modified bp with option for adding stats and boxplplots. Moved old one to redundant
This commit is contained in:
parent
c8e21b928c
commit
2c65bb25d8
8 changed files with 443 additions and 102 deletions
|
|
@ -3,12 +3,6 @@
|
|||
#########################################################
|
||||
#lib_loc = "/usr/local/lib/R/site-library")
|
||||
|
||||
#if (!require("gplots")) {
|
||||
# install.packages("gplots", dependencies = TRUE)
|
||||
# library(gplots)
|
||||
#}
|
||||
require(extrafont)
|
||||
|
||||
require("getopt", quietly = TRUE) # cmd parse arguments
|
||||
|
||||
if (!require("tidyverse")) {
|
||||
|
|
@ -16,9 +10,23 @@ if (!require("tidyverse")) {
|
|||
library(tidyverse)
|
||||
}
|
||||
|
||||
if (!require("ggplot2")) {
|
||||
install.packages("ggplot2", dependencies = TRUE)
|
||||
library(ggplot2)
|
||||
# if (!require("ggplot2")) {
|
||||
# install.packages("ggplot2", dependencies = TRUE)
|
||||
# library(ggplot2)
|
||||
# }
|
||||
|
||||
# if (!require ("dplyr")){
|
||||
# install.packages("dplyr")
|
||||
# library(dplyr)
|
||||
# }
|
||||
|
||||
# Install
|
||||
#if(!require(devtools)) install.packages("devtools")
|
||||
#devtools::install_github("kassambara/ggcorrplot")
|
||||
|
||||
if (!require ("ggbeeswarm")){
|
||||
install.packages("ggbeeswarm")
|
||||
library(ggbeeswarm)
|
||||
}
|
||||
|
||||
if (!require("plotly")) {
|
||||
|
|
@ -101,11 +109,6 @@ if (!require ("psych")){
|
|||
library(psych)
|
||||
}
|
||||
|
||||
if (!require ("dplyr")){
|
||||
install.packages("dplyr")
|
||||
library(dplyr)
|
||||
}
|
||||
|
||||
if (!require ("compare")){
|
||||
install.packages("compare")
|
||||
library(compare)
|
||||
|
|
@ -116,31 +119,25 @@ if (!require ("arsenal")){
|
|||
library(arsenal)
|
||||
}
|
||||
|
||||
if(!require(ggseqlogo)){
|
||||
install.packages("ggseqlogo")
|
||||
library(ggseqlogo)
|
||||
}
|
||||
|
||||
#if (!requireNamespace("BiocManager", quietly = TRUE))
|
||||
# install.packages("BiocManager")
|
||||
|
||||
#BiocManager::install("Logolas")
|
||||
library("Logolas")
|
||||
|
||||
#install.packages("ggseqlogo")
|
||||
library(ggseqlogo)
|
||||
|
||||
|
||||
####TIDYVERSE
|
||||
# Install
|
||||
#if(!require(devtools)) install.packages("devtools")
|
||||
#devtools::install_github("kassambara/ggcorrplot")
|
||||
|
||||
library(ggcorrplot)
|
||||
|
||||
|
||||
###for PDB files
|
||||
#install.packages("bio3d")
|
||||
# for PDB files
|
||||
if(!require(bio3d)){
|
||||
install.packages("bio3d")
|
||||
library(bio3d)
|
||||
}
|
||||
|
||||
#install.packages("protr")
|
||||
library(protr)
|
||||
if(!require(protr)){
|
||||
install.packages("protr")
|
||||
library(protr)
|
||||
}
|
||||
|
||||
#if (!requireNamespace("BiocManager", quietly = TRUE))
|
||||
# install.packages("BiocManager")
|
||||
|
||||
#BiocManager::install("Logolas")
|
||||
library("Logolas")
|
||||
|
|
@ -86,8 +86,10 @@ all_plot_dfs = combining_dfs_plotting(my_df_u
|
|||
, lig_dist_colname = LigDist_colname
|
||||
, lig_dist_cutoff = LigDist_cutoff)
|
||||
|
||||
merged_df2 = all_plot_dfs[[1]]
|
||||
merged_df3 = all_plot_dfs[[2]]
|
||||
merged_df2 = all_plot_dfs[[1]]
|
||||
merged_df3 = all_plot_dfs[[2]]
|
||||
merged_df2_comp = all_plot_dfs[[3]]
|
||||
merged_df3_comp = all_plot_dfs[[4]]
|
||||
#======================================================================
|
||||
# read other files
|
||||
infilename_dynamut = paste0("~/git/Data/", drug, "/output/dynamut_results/", gene
|
||||
|
|
@ -98,10 +100,15 @@ infilename_dynamut2 = paste0("~/git/Data/", drug, "/output/dynamut_results/dyna
|
|||
|
||||
infilename_mcsm_na = paste0("~/git/Data/", drug, "/output/mcsm_na_results/", gene
|
||||
, "_complex_mcsm_na_norm.csv")
|
||||
|
||||
|
||||
infilename_mcsm_f_snps <- paste0("~/git/Data/", drug, "/output/", gene
|
||||
, "_mcsm_formatted_snps.csv")
|
||||
|
||||
dynamut_df = read.csv(infilename_dynamut)
|
||||
dynamut2_df = read.csv(infilename_dynamut2)
|
||||
mcsm_na_df = read.csv(infilename_mcsm_na)
|
||||
mcsm_f_snps = read.csv(infilename_mcsm_f_snps, header = F)
|
||||
names(mcsm_f_snps) = "mutationinformation"
|
||||
|
||||
####################################################################
|
||||
# Data for subcols barplot (~heatmpa)
|
||||
|
|
@ -430,11 +437,17 @@ if (nrow(corr_ps_df3) == nrow(merged_df3) && nrow(merged_df3_comp) == check1) {
|
|||
, "\nGot: ", check1)
|
||||
}
|
||||
|
||||
|
||||
rm(foo)
|
||||
####################################################################
|
||||
# Data for DM OM Plots: Long format dfs
|
||||
####################################################################
|
||||
source("other_plots_data.R")
|
||||
|
||||
########################################################################
|
||||
# End of script
|
||||
########################################################################
|
||||
rm(foo)
|
||||
|
||||
cat("\n===================================================\n"
|
||||
cat("\n######################################################\n"
|
||||
, "\nSuccessful: get_plotting_dfs.R worked!"
|
||||
, "\n====================================================")
|
||||
, "\n###################################################\n")
|
||||
|
|
|
|||
|
|
@ -3,10 +3,9 @@
|
|||
# TASK: producing boxplots for dr and other muts
|
||||
|
||||
#########################################################
|
||||
#=======================================================================
|
||||
# working dir and loading libraries
|
||||
# getwd()
|
||||
setwd("~/git/LSHTM_analysis/scripts/plotting")
|
||||
# setwd("~/git/LSHTM_analysis/scripts/plotting")
|
||||
# getwd()
|
||||
|
||||
# make cmd
|
||||
|
|
@ -14,21 +13,21 @@ setwd("~/git/LSHTM_analysis/scripts/plotting")
|
|||
# drug = "streptomycin"
|
||||
# gene = "gid"
|
||||
|
||||
source("get_plotting_dfs.R")
|
||||
# source("get_plotting_dfs.R")
|
||||
#=======================================================================
|
||||
# MOVE TO COMBINE or singular file for deepddg
|
||||
#
|
||||
# cols_to_select = c("mutation", "mutationinformation"
|
||||
# , "wild_type", "position", "mutant_type"
|
||||
# , "mutation_info")
|
||||
#
|
||||
# merged_df3_short = merged_df3[, cols_to_select]
|
||||
|
||||
cols_to_select = c("mutation", "mutationinformation"
|
||||
, "wild_type", "position", "mutant_type"
|
||||
, "mutation_info")
|
||||
|
||||
merged_df3_short = merged_df3[, cols_to_select]
|
||||
|
||||
infilename_mcsm_f_snps <- paste0("~/git/Data/", drug, "/output/", gene
|
||||
, "_mcsm_formatted_snps.csv")
|
||||
|
||||
mcsm_f_snps<- read.csv(infilename_mcsm_f_snps, header = F)
|
||||
names(mcsm_f_snps) <- "mutationinformation"
|
||||
# infilename_mcsm_f_snps <- paste0("~/git/Data/", drug, "/output/", gene
|
||||
# , "_mcsm_formatted_snps.csv")
|
||||
#
|
||||
# mcsm_f_snps<- read.csv(infilename_mcsm_f_snps, header = F)
|
||||
# names(mcsm_f_snps) <- "mutationinformation"
|
||||
|
||||
# write merged_df3 to generate structural figure on chimera
|
||||
#write.csv(merged_df3_short, "merged_df3_short.csv")
|
||||
|
|
@ -52,11 +51,11 @@ my_min = min(merged_df3$deepddg_scaled); my_min
|
|||
my_max = max(merged_df3$deepddg_scaled); my_max
|
||||
|
||||
if (my_min == -1 && my_max == 1){
|
||||
cat("PASS: DeepDDG successfully scaled b/w -1 and 1"
|
||||
cat("\nPASS: DeepDDG successfully scaled b/w -1 and 1"
|
||||
#, "\nProceeding with assigning deep outcome category")
|
||||
, "\n")
|
||||
}else{
|
||||
cat("FAIL: could not scale DeepDDG ddg values"
|
||||
cat("\nFAIL: could not scale DeepDDG ddg values"
|
||||
, "Aborting!")
|
||||
}
|
||||
|
||||
|
|
@ -100,7 +99,7 @@ if (merging_cols == "mutationinformation") {
|
|||
cols_check <- c(c1, c2, c3, c4)
|
||||
expected_cols = n_comb_cols - ( length(cols_check) - 1)
|
||||
if (all(cols_check)){
|
||||
cat("\nStage 2:Proceeding with merging dfs:\n")
|
||||
cat("\nStage 2: Proceeding with merging dfs:\n")
|
||||
comb_df <- Reduce(inner_join, list(cols_mcsm_df
|
||||
, cols_mcsm_na_df
|
||||
, dynamut_df
|
||||
|
|
@ -115,12 +114,13 @@ if (merging_cols == "mutationinformation") {
|
|||
|
||||
}
|
||||
}
|
||||
names(comb_df_s)
|
||||
#names(comb_df_s)
|
||||
cat("\n!!!IT GOT TO HERE!!!!")
|
||||
#=======================================================================
|
||||
fact_cols = colnames(comb_df_s)[grepl( "_outcome|_info", colnames(comb_df_s) )]
|
||||
fact_cols
|
||||
lapply(comb_df_s[, fact_cols], class)
|
||||
comb_df_s[,fact_cols] <- lapply(comb_df_s[,cols],as.factor)
|
||||
comb_df_s[, fact_cols] <- lapply(comb_df_s[, fact_cols], as.factor)
|
||||
|
||||
if (any(lapply(comb_df_s[, fact_cols], class) == "character")){
|
||||
cat("\nChanging cols to factor")
|
||||
|
|
@ -512,7 +512,6 @@ rm(all_plot_dfs
|
|||
, my_data_snp
|
||||
, my_df
|
||||
, my_df_u
|
||||
, ols_mcsm_df
|
||||
, other_muts
|
||||
, pd_df
|
||||
, subcols_df_ps
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue