updated combining df scripts for duet & lig
This commit is contained in:
parent
d81be80305
commit
954eb88c45
3 changed files with 458 additions and 342 deletions
|
|
@ -1,17 +1,18 @@
|
|||
getwd()
|
||||
setwd("~/git/LSHTM_analysis/mcsm_analysis/pyrazinamide/scripts/")
|
||||
getwd()
|
||||
|
||||
#########################################################
|
||||
# TASK: To combine mcsm and meta data with af and or
|
||||
# by filtering for distance to ligand (<10Ang)
|
||||
# by filtering for distance to ligand (<10Ang).
|
||||
# This script doesn't output anything, but can do if needed.
|
||||
# This script is sourced from other .R scripts for plotting
|
||||
#########################################################
|
||||
getwd()
|
||||
setwd('~/git/LSHTM_analysis/mcsm_analysis/pyrazinamide/scripts/')
|
||||
getwd()
|
||||
|
||||
#########################################################
|
||||
# Installing and loading required packages
|
||||
#########################################################
|
||||
##########################################################
|
||||
# Installing and loading required packages
|
||||
##########################################################
|
||||
|
||||
#source("Header_TT.R")
|
||||
source('Header_TT.R')
|
||||
#require(data.table)
|
||||
#require(arsenal)
|
||||
#require(compare)
|
||||
|
|
@ -22,14 +23,58 @@ getwd()
|
|||
# output of step 4 mcsm_pipeline
|
||||
#################################
|
||||
|
||||
inDir = "~/git/Data/pyrazinamide/input/processed/"
|
||||
inFile = paste0(inDir, "mcsm_complex1_normalised.csv"); inFile
|
||||
#%% variable assignment: input and output paths & filenames
|
||||
drug = 'pyrazinamide'
|
||||
gene = 'pncA'
|
||||
gene_match = paste0(gene,'_p.')
|
||||
cat(gene_match)
|
||||
|
||||
mcsm_data = read.csv(inFile
|
||||
#===========
|
||||
# input
|
||||
#===========
|
||||
# infile1: mCSM data
|
||||
#indir = '~/git/Data/pyrazinamide/input/processed/'
|
||||
indir = paste0('~/git/Data', '/', drug, '/', 'output') # revised {TODO: change in mcsm pipeline}
|
||||
in_filename = 'mcsm_complex1_normalised.csv'
|
||||
infile = paste0(indir, '/', in_filename)
|
||||
cat(paste0('Reading infile1: mCSM output file', ' ', infile) )
|
||||
|
||||
# infile2: gene associated meta data combined with AF and OR
|
||||
#indir: same as above
|
||||
in_filename_comb = paste0(tolower(gene), '_meta_data_with_AFandOR.csv')
|
||||
infile_comb = paste0(indir, '/', in_filename_comb)
|
||||
cat(paste0('Reading infile2: gene associated combined metadata:', infile_comb))
|
||||
|
||||
#===========
|
||||
# output
|
||||
#===========
|
||||
# Uncomment if and when required to output
|
||||
outdir = paste0('~/git/Data', '/', drug, '/', 'output') #same as indir
|
||||
cat('Output dir: ', outdir)
|
||||
#out_filename = paste0(tolower(gene), 'XXX')
|
||||
#outfile = paste0(outdir, '/', out_filename)
|
||||
#cat(paste0('Output file with full path:', outfile))
|
||||
#%% end of variable assignment for input and output files
|
||||
|
||||
#################################
|
||||
# Read file: normalised file
|
||||
# output of step 4 mcsm_pipeline
|
||||
#################################
|
||||
cat('Reading mcsm_data:'
|
||||
, '\nindir: ', indir
|
||||
, '\ninfile_comb: ', in_filename)
|
||||
|
||||
mcsm_data = read.csv(infile
|
||||
, row.names = 1
|
||||
, stringsAsFactors = F
|
||||
, header = T)
|
||||
rm(inDir, inFile)
|
||||
, header = T)
|
||||
|
||||
cat('Read mcsm_data file:'
|
||||
, '\nNo.of rows: ', nrow(mcsm_data)
|
||||
, '\nNo. of cols:', ncol(mcsm_data))
|
||||
|
||||
# clear variables
|
||||
rm(in_filename, infile)
|
||||
|
||||
str(mcsm_data)
|
||||
|
||||
|
|
@ -39,7 +84,7 @@ table(mcsm_data$DUET_outcome); sum(table(mcsm_data$DUET_outcome) )
|
|||
mcsm_data$DUET_outcome[mcsm_data$DUET_outcome=='Stabilizing'] <- 'Stabilising'
|
||||
mcsm_data$DUET_outcome[mcsm_data$DUET_outcome=='Destabilizing'] <- 'Destabilising'
|
||||
|
||||
# checks
|
||||
# checks: should be the same as above
|
||||
table(mcsm_data$DUET_outcome); sum(table(mcsm_data$DUET_outcome) )
|
||||
head(mcsm_data$DUET_outcome); tail(mcsm_data$DUET_outcome)
|
||||
|
||||
|
|
@ -53,6 +98,10 @@ mcsm_data$Lig_outcome[mcsm_data$Lig_outcome=='Destabilizing'] <- 'Destabilising'
|
|||
table(mcsm_data$Lig_outcome); sum(table(mcsm_data$Lig_outcome) )
|
||||
head(mcsm_data$Lig_outcome); tail(mcsm_data$Lig_outcome)
|
||||
|
||||
# muts with opposing effects on protomer and ligand stability
|
||||
# excluded from here as it is redundant.
|
||||
# check 'combining_two_df.R' to refer if required.
|
||||
|
||||
########################### !!! only for mcsm_lig
|
||||
# 4: Filter/subset data
|
||||
# Lig plots < 10Ang
|
||||
|
|
@ -82,57 +131,60 @@ length(unique(mcsm_data2$Mutationinformation))
|
|||
# count Destabilisinga and stabilising
|
||||
table(mcsm_data2$Lig_outcome) #{RESULT: no of mutations within 10Ang}
|
||||
|
||||
#<<<<<<<<<<<<<<<<<<<<<<<<<<<
|
||||
# REASSIGNMENT: so as not to alter the script
|
||||
mcsm_data = mcsm_data2
|
||||
#<<<<<<<<<<<<<<<<<<<<<<<<<<<
|
||||
|
||||
#############################
|
||||
# Extra sanity check:
|
||||
# for mcsm_lig ONLY
|
||||
# Dis_lig_Ang should be <10
|
||||
#############################
|
||||
|
||||
if (max(mcsm_data$Dis_lig_Ang) < 10){
|
||||
if (max(mcsm_data2$Dis_lig_Ang) < 10){
|
||||
print ("Sanity check passed: lig data is <10Ang")
|
||||
}else{
|
||||
print ("Error: data should be filtered to be within 10Ang")
|
||||
}
|
||||
|
||||
#!!!!!!!!!!!!!!!!!!!!!
|
||||
# REASSIGNMENT: so as not to alter the script
|
||||
mcsm_data = mcsm_data2
|
||||
#!!!!!!!!!!!!!!!!!!!!!
|
||||
# clear variables
|
||||
rm(mcsm_data2)
|
||||
|
||||
# count na in each column
|
||||
na_count = sapply(mcsm_data, function(y) sum(length(which(is.na(y))))); na_count
|
||||
|
||||
head(mcsm_data$Mutationinformation)
|
||||
mcsm_data[mcsm_data$Mutationinformation=="Q10P",]
|
||||
mcsm_data[mcsm_data$Mutationinformation=="L4S",]
|
||||
|
||||
# sort by Mutationinformation
|
||||
mcsm_data = mcsm_data[order(mcsm_data$Mutationinformation),]
|
||||
head(mcsm_data$Mutationinformation)
|
||||
|
||||
# check
|
||||
mcsm_data[grep("Q10P", mcsm_data$Mutationinformation),]
|
||||
mcsm_data[grep("A102T", mcsm_data$Mutationinformation),]
|
||||
|
||||
orig_col = ncol(mcsm_data)
|
||||
# get freq count of positions and add to the df
|
||||
setDT(mcsm_data)[, occurrence := .N, by = .(Position)]
|
||||
setDT(mcsm_data)[, occurrence := .N, by = .(Position)]
|
||||
|
||||
cat('Added 1 col: position frequency to see which posn has how many muts'
|
||||
, '\nNo. of cols now', ncol(mcsm_data)
|
||||
, '\nNo. of cols before: ', orig_col)
|
||||
|
||||
pos_count_check = data.frame(mcsm_data$Position, mcsm_data$occurrence)
|
||||
|
||||
###########################
|
||||
# 2: Read file: meta data with AFandOR
|
||||
###########################
|
||||
cat('Reading combined meta data and AFandOR file:'
|
||||
, '\nindir: ', indir
|
||||
, '\ninfile_comb: ', in_filename_comb)
|
||||
|
||||
inDir = "~/git/Data/pyrazinamide/input/processed/"
|
||||
inFile2 = paste0(inDir, "meta_data_with_AFandOR.csv"); inFile2
|
||||
|
||||
meta_with_afor <- read.csv(inFile2
|
||||
meta_with_afor <- read.csv(infile_comb
|
||||
, stringsAsFactors = F
|
||||
, header = T)
|
||||
|
||||
cat('Read mcsm_data file:'
|
||||
, '\nNo.of rows: ', nrow(meta_with_afor)
|
||||
, '\nNo. of cols:', ncol(meta_with_afor))
|
||||
|
||||
# clear variables
|
||||
rm(in_filename_comb, infile_comb)
|
||||
|
||||
str(meta_with_afor)
|
||||
|
||||
# sort by Mutationinformation
|
||||
|
|
@ -140,114 +192,45 @@ head(meta_with_afor$Mutationinformation)
|
|||
meta_with_afor = meta_with_afor[order(meta_with_afor$Mutationinformation),]
|
||||
head(meta_with_afor$Mutationinformation)
|
||||
|
||||
# sanity check: should be True for all the mentioned columns
|
||||
#is.numeric(meta_with_afor$OR)
|
||||
na_var = c("AF", "OR", "pvalue", "logor", "neglog10pvalue")
|
||||
|
||||
c1 = NULL
|
||||
for (i in na_var){
|
||||
print(i)
|
||||
c0 = is.numeric(meta_with_afor[,i])
|
||||
c1 = c(c0, c1)
|
||||
if ( all(c1) ){
|
||||
print("Sanity check passed: These are all numeric cols")
|
||||
} else{
|
||||
print("Error: Please check your respective data types")
|
||||
}
|
||||
}
|
||||
|
||||
# If OR, and P value are not numeric, then convert to numeric and then count
|
||||
# else they will say 0
|
||||
|
||||
# NOW count na in each column: if you did it before, then
|
||||
# OR and Pvalue column would say 0 na since these were not numeric
|
||||
na_count = sapply(meta_with_afor, function(y) sum(length(which(is.na(y))))); na_count
|
||||
str(na_count)
|
||||
|
||||
# compare if the No of "NA" are the same for all these cols
|
||||
na_len = NULL
|
||||
na_var = c("AF", "OR", "pvalue", "logor", "neglog10pvalue")
|
||||
for (i in na_var){
|
||||
temp = na_count[[i]]
|
||||
na_len = c(na_len, temp)
|
||||
}
|
||||
|
||||
my_nrows = NULL
|
||||
|
||||
for ( i in 1: (length(na_len)-1) ){
|
||||
#print(compare(na_len[i]), na_len[i+1])
|
||||
c = compare(na_len[i], na_len[i+1])
|
||||
if ( c$result ) {
|
||||
my_nrows = na_len[i] }
|
||||
else {
|
||||
print("Error: Please check your numbers")
|
||||
}
|
||||
}
|
||||
|
||||
my_nrows
|
||||
|
||||
#=#=#=#=#=#=#=#=#
|
||||
# COMMENT: AF, OR, pvalue, logor and neglog10pvalue
|
||||
# all have 81 NA, with pyrazinamide with 960
|
||||
# and these are the same 7 ones
|
||||
#=#=#=#=#=#=#=#=#
|
||||
|
||||
# sanity check
|
||||
#which(is.na(meta_with_afor$OR))
|
||||
|
||||
# initialise an empty df with nrows as extracted above
|
||||
na_count_df = data.frame(matrix(vector(mode = 'numeric'
|
||||
# , length = length(na_var)
|
||||
)
|
||||
, nrow = my_nrows
|
||||
# , ncol = length(na_var)
|
||||
))
|
||||
|
||||
# populate the df with the indices of the cols that are NA
|
||||
for (i in na_var){
|
||||
print(i)
|
||||
na_i = which(is.na(meta_with_afor[i]))
|
||||
na_count_df = cbind(na_count_df, na_i)
|
||||
colnames(na_count_df)[which(na_var == i)] <- i
|
||||
}
|
||||
|
||||
# Now compare these indices to ensure these are the same
|
||||
c2 = NULL
|
||||
for ( i in 1: ( length(na_count_df)-1 ) ) {
|
||||
# print(na_count_df[i] == na_count_df[i+1])
|
||||
c1 = identical(na_count_df[[i]], na_count_df[[i+1]])
|
||||
c2 = c(c1, c2)
|
||||
if ( all(c2) ) {
|
||||
print("Sanity check passed: The indices for AF, OR, etc are all the same")
|
||||
} else {
|
||||
print ("Error: Please check indices which are NA")
|
||||
}
|
||||
}
|
||||
|
||||
rm( c, c1, c2, i, my_nrows
|
||||
, na_count, na_i, na_len
|
||||
, na_var, temp
|
||||
, na_count_df
|
||||
, pos_count_check )
|
||||
|
||||
###########################
|
||||
# 3:merging two dfs: with NA
|
||||
# 3: merging two dfs: with NA
|
||||
###########################
|
||||
# link col name = 'Mutationinforamtion'
|
||||
cat('Merging dfs with NAs: big df (1-many relationship b/w id & mut)'
|
||||
,'\nlinking col: Mutationinforamtion'
|
||||
,'\nfilename: merged_df2')
|
||||
|
||||
# link col name = Mutationinforamtion
|
||||
head(mcsm_data$Mutationinformation)
|
||||
head(meta_with_afor$Mutationinformation)
|
||||
|
||||
#########
|
||||
# merge 1a: meta data with mcsm
|
||||
# merge 3a: meta data with mcsm
|
||||
#########
|
||||
merged_df2 = merge(x = meta_with_afor
|
||||
, y = mcsm_data
|
||||
, by = "Mutationinformation"
|
||||
,y = mcsm_data
|
||||
, by = 'Mutationinformation'
|
||||
, all.y = T)
|
||||
|
||||
cat('Dim of merged_df2: '
|
||||
, '\nNo. of rows: ', nrow(merged_df2)
|
||||
, '\nNo. of cols: ', ncol(merged_df2))
|
||||
head(merged_df2$Position)
|
||||
|
||||
if(nrow(meta_with_afor) == nrow(merged_df2)){
|
||||
cat('nrow(merged_df2) = nrow (gene associated metadata)'
|
||||
,'\nExpected no. of rows: ',nrow(meta_with_afor)
|
||||
,'\nGot no. of rows: ', nrow(merged_df2))
|
||||
} else{
|
||||
cat('nrow(merged_df2)!= nrow(gene associated metadata)'
|
||||
, '\nExpected no. of rows after merge: ', nrow(meta_with_afor)
|
||||
, '\nGot no. of rows: ', nrow(merged_df2)
|
||||
, '\nFinding discrepancy')
|
||||
merged_muts_u = unique(merged_df2$Mutationinformation)
|
||||
meta_muts_u = unique(meta_with_afor$Mutationinformation)
|
||||
# find the index where it differs
|
||||
unique(meta_muts_u[! meta_muts_u %in% merged_muts_u])
|
||||
}
|
||||
|
||||
# sort by Position
|
||||
head(merged_df2$Position)
|
||||
merged_df2 = merged_df2[order(merged_df2$Position),]
|
||||
|
|
@ -255,13 +238,12 @@ head(merged_df2$Position)
|
|||
|
||||
merged_df2v2 = merge(x = meta_with_afor
|
||||
,y = mcsm_data
|
||||
, by = "Mutationinformation"
|
||||
, by = 'Mutationinformation'
|
||||
, all.x = T)
|
||||
|
||||
#!=!=!=!=!=!=!=!
|
||||
# COMMENT: used all.y since position 186 is not part of the struc,
|
||||
# hence doesn't have a mcsm value
|
||||
# but 186 is associated with with mutation
|
||||
# but 186 is associated with mutation
|
||||
#!=!=!=!=!=!=!=!
|
||||
|
||||
# should be False
|
||||
|
|
@ -271,8 +253,12 @@ table(merged_df2$Position%in%merged_df2v2$Position)
|
|||
rm(merged_df2v2)
|
||||
|
||||
#########
|
||||
# merge 1b:remove duplicate mutation information
|
||||
# merge 3b:remove duplicate mutation information
|
||||
#########
|
||||
cat('Merging dfs with NAs: small df (removing duplicate muts)'
|
||||
,'\nCannot trust lineage info from this'
|
||||
,'\nlinking col: Mutationinforamtion'
|
||||
,'\nfilename: merged_df3')
|
||||
|
||||
#==#=#=#=#=#=#
|
||||
# Cannot trust lineage, country from this df as the same mutation
|
||||
|
|
@ -280,69 +266,60 @@ rm(merged_df2v2)
|
|||
# but this should be good for the numerical corr plots
|
||||
#=#=#=#=#=#=#=
|
||||
merged_df3 = merged_df2[!duplicated(merged_df2$Mutationinformation),]
|
||||
head(merged_df3$Position) ; tail(merged_df3$Position) # should be sorted
|
||||
head(merged_df3$Position); tail(merged_df3$Position) # should be sorted
|
||||
|
||||
# sanity checks
|
||||
# nrows of merged_df3 should be the same as the nrows of mcsm_data
|
||||
if(nrow(mcsm_data) == nrow(merged_df3)){
|
||||
print("sanity check: Passed")
|
||||
cat('PASS: No. of rows match with mcsm_data'
|
||||
,'\nExpected no. of rows: ', nrow(mcsm_data)
|
||||
,'\nGot no. of rows: ', nrow(merged_df3))
|
||||
} else {
|
||||
print("Error!: check data, nrows is not as expected")
|
||||
cat('FAIL: No. of rows mismatch'
|
||||
, '\nNo. of rows mcsm_data: ', nrow(mcsm_data)
|
||||
, '\nNo. of rows merged_df3: ', nrow(merged_df3))
|
||||
}
|
||||
|
||||
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
|
||||
# uncomment as necessary
|
||||
# only need to run this if merged_df2v2 i.e non structural pos included
|
||||
#mcsm = mcsm_data$Mutationinformation
|
||||
#my_merged = merged_df3$Mutationinformation
|
||||
|
||||
# find the index where it differs
|
||||
#diff_n = which(!my_merged%in%mcsm)
|
||||
|
||||
#check if it is indeed pos 186
|
||||
#merged_df3[diff_n,]
|
||||
|
||||
# remove this entry
|
||||
#merged_df3 = merged_df3[-diff_n,]
|
||||
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
|
||||
|
||||
###########################
|
||||
# 3b :merging two dfs: without NA
|
||||
# 4: merging two dfs: without NA
|
||||
###########################
|
||||
cat('Merging dfs without any NAs: big df (1-many relationship b/w id & mut)'
|
||||
,'\nlinking col: Mutationinforamtion'
|
||||
,'\nfilename: merged_df2_comp')
|
||||
|
||||
#########
|
||||
# merge 2a:same as merge 1 but excluding NA
|
||||
# merge 4a: same as merge 1 but excluding NA
|
||||
#########
|
||||
merged_df2_comp = merged_df2[!is.na(merged_df2$AF),]
|
||||
merged_df2_comp = merged_df2[!is.na(merged_df2$AF),]
|
||||
#merged_df2_comp = merged_df2[!duplicated(merged_df2$Mutationinformation),]
|
||||
|
||||
cat('Dim of merged_df2_comp: '
|
||||
, '\nNo. of rows: ', nrow(merged_df2_comp)
|
||||
, '\nNo. of cols: ', ncol(merged_df2_comp))
|
||||
|
||||
#########
|
||||
# merge 2b: remove duplicate mutation information
|
||||
# merge 4b: remove duplicate mutation information
|
||||
#########
|
||||
merged_df3_comp = merged_df2_comp[!duplicated(merged_df2_comp$Mutationinformation),]
|
||||
merged_df3_comp = merged_df2_comp[!duplicated(merged_df2_comp$Mutationinformation),]
|
||||
|
||||
# FIXME: add this as a sanity check. I have manually checked!
|
||||
cat('Dim of merged_df3_comp: '
|
||||
, '\nNo. of rows: ', nrow(merged_df3_comp)
|
||||
, '\nNo. of cols: ', ncol(merged_df3_comp))
|
||||
|
||||
# alternate way of deriving merged_df3_comp
|
||||
foo = merged_df3[!is.na(merged_df3$AF),]
|
||||
|
||||
# compare dfs: foo and merged_df3_com
|
||||
all.equal(foo, merged_df3)
|
||||
|
||||
summary(comparedf(foo, merged_df3))
|
||||
|
||||
#=============== end of combining df
|
||||
#clear variables
|
||||
rm(mcsm_data
|
||||
, meta_with_afor
|
||||
, foo)
|
||||
|
||||
#rm(diff_n, my_merged, mcsm)
|
||||
|
||||
#===============end of script
|
||||
|
||||
#=====================
|
||||
#*********************
|
||||
# write_output files
|
||||
#=====================
|
||||
|
||||
# Not required as this is a subset of the "combining_two_df.R" script
|
||||
# Not required as this is a subset of the combining_two_df.R
|
||||
#*************************
|
||||
# clear variables
|
||||
rm(mcsm_data, meta_with_afor, foo, drug, gene, gene_match, indir, merged_muts_u, meta_muts_u, na_count, orig_col, outdir)
|
||||
rm(pos_count_check)
|
||||
#============================= end of script
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue