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

saving work on logo plots before finishing

Browse source
This commit is contained in:
Tanushree Tunstall 2021-06-23 16:49:18 +01:00
parent 9d964e84b6
commit 48a85ede0c
2 changed files with 38 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

52
scripts/plotting/logo_multiple_muts.R Normal file → Executable file
View file

@ -16,22 +16,45 @@ 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
if(is.null(drug)|is.null(gene)) {
stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
}
#===========
# input
#===========
#---------------------
# call: import_dirs()
#---------------------
import_dirs(drug, gene)
import_dirs(drug_name = drug, gene_name = 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")){ # when running as cmd
#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)
@ -39,21 +62,23 @@ if (!exists("infile_params") && exists("gene")){
}
# Input 1: read <gene>_comb_afor.csv
pd_df = plotting_data(infile_params)
cat("\nReading mcsm combined data file: ", infile_params)
mcsm_df = read.csv(infile_params, header = T)
pd_df = plotting_data(mcsm_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_metadata) && exists("gene")){ # when running as cmd
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)
cat("\nReading meta data file: ", infile_metadata)
gene_metadata <- read.csv(infile_metadata
, stringsAsFactors = F
@ -64,12 +89,7 @@ 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_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]]
merged_df3 = all_plot_dfs[[2]]
#===========
# output
@ -93,7 +113,7 @@ c1 = unique(my_df$position)
nrow(my_df)
# get freq count of positions so you can subset freq<1
#require(data.table)
require(data.table)
setDT(my_df)[, mut_pos_occurrence := .N, by = .(position)] #189, 36
table(my_df$position)