Viral genomes deposited in NCBI per month

README.md

Run the NCBI database interrogation with edirect command line tools and then create the figure with the included R script.

esearch -db nuccore -query "txid10239 [orgn] AND \"complete genome\" [Title] NOT txid131567 [orgn]" | \
efetch -format docsum | \
xtract -pattern DocumentSummary -element CreateDate > viral_dates.txt

ncbi_genomes_histo.R

library(ggplot2)
library(dplyr)
library(scales)
library(lubridate)
library(ggthemes)
# install NCBI edirect to run this:
# esearch -db nuccore -query "txid10239 [orgn] AND \"complete genome\" [Title] NOT txid131567 [orgn]" | \
# efetch -format docsum | \
# xtract -pattern DocumentSummary -element CreateDate > viral_dates.txt

viral_dates = read.table("~/tmp/viral_dates.txt", quote="\"")
vd = data.frame(dates = as.Date(viral_dates$V1))
vd$month = as.Date(cut(vd$dates, breaks = "month"))

dtp = group_by(vd, month) %>%
  summarise(total = n())

p = ggplot(data=dtp, aes(x=month, y=total))
p = p + geom_point()
p = p + theme_solarized() + scale_colour_solarized("blue")
p = p + xlab('') + ylab('sequences created per month')
p = p + ggtitle('NCBI complete viral genomes')
#p = p + theme(axis.title.y = element_text(size=16))
#p = p + theme(axis.text.x = element_text(size=14, angle=0))
#p = p + theme(axis.text.y = element_text(size=14))
p