New Upstream Release - r-bioc-bsgenome
Ready changes
Summary
Merged new upstream version: 1.68.0 (was: 1.66.3).
Diff
diff --git a/DESCRIPTION b/DESCRIPTION
index 6c5128d..d8326ef 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -7,7 +7,7 @@ biocViews: Genetics, Infrastructure, DataRepresentation,
SequenceMatching, Annotation, SNP
URL: https://bioconductor.org/packages/BSgenome
BugReports: https://github.com/Bioconductor/BSgenome/issues
-Version: 1.66.3
+Version: 1.68.0
License: Artistic-2.0
Encoding: UTF-8
Authors@R: c(
@@ -41,12 +41,12 @@ Collate: utils.R OnDiskLongTable_old-class.R OnDiskLongTable-class.R
extractAt-methods.R bsapply.R BSgenomeViews-class.R
BSgenome-utils.R export-methods.R BSgenomeForge.R
git_url: https://git.bioconductor.org/packages/BSgenome
-git_branch: RELEASE_3_16
-git_last_commit: f2f40e0
-git_last_commit_date: 2023-02-16
-Date/Publication: 2023-02-16
+git_branch: RELEASE_3_17
+git_last_commit: c546020
+git_last_commit_date: 2023-04-25
+Date/Publication: 2023-04-25
NeedsCompilation: no
-Packaged: 2023-02-16 21:13:40 UTC; biocbuild
+Packaged: 2023-04-25 20:26:29 UTC; biocbuild
Author: Hervé Pagès [aut, cre],
Prisca Chidimma Maduka [ctb] (add 'replace' argument to
forgeBSgenomeDataPkg())
diff --git a/NAMESPACE b/NAMESPACE
index fd0c2b1..1f914a0 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -162,9 +162,6 @@ export(
snpcount, snplocs,
snpsBySeqname, snpsByOverlaps, snpsById,
- ## OldFashionSNPlocs-class.R:
- snpid2loc, snpid2alleles, snpid2grange,
-
## InjectSNPsHandler-class.R:
SNPlocs_pkgname,
@@ -188,7 +185,6 @@ exportMethods(
releaseName, referenceGenome, compatibleGenomes,
snpcount, snplocs,
snpsBySeqname, snpsByOverlaps, snpsById,
- snpid2loc, snpid2alleles, snpid2grange,
SNPlocs_pkgname,
sourceUrl,
mseqnames,
diff --git a/R/BSgenome-class.R b/R/BSgenome-class.R
index e5bb40e..c643507 100644
--- a/R/BSgenome-class.R
+++ b/R/BSgenome-class.R
@@ -7,8 +7,8 @@ setClass("BSgenome",
## Expected metadata data are:
## - organism
## - common_name
- ## - genome
## - provider
+ ## - genome
## - release_date
## - source_url: permanent URL to the place where the 2bit and/or FASTA
## files used to produce the "single" and "multiple" sequences can be
@@ -341,8 +341,8 @@ BSgenome <- function(organism, common_name, genome,
common_name <- species
metadata <- list(organism=organism,
common_name=common_name,
- genome=genome,
provider=provider,
+ genome=genome,
release_date=release_date,
source_url=source_url)
if (is.null(mseqnames))
@@ -413,58 +413,47 @@ setMethod("bsgenomeName", "BSgenome",
### The "show" method
###
-.print_BSgenome_metadata <- function(metadata, prefix="")
+.print_BSgenome_metadata <- function(metadata, margin="")
{
+ cat(margin, "BSgenome object", sep="")
common_name <- metadata$common_name
if (!is.na(common_name))
- cat(common_name, "genome:\n")
- cat(prefix, "organism: ", metadata$organism,
- " (", common_name, ")\n", sep="")
- cat(prefix, "genome: ", metadata$genome, "\n", sep="")
- cat(prefix, "provider: ", metadata$provider, "\n", sep="")
- cat(prefix, "release date: ", metadata$release_date, "\n", sep="")
+ cat(" for ", common_name, sep="")
+ cat("\n")
+ cat(margin, "- organism: ", metadata$organism, "\n", sep="")
+ cat(margin, "- provider: ", metadata$provider, "\n", sep="")
+ cat(margin, "- genome: ", metadata$genome, "\n", sep="")
+ release_date <- metadata$release_date
+ if (!is.na(release_date))
+ cat(margin, "- release date: ", release_date, "\n", sep="")
}
-.SHOW_BSGENOME_PREFIX <- "# "
-.SHOW_SEQSECTION_PREFIX <- "# "
+.show_BSgenome <- function(x, margin="")
+{
+ mystrwrap <- function(line)
+ writeLines(strwrap(line, width=getOption("width")+1,
+ exdent=0L, prefix=margin))
+ .print_BSgenome_metadata(metadata(x), margin=margin)
+ if (!is.null(SNPlocs_pkgname(x)))
+ cat(margin, "with SNPs injected from package: ",
+ SNPlocs_pkgname(x), "\n", sep="")
+ cat(margin, "- ", length(seqnames(x)), " sequence(s):\n", sep="")
+ margin2 <- paste0(margin, " ")
+ if (length(seqnames(x)) == 0L) {
+ cat(margin2, "NONE\n", sep="")
+ } else {
+ printAtomicVectorInAGrid(seqnames(x), prefix=margin2)
+ cat(margin, "\n", sep="")
+ mystrwrap(paste0("Tips: call 'seqnames()' on the object to get all ",
+ "the sequence names, call 'seqinfo()' to get the ",
+ "full sequence info, use the '$' or '[[' operator ",
+ "to access a given sequence, see '?BSgenome' for ",
+ "more information."))
+ }
+}
setMethod("show", "BSgenome",
- function(object)
- {
- mystrwrap <- function(line)
- writeLines(strwrap(line, width=getOption("width")+1,
- exdent=0L, prefix=.SHOW_BSGENOME_PREFIX))
- .print_BSgenome_metadata(metadata(object), prefix=.SHOW_BSGENOME_PREFIX)
- if (!is.null(SNPlocs_pkgname(object)))
- cat(.SHOW_BSGENOME_PREFIX, "with SNPs injected from package: ", SNPlocs_pkgname(object), "\n", sep="")
- if (length(mseqnames(object)) == 0L) {
- what <- "sequence"
- } else {
- cat(.SHOW_BSGENOME_PREFIX, "\n", sep="")
- what <- "single sequence"
- }
- mystrwrap(paste0(length(seqnames(object)), " ", what, "s:"))
- if (length(seqnames(object)) != 0L) {
- printAtomicVectorInAGrid(seqnames(object),
- prefix=.SHOW_SEQSECTION_PREFIX)
- mystrwrap(paste0("(use 'seqnames()' to see all the ",
- what, " names, ",
- "use the '$' or '[[' operator to access a given ",
- what, ")"))
- } else {
- cat(.SHOW_SEQSECTION_PREFIX, "NONE\n", sep="")
- }
- if (length(mseqnames(object)) != 0L) {
- cat(.SHOW_BSGENOME_PREFIX, "\n", sep="")
- mystrwrap("multiple sequences:")
- printAtomicVectorInAGrid(mseqnames(object),
- prefix=.SHOW_SEQSECTION_PREFIX)
- mystrwrap(paste0("(use 'mseqnames()' to see all the ",
- "multiple sequence names, ",
- "use the '$' or '[[' operator to access a given ",
- "multiple sequence)"))
- }
- }
+ function(object) .show_BSgenome(object, margin="| ")
)
diff --git a/R/BSgenomeForge.R b/R/BSgenomeForge.R
index 65d09d4..2168088 100644
--- a/R/BSgenomeForge.R
+++ b/R/BSgenomeForge.R
@@ -836,13 +836,16 @@ MaskedBSgenomeDataPkgSeed <- function(x)
###
setGeneric("forgeBSgenomeDataPkg", signature="x",
- function(x, seqs_srcdir=".", destdir=".", verbose=TRUE)
+ function(x, seqs_srcdir=".", destdir=".", replace=FALSE, verbose=TRUE)
standardGeneric("forgeBSgenomeDataPkg")
)
setMethod("forgeBSgenomeDataPkg", "BSgenomeDataPkgSeed",
- function(x, seqs_srcdir=".", destdir=".", verbose=TRUE)
+ function(x, seqs_srcdir=".", destdir=".", replace=FALSE, verbose=TRUE)
{
+ if (!isTRUEorFALSE(replace))
+ stop("'replace' must be TRUE or FALSE")
+
## The Biobase package is needed for createPackage().
if (!requireNamespace("Biobase", quietly=TRUE))
stop("Couldn't load the Biobase package. Please install ",
@@ -913,8 +916,16 @@ setMethod("forgeBSgenomeDataPkg", "BSgenomeDataPkgSeed",
bad_syms <- paste(names(is_OK)[!is_OK], collapse=", ")
stop("values for symbols ", bad_syms, " are not single strings")
}
- Biobase::createPackage(x@Package, destdir, template_path, symvals)
pkgdir <- file.path(destdir, x@Package)
+ if (file.exists(pkgdir)) {
+ if (replace) {
+ unlink(pkgdir, recursive=TRUE)
+ } else {
+ stop("directory ", pkgdir, " exists. ",
+ "Use replace=TRUE to replace it.")
+ }
+ }
+ Biobase::createPackage(x@Package, destdir, template_path, symvals)
.mseqnames <- eval(parse(text=x@mseqnames))
seqs_destdir <- file.path(pkgdir, "inst", "extdata")
@@ -956,11 +967,11 @@ setMethod("forgeBSgenomeDataPkg", "BSgenomeDataPkgSeed",
)
setMethod("forgeBSgenomeDataPkg", "list",
- function(x, seqs_srcdir=".", destdir=".", verbose=TRUE)
+ function(x, seqs_srcdir=".", destdir=".", replace=FALSE, verbose=TRUE)
{
y <- BSgenomeDataPkgSeed(x)
forgeBSgenomeDataPkg(y, seqs_srcdir=seqs_srcdir, destdir=destdir,
- verbose=verbose)
+ replace=replace, verbose=verbose)
}
)
@@ -1024,7 +1035,7 @@ read.dcf2 <- function(file, ...)
}
setMethod("forgeBSgenomeDataPkg", "character",
- function(x, seqs_srcdir=".", destdir=".", verbose=TRUE)
+ function(x, seqs_srcdir=".", destdir=".", replace=FALSE, verbose=TRUE)
{
y <- .readSeedFile(x, verbose=verbose)
y <- as.list(y)
@@ -1036,7 +1047,7 @@ setMethod("forgeBSgenomeDataPkg", "character",
}
y <- y[!(names(y) %in% "seqs_srcdir")]
forgeBSgenomeDataPkg(y, seqs_srcdir=seqs_srcdir, destdir=destdir,
- verbose=verbose)
+ replace=replace, verbose=verbose)
}
)
diff --git a/R/OldFashionSNPlocs-class.R b/R/OldFashionSNPlocs-class.R
index fc22839..8f6d69b 100644
--- a/R/OldFashionSNPlocs-class.R
+++ b/R/OldFashionSNPlocs-class.R
@@ -131,6 +131,14 @@ setMethod("snpcount", "OldFashionSNPlocs",
### and "alleles_as_ambig" (character).
###
+.get_rsid_offsets <- function(x)
+{
+ offsets <- c(0L, cumsum(snpcount(x)))
+ offsets <- offsets[-length(offsets)]
+ names(offsets) <- names(snpcount(x))
+ offsets
+}
+
### Load rs ids for a given sequence. Return them in an integer vector.
.load_rsids <- function(x, seqname)
{
@@ -239,39 +247,61 @@ setMethod("snplocs", "OldFashionSNPlocs",
### - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
-### Old SNPlocs extractors (deprecated in BioC 3.5, defunct in BioC 3.15):
-### snpid2loc()
-### snpid2alleles()
-### snpid2grange()
+### NEW API: snpsBySeqname(), snpsByOverlaps(), snpsById() (similar to API
+### for querying an XtraSNPlocs object)
###
-### Returns a named integer vector where each (name, value) pair corresponds
-### to a supplied SNP id (typically an rs id). The name is the chromosome of
-### the SNP id and the value is its position on the chromosome.
-setGeneric("snpid2loc", signature="x",
- function(x, snpid, ...) standardGeneric("snpid2loc")
-)
+.get_GPos_by_seqname_from_SNPlocs <- function(x, seqnames, drop.rs.prefix)
+{
+ gr <- snplocs(x, seqnames, as.GRanges=TRUE)
+ if (!drop.rs.prefix && length(gr) != 0L)
+ mcols(gr)$RefSNP_id <- paste0("rs", mcols(gr)$RefSNP_id)
+ as(gr, "GPos")
+}
-### Returns a named character vector where each (name, value) pair corresponds
-### to a supplied SNP id (typically an rs id). The name is the chromosome of
-### the SNP id and the value is a single IUPAC code representing the associated
-### alleles.
-setGeneric("snpid2alleles", signature="x",
- function(x, snpid, ...) standardGeneric("snpid2alleles")
-)
+.snpsBySeqname_OldFashionSNPlocs <- function(x, seqnames, drop.rs.prefix=FALSE)
+{
+ if (!is.character(seqnames)
+ || any(is.na(seqnames))
+ || any(duplicated(seqnames)))
+ stop(wmsg("'seqnames' must be a character vector ",
+ "with no NAs and no duplicates"))
+ if (!all(seqnames %in% seqlevels(x)))
+ stop(wmsg("'seqnames' must be a subset of: ",
+ paste(seqlevels(x), collapse=", ")))
+ if (!isTRUEorFALSE(drop.rs.prefix))
+ stop(wmsg("'drop.rs.prefix' must be TRUE or FALSE"))
+ .get_GPos_by_seqname_from_SNPlocs(x, seqnames, drop.rs.prefix)
+}
-setGeneric("snpid2grange", signature="x",
- function(x, snpid, ...) standardGeneric("snpid2grange")
+setMethod("snpsBySeqname", "OldFashionSNPlocs",
+ .snpsBySeqname_OldFashionSNPlocs
)
-.get_rsid_offsets <- function(x)
+.snpsByOverlaps_OldFashionSNPlocs <- function(x, ranges,
+ drop.rs.prefix=FALSE, ...)
{
- offsets <- c(0L, cumsum(snpcount(x)))
- offsets <- offsets[-length(offsets)]
- names(offsets) <- names(snpcount(x))
- offsets
+ ranges <- normarg_ranges(ranges)
+ dots <- list(...)
+ if (isTRUE(dots$invert))
+ stop(wmsg("snpsByOverlaps() does not support 'invert=TRUE'"))
+
+ ## The only purpose of the line below is to check that 'x' and 'ranges'
+ ## are based on the same reference genome (merge() will raise an error
+ ## if they are not).
+ merge(seqinfo(x), seqinfo(ranges))
+ seqlevels(ranges, pruning.mode="coarse") <-
+ intersect(seqlevels(x), seqlevelsInUse(ranges))
+ snps_by_seqname <- .snpsBySeqname_OldFashionSNPlocs(x,
+ seqlevels(ranges),
+ drop.rs.prefix=drop.rs.prefix)
+ subsetByOverlaps(snps_by_seqname, ranges, ...)
}
+setMethod("snpsByOverlaps", "OldFashionSNPlocs",
+ .snpsByOverlaps_OldFashionSNPlocs
+)
+
.normarg_snpid <- function(snpid)
{
if (!is.vector(snpid))
@@ -314,13 +344,10 @@ setGeneric("snpid2grange", signature="x",
if (length(bad_snpid_idx) != 0L) {
bad_snpid <- snpid[bad_snpid_idx]
bad_snpid_in1string <- paste(bad_snpid, collapse=", ")
- stop(wmsg("SNP id(s) not found: ", bad_snpid_in1string,
- "\n\nPlease note that rsid2loc(), snpid2loc(), ",
- "rsid2alleles(), snpid2alleles(), rsidsToGRanges(), ",
- "and snpid2grange() are superseded by snpsById(). ",
- "The latter can be called with 'ifnotfound=\"drop\"' ",
- "to drop unknown SNP ids. See '?snpsById' for more ",
- "information.\n\n "))
+ stop(wmsg("SNP id(s) not found: ", bad_snpid_in1string),
+ "\n ",
+ "Use 'ifnotfound=\"drop\"' to drop unknown SNP ids. ",
+ "See '?snpsById' for more information.")
}
}
seqidx <- findInterval(idx - 1L, cumsum(snpcount(x))) + 1L
@@ -347,18 +374,6 @@ setGeneric("snpid2grange", signature="x",
ans
}
-setMethod("snpid2loc", "OldFashionSNPlocs",
- function(x, snpid, caching=TRUE)
- {
- .Defunct(msg=wmsg("snpid2loc() is defunct. ",
- "Please use snpsById() instead."))
- snpid <- .normarg_snpid(snpid)
- if (!isTRUEorFALSE(caching))
- stop("'caching' must be TRUE or FALSE")
- .snpid2loc_OldFashionSNPlocs(x, snpid, caching=caching)
- }
-)
-
.snpid2alleles_OldFashionSNPlocs <- function(x, snpid, caching=TRUE)
{
rowidx <- .snpid2rowidx(x, snpid)
@@ -378,18 +393,6 @@ setMethod("snpid2loc", "OldFashionSNPlocs",
ans
}
-setMethod("snpid2alleles", "OldFashionSNPlocs",
- function(x, snpid, caching=TRUE)
- {
- .Defunct(msg=wmsg("snpid2alleles() is defunct. ",
- "Please use snpsById() instead."))
- snpid <- .normarg_snpid(snpid)
- if (!isTRUEorFALSE(caching))
- stop("'caching' must be TRUE or FALSE")
- .snpid2alleles_OldFashionSNPlocs(x, snpid, caching=caching)
- }
-)
-
.snpid2grange_OldFashionSNPlocs <- function(x, snpid, caching=TRUE)
{
snpid <- .normarg_snpid(snpid)
@@ -404,72 +407,6 @@ setMethod("snpid2alleles", "OldFashionSNPlocs",
.SNPlocsAsGRanges(x, ufsnplocs, names(loc))
}
-setMethod("snpid2grange", "OldFashionSNPlocs",
- function(x, snpid, caching=TRUE)
- {
- .Defunct(msg=wmsg("snpid2grange() is defunct. ",
- "Please use snpsById() instead."))
- .snpid2grange_OldFashionSNPlocs(x, snpid, caching=caching)
- }
-)
-
-
-### - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
-### NEW API: snpsBySeqname(), snpsByOverlaps(), snpsById() (similar to API
-### for querying an XtraSNPlocs object)
-###
-
-.get_GPos_by_seqname_from_SNPlocs <- function(x, seqnames, drop.rs.prefix)
-{
- gr <- snplocs(x, seqnames, as.GRanges=TRUE)
- if (!drop.rs.prefix && length(gr) != 0L)
- mcols(gr)$RefSNP_id <- paste0("rs", mcols(gr)$RefSNP_id)
- as(gr, "GPos")
-}
-
-.snpsBySeqname_OldFashionSNPlocs <- function(x, seqnames, drop.rs.prefix=FALSE)
-{
- if (!is.character(seqnames)
- || any(is.na(seqnames))
- || any(duplicated(seqnames)))
- stop(wmsg("'seqnames' must be a character vector ",
- "with no NAs and no duplicates"))
- if (!all(seqnames %in% seqlevels(x)))
- stop(wmsg("'seqnames' must be a subset of: ",
- paste(seqlevels(x), collapse=", ")))
- if (!isTRUEorFALSE(drop.rs.prefix))
- stop(wmsg("'drop.rs.prefix' must be TRUE or FALSE"))
- .get_GPos_by_seqname_from_SNPlocs(x, seqnames, drop.rs.prefix)
-}
-
-setMethod("snpsBySeqname", "OldFashionSNPlocs",
- .snpsBySeqname_OldFashionSNPlocs
-)
-
-.snpsByOverlaps_OldFashionSNPlocs <- function(x, ranges,
- drop.rs.prefix=FALSE, ...)
-{
- ranges <- normarg_ranges(ranges)
- dots <- list(...)
- if (isTRUE(dots$invert))
- stop(wmsg("snpsByOverlaps() does not support 'invert=TRUE'"))
-
- ## The only purpose of the line below is to check that 'x' and 'ranges'
- ## are based on the same reference genome (merge() will raise an error
- ## if they are not).
- merge(seqinfo(x), seqinfo(ranges))
- seqlevels(ranges, pruning.mode="coarse") <-
- intersect(seqlevels(x), seqlevelsInUse(ranges))
- snps_by_seqname <- .snpsBySeqname_OldFashionSNPlocs(x,
- seqlevels(ranges),
- drop.rs.prefix=drop.rs.prefix)
- subsetByOverlaps(snps_by_seqname, ranges, ...)
-}
-
-setMethod("snpsByOverlaps", "OldFashionSNPlocs",
- .snpsByOverlaps_OldFashionSNPlocs
-)
-
.snpsById_OldFashionSNPlocs <- function(x, ids,
ifnotfound=c("error", "warning", "drop"))
{
diff --git a/build/vignette.rds b/build/vignette.rds
index 2d9988d..7e30201 100644
Binary files a/build/vignette.rds and b/build/vignette.rds differ
diff --git a/debian/changelog b/debian/changelog
index 6c0a055..dc47d1d 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -1,3 +1,9 @@
+r-bioc-bsgenome (1.68.0-1) UNRELEASED; urgency=low
+
+ * New upstream release.
+
+ -- Debian Janitor <janitor@jelmer.uk> Thu, 08 Jun 2023 09:49:52 -0000
+
r-bioc-bsgenome (1.66.3-1) unstable; urgency=medium
* New upstream version
diff --git a/debian/patches/remove_paragraphs_bound_to_fail_from_vignette.patch b/debian/patches/remove_paragraphs_bound_to_fail_from_vignette.patch
index 8664000..ab967e2 100644
--- a/debian/patches/remove_paragraphs_bound_to_fail_from_vignette.patch
+++ b/debian/patches/remove_paragraphs_bound_to_fail_from_vignette.patch
@@ -9,8 +9,10 @@ Description: In the autopkgtest we are trying to reproduce the creation of
investigated by some BioConductor experts.
---- a/vignettes/GenomeSearching.Rnw
-+++ b/vignettes/GenomeSearching.Rnw
+Index: r-bioc-bsgenome.git/vignettes/GenomeSearching.Rnw
+===================================================================
+--- r-bioc-bsgenome.git.orig/vignettes/GenomeSearching.Rnw
++++ r-bioc-bsgenome.git/vignettes/GenomeSearching.Rnw
@@ -107,132 +107,7 @@ The BSgenome data package for the ce2 ge
available in Bioconductor but they could be added if there is demand for
them.
diff --git a/inst/doc/BSgenomeForge.pdf b/inst/doc/BSgenomeForge.pdf
index 9791f8b..5cb8ae6 100644
Binary files a/inst/doc/BSgenomeForge.pdf and b/inst/doc/BSgenomeForge.pdf differ
diff --git a/inst/doc/GenomeSearching.pdf b/inst/doc/GenomeSearching.pdf
index 41f8ec0..45a1fec 100644
Binary files a/inst/doc/GenomeSearching.pdf and b/inst/doc/GenomeSearching.pdf differ
diff --git a/inst/extdata/GentlemanLab/BSgenome.Amellifera.BeeBase.assembly4-seed b/inst/extdata/GentlemanLab/BSgenome.Amellifera.BeeBase.assembly4-seed
index f0e86d7..0ece752 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Amellifera.BeeBase.assembly4-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Amellifera.BeeBase.assembly4-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Amellifera.BeeBase.assembly4
-Title: Full genome sequences for Apis mellifera (BeeBase assembly4)
-Description: iFull genome sequences for Apis mellifera (Honey Bee) as provided by BeeBase (assembly4, Feb. 2008) and stored in Biostrings objects.
+Title: Full genomic sequences for Apis mellifera (BeeBase assembly4)
+Description: iFull genomic sequences for Apis mellifera (Honey Bee) as provided by BeeBase (assembly4, Feb. 2008) and stored in Biostrings objects.
Version: 1.4.2
organism: Apis mellifera
common_name: Honey Bee
@@ -13,5 +13,5 @@ organism_biocview: Apis_mellifera
BSgenomeObjname: Amellifera
seqnames: paste("Group", 1:16, sep="")
mseqnames: "GroupUn"
-PkgExamples: genome$Group1 # same as genome[["Group1"]]
+PkgExamples: bsg$Group1 # same as bsg[["Group1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Amellifera.BeeBase.assembly4/seqs
diff --git a/inst/extdata/GentlemanLab/BSgenome.Amellifera.NCBI.AmelHAv3.1-seed b/inst/extdata/GentlemanLab/BSgenome.Amellifera.NCBI.AmelHAv3.1-seed
index c438619..599b20f 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Amellifera.NCBI.AmelHAv3.1-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Amellifera.NCBI.AmelHAv3.1-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Amellifera.NCBI.AmelHAv3.1
-Title: Full genome sequences for Apis mellifera (Amel_HAv3.1)
-Description: Full genome sequences for Apis mellifera as provided by NCBI (assembly Amel_HAv3.1, assembly accession GCF_003254395.2) and stored in Biostrings objects.
+Title: Full genomic sequences for Apis mellifera (Amel_HAv3.1)
+Description: Full genomic sequences for Apis mellifera as provided by NCBI (assembly Amel_HAv3.1, assembly accession GCF_003254395.2) and stored in Biostrings objects.
Version: 1.5.0
organism: Apis mellifera
common_name: Honey bee
@@ -12,6 +12,6 @@ organism_biocview: Apis_mellifera
BSgenomeObjname: Amellifera
circ_seqs: "MT"
SrcDataFiles: GCF_003254395.2_Amel_HAv3.1_genomic.fna.gz from https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/254/395/GCF_003254395.2_Amel_HAv3.1/
-PkgExamples: genome[["Group1"]]
+PkgExamples: bsg[["Group1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Amellifera.NCBI.AmelHAv3.1/seqs
seqfile_name: Amel_HAv3.1.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Amellifera.UCSC.apiMel2-seed b/inst/extdata/GentlemanLab/BSgenome.Amellifera.UCSC.apiMel2-seed
index 2f95a97..926c5c0 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Amellifera.UCSC.apiMel2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Amellifera.UCSC.apiMel2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Amellifera.UCSC.apiMel2
-Title: Full genome sequences for Apis mellifera (UCSC version apiMel2)
-Description: Full genome sequences for Apis mellifera (Honey Bee) as provided by UCSC (apiMel2, Jan. 2005) and stored in Biostrings objects.
+Title: Full genomic sequences for Apis mellifera (UCSC version apiMel2)
+Description: Full genomic sequences for Apis mellifera (Honey Bee) as provided by UCSC (apiMel2, Jan. 2005) and stored in Biostrings objects.
Version: 1.4.2
organism: Apis mellifera
common_name: Honey Bee
@@ -12,6 +12,6 @@ source_url: http://hgdownload.cse.ucsc.edu/goldenPath/apiMel2/bigZips/
organism_biocview: Apis_mellifera
BSgenomeObjname: Amellifera
SrcDataFiles: apiMel2.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/apiMel2/bigZips/
-PkgExamples: genome$Group1 # same as genome[["Group1"]]
+PkgExamples: bsg$Group1 # same as bsg[["Group1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Amellifera.UCSC.apiMel2/seqs
seqfile_name: apiMel2.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Amellifera.UCSC.apiMel2.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Amellifera.UCSC.apiMel2.masked-seed
index a75f48f..e25e7d5 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Amellifera.UCSC.apiMel2.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Amellifera.UCSC.apiMel2.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Amellifera.UCSC.apiMel2.masked
-Title: Full masked genome sequences for Apis mellifera (UCSC version apiMel2)
-Description: Full genome sequences for Apis mellifera (Honey Bee) as provided by UCSC (apiMel2, Jan. 2005) and stored in Biostrings objects. The sequences are the same as in BSgenome.Amellifera.UCSC.apiMel2, except that each of them has the 3 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), and (3) the mask of repeats from RepeatMasker (RM mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Apis mellifera (UCSC version apiMel2)
+Description: Full genomic sequences for Apis mellifera (Honey Bee) as provided by UCSC (apiMel2, Jan. 2005) and stored in Biostrings objects. The sequences are the same as in BSgenome.Amellifera.UCSC.apiMel2, except that each of them has the 3 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), and (3) the mask of repeats from RepeatMasker (RM mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Amellifera.UCSC.apiMel2
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/apiMel2/bigZips/
@@ -8,9 +8,9 @@ organism_biocview: Apis_mellifera
nmask_per_seq: 3
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/apiMel2/database/
RM masks: GroupOut.zip from http://hgdownload.cse.ucsc.edu/goldenPath/apiMel2/bigZips/
-PkgExamples: genome$Group1 # a MaskedDNAString object!
+PkgExamples: mbsg$Group1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$Group1) # same as BSgenome.Amellifera.UCSC.apiMel2$Group1
+ unmasked(mbsg$Group1) # same as BSgenome.Amellifera.UCSC.apiMel2$Group1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Amellifera.UCSC.apiMel2/masks
AGAPSfiles_name: gap.txt
RMfiles_suffix: .out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.04232008-seed b/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.04232008-seed
index 436087e..0eba528 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.04232008-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.04232008-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Athaliana.TAIR.04232008
-Title: Full genome sequences for Arabidopsis thaliana (TAIR version from April 23, 2008)
-Description: Full genome sequences for Arabidopsis thaliana as provided by TAIR (snapshot from April 23, 2008) and stored in Biostrings objects.
+Title: Full genomic sequences for Arabidopsis thaliana (TAIR version from April 23, 2008)
+Description: Full genomic sequences for Arabidopsis thaliana as provided by TAIR (snapshot from April 23, 2008) and stored in Biostrings objects.
Version: 1.4.2
organism: Arabidopsis thaliana
common_name: Arabidopsis
@@ -18,7 +18,7 @@ SrcDataFiles: all the chr*.fas file from ftp://ftp.arabidopsis.org/home/tair/Seq
NOT aimed to be the permanent URL for the 04232008 snapshot of the genome.
TAIR might update the content of this folder in the future with a new
snapshot and move the 04232008 snapshot to the OLD/ subfolder.
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Athaliana.TAIR.04232008/seqs
seqfiles_suffix: .fas
ondisk_seq_format: rda
diff --git a/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.TAIR10.1-seed b/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.TAIR10.1-seed
index f1b6b5c..f1f0816 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.TAIR10.1-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.TAIR10.1-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Athaliana.TAIR.TAIR10.1
-Title: Full genome sequences for Arabidopsis thaliana (TAIR10.1)
-Description: Full genome sequences for Arabidopsis thaliana as provided by TAIR (TAIR10.1, RefSeq assembly accession: GCF_000001735.4) and stored in Biostrings objects.
+Title: Full genomic sequences for Arabidopsis thaliana (TAIR10.1)
+Description: Full genomic sequences for Arabidopsis thaliana as provided by TAIR (TAIR10.1, RefSeq assembly accession: GCF_000001735.4) and stored in Biostrings objects.
Version: 1.5.0
organism: Arabidopsis thaliana
common_name: Thale cress
@@ -11,6 +11,6 @@ source_url: https://www.ncbi.nlm.nih.gov/assembly/GCF_000001735.4
organism_biocview: Arabidopsis_thaliana
BSgenomeObjname: Athaliana
SrcDataFiles: GCF_000001735.4_TAIR10.1_genomic.fna.gz from https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/735/GCF_000001735.4_TAIR10.1/
-PkgExamples: genome[["1"]]
+PkgExamples: bsg[["1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Athaliana.TAIR.TAIR10.1/seqs
ondisk_seq_format: rds
diff --git a/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.TAIR9-seed b/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.TAIR9-seed
index a542508..2532216 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.TAIR9-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Athaliana.TAIR.TAIR9-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Athaliana.TAIR.TAIR9
-Title: Full genome sequences for Arabidopsis thaliana (TAIR9)
-Description: Full genome sequences for Arabidopsis thaliana as provided by TAIR (TAIR9 Genome Release) and stored in Biostrings objects. Note that TAIR10 is an "annotation release" based on the same genome assembly as TAIR9.
+Title: Full genomic sequences for Arabidopsis thaliana (TAIR9)
+Description: Full genomic sequences for Arabidopsis thaliana as provided by TAIR (TAIR9 Genome Release) and stored in Biostrings objects. Note that TAIR10 is an "annotation release" based on the same genome assembly as TAIR9.
Version: 1.4.2
organism: Arabidopsis thaliana
common_name: Arabidopsis
@@ -14,6 +14,6 @@ BSgenomeObjname: Athaliana
seqnames: paste("Chr", c(1:5, "M", "C"), sep="")
circ_seqs: c("ChrM", "ChrC")
SrcDataFiles: ftp://ftp.arabidopsis.org/home/tair/Genes/TAIR9_genome_release/TAIR9_chr_all.fas
-PkgExamples: genome$Chr1 # same as genome[["Chr1"]]
+PkgExamples: bsg$Chr1 # same as bsg[["Chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Athaliana.TAIR.TAIR9/seqs
ondisk_seq_format: rda
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau3-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau3-seed
index 70bc219..3768565 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau3-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau3
-Title: Full genome sequences for Bos taurus (UCSC version bosTau3)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (bosTau3, Aug. 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Bos taurus (UCSC version bosTau3)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (bosTau3, Aug. 2006) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Bos taurus
@@ -13,7 +13,7 @@ source_url: http://hgdownload.cse.ucsc.edu/goldenPath/bosTau3/bigZips/
organism_biocview: Bos_taurus
BSgenomeObjname: Btaurus
SrcDataFiles: bosTau3.2bit from http://hgdownload.soe.ucsc.edu/goldenPath/bosTau3/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -21,11 +21,11 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## UCSC makes the upstream sequences for bosTau3 available for download
## here http://hgdownload.soe.ucsc.edu/goldenPath/bosTau3/bigZips/
## Alternatively, the upstream sequences can be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("bosTau3", "refGene")
- up1000seqs <- extractUpstreamSeqs(genome, txdb, width=1000)
+ up1000seqs <- extractUpstreamSeqs(bsg, txdb, width=1000)
.
## See ?extractUpstreamSeqs in the GenomicFeatures package for more
## information about this.
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau3.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau3.masked-seed
index 6e0310e..ce48377 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau3.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau3.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau3.masked
-Title: Full masked genome sequences for Bos taurus (UCSC version bosTau3)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (bosTau3, Aug. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Btaurus.UCSC.bosTau3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Bos taurus (UCSC version bosTau3)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (bosTau3, Aug. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Btaurus.UCSC.bosTau3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Btaurus.UCSC.bosTau3
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/bosTau3/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau3/database/
RM masks: bosTau3.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau3/bigZips/
TRF masks: bosTau3.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau3/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Btaurus.UCSC.bosTau3$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Btaurus.UCSC.bosTau3$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Btaurus.UCSC.bosTau3/masks
AGAPSfiles_name: gap.txt
RMfiles_name: bosTau3.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau4-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau4-seed
index 9a2626c..87ad155 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau4-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau4-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau4
-Title: Full genome sequences for Bos taurus (UCSC version bosTau4)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (bosTau4, Oct. 2007) and stored in Biostrings objects.
+Title: Full genomic sequences for Bos taurus (UCSC version bosTau4)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (bosTau4, Oct. 2007) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Bos taurus
@@ -14,7 +14,7 @@ organism_biocview: Bos_taurus
BSgenomeObjname: Btaurus
circ_seqs: "chrM"
SrcDataFiles: bosTau4.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau4/chromosomes/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -22,11 +22,11 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## UCSC makes the upstream sequences for bosTau4 available for download
## here http://hgdownload.soe.ucsc.edu/goldenPath/bosTau4/bigZips/
## Alternatively, the upstream sequences can be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("bosTau4", "refGene")
- up1000seqs <- extractUpstreamSeqs(genome, txdb, width=1000)
+ up1000seqs <- extractUpstreamSeqs(bsg, txdb, width=1000)
.
## See ?extractUpstreamSeqs in the GenomicFeatures package for more
## information about this.
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau4.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau4.masked-seed
index 410a33f..8c565fa 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau4.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau4.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau4.masked
-Title: Full masked genome sequences for Bos taurus (UCSC version bosTau4)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (bosTau4, Oct. 2007) and stored in Biostrings objects. The sequences are the same as in BSgenome.Btaurus.UCSC.bosTau4, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Bos taurus (UCSC version bosTau4)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (bosTau4, Oct. 2007) and stored in Biostrings objects. The sequences are the same as in BSgenome.Btaurus.UCSC.bosTau4, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Btaurus.UCSC.bosTau4
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/bosTau4/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau4/database/
RM masks: bosTau4.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau4/bigZips/
TRF masks: bosTau4.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau4/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Btaurus.UCSC.bosTau4$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Btaurus.UCSC.bosTau4$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Btaurus.UCSC.bosTau4/masks
AGAPSfiles_name: gap.txt
RMfiles_name: bosTau4.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau6-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau6-seed
index a1080ae..97061e0 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau6-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau6-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau6
-Title: Full genome sequences for Bos taurus (UCSC version bosTau6)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (bosTau6, Nov. 2009) and stored in Biostrings objects.
+Title: Full genomic sequences for Bos taurus (UCSC version bosTau6)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (bosTau6, Nov. 2009) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Bos taurus
@@ -16,20 +16,20 @@ seqnames: paste("chr", c(1:29, "X", "M"), sep="")
circ_seqs: "chrM"
mseqnames: "chrUn"
SrcDataFiles: bosTau6.fa.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau6/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## --------------------------------------------------------------------- ## Upstream sequences
## ---------------------------------------------------------------------
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for bosTau6 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("bosTau6", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau6.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau6.masked-seed
index c4a0d3a..931d9b4 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau6.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau6.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau6.masked
-Title: Full masked genome sequences for Bos taurus (UCSC version bosTau6)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (bosTau6, Nov. 2009) and stored in Biostrings objects. The sequences are the same as in BSgenome.Btaurus.UCSC.bosTau6, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Bos taurus (UCSC version bosTau6)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (bosTau6, Nov. 2009) and stored in Biostrings objects. The sequences are the same as in BSgenome.Btaurus.UCSC.bosTau6, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Btaurus.UCSC.bosTau6
source_url: http://hgdownload.soe.ucsc.edu/goldenPath/bosTau6/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau6/database/
RM masks: bosTau6.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau6/bigZips/
TRF masks: bosTau6.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau6/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Btaurus.UCSC.bosTau6$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Btaurus.UCSC.bosTau6$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Btaurus.UCSC.bosTau6/masks
AGAPSfiles_name: gap.txt
RMfiles_name: bosTau6.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau8-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau8-seed
index 40bbca5..e29477d 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau8-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau8-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau8
-Title: Full genome sequences for Bos taurus (UCSC version bosTau8)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (bosTau8, Jun. 2014) and stored in Biostrings objects.
+Title: Full genomic sequences for Bos taurus (UCSC version bosTau8)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (bosTau8, Jun. 2014) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Bos taurus
@@ -14,7 +14,7 @@ organism_biocview: Bos_taurus
BSgenomeObjname: Btaurus
circ_seqs: "chrM"
SrcDataFiles: bosTau8.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau8/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Extract the upstream sequences
@@ -22,11 +22,11 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## The upstream sequences located in
## http://hgdownload.cse.ucsc.edu/goldenPath/bosTau8/bigZips/
## are based on RefSeq genes (RefSeq Genes track in the Genome Browser).
- ## These can easily be extracted from the full genome sequences with:
+ ## These can easily be extracted from the full genomic sequences with:
.
library(GenomicFeatures)
refGene_txdb <- suppressWarnings(makeTxDbFromUCSC("bosTau8", "refGene"))
- refGene_up1000seqs <- extractUpstreamSeqs(genome, refGene_txdb)
+ refGene_up1000seqs <- extractUpstreamSeqs(bsg, refGene_txdb)
.
## Note that you can make a TxDb object from various annotation
## resources. See the makeTxDbFromUCSC(), makeTxDbFromBiomart(), and
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau9-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau9-seed
index e399c2b..00ce04a 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau9-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau9-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau9
-Title: Full genome sequences for Bos taurus (UCSC version bosTau9)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (bosTau9, Apr. 2018) and stored in Biostrings objects.
+Title: Full genomic sequences for Bos taurus (UCSC version bosTau9)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (bosTau9, Apr. 2018) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Bos taurus
@@ -14,7 +14,7 @@ organism_biocview: Bos_taurus
BSgenomeObjname: Btaurus
circ_seqs: "chrM"
SrcDataFiles: bosTau9.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/bosTau9/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Extract the upstream sequences
@@ -22,11 +22,11 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## The upstream sequences located in
## http://hgdownload.cse.ucsc.edu/goldenPath/bosTau9/bigZips/
## are based on RefSeq genes (RefSeq Genes track in the Genome Browser).
- ## These can easily be extracted from the full genome sequences with:
+ ## These can easily be extracted from the full genomic sequences with:
.
library(GenomicFeatures)
refGene_txdb <- suppressWarnings(makeTxDbFromUCSC("bosTau9", "refGene"))
- refGene_up1000seqs <- extractUpstreamSeqs(genome, refGene_txdb)
+ refGene_up1000seqs <- extractUpstreamSeqs(bsg, refGene_txdb)
.
## Note that you can make a TxDb object from various annotation
## resources. See the makeTxDbFromUCSC(), makeTxDbFromEnsembl(), and
diff --git a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau9.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau9.masked-seed
index 85849a5..acd2e9e 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau9.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Btaurus.UCSC.bosTau9.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Btaurus.UCSC.bosTau9.masked
-Title: Full masked genome sequences for Bos taurus (UCSC version bosTau9)
-Description: Full genome sequences for Bos taurus (Cow) as provided by UCSC (genome bosTau9) and stored in Biostrings objects. The sequences are the same as in BSgenome.Btaurus.UCSC.bosTau9, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Bos taurus (UCSC version bosTau9)
+Description: Full genomic sequences for Bos taurus (Cow) as provided by UCSC (genome bosTau9) and stored in Biostrings objects. The sequences are the same as in BSgenome.Btaurus.UCSC.bosTau9, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.4.4
RefPkgname: BSgenome.Btaurus.UCSC.bosTau9
source_url: https://hgdownload.soe.ucsc.edu/goldenPath/bosTau9/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/bosTau9/database/ on March 23, 2022
RM masks: bosTau9.fa.out.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/bosTau9/bigZips/ on March 23, 2022
TRF masks: bosTau9.trf.bed.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/bosTau9/bigZips/ on March 23, 2022
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Btaurus.UCSC.bosTau9$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Btaurus.UCSC.bosTau9$chr1
masks_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Btaurus.UCSC.bosTau9/masks
AGAPSfiles_name: gap.txt.gz
RMfiles_name: bosTau9.fa.out.gz
diff --git a/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce10-seed b/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce10-seed
index 6c02517..59f55af 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce10-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce10-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Celegans.UCSC.ce10
-Title: Full genome sequences for Caenorhabditis elegans (UCSC version ce10)
-Description: Full genome sequences for Caenorhabditis elegans (Worm) as provided by UCSC (ce10, Oct. 2010) and stored in Biostrings objects.
+Title: Full genomic sequences for Caenorhabditis elegans (UCSC version ce10)
+Description: Full genomic sequences for Caenorhabditis elegans (Worm) as provided by UCSC (ce10, Oct. 2010) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Caenorhabditis elegans
@@ -15,20 +15,20 @@ BSgenomeObjname: Celegans
seqnames: paste("chr", c("I", "II", "III", "IV", "V", "X", "M"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from ftp://hgdownload.cse.ucsc.edu/goldenPath/ce10/bigZips/
-PkgExamples: genome$chrI # same as genome[["chrI"]]
+PkgExamples: bsg$chrI # same as bsg[["chrI"]]
.
## --------------------------------------------------------------------- ## Upstream sequences
## ---------------------------------------------------------------------
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for ce10 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("ce10", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce11-seed b/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce11-seed
index b1eee9a..04ffb0d 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce11-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce11-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Celegans.UCSC.ce11
-Title: Full genome sequences for Caenorhabditis elegans (UCSC version ce11)
-Description: Full genome sequences for Caenorhabditis elegans (Worm) as provided by UCSC (ce11, Feb. 2013) and stored in Biostrings objects.
+Title: Full genomic sequences for Caenorhabditis elegans (UCSC version ce11)
+Description: Full genomic sequences for Caenorhabditis elegans (Worm) as provided by UCSC (ce11, Feb. 2013) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Caenorhabditis elegans
@@ -15,6 +15,6 @@ BSgenomeObjname: Celegans
seqnames: paste("chr", c("I", "II", "III", "IV", "V", "X", "M"), sep="")
circ_seqs: "chrM"
SrcDataFiles: ce11.2bit from http://hgdownload.soe.ucsc.edu/goldenPath/ce11/bigZips/
-PkgExamples: genome$chrI # same as genome[["chrI"]]
+PkgExamples: bsg$chrI # same as bsg[["chrI"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Celegans.UCSC.ce11/seqs
seqfile_name: ce11.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce2-seed b/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce2-seed
index 5feeb5a..b10a355 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Celegans.UCSC.ce2
-Title: Full genome sequences for Caenorhabditis elegans (UCSC version ce2)
-Description: Full genome sequences for Caenorhabditis elegans (Worm) as provided by UCSC (ce2, Mar. 2004) and stored in Biostrings objects.
+Title: Full genomic sequences for Caenorhabditis elegans (UCSC version ce2)
+Description: Full genomic sequences for Caenorhabditis elegans (Worm) as provided by UCSC (ce2, Mar. 2004) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Caenorhabditis elegans
@@ -15,20 +15,20 @@ BSgenomeObjname: Celegans
seqnames: paste("chr", c("I", "II", "III", "IV", "V", "X", "M"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.zip from http://hgdownload.cse.ucsc.edu/goldenPath/ce2/bigZips/
-PkgExamples: genome$chrI # same as genome[["chrI"]]
+PkgExamples: bsg$chrI # same as bsg[["chrI"]]
.
## --------------------------------------------------------------------- ## Upstream sequences
## ---------------------------------------------------------------------
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for ce2 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("ce2", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce6-seed b/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce6-seed
index b97c7c3..012ff48 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce6-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Celegans.UCSC.ce6-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Celegans.UCSC.ce6
-Title: Full genome sequences for Caenorhabditis elegans (UCSC version ce6)
-Description: Full genome sequences for Caenorhabditis elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings objects.
+Title: Full genomic sequences for Caenorhabditis elegans (UCSC version ce6)
+Description: Full genomic sequences for Caenorhabditis elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings objects.
Version: 1.4.2
Suggests: TxDb.Celegans.UCSC.ce6.ensGene
organism: Caenorhabditis elegans
@@ -15,7 +15,7 @@ BSgenomeObjname: Celegans
seqnames: paste("chr", c("I", "II", "III", "IV", "V", "X", "M"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from ftp://hgdownload.cse.ucsc.edu/goldenPath/ce6/bigZips/
-PkgExamples: genome$chrI # same as genome[["chrI"]]
+PkgExamples: bsg$chrI # same as bsg[["chrI"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chrI # same as genome[["chrI"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for ce6 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(TxDb.Celegans.UCSC.ce6.ensGene)
txdb <- TxDb.Celegans.UCSC.ce6.ensGene
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam2-seed b/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam2-seed
index f702b8a..5ab7d8e 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Cfamiliaris.UCSC.canFam2
-Title: Full genome sequences for Canis lupus familiaris (UCSC version canFam2)
-Description: Full genome sequences for Canis lupus familiaris (Dog) as provided by UCSC (canFam2, May 2005) and stored in Biostrings objects.
+Title: Full genomic sequences for Canis lupus familiaris (UCSC version canFam2)
+Description: Full genomic sequences for Canis lupus familiaris (Dog) as provided by UCSC (canFam2, May 2005) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Canis lupus familiaris
@@ -15,20 +15,20 @@ BSgenomeObjname: Cfamiliaris
seqnames: paste("chr", c(1:38, "X", "M", "Un"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/canFam2/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
## ---------------------------------------------------------------------
## The upstream sequences for canFam2 (i.e. the sequences 1000 bases
## upstream of annotated transcription starts) can easily be extracted
- ## from the full genome sequences with something like:
+ ## from the full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("canFam2", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam2.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam2.masked-seed
index d0bb9e0..93a19ae 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam2.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam2.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Cfamiliaris.UCSC.canFam2.masked
-Title: Full masked genome sequences for Canis lupus familiaris (UCSC version canFam2)
-Description: Full genome sequences for Canis lupus familiaris (Dog) as provided by UCSC (canFam2, May 2005) and stored in Biostrings objects. The sequences are the same as in BSgenome.Cfamiliaris.UCSC.canFam2, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Canis lupus familiaris (UCSC version canFam2)
+Description: Full genomic sequences for Canis lupus familiaris (Dog) as provided by UCSC (canFam2, May 2005) and stored in Biostrings objects. The sequences are the same as in BSgenome.Cfamiliaris.UCSC.canFam2, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Cfamiliaris.UCSC.canFam2
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/canFam2/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/canFam2/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/canFam2/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/canFam2/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Cfamiliaris.UCSC.canFam2$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Cfamiliaris.UCSC.canFam2$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Cfamiliaris.UCSC.canFam2/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam3-seed b/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam3-seed
index 120a31e..6f78256 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam3-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Cfamiliaris.UCSC.canFam3
-Title: Full genome sequences for Canis lupus familiaris (UCSC version canFam3)
-Description: Full genome sequences for Canis lupus familiaris (Dog) as provided by UCSC (canFam3, Sep. 2011) and stored in Biostrings objects.
+Title: Full genomic sequences for Canis lupus familiaris (UCSC version canFam3)
+Description: Full genomic sequences for Canis lupus familiaris (Dog) as provided by UCSC (canFam3, Sep. 2011) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Canis lupus familiaris
@@ -16,7 +16,7 @@ seqnames: paste("chr", c(1:38, "X", "M"), sep="")
circ_seqs: "chrM"
mseqnames: "chrUn"
SrcDataFiles: canFam3.fa.gz from http://hgdownload.cse.ucsc.edu/goldenPath/canFam3/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -24,13 +24,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for canFam3 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("canFam3", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam3.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam3.masked-seed
index fabe3d2..b2466ac 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam3.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Cfamiliaris.UCSC.canFam3.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Cfamiliaris.UCSC.canFam3.masked
-Title: Full masked genome sequences for Canis lupus familiaris (UCSC version canFam3)
-Description: Full genome sequences for Canis lupus familiaris (Dog) as provided by UCSC (canFam3, Sep. 2011) and stored in Biostrings objects. The sequences are the same as in BSgenome.Cfamiliaris.UCSC.canFam3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Canis lupus familiaris (UCSC version canFam3)
+Description: Full genomic sequences for Canis lupus familiaris (Dog) as provided by UCSC (canFam3, Sep. 2011) and stored in Biostrings objects. The sequences are the same as in BSgenome.Cfamiliaris.UCSC.canFam3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Cfamiliaris.UCSC.canFam3
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/canFam3/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/canFam3/database/
RM masks: canFam3.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/canFam3/bigZips/
TRF masks: canFam3.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/canFam3/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Cfamiliaris.UCSC.canFam3$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Cfamiliaris.UCSC.canFam3$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Cfamiliaris.UCSC.canFam3/masks
AGAPSfiles_name: gap.txt
RMfiles_name: canFam3.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Cjacchus.UCSC.calJac3-seed b/inst/extdata/GentlemanLab/BSgenome.Cjacchus.UCSC.calJac3-seed
index 8fd2eb5..c6e6c70 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Cjacchus.UCSC.calJac3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Cjacchus.UCSC.calJac3-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Cjacchus.UCSC.calJac3
-Title: Full genome sequences for Callithrix jacchus (UCSC version calJac3)
-Description: Full genome sequences for Callithrix jacchus (Marmoset) as provided by UCSC (calJac3, Mar. 2009) and stored in Biostrings objects.
+Title: Full genomic sequences for Callithrix jacchus (UCSC version calJac3)
+Description: Full genomic sequences for Callithrix jacchus (Marmoset) as provided by UCSC (calJac3, Mar. 2009) and stored in Biostrings objects.
Version: 1.4.2
organism: Callithrix jacchus
common_name: Marmoset
@@ -12,6 +12,6 @@ source_url: http://hgdownload.cse.ucsc.edu/goldenPath/calJac3/bigZips/
organism_biocview: Callithrix_jacchus
BSgenomeObjname: Cjacchus
SrcDataFiles: calJac3.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/calJac3/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Cjacchus.UCSC.calJac3/seqs
seqfile_name: calJac3.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Cjacchus.UCSC.calJac4-seed b/inst/extdata/GentlemanLab/BSgenome.Cjacchus.UCSC.calJac4-seed
index 1a64fe9..9d52384 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Cjacchus.UCSC.calJac4-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Cjacchus.UCSC.calJac4-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Cjacchus.UCSC.calJac4
-Title: Full genome sequences for Callithrix jacchus (UCSC version calJac4)
-Description: Full genome sequences for Callithrix jacchus (Marmoset) as provided by UCSC (calJac4, May 2020) and wrapped in a BSgenome object.
+Title: Full genomic sequences for Callithrix jacchus (UCSC version calJac4)
+Description: Full genomic sequences for Callithrix jacchus (Marmoset) as provided by UCSC (calJac4, May 2020) and wrapped in a BSgenome object.
Version: 1.5.0
organism: Callithrix jacchus
common_name: Marmoset
@@ -11,6 +11,6 @@ source_url: http://hgdownload.cse.ucsc.edu/goldenPath/calJac4/bigZips/
organism_biocview: Callithrix_jacchus
BSgenomeObjname: Cjacchus
SrcDataFiles: calJac4.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/calJac4/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Cjacchus.UCSC.calJac4/seqs
seqfile_name: calJac4.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Creinhardtii.JGI.v5.6-seed b/inst/extdata/GentlemanLab/BSgenome.Creinhardtii.JGI.v5.6-seed
index ab95d56..7596b86 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Creinhardtii.JGI.v5.6-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Creinhardtii.JGI.v5.6-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Creinhardtii.JGI.v5.6
-Title: Full genome sequences for Chlamydomonas reinhardtii (v5.6)
-Description: Full genome sequences for Chlamydomonas reinhardtii (v5.6) as provided by JGI and stored in Biostrings objects. The data in this package is public. See 'citation("BSgenome.Creinhardtii.JGI.v5.6")' for how to cite in publications.
+Title: Full genomic sequences for Chlamydomonas reinhardtii (v5.6)
+Description: Full genomic sequences for Chlamydomonas reinhardtii (v5.6) as provided by JGI and stored in Biostrings objects. The data in this package is public. See 'citation("BSgenome.Creinhardtii.JGI.v5.6")' for how to cite in publications.
Version: 1.5.0
organism: Chlamydomonas reinhardtii
common_name: Green algae
@@ -12,7 +12,7 @@ organism_biocview: Chlamydomonas_reinhardtii
BSgenomeObjname: Creinhardtii
circ_seqs: character(0)
SrcDataFiles: Creinhardtii_281_v5.0.fa.gz from https://phytozome-next.jgi.doe.gov/info/Creinhardtii_v5_6
-PkgExamples: genome[["chromosome_1"]]
+PkgExamples: bsg[["chromosome_1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Creinhardtii.JGI.v5.6/seqs
seqfile_name: Creinhardtii_281_v5.0.2bit
citation_file: system.file("extdata", "GentlemanLab", "BSgenome.Creinhardtii.JGI.v5.6-tools", "CITATION", package="BSgenome")
diff --git a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm2-seed b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm2-seed
index 76cf8dd..f635ada 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Dmelanogaster.UCSC.dm2
-Title: Full genome sequences for Drosophila melanogaster (UCSC version dm2)
-Description: Full genome sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm2, Apr. 2004) and stored in Biostrings objects.
+Title: Full genomic sequences for Drosophila melanogaster (UCSC version dm2)
+Description: Full genomic sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm2, Apr. 2004) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Drosophila melanogaster
@@ -15,7 +15,7 @@ BSgenomeObjname: Dmelanogaster
seqnames: paste("chr", c("2L", "2R", "3L", "3R", "4", "X", "U", "M", "2h", "3h", "4h", "Xh", "Yh"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.zip from http://hgdownload.cse.ucsc.edu/goldenPath/dm2/bigZips/
-PkgExamples: genome$chr2L # same as genome[["chr2L"]]
+PkgExamples: bsg$chr2L # same as bsg[["chr2L"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chr2L # same as genome[["chr2L"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for dm2 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("dm2", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm2.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm2.masked-seed
index 59bb9cb..9cef5bf 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm2.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm2.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Dmelanogaster.UCSC.dm2.masked
-Title: Full masked genome sequences for Drosophila melanogaster (UCSC version dm2)
-Description: Full genome sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm2, Apr. 2004) and stored in Biostrings objects. The sequences are the same as in BSgenome.Dmelanogaster.UCSC.dm2, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Drosophila melanogaster (UCSC version dm2)
+Description: Full genomic sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm2, Apr. 2004) and stored in Biostrings objects. The sequences are the same as in BSgenome.Dmelanogaster.UCSC.dm2, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Dmelanogaster.UCSC.dm2
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/dm2/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/dm2/database/
RM masks: chromOut.zip from http://hgdownload.cse.ucsc.edu/goldenPath/dm2/bigZips/
TRF masks: chromTrf.zip from http://hgdownload.cse.ucsc.edu/goldenPath/dm2/bigZips/
-PkgExamples: genome$chr2L # a MaskedDNAString object!
+PkgExamples: mbsg$chr2L # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr2L) # same as BSgenome.Dmelanogaster.UCSC.dm2$$chr2L
+ unmasked(mbsg$chr2L) # same as BSgenome.Dmelanogaster.UCSC.dm2$$chr2L
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Dmelanogaster.UCSC.dm2/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm3-seed b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm3-seed
index fb2d78c..d74bfb5 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm3-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Dmelanogaster.UCSC.dm3
-Title: Full genome sequences for Drosophila melanogaster (UCSC version dm3)
-Description: Full genome sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm3, Apr. 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Drosophila melanogaster (UCSC version dm3)
+Description: Full genomic sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm3, Apr. 2006) and stored in Biostrings objects.
Version: 1.4.2
Suggests: TxDb.Dmelanogaster.UCSC.dm3.ensGene
organism: Drosophila melanogaster
@@ -15,7 +15,7 @@ BSgenomeObjname: Dmelanogaster
seqnames: paste("chr", c("2L", "2R", "3L", "3R", "4", "X", "U", "M", "2LHet", "2RHet", "3LHet", "3RHet", "XHet", "YHet", "Uextra"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/dm3/bigZips/
-PkgExamples: genome$chr2L # same as genome[["chr2L"]]
+PkgExamples: bsg$chr2L # same as bsg[["chr2L"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,7 +23,7 @@ PkgExamples: genome$chr2L # same as genome[["chr2L"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for dm3 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(TxDb.Dmelanogaster.UCSC.dm3.ensGene)
txdb <- TxDb.Dmelanogaster.UCSC.dm3.ensGene
@@ -33,7 +33,7 @@ PkgExamples: genome$chr2L # same as genome[["chr2L"]]
## extracting the upstream sequences for genes located on these
## scaffolds is not reliable. So we exclude them:
exclude <- c("chrU", "chrUextra")
- up1000seqs <- extractUpstreamSeqs(genome, txdb, width=1000,
+ up1000seqs <- extractUpstreamSeqs(bsg, txdb, width=1000,
exclude.seqlevels=exclude)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
diff --git a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm3.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm3.masked-seed
index 446712b..9b2c56d 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm3.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm3.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Dmelanogaster.UCSC.dm3.masked
-Title: Full masked genome sequences for Drosophila melanogaster (UCSC version dm3)
-Description: Full genome sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm3, Apr. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Dmelanogaster.UCSC.dm3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Drosophila melanogaster (UCSC version dm3)
+Description: Full genomic sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm3, Apr. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Dmelanogaster.UCSC.dm3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Dmelanogaster.UCSC.dm3
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/dm3/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/dm3/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/dm3/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/dm3/bigZips/
-PkgExamples: genome$chr2L # a MaskedDNAString object!
+PkgExamples: mbsg$chr2L # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr2L) # same as BSgenome.Dmelanogaster.UCSC.dm3$chr2L
+ unmasked(mbsg$chr2L) # same as BSgenome.Dmelanogaster.UCSC.dm3$chr2L
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Dmelanogaster.UCSC.dm3/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm6-seed b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm6-seed
index df9c4d4..fd1c5ac 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm6-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Dmelanogaster.UCSC.dm6-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Dmelanogaster.UCSC.dm6
-Title: Full genome sequences for Drosophila melanogaster (UCSC version dm6)
-Description: Full genome sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm6, Aug. 2014) and stored in Biostrings objects.
+Title: Full genomic sequences for Drosophila melanogaster (UCSC version dm6)
+Description: Full genomic sequences for Drosophila melanogaster (Fly) as provided by UCSC (dm6, Aug. 2014) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Drosophila melanogaster
@@ -15,7 +15,7 @@ BSgenomeObjname: Dmelanogaster
seqnames: seqnames(Seqinfo(genome="dm6"))
circ_seqs: "chrM"
SrcDataFiles: dm6.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/dm6/bigZips/
-PkgExamples: genome$chr2L # same as genome[["chr2L"]]
+PkgExamples: bsg$chr2L # same as bsg[["chr2L"]]
.
## ---------------------------------------------------------------------
## Extract the upstream sequences
@@ -25,7 +25,7 @@ PkgExamples: genome$chr2L # same as genome[["chr2L"]]
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("dm6", tablename="refGene")
- up1000seqs <- extractUpstreamSeqs(genome, txdb, width=1000)
+ up1000seqs <- extractUpstreamSeqs(bsg, txdb, width=1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object) that
## contains a gene model based on dm6 or on a compatible genome (i.e.
diff --git a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer10-seed b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer10-seed
index ae1cc47..91d58f1 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer10-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer10-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Drerio.UCSC.danRer10
-Title: Full genome sequences for Danio rerio (UCSC version danRer10)
-Description: Full genome sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer10, Sep. 2014) and stored in Biostrings objects.
+Title: Full genomic sequences for Danio rerio (UCSC version danRer10)
+Description: Full genomic sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer10, Sep. 2014) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Danio rerio
@@ -14,7 +14,7 @@ organism_biocview: Danio_rerio
BSgenomeObjname: Drerio
circ_seqs: "chrM"
SrcDataFiles: danRer10.2bit from http://hgdownload.soe.ucsc.edu/goldenPath/danRer10/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Extract the upstream sequences
@@ -22,11 +22,11 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## The upstream sequences located in
## http://hgdownload.cse.ucsc.edu/goldenPath/danRer10/bigZips/
## are based on RefSeq genes (RefSeq Genes track in the Genome Browser).
- ## These can easily be extracted from the full genome sequences with:
+ ## These can easily be extracted from the full genomic sequences with:
.
library(GenomicFeatures)
refGene_txdb <- suppressWarnings(makeTxDbFromUCSC("danRer10", "refGene"))
- refGene_up1000seqs <- extractUpstreamSeqs(genome, refGene_txdb)
+ refGene_up1000seqs <- extractUpstreamSeqs(bsg, refGene_txdb)
.
## Note that you can make a TxDb object from various annotation
## resources. See the makeTxDbFromUCSC(), makeTxDbFromBiomart(), and
diff --git a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer11-seed b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer11-seed
index 810a04b..a035bf1 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer11-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer11-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Drerio.UCSC.danRer11
-Title: Full genome sequences for Danio rerio (UCSC version danRer11)
-Description: Full genome sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer11, May 2017) and stored in Biostrings objects.
+Title: Full genomic sequences for Danio rerio (UCSC version danRer11)
+Description: Full genomic sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer11, May 2017) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Danio rerio
@@ -14,7 +14,7 @@ organism_biocview: Danio_rerio
BSgenomeObjname: Drerio
circ_seqs: "chrM"
SrcDataFiles: danRer11.2bit from http://hgdownload.soe.ucsc.edu/goldenPath/danRer11/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Extract the upstream sequences
@@ -22,11 +22,11 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## The upstream sequences located in
## http://hgdownload.cse.ucsc.edu/goldenPath/danRer11/bigZips/
## are based on RefSeq genes (RefSeq Genes track in the Genome Browser).
- ## These can easily be extracted from the full genome sequences with:
+ ## These can easily be extracted from the full genomic sequences with:
.
library(GenomicFeatures)
refGene_txdb <- suppressWarnings(makeTxDbFromUCSC("danRer11", "refGene"))
- refGene_up1000seqs <- extractUpstreamSeqs(genome, refGene_txdb)
+ refGene_up1000seqs <- extractUpstreamSeqs(bsg, refGene_txdb)
.
## Note that you can make TxDb objects from various annotation
## resources. See the makeTxDbFromUCSC(), makeTxDbFromEnsembl(), and
diff --git a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer5-seed b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer5-seed
index 945ace9..26f2db0 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer5-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer5-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Drerio.UCSC.danRer5
-Title: Full genome sequences for Danio rerio (UCSC version danRer5)
-Description: Full genome sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer5, Jul. 2007) and stored in Biostrings objects.
+Title: Full genomic sequences for Danio rerio (UCSC version danRer5)
+Description: Full genomic sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer5, Jul. 2007) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Danio rerio
@@ -16,7 +16,7 @@ seqnames: paste("chr", c(1:25, "M"), sep="")
circ_seqs: "chrM"
mseqnames: c("Zv7_NA", "Zv7_scaffold")
SrcDataFiles: danRer5.fa.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer5/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -24,13 +24,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for danRer5 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("danRer5", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer5.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer5.masked-seed
index a2443f6..475c9bc 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer5.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer5.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Drerio.UCSC.danRer5.masked
-Title: Full masked genome sequences for Danio rerio (UCSC version danRer5)
-Description: Full genome sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer5, Jul. 2007) and stored in Biostrings objects. The sequences are the same as in BSgenome.Drerio.UCSC.danRer5, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Danio rerio (UCSC version danRer5)
+Description: Full genomic sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer5, Jul. 2007) and stored in Biostrings objects. The sequences are the same as in BSgenome.Drerio.UCSC.danRer5, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Drerio.UCSC.danRer5
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/danRer5/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer5/database/
RM masks: danRer5.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer5/bigZips/
TRF masks: danRer5.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer5/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Drerio.UCSC.danRer5$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Drerio.UCSC.danRer5$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Drerio.UCSC.danRer5/masks
AGAPSfiles_name: gap.txt
RMfiles_name: danRer5.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer6-seed b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer6-seed
index 64e666c..78ceb0e 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer6-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer6-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Drerio.UCSC.danRer6
-Title: Full genome sequences for Danio rerio (UCSC version danRer6)
-Description: Full genome sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer6, Dec. 2008) and stored in Biostrings objects.
+Title: Full genomic sequences for Danio rerio (UCSC version danRer6)
+Description: Full genomic sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer6, Dec. 2008) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Danio rerio
@@ -16,20 +16,20 @@ seqnames: paste("chr", c(1:25, "M"), sep="")
circ_seqs: "chrM"
mseqnames: c("Zv8_NA", "Zv8_scaffold")
SrcDataFiles: danRer6.fa.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer6/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## --------------------------------------------------------------------- ## Upstream sequences
## ---------------------------------------------------------------------
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for danRer6 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("danRer6", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer6.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer6.masked-seed
index 32c8d9c..13595b2 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer6.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer6.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Drerio.UCSC.danRer6.masked
-Title: Full masked genome sequences for Danio rerio (UCSC version danRer6)
-Description: Full genome sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer6, Dec. 2008) and stored in Biostrings objects. The sequences are the same as in BSgenome.Drerio.UCSC.danRer6, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Danio rerio (UCSC version danRer6)
+Description: Full genomic sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer6, Dec. 2008) and stored in Biostrings objects. The sequences are the same as in BSgenome.Drerio.UCSC.danRer6, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Drerio.UCSC.danRer6
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/danRer6/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer6/database/
RM masks: danRer6.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer6/bigZips/
TRF masks: danRer6.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer6/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Drerio.UCSC.danRer6$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Drerio.UCSC.danRer6$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Drerio.UCSC.danRer6/masks
AGAPSfiles_name: gap.txt
RMfiles_name: danRer6.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer7-seed b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer7-seed
index 9cbc4ef..1e18346 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer7-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer7-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Drerio.UCSC.danRer7
-Title: Full genome sequences for Danio rerio (UCSC version danRer7)
-Description: Full genome sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer7, Jul. 2010) and stored in Biostrings objects.
+Title: Full genomic sequences for Danio rerio (UCSC version danRer7)
+Description: Full genomic sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer7, Jul. 2010) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Danio rerio
@@ -16,20 +16,20 @@ seqnames: paste("chr", c(1:25, "M"), sep="")
circ_seqs: "chrM"
mseqnames: c("Zv9_NA", "Zv9_scaffold")
SrcDataFiles: danRer7.fa.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer7/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## --------------------------------------------------------------------- ## Upstream sequences
## ---------------------------------------------------------------------
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for danRer7 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("danRer7", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer7.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer7.masked-seed
index 1dbff2b..19a1d7b 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer7.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Drerio.UCSC.danRer7.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Drerio.UCSC.danRer7.masked
-Title: Full masked genome sequences for Danio rerio (UCSC version danRer7)
-Description: Full genome sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer7, Jul. 2010) and stored in Biostrings objects. The sequences are the same as in BSgenome.Drerio.UCSC.danRer7, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Danio rerio (UCSC version danRer7)
+Description: Full genomic sequences for Danio rerio (Zebrafish) as provided by UCSC (danRer7, Jul. 2010) and stored in Biostrings objects. The sequences are the same as in BSgenome.Drerio.UCSC.danRer7, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Drerio.UCSC.danRer7
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/danRer7/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer7/database/
RM masks: danRer7.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer7/bigZips/
TRF masks: danRer7.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/danRer7/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Drerio.UCSC.danRer7$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Drerio.UCSC.danRer7$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Drerio.UCSC.danRer7/masks
AGAPSfiles_name: gap.txt
RMfiles_name: danRer7.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Dvirilis.Ensembl.dvircaf1-seed b/inst/extdata/GentlemanLab/BSgenome.Dvirilis.Ensembl.dvircaf1-seed
index ab5211e..a3c9b34 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Dvirilis.Ensembl.dvircaf1-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Dvirilis.Ensembl.dvircaf1-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Dvirilis.Ensembl.dvircaf1
-Title: Full genome sequences for Drosophila virilis (assembly dvir_caf1)
-Description: Full genome sequences for Drosophila virilis (assembly dvir_caf1, GenBank assembly accession GCA_000005245.1) as provided by Ensembl and stored in Biostrings objects.
+Title: Full genomic sequences for Drosophila virilis (assembly dvir_caf1)
+Description: Full genomic sequences for Drosophila virilis (assembly dvir_caf1, GenBank assembly accession GCA_000005245.1) as provided by Ensembl and stored in Biostrings objects.
Version: 1.4.3
organism: Drosophila virilis
common_name:
@@ -13,6 +13,6 @@ organism_biocview: Drosophila_virilis
BSgenomeObjname: Dvirilis
circ_seqs: character(0)
SrcDataFiles: Drosophila_virilis.dvir_caf1.dna.toplevel.fa.gz, downloaded from ftp://ftp.ensemblgenomes.org/pub/release-46/metazoa/fasta/drosophila_virilis/dna/ and converted to 2bit format on March 2020
-PkgExamples: genome$scaffold_13049 # same as genome[["scaffold_13049"]]
+PkgExamples: bsg$scaffold_13049 # same as bsg[["scaffold_13049"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Dvirilis.Ensembl.dvircaf1/seqs
seqfile_name: Drosophila_virilis.dvir_caf1.dna.toplevel.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ecoli.NCBI.20080805-seed b/inst/extdata/GentlemanLab/BSgenome.Ecoli.NCBI.20080805-seed
index 3730564..17e1868 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ecoli.NCBI.20080805-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ecoli.NCBI.20080805-seed
@@ -186,7 +186,7 @@ SrcDataFiles: Escherichia_coli_536/NC_008253.fna
Escherichia_coli_W3110/AC_000091.fna
from ftp://ftp.ncbi.nih.gov/genomes/Bacteria/ (downloaded on 2008/08/05)
PkgExamples: ## The names of the sequences are the Refseq numbers!
- genome$NC_008253 # same as genome[["NC_008253"]]
+ bsg$NC_008253 # same as bsg[["NC_008253"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ecoli.NCBI.20080805/seqs
seqfiles_suffix: .fna
ondisk_seq_format: rda
diff --git a/inst/extdata/GentlemanLab/BSgenome.Gaculeatus.UCSC.gasAcu1-seed b/inst/extdata/GentlemanLab/BSgenome.Gaculeatus.UCSC.gasAcu1-seed
index ec6bc9c..95b5ceb 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Gaculeatus.UCSC.gasAcu1-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Gaculeatus.UCSC.gasAcu1-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Gaculeatus.UCSC.gasAcu1
-Title: Full genome sequences for Gasterosteus aculeatus (UCSC version gasAcu1)
-Description: Full genome sequences for Gasterosteus aculeatus (Stickleback) as provided by UCSC (gasAcu1, Feb. 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Gasterosteus aculeatus (UCSC version gasAcu1)
+Description: Full genomic sequences for Gasterosteus aculeatus (Stickleback) as provided by UCSC (gasAcu1, Feb. 2006) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Gasterosteus aculeatus
@@ -15,7 +15,7 @@ BSgenomeObjname: Gaculeatus
seqnames: paste("chr", c("I", "II", "III", "IV", "V", "VI", "VII", "VIII", "IX", "X", "XI", "XII", "XIII", "XIV", "XV", "XVI", "XVII", "XVIII", "XIX", "XX", "XXI", "M", "Un"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/gasAcu1/bigZips/
-PkgExamples: genome$chrI # same as genome[["chrI"]]
+PkgExamples: bsg$chrI # same as bsg[["chrI"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chrI # same as genome[["chrI"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for gasAcu1 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("gasAcu1", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Gaculeatus.UCSC.gasAcu1.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Gaculeatus.UCSC.gasAcu1.masked-seed
index d6eb6ef..369e61b 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Gaculeatus.UCSC.gasAcu1.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Gaculeatus.UCSC.gasAcu1.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Gaculeatus.UCSC.gasAcu1.masked
-Title: Full masked genome sequences for Gasterosteus aculeatus (UCSC version gasAcu1)
-Description: Full genome sequences for Gasterosteus aculeatus (Stickleback) as provided by UCSC (gasAcu1, Feb. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Gaculeatus.UCSC.gasAcu1, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Gasterosteus aculeatus (UCSC version gasAcu1)
+Description: Full genomic sequences for Gasterosteus aculeatus (Stickleback) as provided by UCSC (gasAcu1, Feb. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Gaculeatus.UCSC.gasAcu1, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Gaculeatus.UCSC.gasAcu1
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/gasAcu1/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/gasAcu1/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/gasAcu1/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/gasAcu1/bigZips/
-PkgExamples: genome$chrI # a MaskedDNAString object!
+PkgExamples: mbsg$chrI # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chrI) # same as BSgenome.Gaculeatus.UCSC.gasAcu1$chrI
+ unmasked(mbsg$chrI) # same as BSgenome.Gaculeatus.UCSC.gasAcu1$chrI
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Gaculeatus.UCSC.gasAcu1/masks
AGAPSfiles_name: gap.txt
RMfiles_suffix: .fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal3-seed b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal3-seed
index 7b4499b..51099cb 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal3-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ggallus.UCSC.galGal3
-Title: Full genome sequences for Gallus gallus (UCSC version galGal3)
-Description: Full genome sequences for Gallus gallus (Chicken) as provided by UCSC (galGal3, May 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Gallus gallus (UCSC version galGal3)
+Description: Full genomic sequences for Gallus gallus (Chicken) as provided by UCSC (galGal3, May 2006) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Gallus gallus
@@ -15,7 +15,7 @@ BSgenomeObjname: Ggallus
seqnames: paste("chr", c(1:28, 32, "M", "W", "Z", "E64", "E22C19W28_E50C23", paste(c(1:2, 4:8, 10:13, 16:18, 20, 22, 25, 28, "W", "Z", "E64", "E22C19W28_E50C23", "Un"), "_random", sep="")), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/galGal3/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for galGal3 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("galGal3", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal3.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal3.masked-seed
index 7c5158c..214f937 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal3.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal3.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ggallus.UCSC.galGal3.masked
-Title: Full masked genome sequences for Gallus gallus (UCSC version galGal3)
-Description: Full genome sequences for Gallus gallus (Chicken) as provided by UCSC (galGal3, May 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Ggallus.UCSC.galGal3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Gallus gallus (UCSC version galGal3)
+Description: Full genomic sequences for Gallus gallus (Chicken) as provided by UCSC (galGal3, May 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Ggallus.UCSC.galGal3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Ggallus.UCSC.galGal3
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/galGal3/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/galGal3/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/galGal3/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/galGal3/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Ggallus.UCSC.galGal3$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Ggallus.UCSC.galGal3$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ggallus.UCSC.galGal3/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal4-seed b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal4-seed
index 127c30b..6d52867 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal4-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal4-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ggallus.UCSC.galGal4
-Title: Full genome sequences for Gallus gallus (UCSC version galGal4)
-Description: Full genome sequences for Gallus gallus (Chicken) as provided by UCSC (galGal4, Nov. 2011) and stored in Biostrings objects.
+Title: Full genomic sequences for Gallus gallus (UCSC version galGal4)
+Description: Full genomic sequences for Gallus gallus (Chicken) as provided by UCSC (galGal4, Nov. 2011) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Gallus gallus
@@ -16,7 +16,7 @@ seqnames: paste("chr", c(1:28, 32, "M", "W", "Z", "LGE64", "LGE22C19W28_E50C23")
circ_seqs: "chrM"
mseqnames: c("random", "chrUn")
SrcDataFiles: galGal4.fa.gz from http://hgdownload.cse.ucsc.edu/goldenPath/galGal4/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -24,13 +24,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for galGal4 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("galGal4", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal4.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal4.masked-seed
index c9701ad..17a2a3c 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal4.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal4.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ggallus.UCSC.galGal4.masked
-Title: Full masked genome sequences for Gallus gallus (UCSC version galGal4)
-Description: Full genome sequences for Gallus gallus (Chicken) as provided by UCSC (galGal4, Nov. 2011) and stored in Biostrings objects. The sequences are the same as in BSgenome.Ggallus.UCSC.galGal4, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Gallus gallus (UCSC version galGal4)
+Description: Full genomic sequences for Gallus gallus (Chicken) as provided by UCSC (galGal4, Nov. 2011) and stored in Biostrings objects. The sequences are the same as in BSgenome.Ggallus.UCSC.galGal4, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Ggallus.UCSC.galGal4
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/galGal4/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/galGal4/database/
RM masks: galGal4.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/galGal4/bigZips/
TRF masks: galGal4.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/galGal4/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Ggallus.UCSC.galGal4$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Ggallus.UCSC.galGal4$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ggallus.UCSC.galGal4/masks
AGAPSfiles_name: gap.txt
RMfiles_name: galGal4.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal5-seed b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal5-seed
index 8e474bc..87c2cc1 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal5-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal5-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ggallus.UCSC.galGal5
-Title: Full genome sequences for Gallus gallus (UCSC version galGal5)
-Description: Full genome sequences for Gallus gallus (Chicken) as provided by UCSC (galGal5, Dec. 2015) and stored in Biostrings objects.
+Title: Full genomic sequences for Gallus gallus (UCSC version galGal5)
+Description: Full genomic sequences for Gallus gallus (Chicken) as provided by UCSC (galGal5, Dec. 2015) and stored in Biostrings objects.
Version: 1.4.2
organism: Gallus gallus
common_name: Chicken
@@ -13,6 +13,6 @@ organism_biocview: Gallus_gallus
BSgenomeObjname: Ggallus
circ_seqs: "chrM"
SrcDataFiles: galGal5.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/galGal5/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ggallus.UCSC.galGal5/seqs
seqfile_name: galGal5.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal6-seed b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal6-seed
index b690394..47edb54 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal6-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ggallus.UCSC.galGal6-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ggallus.UCSC.galGal6
-Title: Full genome sequences for Gallus gallus (UCSC version galGal6)
-Description: Full genome sequences for Gallus gallus (Chicken) as provided by UCSC (galGal6, Mar. 2018) and stored in Biostrings objects.
+Title: Full genomic sequences for Gallus gallus (UCSC version galGal6)
+Description: Full genomic sequences for Gallus gallus (Chicken) as provided by UCSC (galGal6, Mar. 2018) and stored in Biostrings objects.
Version: 1.4.2
organism: Gallus gallus
common_name: Chicken
@@ -13,6 +13,6 @@ organism_biocview: Gallus_gallus
BSgenomeObjname: Ggallus
circ_seqs: "chrM"
SrcDataFiles: galGal6.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/galGal6/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ggallus.UCSC.galGal6/seqs
seqfile_name: galGal6.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Gmellonella.NCBI.ASM364042v2-seed b/inst/extdata/GentlemanLab/BSgenome.Gmellonella.NCBI.ASM364042v2-seed
index 570b96f..13ad86f 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Gmellonella.NCBI.ASM364042v2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Gmellonella.NCBI.ASM364042v2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Gmellonella.NCBI.ASM364042v2
-Title: Full genome sequences for Galleria mellonella (ASM364042v2)
-Description: Full genome sequences for Galleria mellonella as provided by NCBI (assembly ASM364042v2, assembly accession GCF_003640425.2) and stored in Biostrings objects.
+Title: Full genomic sequences for Galleria mellonella (ASM364042v2)
+Description: Full genomic sequences for Galleria mellonella as provided by NCBI (assembly ASM364042v2, assembly accession GCF_003640425.2) and stored in Biostrings objects.
Version: 1.5.0
organism: Galleria mellonella
common_name: Greater wax moth
@@ -12,6 +12,6 @@ organism_biocview: Galleria_mellonella
BSgenomeObjname: Gmellonella
circ_seqs: "NC_028532.1"
SrcDataFiles: GCF_003640425.2_ASM364042v2_genomic.fna.gz from https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/640/425/GCF_003640425.2_ASM364042v2/
-PkgExamples: genome[["NC_028532.1"]]
+PkgExamples: bsg[["NC_028532.1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Gmellonella.NCBI.ASM364042v2/seqs
seqfile_name: ASM364042v2.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.NCBI.GRCh38-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.NCBI.GRCh38-seed
index 80051c0..223b0db 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.NCBI.GRCh38-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.NCBI.GRCh38-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Hsapiens.NCBI.GRCh38
-Title: Full genome sequences for Homo sapiens (GRCh38)
-Description: Full genome sequences for Homo sapiens (Human) as provided by NCBI (GRCh38, 2013-12-17) and stored in Biostrings objects.
+Title: Full genomic sequences for Homo sapiens (GRCh38)
+Description: Full genomic sequences for Homo sapiens (Human) as provided by NCBI (GRCh38, 2013-12-17) and stored in Biostrings objects.
Version: 1.4.2
organism: Homo sapiens
common_name: Human
@@ -447,6 +447,6 @@ seqnames: c("1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11",
"HSCHR19KIR_RP5_B_HAP_CTG3_1")
circ_seqs: "MT"
SrcDataFiles: GCA_000001405.15_GRCh38_top-level.fna.gz from ftp://ftp.ncbi.nlm.nih.gov/genbank/genomes/Eukaryotes/vertebrates_mammals/Homo_sapiens/GRCh38
-PkgExamples: genome[["1"]]
+PkgExamples: bsg[["1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Hsapiens.NCBI.GRCh38/seqs
ondisk_seq_format: rda
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.NCBI.T2T.CHM13v2.0-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.NCBI.T2T.CHM13v2.0-seed
index 06f68d0..6c0a2c2 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.NCBI.T2T.CHM13v2.0-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.NCBI.T2T.CHM13v2.0-seed
@@ -11,6 +11,6 @@ source_url: https://www.ncbi.nlm.nih.gov/assembly/GCA_009914755.4
organism_biocview: Homo_sapiens
BSgenomeObjname: Hsapiens
SrcDataFiles: GCA_009914755.4_T2T-CHM13v2.0_genomic.fna.gz from https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/009/914/755/GCA_009914755.4_T2T-CHM13v2.0/
-PkgExamples: genome[["1"]]
+PkgExamples: bsg[["1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Hsapiens.NCBI.T2T.CHM13v2.0/seqs
seqfile_name: T2T-CHM13v2.0.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg17-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg17-seed
index 9f34f13..3f65438 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg17-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg17-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Hsapiens.UCSC.hg17
-Title: Full genome sequences for Homo sapiens (UCSC version hg17)
-Description: Full genome sequences for Homo sapiens (Human) as provided by UCSC (hg17, May 2004) and stored in Biostrings objects.
+Title: Full genomic sequences for Homo sapiens (UCSC version hg17)
+Description: Full genomic sequences for Homo sapiens (Human) as provided by UCSC (hg17, May 2004) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Homo sapiens
@@ -15,20 +15,20 @@ BSgenomeObjname: Hsapiens
seqnames: paste("chr", c(1:22, "X", "Y", "M", "6_hla_hap1", "6_hla_hap2", paste(c((1:22)[-c(11, 14, 20, 21)], "X"), "_random", sep="")), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.zip from http://hgdownload.cse.ucsc.edu/goldenPath/hg17/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## --------------------------------------------------------------------- ## Upstream sequences
## ---------------------------------------------------------------------
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for hg17 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("hg17", "knownGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg17.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg17.masked-seed
index 5ec9871..86ff27e 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg17.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg17.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Hsapiens.UCSC.hg17.masked
-Title: Full masked genome sequences for Homo sapiens (UCSC version hg17)
-Description: Full genome sequences for Homo sapiens (Human) as provided by UCSC (hg17, May 2004) and stored in Biostrings objects. The sequences are the same as in BSgenome.Hsapiens.UCSC.hg17, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Homo sapiens (UCSC version hg17)
+Description: Full genomic sequences for Homo sapiens (Human) as provided by UCSC (hg17, May 2004) and stored in Biostrings objects. The sequences are the same as in BSgenome.Hsapiens.UCSC.hg17, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Hsapiens.UCSC.hg17
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/hg17/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/hg17/database/
RM masks: chromOut.zip from http://hgdownload.cse.ucsc.edu/goldenPath/hg17/bigZips/
TRF masks: chromTrf.zip from http://hgdownload.cse.ucsc.edu/goldenPath/hg17/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Hsapiens.UCSC.hg17$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Hsapiens.UCSC.hg17$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Hsapiens.UCSC.hg17/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg18-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg18-seed
index 23ed752..12fa873 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg18-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg18-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Hsapiens.UCSC.hg18
-Title: Full genome sequences for Homo sapiens (UCSC version hg18)
-Description: Full genome sequences for Homo sapiens (Human) as provided by UCSC (hg18, Mar. 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Homo sapiens (UCSC version hg18)
+Description: Full genomic sequences for Homo sapiens (Human) as provided by UCSC (hg18, Mar. 2006) and stored in Biostrings objects.
Version: 1.4.2
Suggests: TxDb.Hsapiens.UCSC.hg18.knownGene
organism: Homo sapiens
@@ -15,7 +15,7 @@ BSgenomeObjname: Hsapiens
seqnames: paste("chr", c(1:22, "X", "Y", "M", "5_h2_hap1", "6_cox_hap1", "6_qbl_hap2", "22_h2_hap1", paste(c((1:22)[-c(12, 14, 20)], "X"), "_random", sep="")), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.zip from http://hgdownload.cse.ucsc.edu/goldenPath/hg18/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for hg18 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(TxDb.Hsapiens.UCSC.hg18.knownGene)
txdb <- TxDb.Hsapiens.UCSC.hg18.knownGene
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg18.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg18.masked-seed
index 2287fb5..48a595d 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg18.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg18.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Hsapiens.UCSC.hg18.masked
-Title: Full masked genome sequences for Homo sapiens (UCSC version hg18)
-Description: Full genome sequences for Homo sapiens (Human) as provided by UCSC (hg18, Mar. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Hsapiens.UCSC.hg18, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Homo sapiens (UCSC version hg18)
+Description: Full genomic sequences for Homo sapiens (Human) as provided by UCSC (hg18, Mar. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Hsapiens.UCSC.hg18, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Hsapiens.UCSC.hg18
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/hg18/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/
RM masks: chromOut.zip from http://hgdownload.cse.ucsc.edu/goldenPath/hg18/bigZips/
TRF masks: chromTrf.zip from http://hgdownload.cse.ucsc.edu/goldenPath/hg18/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Hsapiens.UCSC.hg18$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Hsapiens.UCSC.hg18$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Hsapiens.UCSC.hg18/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg19-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg19-seed
index 3f91380..bad92f8 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg19-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg19-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Hsapiens.UCSC.hg19
-Title: Full genome sequences for Homo sapiens (UCSC version hg19, based on GRCh37.p13)
-Description: Full genome sequences for Homo sapiens (Human) as provided by UCSC (hg19, based on GRCh37.p13) and stored in Biostrings objects.
+Title: Full genomic sequences for Homo sapiens (UCSC version hg19, based on GRCh37.p13)
+Description: Full genomic sequences for Homo sapiens (Human) as provided by UCSC (hg19, based on GRCh37.p13) and stored in Biostrings objects.
Version: 1.4.3
organism: Homo sapiens
common_name: Human
@@ -12,6 +12,6 @@ source_url: https://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/latest/
organism_biocview: Homo_sapiens
BSgenomeObjname: Hsapiens
SrcDataFiles: hg19.2bit, downloaded from https://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/latest/ on March 24, 2020
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Hsapiens.UCSC.hg19/seqs
seqfile_name: hg19.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg19.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg19.masked-seed
index 129e7d4..054cc98 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg19.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg19.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Hsapiens.UCSC.hg19.masked
-Title: Full masked genome sequences for Homo sapiens (UCSC version hg19, based on GRCh37.p13)
-Description: Full genome sequences for Homo sapiens (Human) as provided by UCSC (hg19, based on GRCh37.p13) and stored in Biostrings objects. The sequences are the same as in BSgenome.Hsapiens.UCSC.hg19, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Homo sapiens (UCSC version hg19, based on GRCh37.p13)
+Description: Full genomic sequences for Homo sapiens (Human) as provided by UCSC (hg19, based on GRCh37.p13) and stored in Biostrings objects. The sequences are the same as in BSgenome.Hsapiens.UCSC.hg19, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.993
RefPkgname: BSgenome.Hsapiens.UCSC.hg19
source_url: https://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/latest/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz, downloaded from https://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/ on March 24, 2020
RM masks: hg19.fa.out.gz, downloaded from https://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/latest/ on March 24, 2020
TRF masks: hg19.trf.bed.gz, downloaded from https://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/latest/ on March 24, 2020
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Hsapiens.UCSC.hg19$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Hsapiens.UCSC.hg19$chr1
masks_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Hsapiens.UCSC.hg19/masks
AGAPSfiles_name: gap.txt.gz
RMfiles_name: hg19.fa.out.gz
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg38-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg38-seed
index 6080b9a..7ee57a9 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg38-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg38-seed
@@ -1,16 +1,58 @@
Package: BSgenome.Hsapiens.UCSC.hg38
-Title: Full genome sequences for Homo sapiens (UCSC version hg38, based on GRCh38.p13)
-Description: Full genome sequences for Homo sapiens (Human) as provided by UCSC (hg38, based on GRCh38.p13) and stored in Biostrings objects.
-Version: 1.4.4
+Title: Full genomic sequences for Homo sapiens (UCSC genome hg38)
+Description: Full genomic sequences for Homo sapiens as provided by UCSC (genome hg38, based on assembly GRCh38.p14 since 2023/01/31). The sequences are stored in DNAString objects.
+Version: 1.4.5
organism: Homo sapiens
common_name: Human
provider: UCSC
genome: hg38
-release_date: Feb 2019
-source_url: https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p13/
+release_date: 2023/01/31
+source_url: https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p14/
organism_biocview: Homo_sapiens
BSgenomeObjname: Hsapiens
-SrcDataFiles: hg38.p13.2bit, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p13/ on October 20, 2021
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+SrcDataFiles: hg38.p14.2bit, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p14/ on Feb 1st, 2023
+PkgExamples: ## Access individual sequences:
+ .
+ bsg$chr1 # same as bsg[["chr1"]]
+ alphabetFrequency(bsg[["chr1"]])
+ .
+ bsg[["chrM"]] # same as bsg$chrM
+ reverseComplement(bsg$chrM)
+ .
+ ## ---------------------------------------------------------------------
+ ## Switch the sequence names back and forth between UCSC and NCBI
+ ## ---------------------------------------------------------------------
+ .
+ ## IMPORTANT NOTE: Even though hg38 is officially based on the
+ ## GRCh38.p14 assembly (this is as of Jan 31, 2023, hg38 was based on
+ ## GRCh38.p13 before that), it contains 2 sequences that do not belong
+ ## to GRCh38.p14: chr11_KQ759759v1_fix and chr22_KQ759762v1_fix
+ ## These 2 foreign sequences belong to GRCh38.p13 (they are named
+ ## HG107_PATCH and HG1311_PATCH there), but they've been replaced with
+ ## sequences HG107_HG2565_PATCH and HG1311_HG2539_PATCH in GRCh38.p14.
+ .
+ seqinfo(bsg)
+ seqlevelsStyle(bsg) # UCSC
+ .
+ ## --- switch to NCBI names ---
+ .
+ bsg0 <- bsg
+ seqlevelsStyle(bsg) <- "NCBI"
+ bsg
+ seqinfo(bsg)
+ bsg[["1"]]
+ .
+ ## Surprise!
+ table(genome(bsg)) # 2 sequences belong to GRCh38.p13!
+ foreign_idx <- which(genome(bsg) == "GRCh38.p13")
+ seqinfo(bsg)[seqnames(bsg)[foreign_idx]]
+ seqlevelsStyle(bsg) # NCBI
+ .
+ ## --- switch back ---
+ .
+ seqlevelsStyle(bsg) <- "UCSC"
+ bsg
+ stopifnot(identical(bsg0, bsg))
+ seqinfo(bsg)[seqnames(bsg)[foreign_idx]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Hsapiens.UCSC.hg38/seqs
-seqfile_name: hg38.p13.2bit
+seqfile_name: hg38.p14.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg38.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg38.masked-seed
index dac8fe0..7b17852 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg38.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hg38.masked-seed
@@ -1,18 +1,18 @@
Package: BSgenome.Hsapiens.UCSC.hg38.masked
-Title: Full masked genome sequences for Homo sapiens (UCSC version hg38, based on GRCh38.p13)
-Description: Full genome sequences for Homo sapiens (Human) as provided by UCSC (genome hg38, based on GRCh38.p13) and stored in Biostrings objects. The sequences are the same as in BSgenome.Hsapiens.UCSC.hg38, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
-Version: 1.4.4
+Title: Full masked genomic sequences for Homo sapiens (UCSC version hg38)
+Description: Full genomic sequences for Homo sapiens as provided by UCSC (genome hg38, based on assembly GRCh38.p14 since 2023/01/31). The sequences are the same as in BSgenome.Hsapiens.UCSC.hg38, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default. The sequences are stored in MaskedDNAString objects.
+Version: 1.4.5
RefPkgname: BSgenome.Hsapiens.UCSC.hg38
-source_url: https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p13/
+source_url: https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p14/
organism_biocview: Homo_sapiens
nmask_per_seq: 4
-SrcDataFiles: AGAPS masks: gap.txt.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hg38/database/ on Oct. 23, 2021
- RM masks: hg38.p13.fa.out.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p13/ on Oct. 23, 2021
- TRF masks: hg38.p13.trf.bed.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p13/ on Oct. 23, 2021
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+SrcDataFiles: AGAPS masks: gap.txt.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hg38/database/ on Feb. 7, 2023
+ RM masks: hg38.p14.fa.out.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p14/ on Feb. 7, 2023
+ TRF masks: hg38.p14.trf.bed.gz, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/p14/ on Feb. 7, 2023
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Hsapiens.UCSC.hg38$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Hsapiens.UCSC.hg38$chr1
masks_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Hsapiens.UCSC.hg38/masks
AGAPSfiles_name: gap.txt.gz
-RMfiles_name: hg38.p13.fa.out.gz
-TRFfiles_name: hg38.p13.trf.bed.gz
+RMfiles_name: hg38.p14.fa.out.gz
+TRFfiles_name: hg38.p14.trf.bed.gz
diff --git a/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hs1-seed b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hs1-seed
new file mode 100644
index 0000000..527c01b
--- /dev/null
+++ b/inst/extdata/GentlemanLab/BSgenome.Hsapiens.UCSC.hs1-seed
@@ -0,0 +1,16 @@
+Package: BSgenome.Hsapiens.UCSC.hs1
+Title: Full genomic sequences for UCSC genome hs1 (Homo sapiens)
+Description: Full genomic sequences for UCSC genome hs1 (the hs1 genome is based on assembly T2T-CHM13v2.0, with GenBank assembly accession GCA_009914755.4). The sequences are stored in DNAString objects.
+Version: 1.4.4
+organism: Homo sapiens
+common_name: Human
+provider: UCSC
+genome: hs1
+release_date: Jan 2022
+source_url: https://hgdownload.soe.ucsc.edu/goldenPath/hs1/
+organism_biocview: Homo_sapiens
+BSgenomeObjname: Hsapiens
+SrcDataFiles: hs1.2bit, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/hs1/bigZips/ on 2023-01-03
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
+seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Hsapiens.UCSC.hs1/seqs
+seqfile_name: hs1.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mdomestica.UCSC.monDom5-seed b/inst/extdata/GentlemanLab/BSgenome.Mdomestica.UCSC.monDom5-seed
index fd0dfb4..f83273a 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mdomestica.UCSC.monDom5-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mdomestica.UCSC.monDom5-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mdomestica.UCSC.monDom5
-Title: Full genome sequences for Monodelphis domestica (UCSC version monDom5)
-Description: Full genome sequences for Monodelphis domestica (Opossum) as provided by UCSC (monDom5, Oct. 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Monodelphis domestica (UCSC version monDom5)
+Description: Full genomic sequences for Monodelphis domestica (Opossum) as provided by UCSC (monDom5, Oct. 2006) and stored in Biostrings objects.
Version: 1.4.2
organism: Monodelphis domestica
common_name: Opossum
@@ -13,6 +13,6 @@ organism_biocview: Monodelphis_domestica
BSgenomeObjname: Mdomestica
circ_seqs: "chrM"
SrcDataFiles: monDom5.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/monDom5/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mdomestica.UCSC.monDom5/seqs
seqfile_name: monDom5.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mfascicularis.NCBI.5.0-seed b/inst/extdata/GentlemanLab/BSgenome.Mfascicularis.NCBI.5.0-seed
index 7d11dc9..80e9906 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mfascicularis.NCBI.5.0-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mfascicularis.NCBI.5.0-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mfascicularis.NCBI.5.0
-Title: Full genome sequences for Macaca fascicularis (Macaca_fascicularis_5.0)
-Description: Full genome sequences for Macaca fascicularis (long-tailed macaque) as provided by NCBI (Macaca_fascicularis_5.0, 2013-06-12) and stored in Biostrings objects.
+Title: Full genomic sequences for Macaca fascicularis (Macaca_fascicularis_5.0)
+Description: Full genomic sequences for Macaca fascicularis (long-tailed macaque) as provided by NCBI (Macaca_fascicularis_5.0, 2013-06-12) and stored in Biostrings objects.
Version: 1.4.2
organism: Macaca fascicularis
common_name: long-tailed macaque
@@ -14,12 +14,12 @@ BSgenomeObjname: Mfascicularis
seqnames:
circ_seqs: "MT"
SrcDataFiles: GCF_000364345.1_Macaca_fascicularis_5.0_genomic.fna.gz from ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF_000364345.1_Macaca_fascicularis_5.0/
-PkgExamples: genome$MFA1 # same as genome[["MFA1"]]
+PkgExamples: bsg$MFA1 # same as bsg[["MFA1"]]
.
## ---------------------------------------------------------------------
## About the ordering of the sequences
## ---------------------------------------------------------------------
- ## The sequences in BSgenome object 'genome' are ordered like in the
+ ## The sequences in BSgenome object 'bsg' are ordered like in the
## assembly report at the following URL
url <- "ftp://ftp.ncbi.nlm.nih.gov/genomes/ASSEMBLY_REPORTS/All/GCF_000364345.1.assembly.txt"
## except that the MT sequence was moved from the last position to the
@@ -27,6 +27,6 @@ PkgExamples: genome$MFA1 # same as genome[["MFA1"]]
## (Scaffold* sequences):
SequenceName <- read.table(url, sep="\t", stringsAsFactors=FALSE)[[1]]
target_seqlevels <- SequenceName[c(1:21, 7601, 22:7600)]
- stopifnot(identical(seqlevels(genome), target_seqlevels))
+ stopifnot(identical(seqlevels(bsg), target_seqlevels))
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mfascicularis.NCBI.5.0/seqs
seqfile_name: Macaca_fascicularis_5.0.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mfascicularis.NCBI.6.0-seed b/inst/extdata/GentlemanLab/BSgenome.Mfascicularis.NCBI.6.0-seed
index 36ef104..7f6a0f9 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mfascicularis.NCBI.6.0-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mfascicularis.NCBI.6.0-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mfascicularis.NCBI.6.0
-Title: Full genome sequences for Macaca fascicularis (Macaca_fascicularis_6.0)
-Description: Full genome sequences for Macaca fascicularis (Crab-eating macaque) as provided by NCBI (assembly Macaca_fascicularis_6.0, assembly accession GCA_011100615.1) and stored in Biostrings objects.
+Title: Full genomic sequences for Macaca fascicularis (Macaca_fascicularis_6.0)
+Description: Full genomic sequences for Macaca fascicularis (Crab-eating macaque) as provided by NCBI (assembly Macaca_fascicularis_6.0, assembly accession GCA_011100615.1) and stored in Biostrings objects.
Version: 1.5.0
organism: Macaca fascicularis
common_name: Crab-eating macaque
@@ -11,6 +11,6 @@ source_url: https://www.ncbi.nlm.nih.gov/assembly/GCA_011100615.1
organism_biocview: Macaca_fascicularis
BSgenomeObjname: Mfascicularis
SrcDataFiles: GCA_011100615.1_Macaca_fascicularis_6.0_genomic.fna.gz from https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/011/100/615/GCA_011100615.1_Macaca_fascicularis_6.0/
-PkgExamples: genome[["1"]]
+PkgExamples: bsg[["1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Mfascicularis.NCBI.6.0/seqs
seqfile_name: Macaca_fascicularis_6.0.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mfuro.UCSC.musFur1-seed b/inst/extdata/GentlemanLab/BSgenome.Mfuro.UCSC.musFur1-seed
index 0b47361..b15a884 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mfuro.UCSC.musFur1-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mfuro.UCSC.musFur1-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mfuro.UCSC.musFur1
-Title: Full genome sequences for Mustela putorius furo (UCSC version musFur1)
-Description: Full genome sequences for Mustela putorius furo (Ferret) as provided by UCSC (musFur1, Apr. 2011) and stored in Biostrings objects.
+Title: Full genomic sequences for Mustela putorius furo (UCSC version musFur1)
+Description: Full genomic sequences for Mustela putorius furo (Ferret) as provided by UCSC (musFur1, Apr. 2011) and stored in Biostrings objects.
Version: 1.4.2
organism: Mustela putorius furo
common_name: Ferret
@@ -12,6 +12,6 @@ source_url: http://hgdownload.soe.ucsc.edu/goldenPath/musFur1/bigZips/
organism_biocview: Mustela_furo
BSgenomeObjname: Mfuro
SrcDataFiles: musFur1.2bit from http://hgdownload.soe.ucsc.edu/goldenPath/musFur1/bigZips/
-PkgExamples: genome$GL896898 # same as genome[["GL896898"]]
+PkgExamples: bsg$GL896898 # same as bsg[["GL896898"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mfuro.UCSC.musFur1/seqs
seqfile_name: musFur1.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac10-seed b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac10-seed
index 29b8567..911044e 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac10-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac10-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmulatta.UCSC.rheMac10
-Title: Full genome sequences for Macaca mulatta (UCSC version rheMac10)
-Description: Full genome sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac10, Feb. 2019) and stored in Biostrings objects.
+Title: Full genomic sequences for Macaca mulatta (UCSC version rheMac10)
+Description: Full genomic sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac10, Feb. 2019) and stored in Biostrings objects.
Version: 1.4.2
organism: Macaca mulatta
common_name: Rhesus
@@ -13,6 +13,6 @@ organism_biocview: Macaca_mulatta
BSgenomeObjname: Mmulatta
circ_seqs: "chrM"
SrcDataFiles: rheMac10.2bit from http://hgdownload.soe.ucsc.edu/goldenPath/rheMac10/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mmulatta.UCSC.rheMac10/seqs
seqfile_name: rheMac10.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac2-seed b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac2-seed
index aa3e0fb..ef2bd25 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmulatta.UCSC.rheMac2
-Title: Full genome sequences for Macaca mulatta (UCSC version rheMac2)
-Description: Full genome sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac2, Jan. 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Macaca mulatta (UCSC version rheMac2)
+Description: Full genomic sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac2, Jan. 2006) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Macaca mulatta
@@ -15,7 +15,7 @@ BSgenomeObjname: Mmulatta
seqnames: paste("chr", c(1:20, "X", "Ur"), sep="")
circ_seqs: character(0)
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rheMac2/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for rheMac2 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("rheMac2", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac2.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac2.masked-seed
index dd8970e..7324a49 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac2.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac2.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmulatta.UCSC.rheMac2.masked
-Title: Full masked genome sequences for Macaca mulatta (UCSC version rheMac2)
-Description: Full genome sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac2, Jan. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmulatta.UCSC.rheMac2, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default. NOTE: In most assemblies available at UCSC, Tandem Repeats Finder repeats were filtered to retain only the repeats with period <= 12. However, the filtering was omitted for this assembly, so the TRF masks contain all Tandem Repeats Finder results.
+Title: Full masked genomic sequences for Macaca mulatta (UCSC version rheMac2)
+Description: Full genomic sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac2, Jan. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmulatta.UCSC.rheMac2, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default. NOTE: In most assemblies available at UCSC, Tandem Repeats Finder repeats were filtered to retain only the repeats with period <= 12. However, the filtering was omitted for this assembly, so the TRF masks contain all Tandem Repeats Finder results.
Version: 1.3.99
RefPkgname: BSgenome.Mmulatta.UCSC.rheMac2
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/rheMac2/
@@ -9,15 +9,15 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rheMac2/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rheMac2/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rheMac2/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## NOTE: In most assemblies available at UCSC, Tandem Repeats
## Finder repeats were filtered to retain only the repeats
## with period <= 12. However, the filtering was omitted for
## this assembly, so, despite the description being displayed
## for this mask, it contains all the Tandem Repeats Finder
## results.
- masks(genome$chr1)$TRF
+ masks(mbsg$chr1)$TRF
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Mmulatta.UCSC.rheMac2$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Mmulatta.UCSC.rheMac2$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mmulatta.UCSC.rheMac2/masks
AGAPSfiles_name: gap.txt.gz
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac3-seed b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac3-seed
index 8ee134f..ecc7405 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac3-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmulatta.UCSC.rheMac3
-Title: Full genome sequences for Macaca mulatta (UCSC version rheMac3)
-Description: Full genome sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac3, Oct. 2010) and stored in Biostrings objects.
+Title: Full genomic sequences for Macaca mulatta (UCSC version rheMac3)
+Description: Full genomic sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac3, Oct. 2010) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Macaca mulatta
@@ -16,7 +16,7 @@ seqnames: paste("chr", c(1:20, "X", "M"), sep="")
circ_seqs: "chrM"
mseqnames: "chrUn"
SrcDataFiles: rheMac3.fa.gz from http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -24,13 +24,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for rheMac3 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("rheMac3", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac3.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac3.masked-seed
index 6ca0bf5..2985151 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac3.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac3.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmulatta.UCSC.rheMac3.masked
-Title: Full masked genome sequences for Macaca mulatta (UCSC version rheMac3)
-Description: Full genome sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac3, Oct. 2010) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmulatta.UCSC.rheMac3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Macaca mulatta (UCSC version rheMac3)
+Description: Full genomic sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac3, Oct. 2010) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmulatta.UCSC.rheMac3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Mmulatta.UCSC.rheMac3
source_url: http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/database/
RM masks: rheMac3.fa.out.gz from http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/bigZips/
TRF masks: rheMac3.trf.bed.gz from http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Mmulatta.UCSC.rheMac3$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Mmulatta.UCSC.rheMac3$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mmulatta.UCSC.rheMac3/masks
AGAPSfiles_name: gap.txt.gz
RMfiles_name: rheMac3.fa.out.gz
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac8-seed b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac8-seed
index f2d7857..1dee997 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac8-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmulatta.UCSC.rheMac8-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmulatta.UCSC.rheMac8
-Title: Full genome sequences for Macaca mulatta (UCSC version rheMac8)
-Description: Full genome sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac8, Nov. 2015) and stored in Biostrings objects.
+Title: Full genomic sequences for Macaca mulatta (UCSC version rheMac8)
+Description: Full genomic sequences for Macaca mulatta (Rhesus) as provided by UCSC (rheMac8, Nov. 2015) and stored in Biostrings objects.
Version: 1.4.2
organism: Macaca mulatta
common_name: Rhesus
@@ -13,6 +13,6 @@ organism_biocview: Macaca_mulatta
BSgenomeObjname: Mmulatta
circ_seqs: "chrM"
SrcDataFiles: rheMac8.2bit from http://hgdownload.soe.ucsc.edu/goldenPath/rheMac8/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mmulatta.UCSC.rheMac8/seqs
seqfile_name: rheMac8.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm10-seed b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm10-seed
index b3e7bef..c08087a 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm10-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm10-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmusculus.UCSC.mm10
-Title: Full genome sequences for Mus musculus (UCSC version mm10, based on GRCm38.p6)
-Description: Full genome sequences for Mus musculus (Mouse) as provided by UCSC (mm10, based on GRCm38.p6) and stored in Biostrings objects.
+Title: Full genomic sequences for Mus musculus (UCSC version mm10, based on GRCm38.p6)
+Description: Full genomic sequences for Mus musculus (Mouse) as provided by UCSC (mm10, based on GRCm38.p6) and stored in Biostrings objects.
Version: 1.4.3
organism: Mus musculus
common_name: Mouse
@@ -11,6 +11,6 @@ source_url: https://hgdownload.soe.ucsc.edu/goldenPath/mm10/bigZips/p6/
organism_biocview: Mus_musculus
BSgenomeObjname: Mmusculus
SrcDataFiles: mm10.p6.2bit, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/mm10/bigZips/p6/ on July 1st, 2021
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Mmusculus.UCSC.mm10/seqs
seqfile_name: mm10.p6.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm10.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm10.masked-seed
index e7c94cd..ca774e6 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm10.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm10.masked-seed
@@ -1,14 +1,14 @@
Package: BSgenome.Mmusculus.UCSC.mm10.masked
-Title: Full masked genome sequences for Mus musculus (UCSC genome mm10, based on GRCm38.p6)
-Description: Full genome sequences for Mus musculus (Mouse) as provided by UCSC (genome mm10, based on GRCm38.p6) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmusculus.UCSC.mm10, except that each of them has the 2 following masks on top: (1) the mask of assembly gaps (AGAPS mask), and (2) the mask of intra-contig ambiguities (AMB mask).
+Title: Full masked genomic sequences for Mus musculus (UCSC genome mm10, based on GRCm38.p6)
+Description: Full genomic sequences for Mus musculus (Mouse) as provided by UCSC (genome mm10, based on GRCm38.p6) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmusculus.UCSC.mm10, except that each of them has the 2 following masks on top: (1) the mask of assembly gaps (AGAPS mask), and (2) the mask of intra-contig ambiguities (AMB mask).
Version: 1.4.3
RefPkgname: BSgenome.Mmusculus.UCSC.mm10
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/mm10/chromosomes/
organism_biocview: Mus_musculus
nmask_per_seq: 2
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/mm10/database/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Mmusculus.UCSC.mm10$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Mmusculus.UCSC.mm10$chr1
masks_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Mmusculus.UCSC.mm10/masks
AGAPSfiles_name: gap.txt
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm39-seed b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm39-seed
index dec2289..cbb5f2e 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm39-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm39-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmusculus.UCSC.mm39
-Title: Full genome sequences for Mus musculus (UCSC genome mm39, based on GRCm39)
-Description: Full genome sequences for Mus musculus (Mouse) as provided by UCSC (genome mm39, based on assembly GRCm39) and stored in Biostrings objects.
+Title: Full genomic sequences for Mus musculus (UCSC genome mm39, based on GRCm39)
+Description: Full genomic sequences for Mus musculus (Mouse) as provided by UCSC (genome mm39, based on assembly GRCm39) and stored in Biostrings objects.
Version: 1.4.3
organism: Mus musculus
common_name: Mouse
@@ -11,6 +11,6 @@ source_url: https://hgdownload.soe.ucsc.edu/goldenPath/mm39/bigZips/
organism_biocview: Mus_musculus
BSgenomeObjname: Mmusculus
SrcDataFiles: mm39.2bit, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/mm39/bigZips/ on August 30, 2021
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Mmusculus.UCSC.mm39/seqs
seqfile_name: mm39.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm8-seed b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm8-seed
index 6e6e1df..abaca39 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm8-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm8-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmusculus.UCSC.mm8
-Title: Full genome sequences for Mus musculus (UCSC version mm8)
-Description: Full genome sequences for Mus musculus (Mouse) as provided by UCSC (mm8, Feb. 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Mus musculus (UCSC version mm8)
+Description: Full genomic sequences for Mus musculus (Mouse) as provided by UCSC (mm8, Feb. 2006) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Mus musculus
@@ -15,20 +15,20 @@ BSgenomeObjname: Mmusculus
seqnames: paste("chr", c(1:19, "X", "Y", "M", paste(c(1, 5, 7, 8, 9, 10, 13, 15, 17, "X", "Y", "Un"), "_random", sep="")), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/mm8/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## --------------------------------------------------------------------- ## Upstream sequences
## ---------------------------------------------------------------------
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for mm8 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("mm8", "knownGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm8.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm8.masked-seed
index d6c4b36..9923bb2 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm8.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm8.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmusculus.UCSC.mm8.masked
-Title: Full masked genome sequences for Mus musculus (UCSC version mm8)
-Description: Full genome sequences for Mus musculus (Mouse) as provided by UCSC (mm8, Feb. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmusculus.UCSC.mm8, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Mus musculus (UCSC version mm8)
+Description: Full genomic sequences for Mus musculus (Mouse) as provided by UCSC (mm8, Feb. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmusculus.UCSC.mm8, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Mmusculus.UCSC.mm8
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/mm8/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/mm8/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/mm8/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/mm8/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Mmusculus.UCSC.mm8$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Mmusculus.UCSC.mm8$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mmusculus.UCSC.mm8/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm9-seed b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm9-seed
index 26ca948..f0e4e64 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm9-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm9-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmusculus.UCSC.mm9
-Title: Full genome sequences for Mus musculus (UCSC version mm9)
-Description: Full genome sequences for Mus musculus (Mouse) as provided by UCSC (mm9, Jul. 2007) and stored in Biostrings objects.
+Title: Full genomic sequences for Mus musculus (UCSC version mm9)
+Description: Full genomic sequences for Mus musculus (Mouse) as provided by UCSC (mm9, Jul. 2007) and stored in Biostrings objects.
Version: 1.4.2
Suggests: TxDb.Mmusculus.UCSC.mm9.knownGene
organism: Mus musculus
@@ -15,7 +15,7 @@ BSgenomeObjname: Mmusculus
seqnames: paste("chr", c(1:19, "X", "Y", "M", paste(c(1, 3, 4, 5, 7, 8, 9, 13, 16, 17, "X", "Y", "Un"), "_random", sep="")), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/mm9/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for mm9 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(TxDb.Mmusculus.UCSC.mm9.knownGene)
txdb <- TxDb.Mmusculus.UCSC.mm9.knownGene
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm9.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm9.masked-seed
index 8db3031..88d5d1e 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm9.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Mmusculus.UCSC.mm9.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Mmusculus.UCSC.mm9.masked
-Title: Full masked genome sequences for Mus musculus (UCSC version mm9)
-Description: Full genome sequences for Mus musculus (Mouse) as provided by UCSC (mm9, Jul. 2007) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmusculus.UCSC.mm9, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Mus musculus (UCSC version mm9)
+Description: Full genomic sequences for Mus musculus (Mouse) as provided by UCSC (mm9, Jul. 2007) and stored in Biostrings objects. The sequences are the same as in BSgenome.Mmusculus.UCSC.mm9, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Mmusculus.UCSC.mm9
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/mm9/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/mm9/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/mm9/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/mm9/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Mmusculus.UCSC.mm9$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Mmusculus.UCSC.mm9$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Mmusculus.UCSC.mm9/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ppaniscus.UCSC.panPan1-seed b/inst/extdata/GentlemanLab/BSgenome.Ppaniscus.UCSC.panPan1-seed
index c4c2dc1..9549c0e 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ppaniscus.UCSC.panPan1-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ppaniscus.UCSC.panPan1-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ppaniscus.UCSC.panPan1
-Title: Full genome sequences for Pan paniscus (UCSC version panPan1)
-Description: Full genome sequences for Pan paniscus (Bonobo) as provided by UCSC (panPan1, May 2012) and stored in Biostrings objects.
+Title: Full genomic sequences for Pan paniscus (UCSC version panPan1)
+Description: Full genomic sequences for Pan paniscus (Bonobo) as provided by UCSC (panPan1, May 2012) and stored in Biostrings objects.
Version: 1.4.3
organism: Pan paniscus
common_name: Bonobo
@@ -12,6 +12,6 @@ source_url: https://hgdownload.cse.ucsc.edu/goldenPath/panPan1/bigZips/
organism_biocview: Pan_paniscus
BSgenomeObjname: Ppaniscus
SrcDataFiles: panPan1.2bit from https://hgdownload.cse.ucsc.edu/goldenPath/panPan1/bigZips/
-PkgExamples: genome$AJFE01000001 # same as genome[["AJFE01000001"]]
+PkgExamples: bsg$AJFE01000001 # same as bsg[["AJFE01000001"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Ppaniscus.UCSC.panPan1/seqs
seqfile_name: panPan1.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ppaniscus.UCSC.panPan2-seed b/inst/extdata/GentlemanLab/BSgenome.Ppaniscus.UCSC.panPan2-seed
index 1ef5124..58911f4 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ppaniscus.UCSC.panPan2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ppaniscus.UCSC.panPan2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ppaniscus.UCSC.panPan2
-Title: Full genome sequences for Pan paniscus (UCSC version panPan2)
-Description: Full genome sequences for Pan paniscus (Bonobo) as provided by UCSC (panPan2, Dec. 2015) and stored in Biostrings objects.
+Title: Full genomic sequences for Pan paniscus (UCSC version panPan2)
+Description: Full genomic sequences for Pan paniscus (Bonobo) as provided by UCSC (panPan2, Dec. 2015) and stored in Biostrings objects.
Version: 1.4.3
organism: Pan paniscus
common_name: Bonobo
@@ -12,6 +12,6 @@ source_url: https://hgdownload.cse.ucsc.edu/goldenPath/panPan2/bigZips/
organism_biocview: Pan_paniscus
BSgenomeObjname: Ppaniscus
SrcDataFiles: panPan2.2bit from https://hgdownload.cse.ucsc.edu/goldenPath/panPan2/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Ppaniscus.UCSC.panPan2/seqs
seqfile_name: panPan2.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro2-seed b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro2-seed
index 0107482..e609c0f 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ptroglodytes.UCSC.panTro2
-Title: Full genome sequences for Pan troglodytes (UCSC version panTro2)
-Description: Full genome sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro2, Mar. 2006) and stored in Biostrings objects.
+Title: Full genomic sequences for Pan troglodytes (UCSC version panTro2)
+Description: Full genomic sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro2, Mar. 2006) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Pan troglodytes
@@ -15,7 +15,7 @@ BSgenomeObjname: Ptroglodytes
seqnames: paste("chr", c(1, "2a", "2b", 3:22, "X", "Y", "M", "Un", "6_hla_hap1", paste(c(1, "2a", "2b", 3:20, 22, "X", "Y"), "_random", sep="")), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/panTro2/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for panTro2 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("panTro2", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro2.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro2.masked-seed
index 1e0a72e..7e0992a 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro2.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro2.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ptroglodytes.UCSC.panTro2.masked
-Title: Full masked genome sequences for Pan troglodytes (UCSC version panTro2)
-Description: Full genome sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro2, Mar. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Ptroglodytes.UCSC.panTro2, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Pan troglodytes (UCSC version panTro2)
+Description: Full genomic sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro2, Mar. 2006) and stored in Biostrings objects. The sequences are the same as in BSgenome.Ptroglodytes.UCSC.panTro2, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Ptroglodytes.UCSC.panTro2
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/panTro2/bigZips/
@@ -9,8 +9,8 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from ftp://hgdownload.cse.ucsc.edu/goldenPath/panTro2/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/panTro2/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/panTro2/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Ptroglodytes.UCSC.panTro2$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Ptroglodytes.UCSC.panTro2$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ptroglodytes.UCSC.panTro2/masks
AGAPSfiles_name: gap.txt
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro3-seed b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro3-seed
index a06f007..6289ac4 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro3-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ptroglodytes.UCSC.panTro3
-Title: Full genome sequences for Pan troglodytes (UCSC version panTro3)
-Description: Full genome sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro3, Oct. 2010) and stored in Biostrings objects.
+Title: Full genomic sequences for Pan troglodytes (UCSC version panTro3)
+Description: Full genomic sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro3, Oct. 2010) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Pan troglodytes
@@ -16,7 +16,7 @@ seqnames: paste("chr", c(1, "2A", "2B", 3:22, "X", "Y", "M"), sep="")
circ_seqs: "chrM"
mseqnames: c(paste("chr", c(1, "2A", "2B", 3:22, "X", "Y", "M"), "_random", sep=""), "chrUn")
SrcDataFiles: panTro3.fa.gz from http://hgdownload.cse.ucsc.edu/goldenPath/panTro3/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -24,13 +24,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for panTro3 are not included in the BSgenome
## data package anymore. However they can easily be extracted from the
- ## full genome sequences with something like:
+ ## full genomic sequences with something like:
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("panTro3", "refGene")
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro3.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro3.masked-seed
index d09e932..1ad0b6f 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro3.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro3.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ptroglodytes.UCSC.panTro3.masked
-Title: Full masked genome sequences for Pan troglodytes (UCSC version panTro3)
-Description: Full genome sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro3, Oct. 2010) and stored in Biostrings objects. The sequences are the same as in BSgenome.Ptroglodytes.UCSC.panTro3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Pan troglodytes (UCSC version panTro3)
+Description: Full genomic sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro3, Oct. 2010) and stored in Biostrings objects. The sequences are the same as in BSgenome.Ptroglodytes.UCSC.panTro3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Ptroglodytes.UCSC.panTro3
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/panTro3/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/panTro3/database/
RM masks: panTro3.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/panTro3/bigZips/
TRF masks: panTro3.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/panTro3/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Ptroglodytes.UCSC.panTro3$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Ptroglodytes.UCSC.panTro3$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ptroglodytes.UCSC.panTro3/masks
AGAPSfiles_name: gap.txt
RMfiles_name: panTro3.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro5-seed b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro5-seed
index 970a6ea..0780142 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro5-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro5-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ptroglodytes.UCSC.panTro5
-Title: Full genome sequences for Pan troglodytes (UCSC version panTro5)
-Description: Full genome sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro5, May 2016) and stored in Biostrings objects.
+Title: Full genomic sequences for Pan troglodytes (UCSC version panTro5)
+Description: Full genomic sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro5, May 2016) and stored in Biostrings objects.
Version: 1.4.2
organism: Pan troglodytes
common_name: Chimp
@@ -13,6 +13,6 @@ organism_biocview: Pan_troglodytes
BSgenomeObjname: Ptroglodytes
circ_seqs: "chrM"
SrcDataFiles: panTro5.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/panTro5/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ptroglodytes.UCSC.panTro5/seqs
seqfile_name: panTro5.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro6-seed b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro6-seed
index 68a8dd4..85efd8c 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro6-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Ptroglodytes.UCSC.panTro6-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Ptroglodytes.UCSC.panTro6
-Title: Full genome sequences for Pan troglodytes (UCSC version panTro6)
-Description: Full genome sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro6, Jan. 2018) and stored in Biostrings objects.
+Title: Full genomic sequences for Pan troglodytes (UCSC version panTro6)
+Description: Full genomic sequences for Pan troglodytes (Chimp) as provided by UCSC (panTro6, Jan. 2018) and stored in Biostrings objects.
Version: 1.4.2
organism: Pan troglodytes
common_name: Chimp
@@ -13,6 +13,6 @@ organism_biocview: Pan_troglodytes
BSgenomeObjname: Ptroglodytes
circ_seqs: "chrM"
SrcDataFiles: panTro6.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/panTro6/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Ptroglodytes.UCSC.panTro6/seqs
seqfile_name: panTro6.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn4-seed b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn4-seed
index 270055b..5eef9e5 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn4-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn4-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Rnorvegicus.UCSC.rn4
-Title: Full genome sequences for Rattus norvegicus (UCSC version rn4)
-Description: Full genome sequences for Rattus norvegicus (Rat) as provided by UCSC (rn4, Nov. 2004) and stored in Biostrings objects.
+Title: Full genomic sequences for Rattus norvegicus (UCSC version rn4)
+Description: Full genomic sequences for Rattus norvegicus (Rat) as provided by UCSC (rn4, Nov. 2004) and stored in Biostrings objects.
Version: 1.4.2
Suggests: TxDb.Rnorvegicus.UCSC.rn4.ensGene
organism: Rattus norvegicus
@@ -15,7 +15,7 @@ BSgenomeObjname: Rnorvegicus
seqnames: paste("chr", c(1:20, "X", "M", "Un", paste(c(1:20, "X", "Un"), "_random", sep="")), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rn4/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Upstream sequences
@@ -23,13 +23,13 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for rn4 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(TxDb.Rnorvegicus.UCSC.rn4.ensGene)
txdb <- TxDb.Rnorvegicus.UCSC.rn4.ensGene
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn4.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn4.masked-seed
index 72e14c6..508ee48 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn4.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn4.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Rnorvegicus.UCSC.rn4.masked
-Title: Full masked genome sequences for Rattus norvegicus (UCSC version rn4)
-Description: Full genome sequences for Rattus norvegicus (Rat) as provided by UCSC (rn4, Nov. 2004) and stored in Biostrings objects. The sequences are the same as in BSgenome.Rnorvegicus.UCSC.rn4, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Rattus norvegicus (UCSC version rn4)
+Description: Full genomic sequences for Rattus norvegicus (Rat) as provided by UCSC (rn4, Nov. 2004) and stored in Biostrings objects. The sequences are the same as in BSgenome.Rnorvegicus.UCSC.rn4, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Rnorvegicus.UCSC.rn4
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/rn4/bigZips/
@@ -9,7 +9,7 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from ftp://hgdownload.cse.ucsc.edu/goldenPath/rn4/database/
RM masks: chromOut.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rn4/bigZips/
TRF masks: chromTrf.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rn4/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Rnorvegicus.UCSC.rn4$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Rnorvegicus.UCSC.rn4$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Rnorvegicus.UCSC.rn4/masks
diff --git a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn5-seed b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn5-seed
index f968527..bdcf8f2 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn5-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn5-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Rnorvegicus.UCSC.rn5
-Title: Full genome sequences for Rattus norvegicus (UCSC version rn5)
-Description: Full genome sequences for Rattus norvegicus (Rat) as provided by UCSC (rn5, Mar. 2012) and stored in Biostrings objects.
+Title: Full genomic sequences for Rattus norvegicus (UCSC version rn5)
+Description: Full genomic sequences for Rattus norvegicus (Rat) as provided by UCSC (rn5, Mar. 2012) and stored in Biostrings objects.
Version: 1.4.2
Suggests: TxDb.Rnorvegicus.UCSC.rn5.refGene
organism: Rattus norvegicus
@@ -16,20 +16,20 @@ seqnames: paste("chr", c(1:20, "X", "M"), sep="")
circ_seqs: "chrM"
mseqnames: c("random", "chrUn")
SrcDataFiles: rn5.fa.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rn5/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## --------------------------------------------------------------------- ## Upstream sequences
## ---------------------------------------------------------------------
## Starting with BioC 3.0, the upstream1000, upstream2000, and
## upstream5000 sequences for rn5 are not included in the BSgenome data
## package anymore. However they can easily be extracted from the full
- ## genome sequences with something like:
+ ## genomic sequences with something like:
.
library(TxDb.Rnorvegicus.UCSC.rn5.refGene)
txdb <- TxDb.Rnorvegicus.UCSC.rn5.refGene
gn <- sort(genes(txdb))
up1000 <- flank(gn, width=1000)
- up1000seqs <- getSeq(genome, up1000)
+ up1000seqs <- getSeq(bsg, up1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object),
## that contains a gene model based on the exact same reference genome
diff --git a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn5.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn5.masked-seed
index a485456..2a8c094 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn5.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn5.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Rnorvegicus.UCSC.rn5.masked
-Title: Full masked genome sequences for Rattus norvegicus (UCSC version rn5)
-Description: Full genome sequences for Rattus norvegicus (Rat) as provided by UCSC (rn5, Mar. 2012) and stored in Biostrings objects. The sequences are the same as in BSgenome.Rnorvegicus.UCSC.rn5, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Rattus norvegicus (UCSC version rn5)
+Description: Full genomic sequences for Rattus norvegicus (Rat) as provided by UCSC (rn5, Mar. 2012) and stored in Biostrings objects. The sequences are the same as in BSgenome.Rnorvegicus.UCSC.rn5, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Rnorvegicus.UCSC.rn5
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/rn5/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rn5/database/
RM masks: rn5.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rn5/bigZips/
TRF masks: rn5.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rn5/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Rnorvegicus.UCSC.rn5$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Rnorvegicus.UCSC.rn5$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Rnorvegicus.UCSC.rn5/masks
AGAPSfiles_name: gap.txt
RMfiles_name: rn5.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn6-seed b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn6-seed
index 0b8e697..af1712b 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn6-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn6-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Rnorvegicus.UCSC.rn6
-Title: Full genome sequences for Rattus norvegicus (UCSC version rn6)
-Description: Full genome sequences for Rattus norvegicus (Rat) as provided by UCSC (rn6, Jul. 2014) and stored in Biostrings objects.
+Title: Full genomic sequences for Rattus norvegicus (UCSC version rn6)
+Description: Full genomic sequences for Rattus norvegicus (Rat) as provided by UCSC (rn6, Jul. 2014) and stored in Biostrings objects.
Version: 1.4.2
Suggests: GenomicFeatures
organism: Rattus norvegicus
@@ -15,7 +15,7 @@ BSgenomeObjname: Rnorvegicus
seqnames: seqnames(Seqinfo(genome="rn6"))
circ_seqs: "chrM"
SrcDataFiles: rn6.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/rn6/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
.
## ---------------------------------------------------------------------
## Extract the upstream sequences
@@ -25,7 +25,7 @@ PkgExamples: genome$chr1 # same as genome[["chr1"]]
.
library(GenomicFeatures)
txdb <- makeTxDbFromUCSC("rn6", tablename="refGene")
- up1000seqs <- extractUpstreamSeqs(genome, txdb, width=1000)
+ up1000seqs <- extractUpstreamSeqs(bsg, txdb, width=1000)
.
## IMPORTANT: Make sure you use a TxDb package (or TxDb object) that
## contains a gene model based on rn6 or on a compatible genome (i.e.
diff --git a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn7-seed b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn7-seed
index bd12a01..17de522 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn7-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Rnorvegicus.UCSC.rn7-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Rnorvegicus.UCSC.rn7
-Title: Full genome sequences for Rattus norvegicus (UCSC genome rn7)
-Description: Full genome sequences for Rattus norvegicus (Rat) as provided by UCSC (genome rn7) and stored in Biostrings objects.
+Title: Full genomic sequences for Rattus norvegicus (UCSC genome rn7)
+Description: Full genomic sequences for Rattus norvegicus (Rat) as provided by UCSC (genome rn7) and stored in Biostrings objects.
Version: 1.4.3
organism: Rattus norvegicus
common_name: Rat
@@ -11,6 +11,6 @@ source_url: https://hgdownload.soe.ucsc.edu/goldenPath/rn7/bigZips/
organism_biocview: Rattus_norvegicus
BSgenomeObjname: Rnorvegicus
SrcDataFiles: rn7.2bit, downloaded from https://hgdownload.soe.ucsc.edu/goldenPath/rn7/bigZips/ on August 24, 2021
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /home/hpages/BSgenomeForge/srcdata/BSgenome.Rnorvegicus.UCSC.rn7/seqs
seqfile_name: rn7.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer1-seed b/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer1-seed
index 3ef2d46..38bd00a 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer1-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer1-seed
@@ -14,5 +14,5 @@ BSgenomeObjname: Scerevisiae
seqnames: paste("chr", c(1:16, "M"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.zip from http://hgdownload.cse.ucsc.edu/goldenPath/sacCer1/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Scerevisiae.UCSC.sacCer1/seqs
diff --git a/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer2-seed b/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer2-seed
index 878c292..68c095c 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer2-seed
@@ -14,5 +14,5 @@ BSgenomeObjname: Scerevisiae
seqnames: c(paste("chr", c("I", "II", "III", "IV", "V", "VI", "VII", "VIII", "IX", "X", "XI", "XII", "XIII", "XIV", "XV", "XVI", "M"), sep=""), "2micron")
circ_seqs: c("chrM", "2micron")
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/sacCer2/bigZips/
-PkgExamples: genome$chrI # same as genome[["chrI"]]
+PkgExamples: bsg$chrI # same as bsg[["chrI"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Scerevisiae.UCSC.sacCer2/seqs
diff --git a/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer3-seed b/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer3-seed
index 905511d..16ba6cf 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Scerevisiae.UCSC.sacCer3-seed
@@ -14,5 +14,5 @@ BSgenomeObjname: Scerevisiae
seqnames: paste("chr", c("I", "II", "III", "IV", "V", "VI", "VII", "VIII", "IX", "X", "XI", "XII", "XIII", "XIV", "XV", "XVI", "M"), sep="")
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.cse.ucsc.edu/goldenPath/sacCer3/bigZips/
-PkgExamples: genome$chrI # same as genome[["chrI"]]
+PkgExamples: bsg$chrI # same as bsg[["chrI"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Scerevisiae.UCSC.sacCer3/seqs
diff --git a/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr11-seed b/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr11-seed
index 28d7cd4..6c7a376 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr11-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr11-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Sscrofa.UCSC.susScr11
-Title: Full genome sequences for Sus scrofa (UCSC version susScr11)
-Description: Full genome sequences for Sus scrofa (Pig) as provided by UCSC (susScr11, Feb. 2017) and stored in Biostrings objects.
+Title: Full genomic sequences for Sus scrofa (UCSC version susScr11)
+Description: Full genomic sequences for Sus scrofa (Pig) as provided by UCSC (susScr11, Feb. 2017) and stored in Biostrings objects.
Version: 1.4.2
organism: Sus scrofa
common_name: Pig
@@ -13,6 +13,6 @@ organism_biocview: Sus_scrofa
BSgenomeObjname: Sscrofa
circ_seqs: "chrM"
SrcDataFiles: susScr11.2bit from http://hgdownload.cse.ucsc.edu/goldenPath/susScr11/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Sscrofa.UCSC.susScr11/seqs
seqfile_name: susScr11.sorted.2bit
diff --git a/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr3-seed b/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr3-seed
index 3397c07..541fcf6 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr3-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr3-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Sscrofa.UCSC.susScr3
-Title: Full genome sequences for Sus scrofa (UCSC version susScr3)
-Description: Full genome sequences for Sus scrofa (Pig) as provided by UCSC (susScr3, Aug. 2011) and stored in Biostrings objects.
+Title: Full genomic sequences for Sus scrofa (UCSC version susScr3)
+Description: Full genomic sequences for Sus scrofa (Pig) as provided by UCSC (susScr3, Aug. 2011) and stored in Biostrings objects.
Version: 1.4.2
organism: Sus scrofa
common_name: Pig
@@ -15,5 +15,5 @@ seqnames: paste0("chr", c(1:18, "X", "Y", "M"))
circ_seqs: "chrM"
mseqnames: "unplaced_scaffolds"
SrcDataFiles: susScr3.fa.gz from http://hgdownload.soe.ucsc.edu/goldenPath/susScr3/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Sscrofa.UCSC.susScr3/seqs
diff --git a/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr3.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr3.masked-seed
index c11c2ab..84aa27a 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr3.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Sscrofa.UCSC.susScr3.masked-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Sscrofa.UCSC.susScr3.masked
-Title: Full masked genome sequences for Sus scrofa (UCSC version susScr3)
-Description: Full genome sequences for Sus scrofa (Pig) as provided by UCSC (susScr3, Aug. 2011) and stored in Biostrings objects. The sequences are the same as in BSgenome.Sscrofa.UCSC.susScr3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
+Title: Full masked genomic sequences for Sus scrofa (UCSC version susScr3)
+Description: Full genomic sequences for Sus scrofa (Pig) as provided by UCSC (susScr3, Aug. 2011) and stored in Biostrings objects. The sequences are the same as in BSgenome.Sscrofa.UCSC.susScr3, except that each of them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats Finder (TRF mask). Only the AGAPS and AMB masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Sscrofa.UCSC.susScr3
source_url: http://hgdownload.cse.ucsc.edu/goldenPath/susScr3/bigZips/
@@ -9,9 +9,9 @@ nmask_per_seq: 4
SrcDataFiles: AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/susScr3/database/
RM masks: susScr3.fa.out.gz from http://hgdownload.cse.ucsc.edu/goldenPath/susScr3/bigZips/
TRF masks: susScr3.trf.bed.gz from http://hgdownload.cse.ucsc.edu/goldenPath/susScr3/bigZips/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples: mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Sscrofa.UCSC.susScr3$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Sscrofa.UCSC.susScr3$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Sscrofa.UCSC.susScr3/masks
AGAPSfiles_name: gap.txt
RMfiles_name: susScr3.fa.out
diff --git a/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut1-seed b/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut1-seed
index d2f7d6b..75cbfa4 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut1-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut1-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Tguttata.UCSC.taeGut1
-Title: Full genome sequences for Taeniopygia guttata (UCSC version taeGut1)
-Description: Full genome sequences for Taeniopygia guttata (Zebra finch) as provided by UCSC (taeGut1, Jul. 2008) and stored in Biostrings objects.
+Title: Full genomic sequences for Taeniopygia guttata (UCSC version taeGut1)
+Description: Full genomic sequences for Taeniopygia guttata (Zebra finch) as provided by UCSC (taeGut1, Jul. 2008) and stored in Biostrings objects.
Version: 1.4.2
organism: Taeniopygia guttata
common_name: Zebra finch
@@ -14,5 +14,5 @@ BSgenomeObjname: Tguttata
seqnames: paste0("chr", c(1, "1A", "1B", 2:4, "4A", 5:28, "LGE22", "LG2", "LG5", "Z", "M", "Un", paste0(c(1, "1A", "1B", 2:4, "4A", 5:28, "LGE22", "Z"), "_random")))
circ_seqs: "chrM"
SrcDataFiles: chromFa.tar.gz from http://hgdownload.soe.ucsc.edu/goldenPath/taeGut1/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Tguttata.UCSC.taeGut1/seqs
diff --git a/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut1.masked-seed b/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut1.masked-seed
index 5ae4909..e7370d6 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut1.masked-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut1.masked-seed
@@ -1,14 +1,14 @@
Package: BSgenome.Tguttata.UCSC.taeGut1.masked
-Title: Full masked genome sequences for Taeniopygia guttata (UCSC version taeGut1)
-Description: Full genome sequences for Taeniopygia guttata (Zebra finch) as provided by UCSC (taeGut1, Jul. 2008) and stored in Biostrings objects. The sequences are the same as in BSgenome.Tguttata.UCSC.taeGut1, except that each of them has the 2 following masks on top: (1) the mask of assembly gaps (AGAPS mask), and (2) the mask of intra-contig ambiguities (AMB mask). Both masks are "active" by default.
+Title: Full masked genomic sequences for Taeniopygia guttata (UCSC version taeGut1)
+Description: Full genomic sequences for Taeniopygia guttata (Zebra finch) as provided by UCSC (taeGut1, Jul. 2008) and stored in Biostrings objects. The sequences are the same as in BSgenome.Tguttata.UCSC.taeGut1, except that each of them has the 2 following masks on top: (1) the mask of assembly gaps (AGAPS mask), and (2) the mask of intra-contig ambiguities (AMB mask). Both masks are "active" by default.
Version: 1.3.99
RefPkgname: BSgenome.Tguttata.UCSC.taeGut1
source_url: http://hgdownload.soe.ucsc.edu/goldenPath/taeGut1/database/
organism_biocview: Taeniopygia_guttata
nmask_per_seq: 2
SrcDataFiles: AGAPS masks: all the chr*_gap.txt.gz files from http://hgdownload.cse.ucsc.edu/goldenPath/taeGut1/database/
-PkgExamples: genome$chr1 # a MaskedDNAString object!
+PkgExamples:mbsg$chr1 # a MaskedDNAString object!
## To get rid of the masks altogether:
- unmasked(genome$chr1) # same as BSgenome.Tguttata.UCSC.taeGut1$chr1
+ unmasked(mbsg$chr1) # same as BSgenome.Tguttata.UCSC.taeGut1$chr1
masks_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Tguttata.UCSC.taeGut1/masks
AGAPSfiles_suffix: _gap.txt.gz
diff --git a/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut2-seed b/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut2-seed
index ad5cd4c..62d0821 100644
--- a/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut2-seed
+++ b/inst/extdata/GentlemanLab/BSgenome.Tguttata.UCSC.taeGut2-seed
@@ -1,6 +1,6 @@
Package: BSgenome.Tguttata.UCSC.taeGut2
-Title: Full genome sequences for Taeniopygia guttata (UCSC version taeGut2)
-Description: Full genome sequences for Taeniopygia guttata (Zebra finch) as provided by UCSC (taeGut2, Feb. 2013) and stored in Biostrings objects.
+Title: Full genomic sequences for Taeniopygia guttata (UCSC version taeGut2)
+Description: Full genomic sequences for Taeniopygia guttata (Zebra finch) as provided by UCSC (taeGut2, Feb. 2013) and stored in Biostrings objects.
Version: 1.4.2
organism: Taeniopygia guttata
common_name: Zebra finch
@@ -13,6 +13,6 @@ organism_biocview: Taeniopygia_guttata
BSgenomeObjname: Tguttata
circ_seqs: "chrM"
SrcDataFiles: taeGut2.2bit from http://hgdownload.soe.ucsc.edu/goldenPath/taeGut2/bigZips/
-PkgExamples: genome$chr1 # same as genome[["chr1"]]
+PkgExamples: bsg$chr1 # same as bsg[["chr1"]]
seqs_srcdir: /fh/fast/morgan_m/BioC/BSgenomeForge/srcdata/BSgenome.Tguttata.UCSC.taeGut2/seqs
seqfile_name: taeGut2.sorted.2bit
diff --git a/inst/extdata/Outreachy/BSgenome.Xtropicalis.NCBI.UCBXtro10.0-seed b/inst/extdata/Outreachy/BSgenome.Xtropicalis.NCBI.UCBXtro10.0-seed
new file mode 100644
index 0000000..ce5f1cf
--- /dev/null
+++ b/inst/extdata/Outreachy/BSgenome.Xtropicalis.NCBI.UCBXtro10.0-seed
@@ -0,0 +1,16 @@
+Package: BSgenome.Xtropicalis.NCBI.UCBXtro10.0
+Title: Full genome sequences for Xenopos tropicalis (NCBI version UCB_Xtro_10.0)
+Description: Full genome sequences for Xenopus tropicalis as provided by NCBI (UCB_Xtro_10.0, 2019/11/14) and stored in Biostrings objects.
+Version: 0.1.0
+organism: Xenopus tropicalis
+common_name: Tropical clawed frog
+genome: UCB_Xtro_10.0
+provider: NCBI
+release_date: 2019/11/14
+source_url: https://www.ncbi.nlm.nih.gov/assembly/GCF_000004195.4/
+organism_biocview: Xenopus_tropicalis
+BSgenomeObjname: Xtropicalis
+SrcDataFiles: GCF_000004195.4_UCB_Xtro_10.0_genomic.fna.gz from https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/004/195/GCF_000004195.4_UCB_Xtro_10.0/
+PkgExamples: genome$Chr1 # same as genome[["Chr1"]]
+seqs_srcdir: /home/emmanuel/seqdatafile
+seqfile_name: UCB_Xtro_10.0.sorted.2bit
diff --git a/inst/extdata/Outreachy/BSgenome.Xtropicalis.UCSC.xenTro10-seed b/inst/extdata/Outreachy/BSgenome.Xtropicalis.UCSC.xenTro10-seed
new file mode 100644
index 0000000..5c49511
--- /dev/null
+++ b/inst/extdata/Outreachy/BSgenome.Xtropicalis.UCSC.xenTro10-seed
@@ -0,0 +1,16 @@
+Package: BSgenome.Xtropicalis.UCSC.xenTro10
+Title: Full genome sequences for Xenopus tropicalis (UCSC version xenTro10)
+Description: Full genome sequences for Xenopus tropicalis (Western clawed frog) as provided by UCSC (xenTro10, Nov. 2019) and stored in Biostrings objects.
+Version: 0.1.0
+organism: Xenopus tropicalis
+common_name: Tropical clawed frog
+provider: UCSC
+genome: xenTro10
+release_date: Nov. 2019
+source_url: https://hgdownload.cse.ucsc.edu/goldenPath/xenTro10/bigZips/
+organism_biocview: Xenopus_tropicalis
+BSgenomeObjname: Xtropicalis
+SrcDataFiles: xenTro10.2bit from https://hgdownload.cse.ucsc.edu/goldenPath/xenTro10/bigZips/
+PkgExamples: genome$chr1 # same as genome[["chr1"]]
+seqs_srcdir: /home/emmanuel/seqdatafile
+seqfile_name: xenTro10.2bit
diff --git a/inst/extdata/Outreachy/fasta_to_sorted_2bit_for_UCB_Xtro_10.0.R b/inst/extdata/Outreachy/fasta_to_sorted_2bit_for_UCB_Xtro_10.0.R
new file mode 100644
index 0000000..fd76dc4
--- /dev/null
+++ b/inst/extdata/Outreachy/fasta_to_sorted_2bit_for_UCB_Xtro_10.0.R
@@ -0,0 +1,23 @@
+###
+library(Biostrings)
+
+### Download GCF_000004195.4_UCB_Xtro_10.0_genomic.fna.gz from
+### https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/004/195/GCF_000004195.4_UCB_Xtro_10.0/
+dna <- readDNAStringSet("GCF_000004195.4_UCB_Xtro_10.0_genomic.fna.gz")
+
+### Check seqnames.
+current_RefSeqAccn <- unlist(heads(strsplit(names(dna), " ", fixed=TRUE), n=1L))
+library(GenomeInfoDb)
+chrominfo <- getChromInfoFromNCBI("GCF_000004195.4")
+expected_RefSeqAccn <- chrominfo[ , "RefSeqAccn"]
+stopifnot(setequal(expected_RefSeqAccn, current_RefSeqAccn))
+
+### Reorder sequences.
+dna <- dna[match(expected_RefSeqAccn, current_RefSeqAccn)]
+
+### Rename sequences.
+names(dna) <- chrominfo[ , "SequenceName"]
+
+### Export as 2bit.
+library(rtracklayer)
+export.2bit(dna, "UCB_Xtro_10.0.sorted.2bit")
diff --git a/inst/pkgtemplates/BSgenome_datapkg/DESCRIPTION b/inst/pkgtemplates/BSgenome_datapkg/DESCRIPTION
index ab8ae53..565a78d 100644
--- a/inst/pkgtemplates/BSgenome_datapkg/DESCRIPTION
+++ b/inst/pkgtemplates/BSgenome_datapkg/DESCRIPTION
@@ -4,14 +4,13 @@ Description: @PKGDESCRIPTION@
Version: @PKGVERSION@
Author: @AUTHOR@
Maintainer: @MAINTAINER@
-Depends: R (>= 3.5.0), BSgenome (>= @BSGENOMEVERSION@)
-Imports: BSgenome
+Depends: R (>= 4.2.0), GenomeInfoDb (>= 1.34.9), BSgenome (>= @BSGENOMEVERSION@)
Suggests: @SUGGESTS@
License: @LICENSE@
organism: @ORGANISM@
common_name: @COMMONNAME@
-genome: @GENOME@
provider: @PROVIDER@
+genome: @GENOME@
release_date: @RELEASEDATE@
source_url: @SOURCEURL@
biocViews: AnnotationData, Genetics, BSgenome, @ORGANISMBIOCVIEW@
diff --git a/inst/pkgtemplates/BSgenome_datapkg/NAMESPACE b/inst/pkgtemplates/BSgenome_datapkg/NAMESPACE
index acdf095..f6784af 100644
--- a/inst/pkgtemplates/BSgenome_datapkg/NAMESPACE
+++ b/inst/pkgtemplates/BSgenome_datapkg/NAMESPACE
@@ -1,3 +1,4 @@
+import(GenomeInfoDb)
import(BSgenome)
### Don't export @PKGNAME@ or @BSGENOMEOBJNAME@ (the new and
diff --git a/inst/pkgtemplates/BSgenome_datapkg/man/package.Rd b/inst/pkgtemplates/BSgenome_datapkg/man/package.Rd
index 7dd7d16..d5863cb 100644
--- a/inst/pkgtemplates/BSgenome_datapkg/man/package.Rd
+++ b/inst/pkgtemplates/BSgenome_datapkg/man/package.Rd
@@ -23,33 +23,47 @@
See \code{?\link[BSgenome]{BSgenomeForge}} and the BSgenomeForge
vignette (\code{vignette("BSgenomeForge")}) in the \pkg{BSgenome}
- software package for how to make a BSgenome data package.
+ software package for how to create a BSgenome data package.
}
\author{@AUTHOR@}
\seealso{
\itemize{
- \item \link[BSgenome]{BSgenome} objects and the
- \code{\link[BSgenome]{available.genomes}} function
- in the \pkg{BSgenome} software package.
+ \item \link[BSgenome]{BSgenome} objects in the \pkg{BSgenome}
+ software package.
+
+ \item The \code{\link[GenomeInfoDb]{seqinfo}} getter and
+ \link[GenomeInfoDb]{Seqinfo} objects in the \pkg{GenomeInfoDb}
+ package.
+
+ \item The \code{\link[GenomeInfoDb]{seqlevelsStyle}} getter and
+ setter in the \pkg{GenomeInfoDb} package.
+
\item \link[Biostrings]{DNAString} objects in the \pkg{Biostrings}
package.
+
+ \item The \code{\link[BSgenome]{available.genomes}} function
+ in the \pkg{BSgenome} software package.
+
\item The BSgenomeForge vignette (\code{vignette("BSgenomeForge")})
- in the \pkg{BSgenome} software package for how to make a BSgenome
+ in the \pkg{BSgenome} software package for how to create a BSgenome
data package.
}
}
\examples{
@PKGNAME@
-genome <- @PKGNAME@
-head(seqlengths(genome))
+bsg <- @PKGNAME@
+head(seqlengths(bsg))
+seqinfo(bsg)
+
@PKGEXAMPLES@
## ---------------------------------------------------------------------
## Genome-wide motif searching
## ---------------------------------------------------------------------
+
## See the GenomeSearching vignette in the BSgenome software
## package for some examples of genome-wide motif searching using
## Biostrings and the BSgenome data packages:
diff --git a/inst/pkgtemplates/MaskedBSgenome_datapkg/DESCRIPTION b/inst/pkgtemplates/MaskedBSgenome_datapkg/DESCRIPTION
index 6fed581..719b8d5 100644
--- a/inst/pkgtemplates/MaskedBSgenome_datapkg/DESCRIPTION
+++ b/inst/pkgtemplates/MaskedBSgenome_datapkg/DESCRIPTION
@@ -4,8 +4,7 @@ Description: @PKGDESCRIPTION@
Version: @PKGVERSION@
Author: @AUTHOR@
Maintainer: @MAINTAINER@
-Depends: R (>= 3.5.0), BSgenome (>= @BSGENOMEVERSION@), @REFPKGNAME@
-Imports: BSgenome, @REFPKGNAME@
+Depends: R (>= 4.2.0), GenomeInfoDb (>= 1.34.9), BSgenome (>= @BSGENOMEVERSION@), @REFPKGNAME@
Suggests: @SUGGESTS@
License: @LICENSE@
organism: @ORGANISM@
diff --git a/inst/pkgtemplates/MaskedBSgenome_datapkg/NAMESPACE b/inst/pkgtemplates/MaskedBSgenome_datapkg/NAMESPACE
index bf11e83..7d26b54 100644
--- a/inst/pkgtemplates/MaskedBSgenome_datapkg/NAMESPACE
+++ b/inst/pkgtemplates/MaskedBSgenome_datapkg/NAMESPACE
@@ -1,3 +1,4 @@
+import(GenomeInfoDb)
import(BSgenome)
import(@REFPKGNAME@)
diff --git a/inst/pkgtemplates/MaskedBSgenome_datapkg/man/package.Rd b/inst/pkgtemplates/MaskedBSgenome_datapkg/man/package.Rd
index b0d6fc7..6190837 100644
--- a/inst/pkgtemplates/MaskedBSgenome_datapkg/man/package.Rd
+++ b/inst/pkgtemplates/MaskedBSgenome_datapkg/man/package.Rd
@@ -27,7 +27,7 @@
See \code{?\link[BSgenome]{BSgenomeForge}} and the BSgenomeForge
vignette (\code{vignette("BSgenomeForge")}) in the \pkg{BSgenome}
- software package for how to make a BSgenome data package.
+ software package for how to create a BSgenome data package.
}
\author{@AUTHOR@}
@@ -36,24 +36,38 @@
\itemize{
\item \link[@REFPKGNAME@]{@REFPKGNAME@} in the \pkg{@REFPKGNAME@} package
for information about how the sequences were obtained.
- \item \link[BSgenome]{BSgenome} objects and the
- \code{\link[BSgenome]{available.genomes}} function
- in the \pkg{BSgenome} software package.
+
+ \item \link[BSgenome]{BSgenome} objects in the \pkg{BSgenome}
+ software package.
+
+ \item The \code{\link[GenomeInfoDb]{seqinfo}} getter and
+ \link[GenomeInfoDb]{Seqinfo} objects in the \pkg{GenomeInfoDb}
+ package.
+
+ \item The \code{\link[GenomeInfoDb]{seqlevelsStyle}} getter and
+ setter in the \pkg{GenomeInfoDb} package.
+
\item \link[Biostrings]{MaskedDNAString} objects in the \pkg{Biostrings}
package.
+
+ \item The \code{\link[BSgenome]{available.genomes}} function
+ in the \pkg{BSgenome} software package.
+
\item The BSgenomeForge vignette (\code{vignette("BSgenomeForge")})
- in the \pkg{BSgenome} software package for how to make a BSgenome
+ in the \pkg{BSgenome} software package for how to create a BSgenome
data package.
}
}
\examples{
@PKGNAME@
-genome <- @PKGNAME@
-head(seqlengths(genome))
+mbsg <- @PKGNAME@
+head(seqlengths(mbsg))
+seqinfo(mbsg)
+
@PKGEXAMPLES@
-if ("AGAPS" \%in\% masknames(genome)) {
+if ("AGAPS" \%in\% masknames(mbsg)) {
## Check that the assembly gaps contain only Ns:
checkOnlyNsInGaps <- function(seq)
@@ -69,14 +83,18 @@ if ("AGAPS" \%in\% masknames(genome)) {
## from the cache:
options(verbose=TRUE)
- for (seqname in seqnames(genome)) {
+ for (seqname in seqnames(mbsg)) {
cat("Checking sequence", seqname, "... ")
- seq <- genome[[seqname]]
+ seq <- mbsg[[seqname]]
checkOnlyNsInGaps(seq)
cat("OK\n")
}
}
+## ---------------------------------------------------------------------
+## Genome-wide motif searching
+## ---------------------------------------------------------------------
+
## See the GenomeSearching vignette in the BSgenome software
## package for some examples of genome-wide motif searching using
## Biostrings and the BSgenome data packages:
diff --git a/man/BSgenome-class.Rd b/man/BSgenome-class.Rd
index 36df1ac..3018439 100644
--- a/man/BSgenome-class.Rd
+++ b/man/BSgenome-class.Rd
@@ -63,13 +63,13 @@
\item \code{common_name}: The common name of the organism that this
BSgenome object is for. E.g. \code{"Human"}, \code{"Mouse"},
\code{"Worm"}, etc...
+ \item \code{provider}: The provider of this genome. E.g.
+ \code{"UCSC"}, \code{"BDGP"}, \code{"FlyBase"}, etc...
\item \code{genome}: The name of the genome. Typically the name of
an NCBI assembly (e.g. \code{"GRCh38.p12"}, \code{"WBcel235"},
\code{"TAIR10.1"}, \code{"ARS-UCD1.2"}, etc...) or UCSC genome
(e.g. \code{"hg38"}, \code{"bosTau9"}, \code{"galGal6"},
\code{"ce11"}, etc...).
- \item \code{provider}: The provider of this genome. E.g.
- \code{"UCSC"}, \code{"BDGP"}, \code{"FlyBase"}, etc...
\item \code{release_date}: The release date of this genome e.g.
\code{"Mar. 2006"}.
\item \code{source_url}: The permanent URL to the place where the
diff --git a/man/BSgenomeForge.Rd b/man/BSgenomeForge.Rd
index ca30fb8..40871ac 100644
--- a/man/BSgenomeForge.Rd
+++ b/man/BSgenomeForge.Rd
@@ -25,7 +25,7 @@
\usage{
## Top-level BSgenomeForge function:
-forgeBSgenomeDataPkg(x, seqs_srcdir=".", destdir=".", verbose=TRUE)
+forgeBSgenomeDataPkg(x, seqs_srcdir=".", destdir=".", replace=FALSE, verbose=TRUE)
## Low-level BSgenomeForge functions:
@@ -73,6 +73,11 @@ forgeMasksFiles(seqnames, nmask_per_seq,
This directory must already exist.
See the BSgenomeForge vignette in this package for more information.
}
+ \item{replace}{
+ \code{TRUE} or \code{FALSE}.
+ When set to TRUE, \code{replace} replaces the package directory
+ if it already exists.
+ }
\item{verbose}{
\code{TRUE} or \code{FALSE}.
}
diff --git a/man/SNPlocs-class.Rd b/man/SNPlocs-class.Rd
index 1dabf2b..db0cfed 100644
--- a/man/SNPlocs-class.Rd
+++ b/man/SNPlocs-class.Rd
@@ -59,17 +59,6 @@
\alias{inferRefAndAltAlleles}
-% Old SNPlocs extractors (defunct)
-\alias{snpid2loc}
-\alias{snpid2loc,SNPlocs-method}
-\alias{snpid2loc,OldFashionSNPlocs-method}
-\alias{snpid2alleles}
-\alias{snpid2alleles,SNPlocs-method}
-\alias{snpid2alleles,OldFashionSNPlocs-method}
-\alias{snpid2grange}
-\alias{snpid2grange,SNPlocs-method}
-\alias{snpid2grange,OldFashionSNPlocs-method}
-
\title{SNPlocs objects}
\description{