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

renamed files for lineage_diff_sensitivites.R

Browse source
This commit is contained in:
Tanushree Tunstall 2022-09-05 13:19:06 +01:00
parent 69a0da0a59
commit 1dacebbaf6
5 changed files with 179 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

62
scripts/plotting/plotting_thesis/embb/lineage_diff_sensitivities.R → scripts/plotting/plotting_thesis/embb/embb_lineage_diff_sensitivities.R
View file

@ -45,20 +45,10 @@ lef_snps_df = df2[df2$mutationinformation%in%left_snps,]
table(lef_snps_df$lineage)
##################################
# selected lineage plos
cols_to_subset = c("mutationinformation"
, "lineage"
, "dst2"
, "sens2")
# selected lineage plots
##################################
#-----------------------------------------------
# step 0: Subset a smaller df
#-----------------------------------------------
plot_df_gene = df2_lin[, cols_to_subset]
#-----------------------------------------------
# step 1: Select muts for each target
# step 0: Select muts for each target
#-----------------------------------------------
# embb
#sel_mutsP = c("D354N", "Y319D", "Y319D", "A962P", "S651N", "A201S")
@ -69,6 +59,18 @@ sel_mutsP = c("P75R", "A19G", "A133P", "R154W", "R118L") #G30D)
# rpob
#sel_mutsP = c("")
#-----------------------------------------------
# step 1: Subset a smaller df
#-----------------------------------------------
# selected lineage plos
cols_to_subset = c("mutationinformation"
, "lineage"
, "dst2"
, "sens2")
plot_df_gene = df2_lin[, cols_to_subset]
#-----------------------------------------------
# step 2: Subset data with just those genes
#-----------------------------------------------
plot_df_gene = plot_df_gene[plot_df_gene$mutationinformation%in%sel_mutsP,]
@ -82,40 +84,8 @@ plot_df = plot_df_gene
#-----------------------------------------------
# step 4: Add p-value
# NOT NEEDED, get it from lineage_diff_sensitivities.R if needed
#-----------------------------------------------
plot_df$pval = NULL
for (i in sel_mutsP) {
#print (i)
s_mut = plot_df[plot_df$mutationinformation == i,]
#print(s_mut)
s_tab = table(s_mut$lineage, s_mut$sens2)
#print(s_tab)
#ft_pvalue_i = round(fisher.test(s_tab)$p.value, 3)
ft_pvalue_i = fisher.test(s_tab
#, workspace=2e9
#, simulate.p.value=TRUE,B=1e7
)$p.value
#print(ft_pvalue_i)
plot_df$pval[plot_df$mutationinformation == i] <- ft_pvalue_i
#print(s_tab)
}
plot_df$pvalR = round(plot_df$pval, 3)
# round P-values
plot_df$pvalRF = plot_df$pvalR
plot_df = dplyr::mutate(plot_df
, pvalRF = case_when(pvalRF == 0.05 ~ "P ."
, pvalRF <=0.0001 ~ 'P ****'
, pvalRF <=0.001 ~ 'P ***'
, pvalRF <=0.01 ~ 'P **'
, pvalRF <0.05 ~ 'P *'
, TRUE ~ 'ns'))
plot_df
head(plot_df)
table(plot_df$pvalR<0.05)
#-----------------------------------------------
# step 5: Plot