From 2acea43bcf2a5d41eb252337f8b4e0caabecba75 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Sun, 14 Aug 2022 12:18:12 +0100
Subject: [PATCH] added maf column in appendix_tables

---
 .../plotting_thesis/appendix_tables.R         | 112 +++++++++----
 scripts/plotting/plotting_thesis/colnames.csv | 156 ------------------
 .../plotting_thesis/colnames_short.csv        |  99 -----------
 3 files changed, 84 insertions(+), 283 deletions(-)
 delete mode 100644 scripts/plotting/plotting_thesis/colnames.csv
 delete mode 100644 scripts/plotting/plotting_thesis/colnames_short.csv

diff --git a/scripts/plotting/plotting_thesis/appendix_tables.R b/scripts/plotting/plotting_thesis/appendix_tables.R
index 0ffe158..0452e5c 100644
--- a/scripts/plotting/plotting_thesis/appendix_tables.R
+++ b/scripts/plotting/plotting_thesis/appendix_tables.R
@@ -23,31 +23,82 @@ geneL_normal  = c("pnca")
 geneL_na      = c("gid", "rpob")
 geneL_ppi2    = c("alr", "embb", "katg", "rpob")
 
-# LigDist_colname # from globals used
-# ppi2Dist_colname #from globals used 
-# naDist_colname #from globals used
+#from plotting_globals()
+LigDist_colname
+ppi2Dist_colname 
+naDist_colname
+
+delta_symbol #delta_symbol = "\u0394"; delta_symbol
+angstroms_symbol
+
+#===========
+# Data used
+#===========
 
 df3 = merged_df3
 
-# Add adjusted P-values
-df3$p_adj_fdr = p.adjust(df3$pval_fisher, method = "fdr")
-df3$signif_fdr = df3$p_adj_fdr
-df3 = dplyr::mutate(df3
+cols_to_output = c("mutationinformation"
+                       , "position"
+                       , affinity_dist_colnames[1]
+                       , "ligand_affinity_change"
+                       , "ligand_outcome"
+                       , "mmcsm_lig"
+                       , "mmcsm_lig_outcome"
+                       , affinity_dist_colnames[2]
+                       , "mcsm_ppi2_affinity"
+                       , "mcsm_ppi2_outcome"
+                       , "maf"
+                       , "or_mychisq"
+                       , "pval_fisher")
+
+cols_to_output
+df3_output = df3[, cols_to_output]
+colnames(df3_output)
+
+#===============================================
+# Add COLS and rounding: adjusted P-values + MAF
+#==============================================
+#-----------------------------
+# adjusted P-values
+#-----------------------------
+# add cols: p_adj_fdr and signif_fdr
+df3_output$p_adj_fdr = p.adjust(df3_output$pval_fisher, method = "fdr")
+df3_output$signif_fdr = df3_output$p_adj_fdr
+df3_output = dplyr::mutate(df3_output
                     , signif_fdr = case_when(signif_fdr == 0.05 ~ "."
                                              , signif_fdr <=0.0001 ~ '****'
                                              , signif_fdr <=0.001 ~ '***'
                                              , signif_fdr <=0.01 ~ '**'
                                              , signif_fdr <0.05 ~ '*'
                                              , TRUE ~ 'ns'))
+# rounding
+df3_output$or_mychisq = round(df3_output$or_mychisq,2)
+df3_output$p_adj_fdr  = round(df3_output$p_adj_fdr,2)
+head(df3_output)
+
+#----------
+# MAF (%)
+#----------
+# add col maf_percent
+df3_output$maf_percent = df3_output$maf*100
+
+# rounding
+df3_output$maf_percent = round(df3_output$maf_percent,2)
+head(df3_output$af); head(df3_output$maf);head(df3_output$maf_percent)
+
+#----------
+# P-value
+#----------
+df3_output$pval_fisher = round(df3_output$pval_fisher,2)
 
 
-
+class(df3_output)
+head(df3_output)
 
 ####################################
 # Appendix: ligand affinity
 ####################################
-df_lig = df3[df3[[LigDist_colname]]<DistCutOff,]
-
+df_lig = df3_output[df3_output[[LigDist_colname]]<DistCutOff,]
 
 cols_to_output_lig = c("mutationinformation"
                    , "position"
@@ -56,20 +107,20 @@ cols_to_output_lig = c("mutationinformation"
                    , "ligand_outcome"
                    , "mmcsm_lig"
                    , "mmcsm_lig_outcome"
+                   , "maf_percent"
                    , "or_mychisq"
+                   , "pval_fisher"
                    , "p_adj_fdr"
                    , "signif_fdr")
-
-# counting
-
+# select cols
 Out_df_lig = df_lig[, cols_to_output_lig]
-Out_df_ligS = Out_df_lig[order(Out_df_lig$or_mychisq, decreasing = T), ]
 
-delta_symbol = "\u0394"; delta_symbol
+# sort df by OR and then MAF: highest OR and highest MAF
+#Out_df_ligS1 = Out_df_lig[order(Out_df_lig$or_mychisq, decreasing = T), ]
+Out_df_ligS = Out_df_lig[order(-Out_df_lig$or_mychisq, Out_df_lig$maf_percent), ]
 
-Out_df_ligS$or_mychisq = round(Out_df_ligS$or_mychisq,2)
-Out_df_ligS$p_adj_fdr = round(Out_df_ligS$p_adj_fdr,2)
-Out_df_ligS
+#head(Out_df_ligS1); tail(Out_df_ligS1)
+head(Out_df_ligS); tail(Out_df_ligS)
 
 colsNames_to_output_lig = c("Mutation"
                    , "position"
@@ -78,12 +129,15 @@ colsNames_to_output_lig = c("Mutation"
                    , "mCSM ligand_outcome"
                    , "mmCSM-ligand affinity"
                    , "mmCSM ligand_outcome"
+                   , paste0("MAF ","(%)")
                    , "Odds Ratio"
-                   , "Adj P-value"
+                   , "P-value"
+                   , "Adjusted P-value"
                    , "P-value significance")
 
 colnames(Out_df_ligS) = colsNames_to_output_lig
-Out_df_ligS
+head(Out_df_ligS)
+
 #--------------------
 # write output file: KS test within grpup
 #----------------------
@@ -99,27 +153,28 @@ write.csv(Out_df_ligS, Out_ligT, row.names = FALSE)
 # Appendix: PPi2 affinity
 ####################################
 
-df_ppi2 = df3[df3[[ppi2Dist_colname]]<DistCutOff,]
-
+# Filtered data
+df_ppi2 = df3_output[df3_output[[ppi2Dist_colname]]<DistCutOff,]
 
+# select cols
 cols_to_output_ppi2 = c("mutationinformation"
                         , "position"
                         , ppi2Dist_colname
                         , "mcsm_ppi2_affinity"
                         , "mcsm_ppi2_outcome"
+                        , "maf_percent"
                         , "or_mychisq"
+                        , "pval_fisher"
                         , "p_adj_fdr"
                         , "signif_fdr")
 
 # extract output cols
 Out_df_ppi2 = df_ppi2[, cols_to_output_ppi2]
-Out_df_ppi2S = Out_df_ppi2[order(Out_df_ppi2$or_mychisq, decreasing = T), ]
 
-delta_symbol = "\u0394"; delta_symbol
+# sort df by OR and then MAF: Highest OR and Highest MAF
+#Out_df_ppi2S = Out_df_ppi2[order(Out_df_ppi2$or_mychisq, decreasing = T), ]
+Out_df_ppi2S = Out_df_ppi2[order(-Out_df_ppi2$or_mychisq, Out_df_ppi2$maf_percent), ]
 
-Out_df_ppi2S$or_mychisq = round(Out_df_ppi2S$or_mychisq,2)
-Out_df_ppi2S$p_adj_fdr = round(Out_df_ppi2S$p_adj_fdr,2)
-Out_df_ppi2S
 
 colsNames_to_output_ppi2 = c("Mutation"
                              , "position"
@@ -127,7 +182,8 @@ colsNames_to_output_ppi2 = c("Mutation"
                              , paste0("mCSM-PPI2 (", delta_symbol, ")")
                              , "mCSM-PPI2 outcome"
                              , "Odds Ratio"
-                             , "Adj P-value"
+                             , "P-value"
+                             , "Adjusted P-value"
                              , "P-value significance")
 
 colnames(Out_df_ppi2S) = colsNames_to_output_ppi2
diff --git a/scripts/plotting/plotting_thesis/colnames.csv b/scripts/plotting/plotting_thesis/colnames.csv
deleted file mode 100644
index f974081..0000000
--- a/scripts/plotting/plotting_thesis/colnames.csv
+++ /dev/null
@@ -1,156 +0,0 @@
-"colnames(merged_df3)"
-"mutationinformation"
-"id"
-"sample"
-"lineage"
-"sublineage"
-"country_code"
-"drtype"
-"ethambutol"
-"mutation"
-"drug_name"
-"mutation_info"
-"mutation_info_orig"
-"mutation_info_v1"
-"wild_type"
-"mutant_type"
-"position"
-"Mut"
-"Mut_copy"
-"index_orig"
-"index_orig_copy"
-"snp_frequency"
-"pos_count"
-"wt_prop_water"
-"mut_prop_water"
-"wt_prop_polarity"
-"mut_prop_polarity"
-"wt_calcprop"
-"mut_calcprop"
-"total_id_ucount"
-"maf"
-"drtype_numeric"
-"drtype_all_vals"
-"drtype_all_names"
-"drtype_multimode"
-"drtype_mode"
-"drtype_max"
-"mutation_info_labels"
-"dm_om_numeric"
-"dm_om_numeric_orig"
-"dst"
-"dst_multimode"
-"dst_mode"
-"mutation_info_labels_v1"
-"mutation_info_labels_orig"
-"lineage_list_all"
-"lineage_count_all"
-"lineage_count_unique"
-"lineage_list_unique"
-"lineage_multimode"
-"chain"
-"ligand_id"
-"ligand_distance"
-"duet_stability_change"
-"duet_outcome"
-"ligand_affinity_change"
-"ligand_outcome"
-"duet_scaled"
-"affinity_scaled"
-"wild_pos"
-"wild_chain_pos"
-"ddg_foldx"
-"contacts"
-"electro_rr"
-"electro_mm"
-"electro_sm"
-"electro_ss"
-"disulfide_rr"
-"disulfide_mm"
-"disulfide_sm"
-"disulfide_ss"
-"hbonds_rr"
-"hbonds_mm"
-"hbonds_sm"
-"hbonds_ss"
-"partcov_rr"
-"partcov_mm"
-"partcov_sm"
-"partcov_ss"
-"vdwclashes_rr"
-"vdwclashes_mm"
-"vdwclashes_sm"
-"vdwclashes_ss"
-"volumetric_rr"
-"volumetric_mm"
-"volumetric_sm"
-"volumetric_ss"
-"foldx_scaled"
-"foldx_outcome"
-"deepddg"
-"deepddg_outcome"
-"deepddg_scaled"
-"asa"
-"rsa"
-"ss"
-"ss_class"
-"kd_values"
-"rd_values"
-"wt_3upper"
-"consurf_score"
-"consurf_scaled"
-"consurf_colour"
-"consurf_colour_rev"
-"consurf_ci_upper"
-"consurf_ci_lower"
-"consurf_ci_colour"
-"consurf_msa_data"
-"consurf_aa_variety"
-"snap2_score"
-"snap2_scaled"
-"snap2_accuracy_pc"
-"snap2_outcome"
-"af"
-"beta_logistic"
-"or_logistic"
-"pval_logistic"
-"se_logistic"
-"zval_logistic"
-"ci_low_logistic"
-"ci_hi_logistic"
-"or_mychisq"
-"log10_or_mychisq"
-"or_fisher"
-"pval_fisher"
-"neglog_pval_fisher"
-"ci_low_fisher"
-"ci_hi_fisher"
-"est_chisq"
-"pval_chisq"
-"ddg_dynamut2"
-"ddg_dynamut2_scaled"
-"ddg_dynamut2_outcome"
-"mcsm_ppi2_affinity"
-"mcsm_ppi2_scaled"
-"mcsm_ppi2_outcome"
-"interface_dist"
-"mut_3upper"
-"seq_offset4pdb"
-"provean_score"
-"provean_outcome"
-"provean_scaled"
-"mmcsm_lig"
-"mmcsm_lig_scaled"
-"mmcsm_lig_outcome"
-"gene_name"
-"pdb_file"
-"lineage_labels"
-"consurf_outcome"
-"sensitivity"
-"foldx_scaled_signC"
-"avg_stability"
-"avg_stability_outcome"
-"avg_stability_scaled"
-"avg_lig_affinity"
-"avg_lig_affinity_outcome"
-"avg_lig_affinity_scaled"
diff --git a/scripts/plotting/plotting_thesis/colnames_short.csv b/scripts/plotting/plotting_thesis/colnames_short.csv
deleted file mode 100644
index bb964e7..0000000
--- a/scripts/plotting/plotting_thesis/colnames_short.csv
+++ /dev/null
@@ -1,99 +0,0 @@
-"mutationinformation"
-"id"
-"lineage"
-"drtype"
-drug
-"mutation"
-"drug_name"
-"mutation_info"
-#"mutation_info_orig"
-#"mutation_info_v1"
-#"wild_type"
-#"mutant_type"
-#"position"
-#"Mut"
-"snp_frequency"
-"pos_count"
-"total_id_ucount"
-"maf"
-"drtype_mode"
-"drtype_max"
-"mutation_info_labels"
-"dst"
-"dst_mode"
-#"mutation_info_labels_v1"
-#"mutation_info_labels_orig"
-"lineage_count_all"
-"lineage_count_unique"
-"chain"
-"ligand_id"
-LigDist_colname
-"duet_stability_change"
-"duet_outcome"
-"ligand_affinity_change"
-"ligand_outcome"
-"duet_scaled"
-"affinity_scaled"
-"wild_pos"
-"wild_chain_pos"
-"ddg_foldx"
-"foldx_scaled"
-"foldx_outcome"
-"deepddg"
-"deepddg_outcome"
-"deepddg_scaled"
-"asa"
-"rsa"
-"ss"
-"ss_class"
-"kd_values"
-"rd_values"
-"wt_3upper"
-"consurf_score"
-"consurf_scaled"
-"consurf_colour"
-"consurf_colour_rev"
-"consurf_ci_upper"
-"consurf_ci_lower"
-"consurf_ci_colour"
-"consurf_msa_data"
-"consurf_aa_variety"
-"snap2_score"
-"snap2_scaled"
-"snap2_accuracy_pc"
-"snap2_outcome"
-"af"
-"or_logistic"
-"pval_logistic"
-"or_mychisq"
-"log10_or_mychisq"
-"or_fisher"
-"pval_fisher"
-"neglog_pval_fisher"
-"ddg_dynamut2"
-"ddg_dynamut2_scaled"
-"ddg_dynamut2_outcome"
-"mcsm_ppi2_affinity"
-"mcsm_ppi2_scaled"
-"mcsm_ppi2_outcome"
-ppi2Dist_colname
-"mut_3upper"
-"seq_offset4pdb"
-"provean_score"
-"provean_outcome"
-"provean_scaled"
-"mmcsm_lig"
-"mmcsm_lig_scaled"
-"mmcsm_lig_outcome"
-"gene_name"
-"pdb_file"
-"lineage_labels"
-"consurf_outcome"
-"sensitivity"
-"foldx_scaled_signC"
-"avg_stability"
-"avg_stability_outcome"
-"avg_stability_scaled"
-"avg_lig_affinity"
-"avg_lig_affinity_outcome"
-"avg_lig_affinity_scaled"