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

added foldx scaled and foldx outcome to plotting_data.R

Browse source
This commit is contained in:
Tanushree Tunstall 2020-09-23 11:12:41 +01:00
parent 5deb12187e
commit 4398c049ca
3 changed files with 48 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

16
scripts/plotting/extreme_muts.R
View file

@ -118,7 +118,6 @@ df_s_foldx = df[df$foldx_outcome == "Stabilising",]
hs_foldx = df_s_foldx[df_s_foldx$ddg == min(df_s_foldx$ddg), ]
hs_foldx
#===============
# active site muts
#===============
@ -132,8 +131,6 @@ cat("No. of active site residues within", aa_dist, ":", nrow(aa_muts))
#====================
# budding hotspots
#====================
# Method
# this is what you want
foo = merged_df3 %>% group_by(position) %>% tally()
bar = merged_df3 %>% group_by(position) %>% count()
@ -149,15 +146,4 @@ n_mult_muts_sites = sum(table(foo$n)) - (table(foo$n)[[1]] - table(foo$n)[[2]])
cat("No of budding hotspots (sites with 2 mutations):", n_budding_sites
, "\nNo. of sites with mutiple (>2) mutations:", n_mult_muts_sites)
# another way
setDT(merged_df3)[, pos_count := .N, by = .(position)]
# this is cummulative
table(merged_df3$pos_count)
# use group by on this: same as the
snpsBYpos_df <- merged_df3 %>%
group_by(position) %>%
summarize(snpsBYpos = mean(pos_count))
#==========================================================================