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

fixed source to contain plotting cols and pos_count correctly

Browse source
This commit is contained in:
Tanushree Tunstall 2022-08-22 14:33:06 +01:00
parent 4147a6b90f
commit 13999a477d
6 changed files with 66 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

28
scripts/functions/combining_dfs_plotting.R
View file

@ -41,7 +41,7 @@ geneL_ppi2 = c("alr", "embb", "katg", "rpob")
combining_dfs_plotting <- function( my_df_u
, gene_metadata
, gene # ADDED
#, gene # ADDED
, lig_dist_colname = ''
, lig_dist_cutoff = ''){
@ -686,8 +686,11 @@ combining_dfs_plotting <- function( my_df_u
min( merged_df3['avg_lig_affinity_scaled']); max( merged_df3['avg_lig_affinity_scaled'])
###################################################################
# Rectify pos_count column in merged_df3
# The one in merged_df2 is correct
#--------------------------------------------
# merged_df3: Rectify pos_count column
# Rename existing pos_count colum to reflect
# that it is correct according to merged_df2
#--------------------------------------------
nc_pc_CHANGE = which(colnames(merged_df3)== "pos_count"); nc_pc_CHANGE
colnames(merged_df3)[nc_pc_CHANGE] = "df2_pos_count_all"
@ -707,16 +710,25 @@ combining_dfs_plotting <- function( my_df_u
nc_change = which(colnames(merged_df3) == "n")
colnames(merged_df3)[nc_change] <- "pos_count"
class(merged_df3)
####################################################################
#-------------------------------------------------
# merged_df2: Rename existing pos_count
# column to df2_pos_count_all like in above df
#-------------------------------------------------
nc_pc_CHANGE_df2 = which(colnames(merged_df2)== "pos_count"); nc_pc_CHANGE_df2
colnames(merged_df2)[nc_pc_CHANGE_df2] = "df2_pos_count_all"
head(merged_df2$pos_count)
head(merged_df2$df2_pos_count_all)
####################################################################
# ADD: distance to Nucleic acid column for na genes
# already done in plotting_data
####################################################################
#TODO
# Choose few columns to return as plot_df
merged_df3 = merged_df3[, colnames(merged_df3)%in%c(plotting_cols, "pos_count", "df2_pos_count_all")]
merged_df2 = merged_df2[, colnames(merged_df2)%in%c(plotting_cols, "df2_pos_count_all")]
####################################################################
return(list( merged_df2