\name{Ecoli}
\docType{package}

\alias{BSgenome.Ecoli.NCBI.20080805-package}
\alias{BSgenome.Ecoli.NCBI.20080805}
\alias{Ecoli}


\title{Escherichia coli full genomes}

\description{
  Escherichia coli full genomes for several strains as provided by NCBI on 2008/08/05 and stored in Biostrings objects.
}

\details{
  The genome of Escherichia coli is made of a single circular DNA sequence.
The full genomes for the following strains are present in
this package (one sequence per strain):
\describe{
\item{}{
Escherichia coli 536
\preformatted{
Taxonomy ID: 362663
Other names: "Escherichia coli strain 536", "Escherichia coli str. 536"
Refseq: NC_008253
Length: 4,938,920 nt
Seq.Status: Completed
Sequencing center: University of Goettingen
Completed: 2006/07/24
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_536/NC_008253.fna
}}
\item{}{
Escherichia coli APEC O1
\preformatted{
Taxonomy ID: 405955
Other names: "Escherichia coli strain APEC O1", "Escherichia coli str. APEC O1"
Refseq: NC_008563
Length: 5,082,025 nt
Seq.Status: Completed
Sequencing center: Iowa State University
Completed: 2006/11/08
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_APEC_O1/NC_008563.fna
}}
\item{}{
Escherichia coli ATCC 8739
\preformatted{
Taxonomy ID: 481805
Other names: "Escherichia coli C (ATCC 8739)", "Escherichia coli C str. ATCC 8739", "Escherichia coli strain ATCC 8739", "Escherichia coli str. ATCC 8739"
Refseq: NC_010468
Length: 4,746,218 nt
Seq.Status: Completed
Sequencing center: US DOE Joint Genome Institute (JGI-PGF)
Completed: 2008/03/17
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_C_ATCC_8739/NC_010468.fna
}}
\item{}{
Escherichia coli CFT073
\preformatted{
Taxonomy ID: 199310
Other names: "Escherichia coli strain CFT073", "Escherichia coli str. CFT073"
Refseq: NC_004431
Length: 5,231,428 nt
Seq.Status: Completed
Sequencing center: Univ. Wisconsin
Completed: 2002/12/09
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_CFT073/NC_004431.fna
}}
\item{}{
Escherichia coli E24377A
\preformatted{
Taxonomy ID: 331111
Refseq: NC_009801
Length: 4,979,619 nt
Seq.Status: Completed
Sequencing center: TIGR
Completed: 2007/09/13
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_E24377A/NC_009801.fna
}}
\item{}{
Escherichia coli HS
\preformatted{
Taxonomy ID: 331112
Refseq: NC_009800
Length: 4,643,538 nt
Seq.Status: Completed
Sequencing center: TIGR
Completed: 2007/09/13
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_HS/NC_009800.fna
}}
\item{}{
Escherichia coli O157:H7 EDL933
\preformatted{
Taxonomy ID: 155864
Refseq: NC_002655
Length: 5,528,445 nt
Seq.Status: Completed
Sequencing center: Univ. Wisconsin
Completed: 2001/09/27
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_O157H7_EDL933/NC_002655.fna
}}
\item{}{
Escherichia coli O157:H7 str. Sakai
\preformatted{
Taxonomy ID: 386585
Other names: "Escherichia coli O157:H7 strain Sakai"
Refseq: NC_002695
Length: 5,498,450 nt
Seq.Status: Completed
Sequencing center: GIRC
Completed: 2001/10/02
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_O157H7/NC_002695.fna
}}
\item{}{
Escherichia coli SMS-3-5
\preformatted{
Taxonomy ID: 439855
Other names: "Escherichia coli strain SMS-3-5", "Escherichia coli str. SMS-3-5"
Refseq: NC_010498
Length: 5,068,389 nt
Seq.Status: Completed
Sequencing center: TIGR
Completed: 2008/03/24
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_SMS_3_5/NC_010498.fna
}}
\item{}{
Escherichia coli UTI89
\preformatted{
Taxonomy ID: 364106
Other names: "Escherichia coli strain UTI89", "Escherichia coli str. UTI89"
Refseq: NC_007946
Length: 5,065,741 nt
Seq.Status: Completed
Sequencing center: Washington University (WashU)
Completed: 2006/04/07
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_UTI89/NC_007946.fna
}}
\item{}{
Escherichia coli str. K12 substr. DH10B
\preformatted{
Taxonomy ID: 316385
Other names: "Escherichia coli DH10B", "Escherichia coli strain K12 substrain DH10B"
Refseq: NC_010473
Length: 4,686,137 nt
Seq.Status: Completed
Sequencing center: University of Wisconsin-Madison
Completed: 2008/03/17
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_K_12_substr__DH10B/NC_010473.fna
}}
\item{}{
Escherichia coli str. K12 substr. MG1655
\preformatted{
Taxonomy ID: 511145
Other names: "Escherichia coli MG1655", "Escherichia coli strain MG1655", "Escherichia coli str. MG1655"
Refseq: NC_000913
Length: 4,639,675 nt
Seq.Status: Completed
Sequencing center: Univ. Wisconsin
Completed: 2001/10/15
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_K12_substr__MG1655/NC_000913.fna
}}
\item{}{
Escherichia coli str. K12 substr. W3110
\preformatted{
Taxonomy ID: 316407
Other names: "Escherichia coli W3110", "Escherichia coli strain W3110", "Escherichia coli str. W3110"
Refseq: AC_000091
Length: 4,646,332 nt
Seq.Status: Completed
Sequencing center: Nara Institute of Science and Technology
Completed: 2006/03/01
File: ftp://ftp.ncbi.nih.gov/genomes/Bacteria/Escherichia_coli_W3110/AC_000091.fna
}}
}
}

\note{
  This BSgenome data package was made from the following source data files:
  \preformatted{
Escherichia_coli_536/NC_008253.fna
Escherichia_coli_APEC_O1/NC_008563.fna
Escherichia_coli_C_ATCC_8739/NC_010468.fna
Escherichia_coli_CFT073/NC_004431.fna
Escherichia_coli_E24377A/NC_009801.fna
Escherichia_coli_HS/NC_009800.fna
Escherichia_coli_O157H7_EDL933/NC_002655.fna
Escherichia_coli_O157H7/NC_002695.fna
Escherichia_coli_SMS_3_5/NC_010498.fna
Escherichia_coli_UTI89/NC_007946.fna
Escherichia_coli_K_12_substr__DH10B/NC_010473.fna
Escherichia_coli_K12_substr__MG1655/NC_000913.fna
Escherichia_coli_W3110/AC_000091.fna
from ftp://ftp.ncbi.nih.gov/genomes/Bacteria/ (downloaded on 2008/08/05)

  }
  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{
## The names of the sequences are the Refseq numbers:
Ecoli
seqlengths(Ecoli)
Ecoli$NC_008253  # same as Ecoli[["NC_008253"]]

if ("AGAPS" \%in\% masknames(Ecoli)) {

  ## 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(Ecoli)) {
    cat("Checking sequence", seqname, "... ")
    seq <- Ecoli[[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}