updates to prepare for Bioc submission

.Rbuildignore

@@ -5,6 +5,7 @@
 ^.*\.Rproj$
 ^\.Rproj\.user$
 ^\.travis\.yml$
+^\.github$
 ^Makefile$
 ^coverage\.txt$
 ^coverage\.r$

.github/workflows/standard-ci-workflow.yml

@@ -23,65 +23,37 @@ jobs:
           - {os: windows-latest, r: 'release'}
           - {os: macOS-latest, r: 'release'}
           - {os: macOS-latest, r: 'devel'}
-          - {os: ubuntu-16.04, r: 'release', rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
+          - {os: ubuntu-latest, r: 'release'}
+          - {os: ubuntu-latest, r: 'oldrel-1'}
 
     env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
-      - uses: r-lib/actions/setup-r@master
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
         with:
           r-version: ${{ matrix.config.r }}
+          use-public-rspm: true
 
-      - uses: r-lib/actions/setup-pandoc@master
-
-      - name: Query dependencies
-        run: |
-          install.packages('remotes')
-          saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)
-        shell: Rscript {0}
-
-      - name: Cache R packages
-        if: runner.os != 'Windows'
-        uses: actions/cache@v1
+      - uses: r-lib/actions/setup-r-dependencies@v2
         with:
-          path: ${{ env.R_LIBS_USER }}
-          key: ${{ runner.os }}-r-${{ matrix.config.r }}-1-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-1-
-
-      - name: Install system dependencies
-        if: runner.os == 'Linux'
-        env:
-          RHUB_PLATFORM: linux-x86_64-ubuntu-gcc
-        run: |
-          Rscript -e "remotes::install_github('r-hub/sysreqs')"
-          sysreqs=$(Rscript -e "cat(sysreqs::sysreq_commands('DESCRIPTION'))")
-          sudo -s eval "$sysreqs"
+          extra-packages: any::rcmdcheck
+          needs: check
 
-      - name: Install Bioconductor
-        run: |
-          install.packages("BiocManager")
-          BiocManager::install()
-        shell: Rscript {0}
-
-      - name: Install dependencies
-        run: |
-          remotes::install_deps(dependencies = TRUE, repos = BiocManager::repositories())
-          remotes::install_cran("rcmdcheck")
-        shell: Rscript {0}
-
-      - name: Check
-        env:
-          _R_CHECK_CRAN_INCOMING_REMOTE_: false
-        run: rcmdcheck::rcmdcheck(args = c("--no-manual", "--as-cran"), error_on = "warning", check_dir = "check")
-        shell: Rscript {0}
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          args: 'c("--no-manual", "--as-cran")'
+          error-on: '"warning"'
+          upload-snapshots: true
 
       - name: Upload check results
         if: failure()
-        uses: actions/upload-artifact@master
+        uses: actions/upload-artifact@v4
         with:
           name: ${{ runner.os }}-r${{ matrix.config.r }}-results
           path: check

DESCRIPTION

@@ -1,11 +1,19 @@
 Package: ribiosAnnotation
 Type: Package
-Title: Annotation of genes, RNAs and proteins in the BIOS system
+Title: Annotation of Genes, RNAs, and Proteins in 'ribios'
 Version: 3.8.0
-Date: 2025-07-28
-Author: Jitao David Zhang <jitao_david.zhang@roche.com>
-Maintainer: Jitao David Zhang <jitao_david.zhang@roche.com>
-Description: Retrieves annotation information of genomic features, genes, RNAs and proteins from the Oracle database of the Roche Bioinformatics environment.
+Date: 2026-02-15
+Authors@R: person("Jitao David", "Zhang",
+    email = "jitao_david.zhang@roche.com",
+    role = c("aut", "cre"),
+    comment = c(ORCID = "0000-0002-3085-0909"))
+Description: Retrieves annotation information of genomic features including
+    genes, RNAs, and proteins from databases. It supports querying by gene
+    identifiers, gene symbols, UniProt accessions, Ensembl identifiers, and
+    RefSeq identifiers, as well as mapping orthologs across species using
+    NCBI data.
+Depends:
+    R (>= 4.1.0)
 Imports:
     ribiosUtils,
     dplyr,
@@ -14,13 +22,13 @@ Imports:
     magrittr,
     mongolite
 Suggests:
-    roxygen2,
     testthat
 LazyData: true
 License: GPL-3
 Encoding: UTF-8
-RoxygenNote: 7.3.2
-Collate: 
+RoxygenNote: 7.3.3
+Additional_repositories: https://bedapub.r-universe.dev
+Collate:
     'sortAnnotationByQuery.R'
     'removeEnsemblVersion.R'
     'utils.R'
@@ -38,6 +46,7 @@ Collate:
     'formatIn.R'
     'gti2bioc.R'
     'humanOrthologsByTaxID.R'
+    'ribiosAnnotation-package.R'
     'taxID.R'
     'uniprotByTaxID.R'
 Remotes:

R/annotateAnyIDs.R

@@ -27,34 +27,28 @@ NULL
 #' @seealso \code{\link{annotateGeneIDs}}, \code{\link{annotateGeneSymbols}}
 #' @importFrom ribiosUtils putColsFirst matchColumn
 #' @examples
-#' 
-#' options(error=utils::recover)
-#' 
+#' \dontrun{
 #' # GeneID
 #' annotateAnyIDs(ids=c(780, 5982, 3310, NA))
-#' 
+#'
 #' # GeneSymbol
 #' annotateAnyIDs(ids=c("DDR1", "RFC2", "HSPA6", "HSAP6"))
-#' 
+#'
 #' # Probesets
 #' myprobes <- c("1000_at", "1004_at", "1002_f_at", "nonsense_at")
 #' annotateAnyIDs(myprobes)
-#' 
+#'
 #' # UniProt
 #' annotateAnyIDs(ids=c("P38398", "Q8NDF8"))
-#' 
-#' # EnsEMBL 
+#'
+#' # EnsEMBL
 #' ensemblIDs <- c("ENSG00000197535", "ENST00000399231.7", "ENSP00000418960.2")
 #' annotateAnyIDs(ensemblIDs)
-#' 
-#' # TODO: ENST and ENSP do not work yet
-#' annotateAnyIDs("ENST00000399231")
-#' 
+#'
 #' # RefSeq
 #' annotateAnyIDs(c("NM_000235", "NM_000498"))
-#' 
-#' options(error=NULL)
-#' 
+#' }
+#'
 #' @export annotateAnyIDs
 annotateAnyIDs <- function(ids, orthologue = FALSE, multiOrth = FALSE) {
   validIDs <- removeEnsemblVersion(ids)

R/annotateGeneIDs.R

@@ -58,7 +58,7 @@ annotateGeneIDs <- function(ids, orthologue=FALSE, multiOrth=FALSE) {
 #' @note \code{annotatemRNAs} is an alias of \code{annotateRefSeqs}
 #' @author Jitao David Zhang <jitao_david.zhang@@roche.com>
 #'
-#' @details The collection {ncbi_gene_info} is used.
+#' @details The collection \code{ncbi_gene_info} is used.
 #' 
 #' @examples
 #' 

R/annotateGeneSymbols.R

@@ -130,5 +130,4 @@ annotateGeneSymbols <- function(ids, taxId=9606, orthologue=FALSE, multiOrth=FAL
     res <- annotateGeneSymbolsWithHumanOrtholog(ids, taxId=taxId, multiOrth=TRUE)
   }
   return(res)
-	return(NULL)
 }

R/annotateProteinGroups.R

@@ -31,12 +31,10 @@ getGenesPerIndex <- function(x) {
 #' In case \code{orthologue} is \code{TRUE}, human orthologue information is 
 #' returned as well.
 #' @examples
-#' options(error=utils::recover)
 #' \dontrun{
 #' annotateProteinGroups(c("A0A024RBG1;Q9NZJ9", "A0A0B4J2D5;P0DPI2",
 #'                            "A0A0B4J2F0;A0A0U1RRL7"))
 #' }
-#' options(error=NULL)
 #' @importFrom dplyr group_by arrange group_modify ungroup
 #' @export
 annotateProteinGroups <- function(ids, delimiter=";",
@@ -62,6 +60,3 @@ annotateProteinGroups <- function(ids, delimiter=";",
     unique
   return(res)
 }
-
-## assignInNamespace("getGenesPerIndex", getGenesPerIndex, "ribiosAnnotation")
-## assignInNamespace("annotateProteinGroups", annotateProteinGroups, "ribiosAnnotation")

R/appendHumanOrthologsWithNCBI.R

@@ -18,14 +18,17 @@ NULL
 #' @note The function does not sort the rows by GeneID. It is the responsibility
 #'  of the calling function to do so.
 #' 
-#' @examples 
+#' @return A \code{data.frame} with annotation and human orthologs appended.
+#' @examples
+#' \dontrun{
 #' anno <- data.frame(GeneID=c(780, 1506, 114483548, 102129055, NA),
 #'                    TaxID=c(9606, 9606, 10116, 9541, NA))
 #' appendHumanOrthologsWithNCBI(anno)
-#' 
+#'
 #' tol_anno <- data.frame(GeneID=c(780, 1506, 114483548, 102129055, NA, "NotV"),
 #'                    TaxID=c(9606, 9606, 10116, 9541, NA, NA))
 #' appendHumanOrthologsWithNCBI(tol_anno)
+#' }
 #' @importFrom ribiosUtils haltifnot
 #' @export
 appendHumanOrthologsWithNCBI <- function(anno,
@@ -66,7 +69,4 @@ appendHumanOrthologsWithNCBI <- function(anno,
 
   res <- unique(res) %>% dplyr::select(-chrGeneID)
   return(res)
-}
-
-## assignInNamespace("appendHumanOrthologsWithNCBI", appendHumanOrthologsWithNCBI, "ribiosAnnotation")
-## rm(appendHumanOrthologsWithNCBI)
+}

R/featureID.R

@@ -220,8 +220,7 @@ guessFeatureType <- function(featureIDs, majority=0.5) {
 #' 
 #' @seealso \code{\link{annotateAnyIDs}}
 #' 
-#' @examples 
-#' options(error=utils::recover)
+#' @examples
 #' \dontrun{
 #'   guessAndAnnotate(c("AKT1", "AKT2", "MAPK14"))
 #'   guessAndAnnotate(c(1,2,14,149))
@@ -231,7 +230,6 @@ guessFeatureType <- function(featureIDs, majority=0.5) {
 #'   guessAndAnnotate(c("O60583", "P05997", "Q7Z624"))
 #'   guessAndAnnotate(c("CM000677.2", "AB003434.2"))
 #' }
-#' options(error=NULL)
 #' @export
 guessAndAnnotate <- function(featureIDs, majority=0.5,
                              orthologue=FALSE, multiOrth=FALSE,

R/gti2bioc.R

@@ -1,3 +1,15 @@
+#' Translation table between GTI and Bioconductor chip type names
+#'
+#' A data frame mapping GTI array names to Bioconductor array names.
+#'
+#' @format A data frame with columns:
+#' \describe{
+#'   \item{GTI}{GTI chip type name}
+#'   \item{Bioconductor}{Bioconductor chip type name}
+#' }
+#' @source Compiled manually in December 2011.
+"gtibioc"
+
 #' @importFrom utils globalVariables
 utils::globalVariables("gtibioc")
 
@@ -33,7 +45,7 @@ bioc2gti <- function (chipname) {
 #' a vector of the GTI names. Both vectors have the chip types in the other
 #' system as names. See examples.
 #' 
-#' @aliases gtibioc gti2bioc bioc2gti
+#' @aliases gti2bioc bioc2gti
 #' @param chipname Character vector, chip names (types). If missing, chip types
 #' supported by both GTI and Bioconductor will be printed, see details.
 #' @return Chracter vector of the same length as the input

R/humanOrthologsByTaxID.R

@@ -6,7 +6,7 @@ NULL
 #'    for instance \code{10116} for rat, \code{10090} for mouse, and \code{9541}
 #'    for cyno (crab-eating macaque).
 #' @return A \code{data.frame} contains following columns:
-#'  \itemize{
+#'  \describe{
 #'     \item{\code{GeneID}}{NCBI Gene ID of the query species}
 #'     \item{\code{GeneSymbol}}{NCBI Gene symbol of the query species}
 #'     \item{\code{Description}}{Gene description of the query species}

R/ribiosAnnotation-package.R

@@ -0,0 +1,5 @@
+#' @keywords internal
+"_PACKAGE"
+
+#' @importFrom ribiosUtils matchColumn
+NULL

R/uniprotByTaxID.R

@@ -9,7 +9,8 @@ NULL
 #' selected top one if multiple exist. Only valid when \code{orthologue} is set 
 #' as \code{TRUE}.
 #' 
-#' @seealso 
+#' @return A \code{data.frame} with UniProt accessions and gene annotations.
+#' @seealso
 #' * \code{\link{annotateUniprotAccession}}, which annotates Uniprot accessions
 #' * \code{\link{annotateTaxID}}, which annotates genes given TaxID.
 #' @examples 

R/utils.R

@@ -55,7 +55,7 @@ locateSecretsFile <- function(path) {
 #' @param instance String, which must be found under the \code{mongodb} section
 #'  of the JSON file
 #' @return A list of the following items:
-#' \itemize{
+#' \describe{
 #'   \item{\code{hostname}}{Hostname of the MongoDB}
 #'   \item{\code{port}}{Port of the MongoDB}
 #'   \item{\code{dbname}}{Database of the MongoDB}
@@ -89,9 +89,11 @@ loadMongodbSecrets <- function(file=locateSecretsFile(),
 #' @param verbose Logical
 #' @return A pointer to a collection on the server, as returned by
 #'  \code{\link[mongolite]{mongo}}.
-#' @examples 
+#' @examples
+#' \dontrun{
 #' giCon <- connectMongoDB(instance="bioinfo_read",
 #'                         collection="ncbi_gene_info")
+#' }
 #' @seealso \code{\link{loadMongodbSecrets}}
 #' @export
 connectMongoDB <- function(instance="bioinfo_read",