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

saving recovered combining_dfs_plotting.R after editing

Browse source
This commit is contained in:
Tanushree Tunstall 2020-09-10 15:52:22 +01:00
parent 68050a93b4
commit 65841e4f5b
1 changed files with 39 additions and 130 deletions
Download patch file Download diff file Expand all files Collapse all files

167
scripts/plotting/combining_dfs_plotting.R
View file

@ -6,7 +6,6 @@
# 2) <gene>_meta_data.csv # 2) <gene>_meta_data.csv
# Output: # Output:
# 1) muts with opposite effects on stability
# 2) large combined df including NAs for AF, OR,etc # 2) large combined df including NAs for AF, OR,etc
# Dim: same no. of rows as gene associated meta_data_with_AFandOR # Dim: same no. of rows as gene associated meta_data_with_AFandOR
# 3) small combined df including NAs for AF, OR, etc. # 3) small combined df including NAs for AF, OR, etc.
@ -36,18 +35,18 @@ source("plotting_data.R")
# my_df_u_lig # my_df_u_lig
# dup_muts # dup_muts
cat(paste0("Directories imported:" cat("Directories imported:"
, "\ndatadir:", datadir , "\ndatadir:", datadir
, "\nindir:", indir , "\nindir:", indir
, "\noutdir:", outdir , "\noutdir:", outdir
, "\nplotdir:", plotdir)) , "\nplotdir:", plotdir)
cat(paste0("Variables imported:" cat("Variables imported:"
, "\ndrug:", drug , "\ndrug:", drug
, "\ngene:", gene , "\ngene:", gene
, "\ngene_match:", gene_match , "\ngene_match:", gene_match
, "\nLength of upos:", length(upos) , "\nLength of upos:", length(upos)
, "\nAngstrom symbol:", angstroms_symbol)) , "\nAngstrom symbol:", angstroms_symbol)
# clear excess variable # clear excess variable
rm(my_df, upos, dup_muts) rm(my_df, upos, dup_muts)
@ -58,24 +57,6 @@ rm(my_df, upos, dup_muts)
#in_file1: output of plotting_data.R #in_file1: output of plotting_data.R
# my_df_u # my_df_u
# quick checks
head(my_df_u[, c("mutation")])
cols_to_extract = c("mutationinformation", "mutation", "or_mychisq", "or_kin", "af", "af_kin")
foo = my_df_u[, colnames(my_df_u)%in% cols_to_extract]
table(which(is.na(my_df_u$af_kin)) == which(is.na(my_df_u$af)))
baz = read.csv(file.choose())
baz = cbind(my_df_u$mutation, my_df_u$or_mychisq, bar$mutation, bar$or_mychisq)
baz = as.data.frame(baz)
colnames(baz) = c("my_df_u_muts", "my_df_u_or", "real_muts", "real_or")
sum(is.na(baz$my_df_u_or)) == sum(is.na(my_df_u$or_mychisq))
cat("\nNo. of with NA in or_mychisq:", sum(is.na(my_df_u$or_mychisq))
,"\nNo. of NA in or_kin:" , sum(is.na(my_df_u$or_kin)))
# infile 2: gene associated meta data # infile 2: gene associated meta data
#in_filename_gene_metadata = paste0(tolower(gene), "_meta_data_with_AFandOR.csv") #in_filename_gene_metadata = paste0(tolower(gene), "_meta_data_with_AFandOR.csv")
@ -145,67 +126,6 @@ if (identical(sum(is.na(my_df_u$or_kin))
str(gene_metadata) str(gene_metadata)
# change category of ambiguos mutations
table(gene_metadata$mutation_info)
cols_to_extract2 = c("mutationinformation", "mutation", "mutation_info")
foo2 = gene_metadata[, colnames(gene_metadata)%in% cols_to_extract2]
dr_muts = foo2[foo2$mutation_info == dr_muts_col,]
other_muts = foo2[foo2$mutation_info == other_muts_col,]
common_muts = dr_muts[dr_muts$mutation%in%other_muts$mutation,]
#write.csv(common_muts, 'common_muts.csv')
rm(common_muts)
# FIXME read properly
# "ambiguous_mut_names.csv"
#"pnca_p.gly108arg", "pnca_p.gly132ala", "pnca_p.val180phe"
ambiguous_muts = read.csv(file.choose())
ambiguous_muts_names = ambiguous_muts$mutation
common_muts_all = gene_metadata[gene_metadata$mutation%in%ambiguous_muts_names,]
if (gene_metadata$mutation_info[gene_metadata$mutation%in%ambiguous_muts_names] == other_muts_col){
print('change me')
}
# make a copy
gene_metadata2 = gene_metadata
table(gene_metadata$mutation_info)
count_check = as.data.frame(cbind(table(gene_metadata$mutationinformation, gene_metadata$mutation_info)))
#count_check$checks = ifelse(count_check$dr_mutations_pyrazinamide&&count_check$other_mutations_pyrazinamide>0, "ambi", "pass")
table(count_check$checks)
poo = c("V180F", "G132A", "D49G")
poo2 = count_check[rownames(count_check)%in%poo,]
poo2[[dr_muts_col]]&& poo2[[other_muts_col]]>0
poo2$checks = ifelse(all(poo2$checkspoo2[[dr_muts_col]]&& poo2[[other_muts_col]])>0, "ambi", "pass")
# remove common_muts_all
ids = gene_metadata$mutation%in%common_muts_all$mutation; table(ids)
gene_metadata_unambiguous = gene_metadata2[!ids,]
# sanity checks: should be true
table(gene_metadata_unambiguous$mutation%in%common_muts_all$mutation)[[1]] == nrow(gene_metadata_unambiguous)
nrow(gene_metadata_unambiguous) + nrow(common_muts_all) == nrow(gene_metadata)
# correct common muts
table(common_muts_all$mutation_info)
common_muts_all$mutation_info = as.factor(common_muts_all$mutation_info)
# change the other_muts to dr_muts
common_muts_all$mutation_info[common_muts_all$mutation_info==other_muts_col] <- dr_muts_col
table(common_muts_all$mutation_info)
common_muts_all$mutation_info = factor(common_muts_all$mutation_info)
table(common_muts_all$mutation_info)
# add it back to
gene_metadata2 = rbind(gene_metadata_unambiguous, common_muts_all)
nrow(gene_metadata2) == nrow(gene_metadata)
################################################################### ###################################################################
# combining: PS # combining: PS
################################################################### ###################################################################
@ -326,54 +246,44 @@ cat("Merging dfs without any NAs: big df (1-many relationship b/w id & mut)"
,"\nlinking col: Mutationinforamtion" ,"\nlinking col: Mutationinforamtion"
,"\nfilename: merged_df2_comp") ,"\nfilename: merged_df2_comp")
if ( identical( which(is.na(merged_df2$af)), which(is.na(merged_df2$af_kin))) ){ na_count_df2 = sum(is.na(merged_df2$af))
print("mychisq and kin ors missing indices match. Procedding with omitting NAs") merged_df2_comp = merged_df2[!is.na(merged_df2$af),]
na_count_df2 = sum(is.na(merged_df2$af)) # sanity check: no +-1 gymnastics
merged_df2_comp = merged_df2[!is.na(merged_df2$af),] cat("Checking nrows in merged_df2_comp")
# sanity check: no +-1 gymnastics if(nrow(merged_df2_comp) == (nrow(merged_df2) - na_count_df2)){
cat("Checking nrows in merged_df2_comp") cat("\nPASS: No. of rows match"
if(nrow(merged_df2_comp) == (nrow(merged_df2) - na_count_df2)){ ,"\nDim of merged_df2_comp: "
cat("\nPASS: No. of rows match" ,"\nExpected no. of rows: ", nrow(merged_df2) - na_count_df2
,"\nDim of merged_df2_comp: " , "\nNo. of rows: ", nrow(merged_df2_comp)
,"\nExpected no. of rows: ", nrow(merged_df2) - na_count_df2 , "\nNo. of cols: ", ncol(merged_df2_comp))
, "\nNo. of rows: ", nrow(merged_df2_comp) }else{
, "\nNo. of cols: ", ncol(merged_df2_comp))
}else{
cat("FAIL: No. of rows mismatch" cat("FAIL: No. of rows mismatch"
,"\nExpected no. of rows: ", nrow(merged_df2) - na_count_df2 ,"\nExpected no. of rows: ", nrow(merged_df2) - na_count_df2
,"\nGot no. of rows: ", nrow(merged_df2_comp)) ,"\nGot no. of rows: ", nrow(merged_df2_comp))
}
}else{
print("Index mismatch for mychisq and kin ors. Aborting NA ommission")
} }
#========================= #=========================
# Merge4: merged_df3_comp # Merge4: merged_df3_comp
# same as merge 2 but excluding NAs from ORs, etc or # same as merge 2 but excluding NAs from ORs, etc or
# remove duplicate mutation information # remove duplicate mutation information
#========================= #=========================
if ( identical( which(is.na(merged_df3$af)), which(is.na(merged_df3$af_kin))) ){ na_count_df3 = sum(is.na(merged_df3$af))
print("mychisq and kin ors missing indices match. Procedding with omitting NAs") #merged_df3_comp = merged_df3_comp[!duplicated(merged_df3_comp$mutationinformation),] # a way
na_count_df3 = sum(is.na(merged_df3$af)) merged_df3_comp = merged_df3[!is.na(merged_df3$af),] # another way
#merged_df3_comp = merged_df3_comp[!duplicated(merged_df3_comp$mutationinformation),] # a way cat("Checking nrows in merged_df3_comp")
merged_df3_comp = merged_df3[!is.na(merged_df3$af),] # another way if(nrow(merged_df3_comp) == (nrow(merged_df3) - na_count_df3)){
cat("Checking nrows in merged_df3_comp") cat("\nPASS: No. of rows match"
if(nrow(merged_df3_comp) == (nrow(merged_df3) - na_count_df3)){ ,"\nDim of merged_df3_comp: "
cat("\nPASS: No. of rows match" ,"\nExpected no. of rows: ", nrow(merged_df3) - na_count_df3
,"\nDim of merged_df3_comp: " , "\nNo. of rows: ", nrow(merged_df3_comp)
,"\nExpected no. of rows: ", nrow(merged_df3) - na_count_df3 , "\nNo. of cols: ", ncol(merged_df3_comp))
, "\nNo. of rows: ", nrow(merged_df3_comp) }else{
, "\nNo. of cols: ", ncol(merged_df3_comp)) cat("FAIL: No. of rows mismatch"
}else{ ,"\nExpected no. of rows: ", nrow(merged_df3) - na_count_df3
cat("FAIL: No. of rows mismatch" , "\nGot no. of rows: ", nrow(merged_df3_comp))
,"\nExpected no. of rows: ", nrow(merged_df3) - na_count_df3
,"\nGot no. of rows: ", nrow(merged_df3_comp))
}
} else{
print("Index mismatch for mychisq and kin ors. Aborting NA ommission")
} }
# alternate way of deriving merged_df3_comp # alternate way of deriving merged_df3_comp
foo = merged_df3[!is.na(merged_df3$af),] foo = merged_df3[!is.na(merged_df3$af),]
bar = merged_df3_comp[!duplicated(merged_df3_comp$mutationinformation),] bar = merged_df3_comp[!duplicated(merged_df3_comp$mutationinformation),]
@ -408,8 +318,7 @@ all.equal(foo, bar)
# clear variables # clear variables
rm(foo, bar, gene_metadata rm(foo, bar, gene_metadata
, in_filename_params, infile_params, merging_cols , in_filename_params, infile_params, merging_cols
, in_filename_gene_metadata, infile_gene_metadata , in_filename_gene_metadata, infile_gene_metadata)
, merged_df2v2, merged_df2v3)
#************************* #*************************
##################################################################### #####################################################################
# Combining: LIG # Combining: LIG