#source("~/git/LSHTM_analysis/config/pnca.R") #source("~/git/LSHTM_analysis/config/alr.R") #source("~/git/LSHTM_analysis/config/gid.R") #source("~/git/LSHTM_analysis/config/embb.R") #source("~/git/LSHTM_analysis/config/katg.R") source("~/git/LSHTM_analysis/config/rpob.R") source("~/git/LSHTM_analysis/my_header.R") ######################################################### # TASK: Generate averaged affinity values # across all affinity tools for a given structure # as applicable... ######################################################### #======= # output #======= outdir_images = paste0("~/git/Writing/thesis/images/results/", tolower(gene)) #OutFile1 outfile_mean_aff = paste0(outdir_images, "/", tolower(gene) , "_mean_affinity_all.csv") print(paste0("Output file:", outfile_mean_aff)) #OutFile2 outfile_mean_aff_priorty = paste0(outdir_images, "/", tolower(gene) , "_mean_affinity_priority.csv") print(paste0("Output file:", outfile_mean_aff_priorty)) #%%=============================================================== #============= # Input #============= df3_filename = paste0("~/git/Data/", drug, "/output/", tolower(gene), "_merged_df3.csv") df3 = read.csv(df3_filename) length(df3$mutationinformation) # mut_info checks table(df3$mutation_info) table(df3$mutation_info_orig) table(df3$mutation_info_labels_orig) # used in plots and analyses table(df3$mutation_info_labels) # different, and matches dst_mode table(df3$dst_mode) # create column based on dst mode with different colname table(is.na(df3$dst)) table(is.na(df3$dst_mode)) #=============== # Create column: sensitivity mapped to dst_mode #=============== df3$sensitivity = ifelse(df3$dst_mode == 1, "R", "S") table(df3$sensitivity) length(unique((df3$mutationinformation))) all_colnames = as.data.frame(colnames(df3)) common_cols = c("mutationinformation" , "X5uhc_position" , "X5uhc_offset" , "position" , "dst_mode" , "mutation_info_labels" , "sensitivity" , "ligand_distance" , "interface_dist") all_colnames$`colnames(df3)`[grep("scaled", all_colnames$`colnames(df3)`)] all_colnames$`colnames(df3)`[grep("outcome", all_colnames$`colnames(df3)`)] #=================== # 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 , raw_cols_affinity , scaled_cols_affinity , outcome_cols_affinity , raw_cols_stability , scaled_cols_stability , outcome_cols_stability )] cols_to_extract = cols_to_consider[cols_to_consider%in%c(common_cols #, raw_cols_affinity , scaled_cols_stability , scaled_cols_affinity)] df3_plot = df3[, cols_to_extract] # FIXME: ADD distance to NA when SP replies DistCutOff_colnames = c("ligand_distance", "interface_dist") DistCutOff = 10 #df3_affinity_filtered = df3_plot[ (df3_plot$ligand_distance<10 | df3_plot$interface_dist <10),] df3_affinity_filtered = df3_plot[ (df3_plot$ligand_distance<10 & df3_plot$interface_dist <10),] c0u = unique(df3_affinity_filtered$position) length(c0u) foo = df3_affinity_filtered[df3_affinity_filtered$ligand_distance<10,] bar = df3_affinity_filtered[df3_affinity_filtered$interface_dist<10,] wilcox.test(foo$mmcsm_lig_scaled~foo$sensitivity) wilcox.test(foo$mmcsm_lig~foo$sensitivity) wilcox.test(foo$affinity_scaled~foo$sensitivity) wilcox.test(foo$ligand_affinity_change~foo$sensitivity) wilcox.test(bar$mcsm_na_scaled~bar$sensitivity) wilcox.test(bar$mcsm_na_affinity~bar$sensitivity) wilcox.test(bar$mcsm_ppi2_scaled~bar$sensitivity) wilcox.test(bar$mcsm_ppi2_affinity~bar$sensitivity) ############################################################## df = df3_affinity_filtered sum(is.na(df)) df2 = na.omit(df) # Apply na.omit function gene_dist_cols = colnames(df2)[colnames(df2)%in%DistCutOff_colnames] gene_aff_cols = colnames(df2)[colnames(df2)%in%scaled_cols_affinity] gene_stab_cols = colnames(df2)[colnames(df2)%in%scaled_cols_stability] sel_cols = c("mutationinformation", "position", gene_stab_cols, gene_dist_cols, gene_aff_cols) df3 = df2[, sel_cols] give_col=function(x,y,df=df3){ df[df$position==x,y] } for (i in unique(df3$position) ){ #print(i) biggest = max(abs(give_col(i,gene_aff_cols))) df3[df3$position==i,'abs_max_effect'] = biggest df3[df3$position==i,'effect_type']= names( give_col(i,gene_aff_cols)[which( abs( give_col(i,gene_aff_cols) ) == biggest, arr.ind=T )[, "col"]]) effect_name = unique(df3[df3$position==i,'effect_type']) # get index/rowname for value of max effect, and then use it to get the original sign # here #df3[df3$position==i,c(effect_name)] #which(abs(df3[df3$position==i,c('position',effect_name)][effect_name])==biggest, arr.ind=T) ind = rownames(which(abs(df3[df3$position==i ,c('position', effect_name)][effect_name])== biggest , arr.ind=T)) df3[df3$position==i,'effect_sign'] = sign(df3[effect_name][ind,]) } #%%============================================================ # output write.csv(combined_df, outfile_mean_ens_st_aff , row.names = F) cat("Finished writing file:\n" , outfile_mean_ens_st_aff , "\nNo. of rows:", nrow(combined_df) , "\nNo. of cols:", ncol(combined_df)) # end of script #===============================================================