Dataset summary output of Hecatomb pipeline. These files are all you need to reproduce the figures in the manuscript. # in R # read data and metadata data=read.table('big_table.tsv',sep='\t',header=T) meta=read.table('metadata.tsv',sep='\t',header=T) # combine data=merge(data, meta, by.x='sample',by.y='sample_id') # patients #7 and #14 were excluded data = data[! data$individual %in% c(7,14),] # filter (ignore non virus, ignore poor evalue, ignore nt-only hits) data = data[data$Kingdom=='Viruses' & data$ali_evalue<1e-20 & data$nt_aa=='aa',] # Figure 1 library(ggplot2) ggplot(data) + geom_point(aes(x=ali_len, y=ali_perc, color=source, size=count),alpha=0.1) + facet_wrap(~Family) + scale_color_brewer(palette = "Dark2") + theme_bw() + theme(panel.spacing = unit(0,'mm'), strip.background = element_rect(color = 'black',fill = 'white')) + scale_x_continuous(name='Alignment length') + scale_y_continuous(name='Alignment identitiy') # etc.