In rsimon64/bioinfodem:

knitr::opts_chunk$set(echo = TRUE)

options("citation_format" = "pandoc")
library("knitcitations")
cleanbib()

Obteniendo datos

term <- "Solanum tuberosum[Organism]"

Se realizó una busqueda en la base de datos ENTREZ r citep("10.1093/nar/gki031") con el 'term': r term y usando el paquete rentrez r citep(citation("rentrez")). Además, usamos los paquetes knitr r citep(citation("knitr")), knitcations r citep(citation("knitcitations")), msa r citep(citation("msa")), seqinr r citep(citation("seqinr")) y ape r citep(citation("ape")).

library(rentrez)
st_search <- entrez_search(db="popset", term=term)
st_summs <- entrez_summary(db = "popset", id = st_search$ids)
titles <- extract_from_esummary(st_summs, "title")
ids <- unname(titles)
sol_id <- st_search$ids[4]
sol <- entrez_fetch(db="popset", id=sol_id, rettype="fasta")
write(sol, "inst/datos/sol.fasta")

Los siguients datasets son disponibles a la fecha indicada: r paste(ids, collapse = ", ").

library(msa)
library(knitr)

msa_aln2 <- msa("inst/datos/sol.fasta", type = "dna")
msaPrettyPrint(msa_aln2, output = "tex", askForOverwrite = FALSE)
system("pdflatex msa_aln2.tex")
include_graphics("msa_aln2.pdf")

library(seqinr)

msa_aln <- msaConvert(msa_aln2, type="seqinr::alignment")
d <- dist.alignment(msa_aln, "identity")
head(d)

library(ape)
soltree <- nj(d)

dna <- read.dna("inst/datos/sol.fasta", format = "fasta" )
species_label <- stringr::str_extract(names(dna), "(Ipomoea|Solanum|Turbina)(\\s){1}[a-z]{1,15}")

soltree$tip.label <- species_label[as.integer(soltree$tip.label)]
plot_title <- stringr::str_split(ids[4], ";")[[1]][1]
plot(soltree, main = plot_title)