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

added appendix tables script

Browse source
This commit is contained in:
Tanushree Tunstall 2022-08-13 21:19:19 +01:00
parent d984d283c5
commit 4609757efb
1 changed files with 144 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

144
scripts/plotting/plotting_thesis/appendix_tables.R Normal file
View file

@ -0,0 +1,144 @@
#!/usr/bin/env Rscript
#source("~/git/LSHTM_analysis/config/alr.R")
source("~/git/LSHTM_analysis/config/embb.R")
#source("~/git/LSHTM_analysis/config/katg.R")
#source("~/git/LSHTM_analysis/config/gid.R")
#source("~/git/LSHTM_analysis/config/pnca.R")
#source("~/git/LSHTM_analysis/config/rpob.R")
# get plottting dfs
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
source("~/git/LSHTM_analysis/scripts/plotting/plotting_colnames.R")
#=======
# output
#=======
outdir_images = paste0("~/git/Writing/thesis/images/results/", tolower(gene), "/")
outdir_stats = paste0(outdir_images,"stats/")
###################################################################
# FIXME: ADD distance to NA when SP replies
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
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
, 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'))
####################################
# Appendix: ligand affinity
####################################
df_lig = df3[df3[[LigDist_colname]]<DistCutOff,]
cols_to_output_lig = c("mutationinformation"
, "position"
, LigDist_colname
, "ligand_affinity_change"
, "ligand_outcome"
, "mmcsm_lig"
, "mmcsm_lig_outcome"
, "or_mychisq"
, "p_adj_fdr"
, "signif_fdr")
# counting
Out_df_lig = df_lig[, cols_to_output_lig]
Out_df_ligS = Out_df_lig[order(Out_df_lig$or_mychisq, decreasing = T), ]
delta_symbol = "\u0394"; delta_symbol
Out_df_ligS$or_mychisq = round(Out_df_ligS$or_mychisq,2)
Out_df_ligS$p_adj_fdr = round(Out_df_ligS$p_adj_fdr,2)
Out_df_ligS
colsNames_to_output_lig = c("Mutation"
, "position"
, paste0("Lig-Dist (", angstroms_symbol, ")")
, "mCSM-ligand affinity"
, "mCSM ligand_outcome"
, "mmCSM-ligand affinity"
, "mmCSM ligand_outcome"
, "Odds Ratio"
, "Adj P-value"
, "P-value significance")
colnames(Out_df_ligS) = colsNames_to_output_lig
Out_df_ligS
#--------------------
# write output file: KS test within grpup
#----------------------
Out_ligT = paste0(outdir_stats
, tolower(gene)
, "_lig_muts.csv")
cat("Output of Ligand muts:", Out_ligT )
write.csv(Out_df_ligS, Out_ligT, row.names = FALSE)
########################################################################
####################################
# Appendix: PPi2 affinity
####################################
df_ppi2 = df3[df3[[ppi2Dist_colname]]<DistCutOff,]
cols_to_output_ppi2 = c("mutationinformation"
, "position"
, ppi2Dist_colname
, "mcsm_ppi2_affinity"
, "mcsm_ppi2_outcome"
, "or_mychisq"
, "p_adj_fdr"
, "signif_fdr")
# extract output cols
Out_df_ppi2 = df_ppi2[, cols_to_output_ppi2]
Out_df_ppi2S = Out_df_ppi2[order(Out_df_ppi2$or_mychisq, decreasing = T), ]
delta_symbol = "\u0394"; delta_symbol
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"
, paste0("PPI2-Dist (", angstroms_symbol, ")")
, paste0("mCSM-PPI2 (", delta_symbol, ")")
, "mCSM-PPI2 outcome"
, "Odds Ratio"
, "Adj P-value"
, "P-value significance")
colnames(Out_df_ppi2S) = colsNames_to_output_ppi2
Out_df_ppi2S
#--------------------
# write output file: KS test within grpup
#----------------------
Out_ppi2T = paste0(outdir_stats
, tolower(gene)
, "_ppi2_muts.csv")
cat("Output of PPI2 muts:", Out_ppi2T )
write.csv(Out_df_ppi2S, Out_ppi2T, row.names = FALSE)