diff --git a/DESCRIPTION b/DESCRIPTION index 309c8e6..bdbedfd 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -9,13 +9,15 @@ Description: Precomputed transcription factor binding sites, motif GC for sequence composition. The data are hosted on AnnotationHub and retrieved on first use; this package provides the accessors and the documentation. -Authors@R: person( - given = "Irem B.", family = "Gunduz", - email = "irembgunduz@gmail.com", role = c("aut", "cre"), - comment = c(ORCID = "0000-0003-2641-0916")) +Authors@R: c( + person("Irem B.", "Gündüz", , "irembgunduz@gmail.com", role = c("aut", "cre"), + comment = c(ORCID = "0000-0003-2641-0916")), + person("Fabian", "Muller", , "fabian.mueller@uni-saarland.de", role = "aut", + comment = c(ORCID = "0000-0001-5809-2321")) + ) License: Artistic-2.0 Encoding: UTF-8 -Version: 0.99.6 +Version: 0.99.8 Depends: R (>= 4.3.0) Imports: AnnotationHub, GenomicRanges, utils Suggests: knitr, rmarkdown, testthat (>= 3.0.0), BiocStyle diff --git a/NEWS.md b/NEWS.md index b32926b..120aae2 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,4 +1,4 @@ -# methylTFRAnnotationHg38 0.99.6 +# methylTFRAnnotationHg38 0.99.8 * Initial submission to Bioconductor. diff --git a/inst/extdata/metadata.csv b/inst/extdata/metadata.csv index fb599da..d67a829 100644 --- a/inst/extdata/metadata.csv +++ b/inst/extdata/metadata.csv @@ -1,9 +1,9 @@ "Title","Description","BiocVersion","Genome","SourceType","SourceUrl","SourceVersion","Species","TaxonomyId","Coordinate_1_based","DataProvider","Maintainer","RDataClass","DispatchClass","Location_Prefix","RDataPath","Tags" -"altius_motif_gcfreq.rds","GC bin frequency tables for ALTIUS motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.","3.23","hg38","RDS","https://resources.altius.org/~jvierstra/projects/motif-clustering/releases/v1.0/","Vierstra motif archetypes v1.0","Homo sapiens",9606,TRUE,"Altius Institute","Irem B. Gunduz ","list","Rds","https://bioconductorhubs.blob.core.windows.net/annotationhub/","methylTFRAnnotationHg38/altius_motif_gcfreq.rds","methylTFRAnnotationHg38:GCcontent:MotifAnnotation:ALTIUS" -"altius_tf_bindsites.rds","Genome-wide ALTIUS transcription factor binding site predictions for hg38, one GRanges per motif, each range extended by 200 bases on either side of the motif match so that methylTFR can read methylation across the footprint window.","3.23","hg38","RDS","https://resources.altius.org/~jvierstra/projects/motif-clustering/releases/v1.0/","Vierstra motif archetypes v1.0","Homo sapiens",9606,TRUE,"Altius Institute","Irem B. Gunduz ","GRangesList","Rds","https://bioconductorhubs.blob.core.windows.net/annotationhub/","methylTFRAnnotationHg38/altius_tf_bindsites.rds","methylTFRAnnotationHg38:TFBS:MotifAnnotation:ALTIUS" -"cisbpv2_motif_gcfreq.rds","GC bin frequency tables for CISBPV2 motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.","3.23","hg38","RDS","https://github.com/GreenleafLab/chromVARmotifs","CIS-BP v2 (chromVARmotifs pwms_v2)","Homo sapiens",9606,TRUE,"CIS-BP","Irem B. Gunduz ","list","Rds","https://bioconductorhubs.blob.core.windows.net/annotationhub/","methylTFRAnnotationHg38/cisbpv2_motif_gcfreq.rds","methylTFRAnnotationHg38:GCcontent:MotifAnnotation:CISBPV2" -"cisbpv2_tf_bindsites.rds","Genome-wide CISBPV2 transcription factor binding site predictions for hg38, one GRanges per motif, each range extended by 200 bases on either side of the motif match so that methylTFR can read methylation across the footprint window.","3.23","hg38","RDS","https://github.com/GreenleafLab/chromVARmotifs","CIS-BP v2 (chromVARmotifs pwms_v2)","Homo sapiens",9606,TRUE,"CIS-BP","Irem B. Gunduz ","GRangesList","Rds","https://bioconductorhubs.blob.core.windows.net/annotationhub/","methylTFRAnnotationHg38/cisbpv2_tf_bindsites.rds","methylTFRAnnotationHg38:TFBS:MotifAnnotation:CISBPV2" -"genomewide_GC_hg38.rds","Genome-wide GC content distribution for hg38. A GRanges of tiled windows carrying GC_bias and a GC_bin assignment into genome-wide quintiles. methylTFR uses it to assign each methylation call to a GC bin.","3.23","hg38","RDS","https://bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg38/","hg38","Homo sapiens",9606,TRUE,"UCSC","Irem B. Gunduz ","GRanges","Rds","https://bioconductorhubs.blob.core.windows.net/annotationhub/","methylTFRAnnotationHg38/genomewide_GC_hg38.rds","methylTFRAnnotationHg38:GCcontent:Genome" -"jaspar2020_distal_motif_gcfreq.rds","GC bin frequency tables for JASPAR2020_DISTAL motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.","3.23","hg38","RDS","https://jaspar.elixir.no/","JASPAR2020 CORE","Homo sapiens",9606,TRUE,"JASPAR","Irem B. Gunduz ","list","Rds","https://bioconductorhubs.blob.core.windows.net/annotationhub/","methylTFRAnnotationHg38/jaspar2020_distal_motif_gcfreq.rds","methylTFRAnnotationHg38:GCcontent:MotifAnnotation:JASPAR2020_DISTAL" -"jaspar2020_motif_gcfreq.rds","GC bin frequency tables for JASPAR2020 motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.","3.23","hg38","RDS","https://jaspar.elixir.no/","JASPAR2020 CORE","Homo sapiens",9606,TRUE,"JASPAR","Irem B. Gunduz ","list","Rds","https://bioconductorhubs.blob.core.windows.net/annotationhub/","methylTFRAnnotationHg38/jaspar2020_motif_gcfreq.rds","methylTFRAnnotationHg38:GCcontent:MotifAnnotation:JASPAR2020" -"jaspar2020_tf_bindsites.rds","Genome-wide JASPAR2020 transcription factor binding site predictions for hg38, one GRanges per motif, each range extended by 200 bases on either side of the motif match so that methylTFR can read methylation across the footprint window.","3.23","hg38","RDS","https://jaspar.elixir.no/","JASPAR2020 CORE","Homo sapiens",9606,TRUE,"JASPAR","Irem B. Gunduz ","GRangesList","Rds","https://bioconductorhubs.blob.core.windows.net/annotationhub/","methylTFRAnnotationHg38/jaspar2020_tf_bindsites.rds","methylTFRAnnotationHg38:TFBS:MotifAnnotation:JASPAR2020" +"altius_motif_gcfreq.rds","GC bin frequency tables for ALTIUS motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.","3.24","hg38","RDS","https://resources.altius.org/~jvierstra/projects/motif-clustering/releases/v1.0/","Vierstra motif archetypes v1.0","Homo sapiens",9606,TRUE,"Altius Institute","Irem B. Gunduz ","list","Rds","https://zenodo.org/","records/22206980/files/altius_motif_gcfreq.rds","methylTFRAnnotationHg38:GCcontent:MotifAnnotation:ALTIUS" +"altius_tf_bindsites.rds","Genome-wide ALTIUS transcription factor binding site predictions for hg38, one GRanges per motif, each range extended by 200 bases on either side of the motif match so that methylTFR can read methylation across the footprint window.","3.24","hg38","RDS","https://resources.altius.org/~jvierstra/projects/motif-clustering/releases/v1.0/","Vierstra motif archetypes v1.0","Homo sapiens",9606,TRUE,"Altius Institute","Irem B. Gunduz ","GRangesList","Rds","https://zenodo.org/","records/22206980/files/altius_tf_bindsites.rds","methylTFRAnnotationHg38:TFBS:MotifAnnotation:ALTIUS" +"cisbpv2_motif_gcfreq.rds","GC bin frequency tables for CISBPV2 motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.","3.24","hg38","RDS","https://github.com/GreenleafLab/chromVARmotifs","CIS-BP v2 (chromVARmotifs pwms_v2)","Homo sapiens",9606,TRUE,"CIS-BP","Irem B. Gunduz ","list","Rds","https://zenodo.org/","records/22206980/files/cisbpv2_motif_gcfreq.rds","methylTFRAnnotationHg38:GCcontent:MotifAnnotation:CISBPV2" +"cisbpv2_tf_bindsites.rds","Genome-wide CISBPV2 transcription factor binding site predictions for hg38, one GRanges per motif, each range extended by 200 bases on either side of the motif match so that methylTFR can read methylation across the footprint window.","3.24","hg38","RDS","https://github.com/GreenleafLab/chromVARmotifs","CIS-BP v2 (chromVARmotifs pwms_v2)","Homo sapiens",9606,TRUE,"CIS-BP","Irem B. Gunduz ","GRangesList","Rds","https://zenodo.org/","records/22206980/files/cisbpv2_tf_bindsites.rds","methylTFRAnnotationHg38:TFBS:MotifAnnotation:CISBPV2" +"genomewide_GC_hg38.rds","Genome-wide GC content distribution for hg38. A GRanges of tiled windows carrying GC_bias and a GC_bin assignment into genome-wide quintiles. methylTFR uses it to assign each methylation call to a GC bin.","3.24","hg38","RDS","https://bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg38/","hg38","Homo sapiens",9606,TRUE,"UCSC","Irem B. Gunduz ","GRanges","Rds","https://zenodo.org/","records/22206980/files/genomewide_GC_hg38.rds","methylTFRAnnotationHg38:GCcontent:Genome" +"jaspar2020_distal_motif_gcfreq.rds","GC bin frequency tables for JASPAR2020_DISTAL motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.","3.24","hg38","RDS","https://jaspar.elixir.no/","JASPAR2020 CORE","Homo sapiens",9606,TRUE,"JASPAR","Irem B. Gunduz ","list","Rds","https://zenodo.org/","records/22206980/files/jaspar2020_distal_motif_gcfreq.rds","methylTFRAnnotationHg38:GCcontent:MotifAnnotation:JASPAR2020_DISTAL" +"jaspar2020_motif_gcfreq.rds","GC bin frequency tables for JASPAR2020 motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.","3.24","hg38","RDS","https://jaspar.elixir.no/","JASPAR2020 CORE","Homo sapiens",9606,TRUE,"JASPAR","Irem B. Gunduz ","list","Rds","https://zenodo.org/","records/22206980/files/jaspar2020_motif_gcfreq.rds","methylTFRAnnotationHg38:GCcontent:MotifAnnotation:JASPAR2020" +"jaspar2020_tf_bindsites.rds","Genome-wide JASPAR2020 transcription factor binding site predictions for hg38, one GRanges per motif, each range extended by 200 bases on either side of the motif match so that methylTFR can read methylation across the footprint window.","3.24","hg38","RDS","https://jaspar.elixir.no/","JASPAR2020 CORE","Homo sapiens",9606,TRUE,"JASPAR","Irem B. Gunduz ","GRangesList","Rds","https://zenodo.org/","records/22206980/files/jaspar2020_tf_bindsites.rds","methylTFRAnnotationHg38:TFBS:MotifAnnotation:JASPAR2020" diff --git a/inst/scripts/make-metadata.R b/inst/scripts/make-metadata.R index 540aa4f..35bf4d4 100644 --- a/inst/scripts/make-metadata.R +++ b/inst/scripts/make-metadata.R @@ -1,5 +1,5 @@ # 1. Define the shared (constant) variables for cleaner code -bioc_version <- "3.23" +bioc_version <- "3.24" genome <- "hg38" source_type <- "RDS" species <- "Homo sapiens" @@ -7,7 +7,7 @@ tax_id <- 9606 coord_1_based <- TRUE maintainer <- "Irem B. Gunduz " dispatch_class <- "Rds" -location_prefix <- "https://bioconductorhubs.blob.core.windows.net/annotationhub/" +location_prefix <- "https://zenodo.org/" # 2. Build the data frame metadata <- data.frame( @@ -21,7 +21,7 @@ metadata <- data.frame( "jaspar2020_motif_gcfreq.rds", "jaspar2020_tf_bindsites.rds" ), - + Description = c( "GC bin frequency tables for ALTIUS motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.", "Genome-wide ALTIUS transcription factor binding site predictions for hg38, one GRanges per motif, each range extended by 200 bases on either side of the motif match so that methylTFR can read methylation across the footprint window.", @@ -32,11 +32,11 @@ metadata <- data.frame( "GC bin frequency tables for JASPAR2020 motifs on hg38. One five-row matrix per motif giving the number of binding sites falling in each genome-wide GC quintile, used by methylTFR to compute the expected methylation a motif would show from GC content alone.", "Genome-wide JASPAR2020 transcription factor binding site predictions for hg38, one GRanges per motif, each range extended by 200 bases on either side of the motif match so that methylTFR can read methylation across the footprint window." ), - + BiocVersion = rep(bioc_version, 8), Genome = rep(genome, 8), SourceType = rep(source_type, 8), - + SourceUrl = c( "https://resources.altius.org/~jvierstra/projects/motif-clustering/releases/v1.0/", "https://resources.altius.org/~jvierstra/projects/motif-clustering/releases/v1.0/", @@ -47,7 +47,7 @@ metadata <- data.frame( "https://jaspar.elixir.no/", "https://jaspar.elixir.no/" ), - + SourceVersion = c( "Vierstra motif archetypes v1.0", "Vierstra motif archetypes v1.0", @@ -58,11 +58,11 @@ metadata <- data.frame( "JASPAR2020 CORE", "JASPAR2020 CORE" ), - + Species = rep(species, 8), TaxonomyId = rep(tax_id, 8), Coordinate_1_based = rep(coord_1_based, 8), - + DataProvider = c( "Altius Institute", "Altius Institute", @@ -73,9 +73,9 @@ metadata <- data.frame( "JASPAR", "JASPAR" ), - + Maintainer = rep(maintainer, 8), - + RDataClass = c( "list", "GRangesList", @@ -86,21 +86,21 @@ metadata <- data.frame( "list", "GRangesList" ), - + DispatchClass = rep(dispatch_class, 8), Location_Prefix = rep(location_prefix, 8), - + RDataPath = c( - "methylTFRAnnotationHg38/altius_motif_gcfreq.rds", - "methylTFRAnnotationHg38/altius_tf_bindsites.rds", - "methylTFRAnnotationHg38/cisbpv2_motif_gcfreq.rds", - "methylTFRAnnotationHg38/cisbpv2_tf_bindsites.rds", - "methylTFRAnnotationHg38/genomewide_GC_hg38.rds", - "methylTFRAnnotationHg38/jaspar2020_distal_motif_gcfreq.rds", - "methylTFRAnnotationHg38/jaspar2020_motif_gcfreq.rds", - "methylTFRAnnotationHg38/jaspar2020_tf_bindsites.rds" + "records/22206980/files/altius_motif_gcfreq.rds", + "records/22206980/files/altius_tf_bindsites.rds", + "records/22206980/files/cisbpv2_motif_gcfreq.rds", + "records/22206980/files/cisbpv2_tf_bindsites.rds", + "records/22206980/files/genomewide_GC_hg38.rds", + "records/22206980/files/jaspar2020_distal_motif_gcfreq.rds", + "records/22206980/files/jaspar2020_motif_gcfreq.rds", + "records/22206980/files/jaspar2020_tf_bindsites.rds" ), - + Tags = c( "methylTFRAnnotationHg38:GCcontent:MotifAnnotation:ALTIUS", "methylTFRAnnotationHg38:TFBS:MotifAnnotation:ALTIUS", @@ -111,7 +111,7 @@ metadata <- data.frame( "methylTFRAnnotationHg38:GCcontent:MotifAnnotation:JASPAR2020", "methylTFRAnnotationHg38:TFBS:MotifAnnotation:JASPAR2020" ), - + stringsAsFactors = FALSE ) @@ -120,9 +120,9 @@ metadata <- data.frame( dir.create("inst/extdata", recursive = TRUE, showWarnings = FALSE) write.csv( - x = metadata, - file = "inst/extdata/metadata.csv", - row.names = FALSE, + x = metadata, + file = "inst/extdata/metadata.csv", + row.names = FALSE, quote = TRUE # This ensures strings containing spaces/commas are properly enclosed ) @@ -130,6 +130,6 @@ write.csv( if (!requireNamespace("AnnotationHubData", quietly = TRUE)) { message("Please install AnnotationHubData to validate your metadata.csv") } else { - AnnotationHubData::makeAnnotationHubMetadata("inst/extdata") + AnnotationHubData::makeAnnotationHubMetadata(".") message("Metadata validation completed successfully!") } \ No newline at end of file