [PATCH] added extreme_muts.R

---
 scripts/plotting/extreme_muts.R  | 108 +++++++++++++++++++++++++++++++
 scripts/plotting/output_tables.R |   4 ++
 2 files changed, 112 insertions(+)
 create mode 100644 scripts/plotting/extreme_muts.R

diff --git a/scripts/plotting/extreme_muts.R b/scripts/plotting/extreme_muts.R
new file mode 100644
index 0000000..b29b34c
--- /dev/null
+++ b/scripts/plotting/extreme_muts.R
@@ -0,0 +1,108 @@
+#!/usr/bin/env Rscript  
+#########################################################
+# TASK: producing boxplots for dr and other muts
+
+#########################################################
+#=======================================================================
+# working dir and loading libraries
+getwd()
+setwd("~/git/LSHTM_analysis/scripts/plotting")
+getwd()
+
+#source("Header_TT.R")
+library(ggplot2)
+library(data.table)
+library(dplyr)
+
+#=========
+# Input
+#=========
+#source("combining_dfs_plotting.R")
+
+# FIXME: add a separate script to add foldx values and others
+source("output_tables.R")
+rm(df, merged_df3_short, df_output)
+
+#===============================================================
+df_comp = df_ordered[!is.na(df_ordered$af),]
+
+#%%%%%%%%%%%%%%%%%%%%%
+# REASSIGNMENT
+df = df_comp
+#%%%%%%%%%%%%%%%%%%%%%
+
+cols_all_muts_table = c("mutationinformation"
+                        , "mutation_info"
+                        , "af"
+                        , "af_percent"
+
+                        , "or_mychisq"
+
+                        , "pval_fisher"
+                        , "or_kin"
+   
+                        , "pwald_kin"
+                        , "duet_stability_change"
+                        , "duet_outcome"
+                        , "ligand_distance"
+                        , "ligand_affinity_change"
+                        , "ligand_outcome"
+                        , "ddg"
+                        , "foldx_outcome"
+                        , "asa"
+                        , "rsa"
+                        , "kd_values"
+                        , "rd_values")
+
+df = df[,cols_all_muts_table]
+#===============================================================
+
+#Most Frequent mutation 
+
+mf = df[df$af_percent == max(df$af_percent), ]
+mf
+
+# highest OR
+hor = df[df$or_mychisq == max(df$or_mychisq), ]
+hor
+
+
+# Most Destabilising for protein stability (DUET)
+df_d = df[df$duet_outcome == "Destabilising",]
+
+hd_duet = df_d[df_d$duet_stability_change == min(df_d$duet_stability_change), ]
+hd_duet
+
+# Most Stabilising for protein stability (DUET)
+df_s = df[df$duet_outcome == "Stabilising",]
+hs_duet = df_s[df_s$duet_stability_change == max(df_s$duet_stability_change), ]
+hs_duet
+
+# Closest Destabilising for protein stability
+close_d = df_d[order(df_d$ligand_distance, df_d$duet_stability_change),]
+
+# Closest Stabilising for protein stability
+close_s = df_s[order(df_s$ligand_distance, df_s$duet_stability_change),]
+
+
+#===============
+# ligand affinity: filtered
+#================
+df_lig = df[df$ligand_distance<10,]
+
+df_d_lig = df_lig[df_lig$ligand_outcome == "Destabilising",]
+hd_lig= df_d_lig[df_d_lig$ligand_affinity_change == min(df_d_lig$ligand_affinity_change), ]
+hd_lig
+
+
+df_s_lig = df[df$ligand_outcome == "Stabilising",]
+hs_lig= df_s_lig[df_s_lig$ligand_affinity_change == max(df_s_lig$ligand_affinity_change), ]
+hs_lig
+
+
+# Closest Destabilising for ligand affintiy
+close_d_lig = df_d_lig[order(df_d_lig$ligand_distance, df_d_lig$ligand_affinity_change),]
+
+# Closest Stabilising for ligand affinity
+close_s_lig = df_s_lig[order(df_s_lig$ligand_distance, df_s_lig$ligand_affinity_change),]
+
diff --git a/scripts/plotting/output_tables.R b/scripts/plotting/output_tables.R
index 9eb9b7d..0a15176 100644
--- a/scripts/plotting/output_tables.R
+++ b/scripts/plotting/output_tables.R
@@ -253,3 +253,7 @@ cat("\nOutput table (csv) written:", outfile_all_muts_table
 
 # clear excess variables
 
+rm(check_colnames, c1, c2, cols_all_muts_table
+   , cols_mut_landscape, all_muts_table, mut_landscape_data, my_max, my_min, my_pretty_colnames
+   , na_count, na_count_df2, na_count_df3, outfile_all_muts_table, outfile_mut_landscape_data)
+