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(): 2023-10-24
#> # $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(): 2023-10-24
#> # 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 4.3.1 (2023-06-16)
#> Platform: x86_64-pc-linux-gnu (64-bit)
#> Running under: Ubuntu 22.04.3 LTS
#>
#> Matrix products: default
#> BLAS: /home/biocbuild/bbs-3.18-bioc/R/lib/libRblas.so
#> LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0
#>
#> 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_1.12.0 ExperimentHub_2.10.0 AnnotationHub_3.10.0
#> [4] BiocFileCache_2.10.0 dbplyr_2.3.4 BiocGenerics_0.48.0
#> [7] BiocStyle_2.30.0
#>
#> loaded via a namespace (and not attached):
#> [1] tidyselect_1.2.0 dplyr_1.1.3
#> [3] blob_1.2.4 filelock_1.0.2
#> [5] Biostrings_2.70.1 bitops_1.0-7
#> [7] SingleCellExperiment_1.24.0 fastmap_1.1.1
#> [9] RCurl_1.98-1.12 promises_1.2.1
#> [11] digest_0.6.33 mime_0.12
#> [13] lifecycle_1.0.3 ellipsis_0.3.2
#> [15] KEGGREST_1.42.0 interactiveDisplayBase_1.40.0
#> [17] RSQLite_2.3.1 magrittr_2.0.3
#> [19] clustifyr_1.14.0 compiler_4.3.1
#> [21] rlang_1.1.1 sass_0.4.7
#> [23] tools_4.3.1 utf8_1.2.4
#> [25] yaml_2.3.7 data.table_1.14.8
#> [27] knitr_1.44 S4Arrays_1.2.0
#> [29] bit_4.0.5 curl_5.1.0
#> [31] DelayedArray_0.28.0 BiocParallel_1.36.0
#> [33] abind_1.4-5 withr_2.5.1
#> [35] purrr_1.0.2 grid_4.3.1
#> [37] stats4_4.3.1 fansi_1.0.5
#> [39] xtable_1.8-4 colorspace_2.1-0
#> [41] ggplot2_3.4.4 scales_1.2.1
#> [43] SummarizedExperiment_1.32.0 cli_3.6.1
#> [45] rmarkdown_2.25 crayon_1.5.2
#> [47] generics_0.1.3 httr_1.4.7
#> [49] DBI_1.1.3 cachem_1.0.8
#> [51] zlibbioc_1.48.0 parallel_4.3.1
#> [53] AnnotationDbi_1.64.0 BiocManager_1.30.22
#> [55] XVector_0.42.0 matrixStats_1.0.0
#> [57] vctrs_0.6.4 Matrix_1.6-1.1
#> [59] jsonlite_1.8.7 bookdown_0.36
#> [61] IRanges_2.36.0 S4Vectors_0.40.0
#> [63] bit64_4.0.5 tidyr_1.3.0
#> [65] jquerylib_0.1.4 glue_1.6.2
#> [67] codetools_0.2-19 cowplot_1.1.1
#> [69] gtable_0.3.4 BiocVersion_3.18.0
#> [71] later_1.3.1 GenomeInfoDb_1.38.0
#> [73] GenomicRanges_1.54.0 munsell_0.5.0
#> [75] tibble_3.2.1 pillar_1.9.0
#> [77] rappdirs_0.3.3 htmltools_0.5.6.1
#> [79] fgsea_1.28.0 entropy_1.3.1
#> [81] GenomeInfoDbData_1.2.11 R6_2.5.1
#> [83] evaluate_0.22 shiny_1.7.5.1
#> [85] Biobase_2.62.0 lattice_0.22-5
#> [87] png_0.1-8 memoise_2.0.1
#> [89] httpuv_1.6.12 bslib_0.5.1
#> [91] fastmatch_1.1-4 Rcpp_1.0.11
#> [93] SparseArray_1.2.0 xfun_0.40
#> [95] MatrixGenerics_1.14.0 pkgconfig_2.0.3