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

changes made to combining_dfs_plotting.R

Browse source
This commit is contained in:
Tanushree Tunstall 2021-06-23 16:15:15 +01:00
parent c6d1260f74
commit 2aec79af31
9 changed files with 258 additions and 126 deletions
Download patch file Download diff file Expand all files Collapse all files

45
scripts/plotting/logo_plot.R Normal file → Executable file
View 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)