fixed cmd running script problem for logo plots
This commit is contained in:
parent
552c5e77aa
commit
ca2315523d
14 changed files with 206 additions and 748 deletions
66
scripts/plotting/logo_combined.R
Normal file → Executable file
66
scripts/plotting/logo_combined.R
Normal file → Executable file
|
|
@ -16,8 +16,32 @@ 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
|
||||
|
|
@ -25,13 +49,13 @@ gene = 'gid'
|
|||
#---------------------
|
||||
# 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 +63,23 @@ if (!exists("infile_params") && exists("gene")){
|
|||
}
|
||||
|
||||
# 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()
|
||||
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[[2]]
|
||||
|
||||
#--------------------------------
|
||||
# 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 +90,8 @@ 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
|
||||
#===========
|
||||
|
|
@ -157,7 +179,7 @@ p0 = ggseqlogo(tab_mt
|
|||
, limits = c(0, max_mult_mut))
|
||||
|
||||
|
||||
p0
|
||||
#p0
|
||||
|
||||
# further customisation
|
||||
p1 = p0 + theme(axis.text.x = element_text(size = 16
|
||||
|
|
@ -167,7 +189,7 @@ p1 = p0 + theme(axis.text.x = element_text(size = 16
|
|||
, axis.text.y = element_blank()
|
||||
, legend.position = "none")
|
||||
#, axis.text.y = element_text(size = 20))
|
||||
p1
|
||||
#p1
|
||||
|
||||
#==============
|
||||
# matrix for wild type
|
||||
|
|
@ -204,7 +226,7 @@ p2 = ggseqlogo(tab_wt
|
|||
#theme_logo() +
|
||||
scale_x_discrete(breaks = 1:ncol(tab_wt)
|
||||
, labels = colnames(tab_wt))
|
||||
p2
|
||||
#p2
|
||||
|
||||
# further customise
|
||||
p3 = p2 +
|
||||
|
|
@ -219,7 +241,7 @@ p3 = p2 +
|
|||
|
||||
labs(x= "Wild-type Position")
|
||||
|
||||
p3
|
||||
#p3
|
||||
#======================================================================
|
||||
# logo with OR
|
||||
#=======================================================================
|
||||
|
|
@ -302,7 +324,7 @@ logo_or = ggseqlogo(wide_df_or, method="custom", seq_type="aa") + ylab("my custo
|
|||
xlab("Position") +
|
||||
ylab("Odds Ratio")
|
||||
|
||||
logo_or
|
||||
#logo_or
|
||||
########################################################################
|
||||
|
||||
#=============================
|
||||
|
|
@ -321,4 +343,4 @@ OutPlot2 = cowplot::plot_grid(logo_or, p1, p3
|
|||
, label_size = 25)
|
||||
|
||||
print(OutPlot2)
|
||||
dev.off()
|
||||
#dev.off()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue