inst/doc/MetaGenome_Retrieval.R

## ----echo = FALSE, message = FALSE------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
options(width = 750)
knitr::opts_chunk$set(
  comment = "#>",
  error = FALSE,
  tidy = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate genomes, then apply ...
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "refseq", type = "genome") %>% ...

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  getKingdoms(db = "refseq")

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  getKingdoms(db = "genbank")

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  getKingdoms(db = "ensembl")

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate genomes
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all bacteria genomes
#  meta.retrieval(kingdom = "bacteria", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all virus genomes
#  meta.retrieval(kingdom = "viral", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all archaea genomes
#  meta.retrieval(kingdom = "archaea", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all fungi genomes
#  meta.retrieval(kingdom = "fungi", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all plant genomes
#  meta.retrieval(kingdom = "plant", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all invertebrate genomes
#  meta.retrieval(kingdom = "invertebrate", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all invertebrate genomes
#  meta.retrieval(kingdom = "protozoa", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate genomes
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "genbank", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all bacteria genomes
#  meta.retrieval(kingdom = "bacteria", db = "genbank", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all archaea genomes
#  meta.retrieval(kingdom = "archaea", db = "genbank", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all fungi genomes
#  meta.retrieval(kingdom = "fungi", db = "genbank", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all plant genomes
#  meta.retrieval(kingdom = "plant", db = "genbank", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all invertebrate genomes
#  meta.retrieval(kingdom = "invertebrate", db = "genbank", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all invertebrate genomes
#  meta.retrieval(kingdom = "protozoa", db = "genbank", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all genomes from ENSEMBL
#  meta.retrieval(kingdom = "Ensembl", db = "ensembl", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  getKingdoms(db = "refseq")

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  getGroups(db = "refseq", kingdom = "bacteria")

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  meta.retrieval(kingdom = "bacteria", group = "Gammaproteobacteria", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  getGroups(db = "refseq", kingdom = "viral")

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  meta.retrieval(kingdom = "viral", group = "Adenoviridae", db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # show all elements of the data.frame
#  options(tibble.print_max = Inf)
#  # retrieve genome assembly stats for all mammal genome assemblies
#  # and store these stats in a data.frame
#  mammals.gc <- meta.retrieval(kingdom = "vertebrate_mammalian",
#                               db      = "refseq",
#                               type    = "assemblystats",
#                               combine = TRUE)
#  
#  mammals.gc

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # list available metagenomes at NCBI Genbank
#  listMetaGenomes()

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # show all elements of the data.frame
#  options(tibble.print_max = Inf)
#  # detailed information on available metagenomes at NCBI Genbank
#  listMetaGenomes(details = TRUE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # retrieve all genomes belonging to the human gut metagenome project
#  getMetaGenomes(name = "human gut metagenome", path = file.path("_ncbi_downloads","human_gut"))

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # retrieve all genomes belonging to the human gut metagenome project
#  getMetaGenomeAnnotations(name = "human gut metagenome", path = file.path("_ncbi_downloads","human_gut","annotations"))

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate genomes
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "refseq", type = "proteome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate genomes
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "genbank", type = "proteome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all Ensembl proteome sequneces
#  meta.retrieval(kingdom = "Ensembl", db = "ensembl", type = "proteome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate genomes
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "refseq", type = "cds", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate genomes
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "genbank", type = "cds", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all Ensembl CDS sequneces
#  meta.retrieval(kingdom = "Ensembl", db = "ensembl", type = "cds", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate gff files
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "refseq", type = "gff", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate gff files
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "genbank", type = "gff", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate gff files
#  meta.retrieval(kingdom = "Ensembl", db = "ensembl", type = "gtf", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate RNA sequneces
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "refseq", type = "rna", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate RNA sequneces
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "genbank", type = "rna", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all Ensembl RNA sequneces
#  meta.retrieval(kingdom = "Ensembl", db = "ensembl", type = "rna", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate RNA sequneces
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "refseq", type = "rm", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all vertebrate RNA sequneces
#  meta.retrieval(kingdom = "vertebrate_mammalian", db = "genbank", type = "rm", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all geneomes stored in RefSeq
#  meta.retrieval.all(db = "refseq", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all geneomes stored in Genbank
#  meta.retrieval.all(db = "genbank", type = "genome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all proteome stored in RefSeq
#  meta.retrieval.all(db = "refseq", type = "proteome", reference = FALSE)

## ----eval=FALSE-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
#  # download all proteome stored in Genbank
#  meta.retrieval.all(db = "genbank", type = "proteome", reference = FALSE)

Try the biomartr package in your browser

Any scripts or data that you put into this service are public.

biomartr documentation built on Oct. 25, 2023, 1:08 a.m.