Dimensionality reduction
A useful tool for visualizing the phenotypic relationships between single cells and clusters of cells is dimensionality reduction, a form of unsupervised machine learning used to represent high-dimensional datasets in a smaller number of dimensions.
{tidytof} includes several dimensionality reduction
algorithms commonly used by biologists: Principal component analysis
(PCA), t-distributed stochastic neighbor embedding (tSNE), and uniform
manifold approximation and projection (UMAP). To apply these to a
dataset, use tof_reduce_dimensions().
Dimensionality reduction with
tof_reduce_dimensions().
Here is an example call to tof_reduce_dimensions() in
which we use tSNE to visualize data in {tidytof}’s built-in
phenograph_data dataset.
data(phenograph_data)
# perform the dimensionality reduction
phenograph_tsne <-
phenograph_data |>
tof_preprocess() |>
tof_reduce_dimensions(method = "tsne")
#> Loading required namespace: Rtsne
# select only the tsne embedding columns
phenograph_tsne |>
select(contains("tsne")) |>
head()
#> # A tibble: 6 × 2
#> .tsne1 .tsne2
#> <dbl> <dbl>
#> 1 -5.77 6.61
#> 2 -1.69 9.81
#> 3 14.2 31.6
#> 4 4.47 17.6
#> 5 -2.75 7.37
#> 6 3.15 25.5By default, tof_reduce_dimensions will add
reduced-dimension feature embeddings to the input tof_tbl
and return the augmented tof_tbl (that is, a
tof_tbl with new columns for each embedding dimension) as
its result. To return only the features embeddings themselves, set
augment to FALSE (as in
tof_cluster).
phenograph_data |>
tof_preprocess() |>
tof_reduce_dimensions(method = "tsne", augment = FALSE)
#> # A tibble: 3,000 × 2
#> .tsne1 .tsne2
#> <dbl> <dbl>
#> 1 17.1 -1.43
#> 2 15.5 -7.89
#> 3 25.5 -25.0
#> 4 10.4 -16.2
#> 5 18.1 -4.64
#> 6 18.8 -15.7
#> 7 16.7 -9.65
#> 8 24.1 -16.8
#> 9 11.6 -19.1
#> 10 9.77 -2.53
#> # ℹ 2,990 more rowsChanging the method argument results in different
low-dimensional embeddings:
phenograph_data |>
tof_reduce_dimensions(method = "umap", augment = FALSE)
#> # A tibble: 3,000 × 2
#> .umap1 .umap2
#> <dbl> <dbl>
#> 1 9.95 -2.37
#> 2 8.75 -2.24
#> 3 3.79 0.695
#> 4 3.66 2.09
#> 5 9.91 -2.15
#> 6 1.33 2.84
#> 7 9.74 -1.85
#> 8 3.17 1.26
#> 9 5.48 -1.08
#> 10 9.54 -4.72
#> # ℹ 2,990 more rows
phenograph_data |>
tof_reduce_dimensions(method = "pca", augment = FALSE)
#> # A tibble: 3,000 × 5
#> .pc1 .pc2 .pc3 .pc4 .pc5
#> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 -2.77 1.23 -0.868 0.978 3.49
#> 2 -0.969 -1.02 -0.787 1.22 0.329
#> 3 -2.36 2.54 -1.95 -0.882 -1.30
#> 4 -3.68 -0.00565 0.962 0.410 0.788
#> 5 -4.03 2.07 -0.829 1.59 5.39
#> 6 -2.59 -0.108 1.32 -1.41 -1.24
#> 7 -1.55 -0.651 -0.233 1.08 0.129
#> 8 -1.18 -0.446 0.134 -0.771 -0.932
#> 9 -2.00 -0.485 0.593 -0.0416 -0.658
#> 10 -0.0356 -0.924 -0.692 1.45 0.270
#> # ℹ 2,990 more rowsMethod specifications for tof_reduce_*() functions
tof_reduce_dimensions() provides a high-level API for
three lower-level functions: tof_reduce_pca(),
tof_reduce_umap(), and tof_reduce_tsne(). The
help files for each of these functions provide details about the
algorithm-specific method specifications associated with each of these
dimensionality reduction approaches. For example,
tof_reduce_pca takes the num_comp argument to
determine how many principal components should be returned:
# 2 principal components
phenograph_data |>
tof_reduce_pca(num_comp = 2)
#> # A tibble: 3,000 × 2
#> .pc1 .pc2
#> <dbl> <dbl>
#> 1 -2.77 1.23
#> 2 -0.969 -1.02
#> 3 -2.36 2.54
#> 4 -3.68 -0.00565
#> 5 -4.03 2.07
#> 6 -2.59 -0.108
#> 7 -1.55 -0.651
#> 8 -1.18 -0.446
#> 9 -2.00 -0.485
#> 10 -0.0356 -0.924
#> # ℹ 2,990 more rows# 3 principal components
phenograph_data |>
tof_reduce_pca(num_comp = 3)
#> # A tibble: 3,000 × 3
#> .pc1 .pc2 .pc3
#> <dbl> <dbl> <dbl>
#> 1 -2.77 1.23 -0.868
#> 2 -0.969 -1.02 -0.787
#> 3 -2.36 2.54 -1.95
#> 4 -3.68 -0.00565 0.962
#> 5 -4.03 2.07 -0.829
#> 6 -2.59 -0.108 1.32
#> 7 -1.55 -0.651 -0.233
#> 8 -1.18 -0.446 0.134
#> 9 -2.00 -0.485 0.593
#> 10 -0.0356 -0.924 -0.692
#> # ℹ 2,990 more rowssee ?tof_reduce_pca, ?tof_reduce_umap, and
?tof_reduce_tsne for additional details.
Visualization using tof_plot_cells_embedding()
Regardless of the method used, reduced-dimension feature embeddings
can be visualized using {ggplot2} (or any graphics
package). {tidytof} also provides some helper functions for
easily generating dimensionality reduction plots from a
tof_tbl or tibble with columns representing embedding
dimensions:
# plot the tsne embeddings using color to distinguish between clusters
phenograph_tsne |>
tof_plot_cells_embedding(
embedding_cols = contains(".tsne"),
color_col = phenograph_cluster
)
# plot the tsne embeddings using color to represent CD11b expression
phenograph_tsne |>
tof_plot_cells_embedding(
embedding_cols = contains(".tsne"),
color_col = cd11b
) +
ggplot2::scale_fill_viridis_c()
Such visualizations can be helpful in qualitatively describing the phenotypic differences between the clusters in a dataset. For example, in the example above, we can see that one of the clusters has high CD11b expression, whereas the others have lower CD11b expression.
Session info
sessionInfo()
#> R version 4.6.0 (2026-04-24)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.4 LTS
#>
#> Matrix products: default
#> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3
#> LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.26.so; LAPACK version 3.12.0
#>
#> locale:
#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
#> [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
#> [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: Etc/UTC
#> tzcode source: system (glibc)
#>
#> attached base packages:
#> [1] stats4 stats graphics grDevices utils datasets methods
#> [8] base
#>
#> other attached packages:
#> [1] tidyr_1.3.2 stringr_1.6.0
#> [3] HDCytoData_1.32.0 flowCore_2.24.0
#> [5] SummarizedExperiment_1.42.0 Biobase_2.72.0
#> [7] GenomicRanges_1.64.0 Seqinfo_1.2.0
#> [9] IRanges_2.46.0 S4Vectors_0.50.1
#> [11] MatrixGenerics_1.24.0 matrixStats_1.5.0
#> [13] ExperimentHub_3.2.0 AnnotationHub_4.2.0
#> [15] BiocFileCache_3.2.0 dbplyr_2.5.2
#> [17] BiocGenerics_0.58.1 generics_0.1.4
#> [19] forcats_1.0.1 ggplot2_4.0.3
#> [21] dplyr_1.2.1 tidytof_1.6.0
#> [23] rmarkdown_2.31
#>
#> loaded via a namespace (and not attached):
#> [1] RColorBrewer_1.1-3 sys_3.4.3 jsonlite_2.0.0
#> [4] shape_1.4.6.1 magrittr_2.0.5 farver_2.1.2
#> [7] vctrs_0.7.3 memoise_2.0.1 sparsevctrs_0.3.6
#> [10] htmltools_0.5.9 S4Arrays_1.12.0 curl_7.1.0
#> [13] SparseArray_1.12.2 sass_0.4.10 parallelly_1.47.0
#> [16] bslib_0.11.0 httr2_1.2.2 lubridate_1.9.5
#> [19] cachem_1.1.0 buildtools_1.0.0 igraph_2.3.1
#> [22] lifecycle_1.0.5 iterators_1.0.14 pkgconfig_2.0.3
#> [25] Matrix_1.7-5 R6_2.6.1 fastmap_1.2.0
#> [28] future_1.70.0 digest_0.6.39 AnnotationDbi_1.74.0
#> [31] RSpectra_0.16-2 RSQLite_3.53.1 labeling_0.4.3
#> [34] filelock_1.0.3 cytolib_2.24.0 yardstick_1.4.0
#> [37] timechange_0.4.0 httr_1.4.8 polyclip_1.10-7
#> [40] abind_1.4-8 compiler_4.6.0 bit64_4.8.2
#> [43] withr_3.0.2 doParallel_1.0.17 S7_0.2.2
#> [46] viridis_0.6.5 DBI_1.3.0 ggforce_0.5.0
#> [49] MASS_7.3-65 lava_1.9.1 embed_1.2.2
#> [52] rappdirs_0.3.4 DelayedArray_0.38.2 tools_4.6.0
#> [55] otel_0.2.0 future.apply_1.20.2 nnet_7.3-20
#> [58] glue_1.8.1 grid_4.6.0 Rtsne_0.17
#> [61] recipes_1.3.2 gtable_0.3.6 tzdb_0.5.0
#> [64] class_7.3-23 data.table_1.18.4 hms_1.1.4
#> [67] utf8_1.2.6 tidygraph_1.3.1 XVector_0.52.0
#> [70] RcppAnnoy_0.0.23 ggrepel_0.9.8 BiocVersion_3.23.1
#> [73] foreach_1.5.2 pillar_1.11.1 RcppHNSW_0.7.0
#> [76] splines_4.6.0 tweenr_2.0.3 lattice_0.22-9
#> [79] survival_3.8-6 bit_4.6.0 RProtoBufLib_2.24.0
#> [82] tidyselect_1.2.1 maketools_1.3.2 Biostrings_2.80.1
#> [85] knitr_1.51 gridExtra_2.3 xfun_0.57
#> [88] graphlayouts_1.2.3 hardhat_1.4.3 timeDate_4052.112
#> [91] stringi_1.8.7 yaml_2.3.12 evaluate_1.0.5
#> [94] codetools_0.2-20 ggraph_2.2.2 tibble_3.3.1
#> [97] BiocManager_1.30.27 cli_3.6.6 uwot_0.2.4
#> [100] rpart_4.1.27 jquerylib_0.1.4 Rcpp_1.1.1-1.1
#> [103] globals_0.19.1 png_0.1-9 parallel_4.6.0
#> [106] gower_1.0.2 readr_2.2.0 blob_1.3.0
#> [109] listenv_0.10.1 glmnet_5.0 viridisLite_0.4.3
#> [112] ipred_0.9-15 ggridges_0.5.7 scales_1.4.0
#> [115] prodlim_2026.03.11 crayon_1.5.3 purrr_1.2.2
#> [118] rlang_1.2.0 KEGGREST_1.52.0