clustifyrdatahub provides external reference data sets for cell-type assignment with clustifyr.
if (!requireNamespace("BiocManager", quietly = TRUE))
install.packages("BiocManager")
BiocManager::install("clustifyrdatahub")knitr::kable(dplyr::select(
read.csv(system.file("extdata", "metadata.csv", package = "clustifyrdatahub")),
c(1, 9, 2:7)))| Title | Species | Description | RDataPath | BiocVersion | Genome | SourceType | SourceUrl |
|---|---|---|---|---|---|---|---|
| ref_MCA | Mus musculus | Mouse Cell Atlas | clustifyrdatahub/ref_MCA.rda | 3.12 | mm10 | Zip | https://ndownloader.figshare.com/files/10756795 |
| ref_tabula_muris_drop | Mus musculus | Tabula Muris (10X) | clustifyrdatahub/ref_tabula_muris_drop.rda | 3.12 | mm10 | Zip | https://ndownloader.figshare.com/articles/5821263 |
| ref_tabula_muris_facs | Mus musculus | Tabula Muris (SmartSeq2) | clustifyrdatahub/ref_tabula_muris_facs.rda | 3.12 | mm10 | Zip | https://ndownloader.figshare.com/articles/5821263 |
| ref_mouse.rnaseq | Mus musculus | Mouse RNA-seq from 28 cell types | clustifyrdatahub/ref_mouse.rnaseq.rda | 3.12 | mm10 | RDA | https://github.com/dviraran/SingleR/tree/master/data |
| ref_moca_main | Mus musculus | Mouse Organogenesis Cell Atlas (main cell types) | clustifyrdatahub/ref_moca_main.rda | 3.12 | mm10 | RDA | https://oncoscape.v3.sttrcancer.org/atlas.gs.washington.edu.mouse.rna/downloads |
| ref_immgen | Mus musculus | Mouse sorted immune cells | clustifyrdatahub/ref_immgen.rda | 3.12 | mm10 | RDA | https://github.com/dviraran/SingleR/tree/master/data |
| ref_hema_microarray | Homo sapiens | Human hematopoietic cell microarray | clustifyrdatahub/ref_hema_microarray.rda | 3.12 | hg38 | TXT | https://ftp.ncbi.nlm.nih.gov/geo/series/GSE24nnn/GSE24759/matrix/GSE24759_series_matrix.txt.gz |
| ref_cortex_dev | Homo sapiens | Human cortex development scRNA-seq | clustifyrdatahub/ref_cortex_dev.rda | 3.12 | hg38 | TSV | https://cells.ucsc.edu/cortex-dev/exprMatrix.tsv.gz |
| ref_pan_indrop | Homo sapiens | Human pancreatic cell scRNA-seq (inDrop) | clustifyrdatahub/ref_pan_indrop.rda | 3.12 | hg38 | RDA | https://scrnaseq-public-datasets.s3.amazonaws.com/scater-objects/baron-human.rds |
| ref_pan_smartseq2 | Homo sapiens | Human pancreatic cell scRNA-seq (SmartSeq2) | clustifyrdatahub/ref_pan_smartseq2.rda | 3.12 | hg38 | RDA | https://scrnaseq-public-datasets.s3.amazonaws.com/scater-objects/segerstolpe.rds |
| ref_mouse_atlas | Mus musculus | Mouse Atlas scRNA-seq from 321 cell types | clustifyrdatahub/ref_mouse_atlas.rda | 3.12 | mm10 | RDA | https://github.com/rnabioco/scRNA-seq-Cell-Ref-Matrix/blob/master/atlas/musMusculus/MouseAtlas.rda |
clustifyrdatahublibrary(ExperimentHub)
eh <- ExperimentHub()
## query
refs <- query(eh, "clustifyrdatahub")
refs
#> ExperimentHub with 11 records
#> # snapshotDate(): 2025-04-11
#> # $dataprovider: figshare, S3, GitHub, GEO, washington.edu, UCSC
#> # $species: Mus musculus, Homo sapiens
#> # $rdataclass: data.frame
#> # additional mcols(): taxonomyid, genome, description,
#> # coordinate_1_based, maintainer, rdatadateadded, preparerclass, tags,
#> # rdatapath, sourceurl, sourcetype
#> # retrieve records with, e.g., 'object[["EH3444"]]'
#>
#> title
#> EH3444 | ref_MCA
#> EH3445 | ref_tabula_muris_drop
#> EH3446 | ref_tabula_muris_facs
#> EH3447 | ref_mouse.rnaseq
#> EH3448 | ref_moca_main
#> ... ...
#> EH3450 | ref_hema_microarray
#> EH3451 | ref_cortex_dev
#> EH3452 | ref_pan_indrop
#> EH3453 | ref_pan_smartseq2
#> EH3779 | ref_mouse_atlas
## either by index or id
ref_hema_microarray <- refs[[7]] ## load the first resource in the list
ref_hema_microarray <- refs[["EH3450"]] ## load by EH id
## or list and load
refs <- listResources(eh, "clustifyrdatahub")
ref_hema_microarray <- loadResources(
eh,
"clustifyrdatahub",
"ref_hema_microarray"
)[[1]]
## use for classification of cell types
res <- clustifyr::clustify(
input = clustifyr::pbmc_matrix_small,
metadata = clustifyr::pbmc_meta$classified,
ref_mat = ref_hema_microarray,
query_genes = clustifyr::pbmc_vargenes
)## or load refs by function name (after loading hub library)
library(clustifyrdatahub)
ref_hema_microarray()[1:5, 1:5] ## data are loaded
#> Basophils CD4+ Central Memory CD4+ Effector Memory CD8+ Central Memory
#> DDR1 6.084244 5.967502 5.933039 6.005278
#> RFC2 6.280044 6.028615 6.047005 5.992979
#> HSPA6 6.535444 5.811475 5.746326 5.928349
#> PAX8 6.669153 5.896401 6.118577 6.270870
#> GUCA1A 5.239230 5.232116 5.206960 5.227415
#> CD8+ Effector Memory
#> DDR1 5.895926
#> RFC2 5.942426
#> HSPA6 5.942670
#> PAX8 6.323922
#> GUCA1A 5.090882
ref_hema_microarray(metadata = TRUE) ## only metadata
#> ExperimentHub with 1 record
#> # snapshotDate(): 2025-04-11
#> # names(): EH3450
#> # package(): clustifyrdatahub
#> # $dataprovider: GEO
#> # $species: Homo sapiens
#> # $rdataclass: data.frame
#> # $rdatadateadded: 2020-05-14
#> # $title: ref_hema_microarray
#> # $description: Human hematopoietic cell microarray
#> # $taxonomyid: 9606
#> # $genome: hg38
#> # $sourcetype: TXT
#> # $sourceurl: https://ftp.ncbi.nlm.nih.gov/geo/series/GSE24nnn/GSE24759/matr...
#> # $sourcesize: NA
#> # $tags: c("SingleCellData", "SequencingData", "MicroarrayData",
#> # "ExperimentHub")
#> # retrieve record with 'object[["EH3450"]]'sessionInfo()
#> R version 4.5.0 RC (2025-04-04 r88126)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.2 LTS
#>
#> Matrix products: default
#> BLAS: /home/biocbuild/bbs-3.21-bioc/R/lib/libRblas.so
#> LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0 LAPACK version 3.12.0
#>
#> locale:
#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
#> [3] LC_TIME=en_GB LC_COLLATE=C
#> [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
#> [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
#> [9] LC_ADDRESS=C LC_TELEPHONE=C
#> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
#>
#> time zone: America/New_York
#> tzcode source: system (glibc)
#>
#> attached base packages:
#> [1] stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] clustifyrdatahub_1.18.0 ExperimentHub_2.16.0 AnnotationHub_3.16.0
#> [4] BiocFileCache_2.16.0 dbplyr_2.5.0 BiocGenerics_0.54.0
#> [7] generics_0.1.3 BiocStyle_2.36.0
#>
#> loaded via a namespace (and not attached):
#> [1] tidyselect_1.2.1 dplyr_1.1.4
#> [3] blob_1.2.4 filelock_1.0.3
#> [5] Biostrings_2.76.0 SingleCellExperiment_1.30.0
#> [7] fastmap_1.2.0 digest_0.6.37
#> [9] dotCall64_1.2 mime_0.13
#> [11] lifecycle_1.0.4 SeuratObject_5.0.2
#> [13] KEGGREST_1.48.0 RSQLite_2.3.9
#> [15] magrittr_2.0.3 clustifyr_1.20.0
#> [17] compiler_4.5.0 rlang_1.1.6
#> [19] sass_0.4.10 tools_4.5.0
#> [21] yaml_2.3.10 data.table_1.17.0
#> [23] knitr_1.50 S4Arrays_1.8.0
#> [25] bit_4.6.0 sp_2.2-0
#> [27] curl_6.2.2 DelayedArray_0.34.0
#> [29] BiocParallel_1.42.0 abind_1.4-8
#> [31] withr_3.0.2 purrr_1.0.4
#> [33] grid_4.5.0 stats4_4.5.0
#> [35] colorspace_2.1-1 future_1.40.0
#> [37] progressr_0.15.1 ggplot2_3.5.2
#> [39] globals_0.17.0 scales_1.3.0
#> [41] SummarizedExperiment_1.38.0 cli_3.6.4
#> [43] rmarkdown_2.29 crayon_1.5.3
#> [45] future.apply_1.11.3 httr_1.4.7
#> [47] DBI_1.2.3 cachem_1.1.0
#> [49] parallel_4.5.0 AnnotationDbi_1.70.0
#> [51] BiocManager_1.30.25 XVector_0.48.0
#> [53] matrixStats_1.5.0 vctrs_0.6.5
#> [55] Matrix_1.7-3 jsonlite_2.0.0
#> [57] bookdown_0.43 IRanges_2.42.0
#> [59] S4Vectors_0.46.0 bit64_4.6.0-1
#> [61] listenv_0.9.1 tidyr_1.3.1
#> [63] jquerylib_0.1.4 glue_1.8.0
#> [65] parallelly_1.43.0 spam_2.11-1
#> [67] codetools_0.2-20 cowplot_1.1.3
#> [69] gtable_0.3.6 BiocVersion_3.21.1
#> [71] GenomeInfoDb_1.44.0 GenomicRanges_1.60.0
#> [73] UCSC.utils_1.4.0 munsell_0.5.1
#> [75] tibble_3.2.1 pillar_1.10.2
#> [77] rappdirs_0.3.3 htmltools_0.5.8.1
#> [79] fgsea_1.34.0 entropy_1.3.2
#> [81] GenomeInfoDbData_1.2.14 R6_2.6.1
#> [83] evaluate_1.0.3 lattice_0.22-7
#> [85] Biobase_2.68.0 png_0.1-8
#> [87] memoise_2.0.1 bslib_0.9.0
#> [89] fastmatch_1.1-6 Rcpp_1.0.14
#> [91] SparseArray_1.8.0 xfun_0.52
#> [93] MatrixGenerics_1.20.0 pkgconfig_2.0.3