@@ -27,6 +27,23 @@ tip_order=tree$data %>%
2727# ##plotting repeat similarities using global ANI in tile colours
2828within_gANI = read.csv(file = " gANI.within_repeats.tsv" , header = T , sep = ' \t ' )
2929
30+ # #add the missing samples that are in the tree
31+ missing <- setdiff(tip_order , within_gANI $ sample )
32+
33+ # #add blank rows
34+ if (length(missing ) > 0 ){
35+ blank_rows <- data.frame (
36+ sample = missing ,
37+ average_gANI = NA ,
38+ count = NA ,
39+ repeat_representative = missing
40+ )
41+ within_gANI <- rbind(within_gANI , blank_rows )
42+ }
43+
44+ # #reorder after adding blanks
45+ within_gANI $ sample = factor (within_gANI $ sample , levels = tip_order )
46+
3047within_gANI $ gANI = within_gANI $ average_gANI * 100
3148
3249# #rearrange order of genomes by tree
@@ -42,9 +59,27 @@ within=suppressMessages(suppressWarnings(print(ggplot(data=within_gANI, aes(x=""
4259 theme_classic()+
4360 theme(axis.text.x = element_blank(), axis.title.x = element_blank(), axis.ticks.x = element_blank(), axis.text.y = element_blank(), axis.title.y = element_blank(), legend.position = " NA" ))))
4461
45- # ##
62+ # ##read in gANI comparisons between samples
4663rep_gANI = read.csv(file = " gANI.between_repeat_representatives.tsv" , header = T , sep = ' \t ' )
4764
65+ # #add missing samples
66+ all_pairs <- expand.grid(
67+ query_sample = tip_order ,
68+ ref_sample = tip_order ,
69+ stringsAsFactors = FALSE
70+ )
71+
72+ # #left-join your data into the complete matrix
73+ rep_gANI_full <- dplyr :: left_join(all_pairs , rep_gANI ,
74+ by = c(" query_sample" ," ref_sample" ))
75+
76+ # #reorder
77+ rep_gANI_full $ query_sample = factor (rep_gANI_full $ query_sample , levels = tip_order )
78+ rep_gANI_full $ ref_sample = factor (rep_gANI_full $ ref_sample , levels = tip_order )
79+
80+ rep_gANI = rep_gANI_full
81+
82+
4883rep_gANI $ gANI = rep_gANI $ gANI * 100
4984
5085# #rearrange order of genomes by tree
0 commit comments