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

changing category of ambiguous muts

Browse source
This commit is contained in:
Tanushree Tunstall 2020-09-08 18:51:03 +01:00
parent eb5491aad9
commit 46b43cf261
3 changed files with 55 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

39
scripts/plotting/combining_dfs_plotting.R
View file

@ -59,18 +59,23 @@ rm(my_df, upos, dup_muts)
# my_df_u
# quick checks
head(my_df_u[, c("mutation", "mutation2")])
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]
which(is.na(my_df_u$af_kin)) == which(is.na(my_df_u$af))
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
#in_filename_gene_metadata = paste0(tolower(gene), "_meta_data_with_AFandOR.csv")
@ -109,7 +114,8 @@ gene_metadata <- read.csv(infile_gene_metadata
cat("Dim:", dim(gene_metadata))
# counting NAs in AF, OR cols:
# counting NAs in AF, OR cols
# or_mychisq
if (identical(sum(is.na(my_df_u$or_mychisq))
, sum(is.na(my_df_u$pval_fisher))
, sum(is.na(my_df_u$af)))){
@ -123,7 +129,7 @@ if (identical(sum(is.na(my_df_u$or_mychisq))
, "\nNA in AF:", sum(is.na(my_df_u$af)))
}
# or kin
if (identical(sum(is.na(my_df_u$or_kin))
, sum(is.na(my_df_u$pwald_kin))
, sum(is.na(my_df_u$af_kin)))){
@ -139,6 +145,31 @@ if (identical(sum(is.na(my_df_u$or_kin))
str(gene_metadata)
# change category of ambiguos mutations
table(gene_metadata$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')
# 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,]
gene_metadata2 = gene_metadata
if (gene_metadata$mutation_info[gene_metadata$mutation%in%ambiguous_muts_names] == other_muts_col){
print('change me')
}
###################################################################
# combining: PS
###################################################################