anndataR 0.99.6
anndataR works with Python AnnData objects through reticulate.
You can load Python objects, apply Python functions to them, and convert them to Seurat or SingleCellExperiment objects.
message(
"Python packages scanpy and mudata are required to run this vignette. Code chunks will not be evaluated."
)This vignette requires Python with the scanpy and mudata packages installed. If these are not available, the code chunks will not be evaluated but the examples remain visible.
Install required Python packages if needed:
reticulate::py_require("scanpy")library(anndataR)
library(reticulate)
sc <- import("scanpy")Load a dataset directly from scanpy:
adata <- sc$datasets$pbmc3k_processed()
adata
#> ReticulateAnnData object with n_obs × n_vars = 2638 × 1838
#> obs: 'n_genes', 'percent_mito', 'n_counts', 'louvain'
#> var: 'n_cells'
#> uns: 'draw_graph', 'louvain', 'louvain_colors', 'neighbors', 'pca', 'rank_genes_groups'
#> obsm: 'X_pca', 'X_tsne', 'X_umap', 'X_draw_graph_fr'
#> varm: 'PCs'
#> obsp: 'distances', 'connectivities'Apply scanpy functions directly:
sc$pp$filter_cells(adata, min_genes = 200L)
sc$pp$normalize_total(adata, target_sum = 1e4)
sc$pp$log1p(adata)Convert to SingleCellExperiment (see vignette("usage_singlecellexperiment")):
sce_obj <- adata$as_SingleCellExperiment()
sce_obj
#> class: SingleCellExperiment
#> dim: 1838 538
#> metadata(7): draw_graph louvain ... rank_genes_groups log1p
#> assays(1): X
#> rownames(1838): TNFRSF4 CPSF3L ... S100B PRMT2
#> rowData names(1): n_cells
#> colnames(538): AAACATTGAGCTAC-1 AAACATTGATCAGC-1 ... TTTCGAACTCTCAT-1
#> TTTCTACTGAGGCA-1
#> colData names(4): n_genes percent_mito n_counts louvain
#> reducedDimNames(4): X_pca X_tsne X_umap X_draw_graph_fr
#> mainExpName: NULL
#> altExpNames(0):Convert to Seurat (see vignette("usage_seurat")):
seurat_obj <- adata$as_Seurat()
#> Warning: No "counts" or "data" layer found in `names(layers_mapping)`, this may lead to
#> unexpected results when using the resulting <Seurat> object.
#> Warning: Data is of class matrix. Coercing to dgCMatrix.
seurat_obj
#> An object of class Seurat
#> 1838 features across 538 samples within 1 assay
#> Active assay: RNA (1838 features, 0 variable features)
#> 1 layer present: X
#> 4 dimensional reductions calculated: X_pca, X_tsne, X_umap, X_draw_graph_frInstall required Python packages if needed:
reticulate::py_install("mudata")md <- import("mudata")Load a MuData object from file:
cache <- BiocFileCache::BiocFileCache(ask = FALSE)
h5mu_file <- BiocFileCache::bfcrpath(
cache,
"https://github.com/gtca/h5xx-datasets/raw/b1177ac8877c89d8bb355b072164384b4e9cc81d/datasets/minipbcite.h5mu"
)
#> adding rname 'https://github.com/gtca/h5xx-datasets/raw/b1177ac8877c89d8bb355b072164384b4e9cc81d/datasets/minipbcite.h5mu'
mdata <- md$read_h5mu(h5mu_file)Access individual modalities and convert them:
rna_mod <- mdata$mod[["rna"]]
rna_seurat <- rna_mod$as_Seurat()
#> Warning: No "counts" or "data" layer found in `names(layers_mapping)`, this may lead to
#> unexpected results when using the resulting <Seurat> object.
#> Warning: Data is of class matrix. Coercing to dgCMatrix.
print(rna_seurat)
#> An object of class Seurat
#> 27 features across 411 samples within 1 assay
#> Active assay: RNA (27 features, 0 variable features)
#> 1 layer present: X
#> 2 dimensional reductions calculated: X_pca, X_umap
rna_sce <- rna_mod$as_SingleCellExperiment()
print(rna_sce)
#> class: SingleCellExperiment
#> dim: 27 411
#> metadata(8): celltype_colors hvg ... rank_genes_groups umap
#> assays(1): X
#> rownames(27): NKG7 KLRC2 ... MS4A1 KLF4
#> rowData names(13): gene_ids feature_types ... mean std
#> colnames(411): CAGCCAGGTCTCGACG-1 TTCTTCCTCTCGGTAA-1 ...
#> GACTCTCCAGCTCTGG-1 GAAATGACAAGCACCC-1
#> colData names(6): n_genes_by_counts total_counts ... leiden celltype
#> reducedDimNames(2): X_pca X_umap
#> mainExpName: NULL
#> altExpNames(0):sessionInfo()
#> R version 4.5.1 Patched (2025-08-23 r88802)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.3 LTS
#>
#> Matrix products: default
#> BLAS: /home/biocbuild/bbs-3.22-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] stats4 stats graphics grDevices utils datasets methods
#> [8] base
#>
#> other attached packages:
#> [1] reticulate_1.43.0 anndataR_0.99.6
#> [3] SingleCellExperiment_1.31.1 SummarizedExperiment_1.39.2
#> [5] Biobase_2.69.1 GenomicRanges_1.61.6
#> [7] Seqinfo_0.99.3 IRanges_2.43.5
#> [9] S4Vectors_0.47.4 BiocGenerics_0.55.4
#> [11] generics_0.1.4 MatrixGenerics_1.21.0
#> [13] matrixStats_1.5.0 SeuratObject_5.2.0
#> [15] sp_2.2-0 BiocStyle_2.37.1
#>
#> loaded via a namespace (and not attached):
#> [1] RColorBrewer_1.1-3 jsonlite_2.0.0 magrittr_2.0.4
#> [4] spatstat.utils_3.2-0 farver_2.1.2 rmarkdown_2.30
#> [7] vctrs_0.6.5 ROCR_1.0-11 memoise_2.0.1
#> [10] spatstat.explore_3.5-3 htmltools_0.5.8.1 S4Arrays_1.9.1
#> [13] curl_7.0.0 Rhdf5lib_1.31.1 SparseArray_1.9.1
#> [16] rhdf5_2.53.6 sass_0.4.10 sctransform_0.4.2
#> [19] parallelly_1.45.1 KernSmooth_2.23-26 bslib_0.9.0
#> [22] htmlwidgets_1.6.4 ica_1.0-3 httr2_1.2.1
#> [25] plyr_1.8.9 plotly_4.11.0 zoo_1.8-14
#> [28] cachem_1.1.0 igraph_2.2.0 mime_0.13
#> [31] lifecycle_1.0.4 pkgconfig_2.0.3 Matrix_1.7-4
#> [34] R6_2.6.1 fastmap_1.2.0 fitdistrplus_1.2-4
#> [37] future_1.67.0 shiny_1.11.1 digest_0.6.37
#> [40] patchwork_1.3.2 Seurat_5.3.0 tensor_1.5.1
#> [43] RSpectra_0.16-2 irlba_2.3.5.1 RSQLite_2.4.3
#> [46] filelock_1.0.3 progressr_0.17.0 spatstat.sparse_3.1-0
#> [49] httr_1.4.7 polyclip_1.10-7 abind_1.4-8
#> [52] compiler_4.5.1 bit64_4.6.0-1 withr_3.0.2
#> [55] S7_0.2.0 DBI_1.2.3 fastDummies_1.7.5
#> [58] MASS_7.3-65 rappdirs_0.3.3 DelayedArray_0.35.3
#> [61] tools_4.5.1 lmtest_0.9-40 otel_0.2.0
#> [64] httpuv_1.6.16 future.apply_1.20.0 goftest_1.2-3
#> [67] glue_1.8.0 nlme_3.1-168 rhdf5filters_1.21.4
#> [70] promises_1.4.0 grid_4.5.1 Rtsne_0.17
#> [73] cluster_2.1.8.1 reshape2_1.4.4 gtable_0.3.6
#> [76] spatstat.data_3.1-9 tidyr_1.3.1 data.table_1.17.8
#> [79] XVector_0.49.1 spatstat.geom_3.6-0 RcppAnnoy_0.0.22
#> [82] ggrepel_0.9.6 RANN_2.6.2 pillar_1.11.1
#> [85] stringr_1.5.2 spam_2.11-1 RcppHNSW_0.6.0
#> [88] later_1.4.4 splines_4.5.1 dplyr_1.1.4
#> [91] BiocFileCache_2.99.6 lattice_0.22-7 bit_4.6.0
#> [94] survival_3.8-3 deldir_2.0-4 tidyselect_1.2.1
#> [97] miniUI_0.1.2 pbapply_1.7-4 knitr_1.50
#> [100] gridExtra_2.3 bookdown_0.45 scattermore_1.2
#> [103] xfun_0.53 stringi_1.8.7 lazyeval_0.2.2
#> [106] yaml_2.3.10 evaluate_1.0.5 codetools_0.2-20
#> [109] tibble_3.3.0 BiocManager_1.30.26 cli_3.6.5
#> [112] uwot_0.2.3 xtable_1.8-4 jquerylib_0.1.4
#> [115] dichromat_2.0-0.1 Rcpp_1.1.0 spatstat.random_3.4-2
#> [118] globals_0.18.0 dbplyr_2.5.1 png_0.1-8
#> [121] spatstat.univar_3.1-4 parallel_4.5.1 blob_1.2.4
#> [124] ggplot2_4.0.0 dotCall64_1.2 listenv_0.9.1
#> [127] viridisLite_0.4.2 scales_1.4.0 ggridges_0.5.7
#> [130] purrr_1.1.0 crayon_1.5.3 rlang_1.1.6
#> [133] cowplot_1.2.0reticulate::py_config()
#> python: /home/biocbuild/.cache/R/reticulate/uv/cache/archive-v0/uZEkqzFaL9vSWU6B7tDTE/bin/python3
#> libpython: /home/biocbuild/.cache/R/reticulate/uv/python/cpython-3.11.13-linux-x86_64-gnu/lib/libpython3.11.so
#> pythonhome: /home/biocbuild/.cache/R/reticulate/uv/cache/archive-v0/uZEkqzFaL9vSWU6B7tDTE:/home/biocbuild/.cache/R/reticulate/uv/cache/archive-v0/uZEkqzFaL9vSWU6B7tDTE
#> virtualenv: /home/biocbuild/.cache/R/reticulate/uv/cache/archive-v0/uZEkqzFaL9vSWU6B7tDTE/bin/activate_this.py
#> version: 3.11.13 (main, Jul 11 2025, 22:43:55) [Clang 20.1.4 ]
#> numpy: /home/biocbuild/.cache/R/reticulate/uv/cache/archive-v0/uZEkqzFaL9vSWU6B7tDTE/lib/python3.11/site-packages/numpy
#> numpy_version: 2.3.4
#> scanpy: /home/biocbuild/.cache/R/reticulate/uv/cache/archive-v0/uZEkqzFaL9vSWU6B7tDTE/lib/python3.11/site-packages/scanpy
#>
#> NOTE: Python version was forced by py_require()
reticulate::py_list_packages()
#> package version requirement
#> 1 anndata 0.12.3 anndata==0.12.3
#> 2 array-api-compat 1.12.0 array-api-compat==1.12.0
#> 3 contourpy 1.3.3 contourpy==1.3.3
#> 4 crc32c 2.8 crc32c==2.8
#> 5 cycler 0.12.1 cycler==0.12.1
#> 6 donfig 0.8.1.post1 donfig==0.8.1.post1
#> 7 fonttools 4.60.1 fonttools==4.60.1
#> 8 h5py 3.15.1 h5py==3.15.1
#> 9 joblib 1.5.2 joblib==1.5.2
#> 10 kiwisolver 1.4.9 kiwisolver==1.4.9
#> 11 legacy-api-wrap 1.4.1 legacy-api-wrap==1.4.1
#> 12 llvmlite 0.45.1 llvmlite==0.45.1
#> 13 matplotlib 3.10.7 matplotlib==3.10.7
#> 14 mudata 0.3.2 mudata==0.3.2
#> 15 natsort 8.4.0 natsort==8.4.0
#> 16 networkx 3.5 networkx==3.5
#> 17 numba 0.62.1 numba==0.62.1
#> 18 numcodecs 0.16.3 numcodecs==0.16.3
#> 19 numpy 2.3.4 numpy==2.3.4
#> 20 packaging 25.0 packaging==25.0
#> 21 pandas 2.3.3 pandas==2.3.3
#> 22 patsy 1.0.2 patsy==1.0.2
#> 23 pillow 12.0.0 pillow==12.0.0
#> 24 pynndescent 0.5.13 pynndescent==0.5.13
#> 25 pyparsing 3.2.5 pyparsing==3.2.5
#> 26 python-dateutil 2.9.0.post0 python-dateutil==2.9.0.post0
#> 27 pytz 2025.2 pytz==2025.2
#> 28 PyYAML 6.0.3 PyYAML==6.0.3
#> 29 scanpy 1.11.5 scanpy==1.11.5
#> 30 scikit-learn 1.7.2 scikit-learn==1.7.2
#> 31 scipy 1.16.2 scipy==1.16.2
#> 32 seaborn 0.13.2 seaborn==0.13.2
#> 33 session-info2 0.2.3 session-info2==0.2.3
#> 34 six 1.17.0 six==1.17.0
#> 35 statsmodels 0.14.5 statsmodels==0.14.5
#> 36 threadpoolctl 3.6.0 threadpoolctl==3.6.0
#> 37 tqdm 4.67.1 tqdm==4.67.1
#> 38 typing_extensions 4.15.0 typing_extensions==4.15.0
#> 39 tzdata 2025.2 tzdata==2025.2
#> 40 umap-learn 0.5.9.post2 umap-learn==0.5.9.post2
#> 41 zarr 3.1.3 zarr==3.1.3