changes made to combining_dfs_plotting.R
This commit is contained in:
parent
c6d1260f74
commit
2aec79af31
9 changed files with 258 additions and 126 deletions
|
|
@ -7,6 +7,7 @@
|
|||
# install.packages("gplots", dependencies = TRUE)
|
||||
# library(gplots)
|
||||
#}
|
||||
require("getopt", quietly = TRUE) # cmd parse arguments
|
||||
|
||||
if (!require("tidyverse")) {
|
||||
install.packages("tidyverse", dependencies = TRUE)
|
||||
|
|
|
|||
|
|
@ -10,15 +10,66 @@ setwd("~/git/LSHTM_analysis/scripts/plotting")
|
|||
getwd()
|
||||
|
||||
source("Header_TT.R")
|
||||
#library(ggplot2)
|
||||
#library(data.table)
|
||||
#library(dplyr)
|
||||
source("../functions/plotting_globals.R")
|
||||
source("../functions/plotting_data.R")
|
||||
source("../functions/combining_dfs_plotting.R")
|
||||
###########################################################
|
||||
# command line args
|
||||
#********************
|
||||
drug = 'streptomycin'
|
||||
gene = 'gid'
|
||||
|
||||
#===========
|
||||
# input
|
||||
#===========
|
||||
source("combining_dfs_plotting.R")
|
||||
#---------------------
|
||||
# call: import_dirs()
|
||||
#---------------------
|
||||
import_dirs(drug, gene)
|
||||
|
||||
#---------------------------
|
||||
# call: plotting_data()
|
||||
#---------------------------
|
||||
if (!exists("infile_params") && exists("gene")){
|
||||
#if (!is.character(infile_params) && exists("gene")){
|
||||
#in_filename_params = paste0(tolower(gene), "_all_params.csv")
|
||||
in_filename_params = paste0(tolower(gene), "_comb_afor.csv") # part combined for gid
|
||||
infile_params = paste0(outdir, "/", in_filename_params)
|
||||
cat("\nInput file for mcsm comb data not specified, assuming filename: ", infile_params, "\n")
|
||||
}
|
||||
|
||||
# Input 1: read <gene>_comb_afor.csv
|
||||
pd_df = plotting_data(infile_params)
|
||||
my_df_u = pd_df[[1]] # this forms one of the input for combining_dfs_plotting()
|
||||
|
||||
#--------------------------------
|
||||
# call: combining_dfs_plotting()
|
||||
#--------------------------------
|
||||
if (!exists("infile_metadata") && exists("gene")){
|
||||
#if (!is.character(infile_params) && exists("gene")){{
|
||||
in_filename_metadata = paste0(tolower(gene), "_metadata.csv") # part combined for gid
|
||||
infile_metadata = paste0(outdir, "/", in_filename_metadata)
|
||||
cat("\nInput file for gene metadata not specified, assuming filename: ", infile_metadata, "\n")
|
||||
}
|
||||
|
||||
# Input 2: read <gene>_meta data.csv
|
||||
cat("\nReading meta data file:", infile_metadata)
|
||||
|
||||
gene_metadata <- read.csv(infile_metadata
|
||||
, stringsAsFactors = F
|
||||
, header = T)
|
||||
|
||||
all_plot_dfs = combining_dfs_plotting(my_df_u
|
||||
, gene_metadata
|
||||
, lig_dist_colname = 'ligand_distance'
|
||||
, lig_dist_cutoff = 10)
|
||||
|
||||
#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]]
|
||||
#merged_df2_lig = all_plot_dfs[[5]]
|
||||
#merged_df3_lig = all_plot_dfs[[6]]
|
||||
#===========
|
||||
# output
|
||||
#===========
|
||||
|
|
@ -32,12 +83,6 @@ plot_logo_combined_labelled = paste0(plotdir,"/", logo_combined_labelled)
|
|||
# REASSIGNMENT
|
||||
my_df = merged_df3
|
||||
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||||
|
||||
# clear excess variables
|
||||
rm(merged_df2, merged_df2_comp, merged_df2_lig, merged_df2_comp_lig
|
||||
, merged_df3_comp, merged_df3_comp_lig
|
||||
, my_df_u, my_df_u_lig, merged_df3_lig)
|
||||
|
||||
colnames(my_df)
|
||||
str(my_df)
|
||||
|
||||
|
|
@ -166,8 +211,8 @@ p3 = p2 +
|
|||
theme(legend.position = "bottom"
|
||||
#, legend.title = element_blank()
|
||||
, legend.title = element_text("Amino acid properties", size = 20)
|
||||
, legend.text = element_text( size = 20)
|
||||
, axis.text.x = element_text(size = 20, angle = 90)
|
||||
, legend.text = element_text(size = 20)
|
||||
, axis.text.x = element_text(size = 16, angle = 90)
|
||||
, axis.text.y = element_blank()
|
||||
, axis.title.y = element_blank()
|
||||
, axis.title.x = element_text(size = 22))+
|
||||
|
|
@ -237,7 +282,7 @@ position_or = as.numeric(colnames(wide_df_or))
|
|||
#============================================
|
||||
# custom height (OR) logo plot: yayy works
|
||||
logo_or = ggseqlogo(wide_df_or, method="custom", seq_type="aa") + ylab("my custom height") +
|
||||
theme(axis.text.x = element_text(size = 16
|
||||
theme(axis.text.x = element_text(size = 15
|
||||
, angle = 90
|
||||
, hjust = 1
|
||||
, vjust = 0.4)
|
||||
|
|
|
|||
|
|
@ -10,14 +10,66 @@ setwd("~/git/LSHTM_analysis/scripts/plotting")
|
|||
getwd()
|
||||
|
||||
source("Header_TT.R")
|
||||
#library(ggplot2)
|
||||
#library(data.table)
|
||||
#library(dplyr)
|
||||
source("../functions/plotting_globals.R")
|
||||
source("../functions/plotting_data.R")
|
||||
source("../functions/combining_dfs_plotting.R")
|
||||
###########################################################
|
||||
# command line args
|
||||
#********************
|
||||
drug = 'streptomycin'
|
||||
gene = 'gid'
|
||||
|
||||
#===========
|
||||
# input
|
||||
#===========
|
||||
source("combining_dfs_plotting.R")
|
||||
#---------------------
|
||||
# call: import_dirs()
|
||||
#---------------------
|
||||
import_dirs(drug, gene)
|
||||
|
||||
#---------------------------
|
||||
# call: plotting_data()
|
||||
#---------------------------
|
||||
if (!exists("infile_params") && exists("gene")){
|
||||
#if (!is.character(infile_params) && exists("gene")){
|
||||
#in_filename_params = paste0(tolower(gene), "_all_params.csv")
|
||||
in_filename_params = paste0(tolower(gene), "_comb_afor.csv") # part combined for gid
|
||||
infile_params = paste0(outdir, "/", in_filename_params)
|
||||
cat("\nInput file for mcsm comb data not specified, assuming filename: ", infile_params, "\n")
|
||||
}
|
||||
|
||||
# Input 1: read <gene>_comb_afor.csv
|
||||
pd_df = plotting_data(infile_params)
|
||||
my_df_u = pd_df[[1]] # this forms one of the input for combining_dfs_plotting()
|
||||
|
||||
#--------------------------------
|
||||
# call: combining_dfs_plotting()
|
||||
#--------------------------------
|
||||
if (!exists("infile_metadata") && exists("gene")){
|
||||
#if (!is.character(infile_params) && exists("gene")){{
|
||||
in_filename_metadata = paste0(tolower(gene), "_metadata.csv") # part combined for gid
|
||||
infile_metadata = paste0(outdir, "/", in_filename_metadata)
|
||||
cat("\nInput file for gene metadata not specified, assuming filename: ", infile_metadata, "\n")
|
||||
}
|
||||
|
||||
# Input 2: read <gene>_meta data.csv
|
||||
cat("\nReading meta data file:", infile_metadata)
|
||||
|
||||
gene_metadata <- read.csv(infile_metadata
|
||||
, stringsAsFactors = F
|
||||
, header = T)
|
||||
|
||||
all_plot_dfs = combining_dfs_plotting(my_df_u
|
||||
, gene_metadata
|
||||
, lig_dist_colname = 'ligand_distance'
|
||||
, lig_dist_cutoff = 10)
|
||||
|
||||
#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]]
|
||||
#merged_df2_lig = all_plot_dfs[[5]]
|
||||
#merged_df3_lig = all_plot_dfs[[6]]
|
||||
|
||||
#===========
|
||||
# output
|
||||
|
|
@ -32,12 +84,6 @@ plot_logo_multiple_muts = paste0(plotdir,"/", logo_multiple_muts)
|
|||
# REASSIGNMENT
|
||||
my_df = merged_df3
|
||||
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||||
|
||||
# clear excess variables
|
||||
rm(merged_df2, merged_df2_comp, merged_df2_lig, merged_df2_comp_lig
|
||||
, merged_df3_comp, merged_df3_comp_lig
|
||||
, my_df_u, my_df_u_lig, merged_df3_lig)
|
||||
|
||||
colnames(my_df)
|
||||
str(my_df)
|
||||
|
||||
|
|
@ -117,7 +163,7 @@ p0
|
|||
p1 = p0 + theme(legend.position = "none"
|
||||
, legend.title = element_blank()
|
||||
, legend.text = element_text(size = 20)
|
||||
, axis.text.x = element_text(size = 20, angle = 90)
|
||||
, axis.text.x = element_text(size = 17, angle = 90)
|
||||
, axis.text.y = element_blank())
|
||||
p1
|
||||
|
||||
|
|
@ -138,7 +184,6 @@ rownames(tab_wt)
|
|||
|
||||
#**************
|
||||
# Plot 2: wild_type logo
|
||||
|
||||
#**************
|
||||
# sanity check: MUST BE TRUE
|
||||
|
||||
|
|
@ -164,8 +209,8 @@ p3 = p2 +
|
|||
theme(legend.position = "bottom"
|
||||
#, legend.title = element_blank()
|
||||
, legend.title = element_text("Amino acid properties", size = 20)
|
||||
, legend.text = element_text( size = 20)
|
||||
, axis.text.x = element_text(size = 20, angle = 90)
|
||||
, legend.text = element_text(size = 20)
|
||||
, axis.text.x = element_text(size = 17, angle = 90)
|
||||
, axis.text.y = element_blank()
|
||||
, axis.title.x = element_text(size = 22))+
|
||||
|
||||
|
|
|
|||
45
scripts/plotting/logo_plot.R
Normal file → Executable file
45
scripts/plotting/logo_plot.R
Normal file → Executable file
|
|
@ -15,9 +15,36 @@ source("../functions/combining_dfs_plotting.R")
|
|||
###########################################################
|
||||
# command line args
|
||||
#********************
|
||||
drug = 'streptomycin'
|
||||
gene = 'gid'
|
||||
#drug = 'streptomycin'
|
||||
#gene = 'gid'
|
||||
#********************
|
||||
# !!!FUTURE TODO!!!
|
||||
# Can pass additional params of output/plot dir by user.
|
||||
# Not strictly required for my workflow since it is optimised
|
||||
# to have a streamlined input/output flow without filename worries.
|
||||
#********************
|
||||
spec = matrix(c(
|
||||
"drug" , "d", 1, "character",
|
||||
"gene" , "g", 1, "character",
|
||||
"data_file1" , "fa", 2, "character",
|
||||
"data_file2" , "fb", 2, "character"
|
||||
), byrow = TRUE, ncol = 4)
|
||||
|
||||
opt = getopt(spec)
|
||||
|
||||
#FIXME: detect if script running from cmd, then set these
|
||||
drug = opt$drug
|
||||
gene = opt$gene
|
||||
infile_params = opt$data_file1
|
||||
infile_metadata = opt$data_file2
|
||||
|
||||
# hardcoding when not using cmd
|
||||
#drug = "streptomycin"
|
||||
#gene = "gid"
|
||||
|
||||
if(is.null(drug)|is.null(gene)) {
|
||||
stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
|
||||
}
|
||||
#===========
|
||||
# input
|
||||
#===========
|
||||
|
|
@ -29,8 +56,8 @@ import_dirs(drug, gene)
|
|||
#---------------------------
|
||||
# call: plotting_data()
|
||||
#---------------------------
|
||||
if (!exists("infile_params") && exists("gene")){
|
||||
#if (!is.character(infile_params) && exists("gene")){
|
||||
#if (!exists("infile_params") && exists("gene")){
|
||||
if (!is.character(infile_params) && exists("gene")){
|
||||
#in_filename_params = paste0(tolower(gene), "_all_params.csv")
|
||||
in_filename_params = paste0(tolower(gene), "_comb_afor.csv") # part combined for gid
|
||||
infile_params = paste0(outdir, "/", in_filename_params)
|
||||
|
|
@ -38,14 +65,15 @@ if (!exists("infile_params") && exists("gene")){
|
|||
}
|
||||
|
||||
# Input 1: read <gene>_comb_afor.csv
|
||||
pd_df = plotting_data(infile_params)
|
||||
my_df = read.csv(infile_params, header = T)
|
||||
pd_df = plotting_data(my_df)
|
||||
my_df_u = pd_df[[1]] # this forms one of the input for combining_dfs_plotting()
|
||||
|
||||
#--------------------------------
|
||||
# call: combining_dfs_plotting()
|
||||
#--------------------------------
|
||||
if (!exists("infile_metadata") && exists("gene")){
|
||||
#if (!is.character(infile_params) && exists("gene")){{
|
||||
#if (!exists("infile_metadata") && exists("gene")){
|
||||
if (!is.character(infile_params) && exists("gene")){
|
||||
in_filename_metadata = paste0(tolower(gene), "_metadata.csv") # part combined for gid
|
||||
infile_metadata = paste0(outdir, "/", in_filename_metadata)
|
||||
cat("\nInput file for gene metadata not specified, assuming filename: ", infile_metadata, "\n")
|
||||
|
|
@ -63,7 +91,7 @@ all_plot_dfs = combining_dfs_plotting(my_df_u
|
|||
, lig_dist_colname = 'ligand_distance'
|
||||
, lig_dist_cutoff = 10)
|
||||
|
||||
merged_df2 = all_plot_dfs[[1]]
|
||||
#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]]
|
||||
|
|
@ -146,6 +174,7 @@ wide_df_or <- logo_data_or %>% spread(position, or_mychisq, fill = 0.0)
|
|||
|
||||
wide_df_or = as.matrix(wide_df_or)
|
||||
rownames(wide_df_or) = wide_df_or[,1]
|
||||
dim(wide_df_or)
|
||||
wide_df_or = wide_df_or[,-1]
|
||||
str(wide_df_or)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue