\name{Athaliana} \docType{package} \alias{BSgenome.Athaliana.TAIR.01222004-package} \alias{BSgenome.Athaliana.TAIR.01222004} \alias{Athaliana} \title{Arabidopsis thaliana full genome (TAIR version from January 22, 2004)} \description{ Arabidopsis thaliana full genome as provided by TAIR (snapshot from January 22, 2004) and stored in Biostrings objects. } \details{ } \note{ This BSgenome data package was made from the following source data files: \preformatted{ ATH1_chr1.1con.01222004 ATH1_chr2.1con.01222004 ATH1_chr3.1con.01222004 ATH1_chr4.1con.01222004 ATH1_chr5.1con.01222004 mitochondrial_genomic_sequence ATH1_chloroplast.1con.01072002 from ftp://ftp.arabidopsis.org/home/tair/Sequences/whole_chromosomes/OLD/ } See \code{?\link[BSgenome]{BSgenomeForge}} and the BSgenomeForge vignette (\code{vignette("BSgenomeForge")}) in the BSgenome software package for how to make a BSgenome data package. } \author{H. Pages} \seealso{ \link[BSgenome]{BSgenome-class}, \link[Biostrings]{DNAString-class}, \code{\link[BSgenome]{available.genomes}}, \link[BSgenome]{BSgenomeForge} } \examples{ Athaliana seqlengths(Athaliana) Athaliana$chr1 # same as Athaliana[["chr1"]] if ("AGAPS" \%in\% masknames(Athaliana)) { ## Check that the assembly gaps contain only Ns: checkOnlyNsInGaps <- function(seq) { ## Replace all masks by the inverted AGAPS mask masks(seq) <- gaps(masks(seq)["AGAPS"]) unique_letters <- uniqueLetters(seq) if (any(unique_letters != "N")) stop("assembly gaps contain more than just Ns") } ## A message will be printed each time a sequence is removed ## from the cache: options(verbose=TRUE) for (seqname in seqnames(Athaliana)) { cat("Checking sequence", seqname, "... ") seq <- Athaliana[[seqname]] checkOnlyNsInGaps(seq) cat("OK\n") } } ## See the GenomeSearching vignette in the BSgenome software ## package for some examples of genome-wide motif searching using ## Biostrings and the BSgenome data packages: if (interactive()) vignette("GenomeSearching", package="BSgenome") } \keyword{package} \keyword{data}