updated logo plot data to source from combining_df_plotting.R

scripts/plotting/logo_plot.R

@@ -1,71 +1,30 @@
-#=======================================================================
+#!/usr/bin/env Rscript  
-# Task: To generate a logo plot  or bar plot but coloured 
+#########################################################
-# aa properties.
+# TASK: producing boxplots for dr and other muts
-# step1: read mcsm file and OR file
-# step2: plot wild type positions
-# step3: plot mutants per position coloured by aa properties
-# step4: make the size of the letters/bars prop to OR if you can!
 
-# useful links
+#########################################################
-# https://stackoverflow.com/questions/5438474/plotting-a-sequence-logo-using-ggplot2
-# https://omarwagih.github.io/ggseqlogo/
-# https://kkdey.github.io/Logolas-pages/workflow.html
-# A new sequence logo plot to highlight enrichment and depletion.
-#    https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6288878/
-
-#very good: http://www.cbs.dtu.dk/biotools/Seq2Logo-2.0/
 #=======================================================================
-#%% specify curr dir
+# working dir and loading libraries
 getwd()
-setwd("~/git/LSHTM_analysis/plotting_test/")
+setwd("~/git/LSHTM_analysis/scripts/plotting")
 getwd()
-#=======================================================================
-#%% load packages
 
-# header file
+source("Header_TT.R")
-header_dir = "~/git/LSHTM_analysis/"
+#library(ggplot2)
-source(paste0(header_dir, "/", "my_header.R"))
+#library(data.table)
-#=======================================================================
+#library(dplyr)
-#%% variable assignment: input and output paths & filenames
-drug = "pyrazinamide"
-gene = "pncA"
-gene_match = paste0(gene,"_p.")
-cat(gene_match)
-
-#===========
-# data dir
-#===========
-datadir = paste0("~/git/Data")
 
 #===========
 # input
 #===========
-# source R script "combining_two_df.R"
+source("combining_dfs_plotting.R")
-#indir = paste0(datadir, "/", drug, "/", "output") # reading files
-indir = "../meta_data_analysis" # sourcing R script
-in_filename = "combining_df_ps.R"
-infile = paste0(indir, "/", in_filename)
-cat(paste0("Input is a R script: ", "\"", infile, "\"")
-    , "\n========================================================")
 
 #===========
 # output
 #===========
-# 1) lineage dist of all muts
-outdir = paste0("~/git/Data", "/", drug, "/", "output/plots") #same as indir
-#cat("Output dir: ", outdir, "\n")
-#file_type = ".svg"
-#out_filename1 = paste0(tolower(gene), "_lineage_dist_ps", file_type) 
-#outfile1 = paste0(outdir, "/", out_filename1)
-#cat(paste0("Output plot1 :", outfile1)
-#    , "\n========================================================")
 
-#%% end of variable assignment for input and output files
+logo_plot = "logo_plot.svg"
-#=======================================================================
+plot_logo_plot = paste0(plotdir,"/", logo_plot)
-##%% read input file
-cat("Reading input file(sourcing R script):", in_filename)
-
-source(infile)
 
 #==========================
 # This will return:
@@ -205,6 +164,7 @@ ggseqlogo(wide_df_logor, method="custom", seq_type="aa") + ylab("my custom heigh
 library(Logolas)
 
 # data was pnca_msa.txt
+#FIXME: generate this file 
 
 seqs = read.csv("~/git//Data/pyrazinamide/snp_seqsfile.txt"
                 , header = FALSE