Often, clustering single-cell data to identify communities of cells with shared characteristics is a major goal of high-dimensional cytometry data analysis.
To do this, {tidytof} provides the
tof_cluster() verb. Several clustering methods are
implemented in {tidytof}, including the following:
Each of these methods are wrapped by tof_cluster().
tof_cluster()To demonstrate, we can apply the PhenoGraph clustering algorithm to
{tidytof}’s built-in phenograph_data. Note
that phenograph_data contains 3000 total cells (1000 each
from 3 clusters identified in the original PhenoGraph
publication). For demonstration purposes, we also metacluster our
PhenoGraph clusters using k-means clustering.
data(phenograph_data)
set.seed(203L)
phenograph_clusters <-
phenograph_data |>
tof_preprocess() |>
tof_cluster(
cluster_cols = starts_with("cd"),
num_neighbors = 50L,
distance_function = "cosine",
method = "phenograph"
) |>
tof_metacluster(
cluster_col = .phenograph_cluster,
metacluster_cols = starts_with("cd"),
num_metaclusters = 3L,
method = "kmeans"
)
phenograph_clusters |>
dplyr::select(sample_name, .phenograph_cluster, .kmeans_metacluster) |>
head()
#> # A tibble: 6 × 3
#> sample_name .phenograph_cluster .kmeans_metacluster
#> <chr> <chr> <chr>
#> 1 H1_PhenoGraph_cluster1 5 2
#> 2 H1_PhenoGraph_cluster1 1 2
#> 3 H1_PhenoGraph_cluster1 5 2
#> 4 H1_PhenoGraph_cluster1 1 2
#> 5 H1_PhenoGraph_cluster1 1 2
#> 6 H1_PhenoGraph_cluster1 5 2The outputs of both tof_cluster() and
tof_metacluster() are a tof_tbl identical to
the input tibble, but now with the addition of an additional column (in
this case, “.phenograph_cluster” and “.kmeans_metacluster”) that encodes
the cluster id for each cell in the input tof_tbl. Note
that all output columns added to a tibble or tof_tbl by
{tidytof} begin with a full-stop (“.”) to reduce the
likelihood of collisions with existing column names.
Because the output of tof_cluster is a
tof_tbl, we can use dplyr’s count
method to assess the accuracy of our clustering procedure compared to
the original clustering from the PhenoGraph paper.
phenograph_clusters |>
dplyr::count(phenograph_cluster, .kmeans_metacluster, sort = TRUE)
#> # A tibble: 4 × 3
#> phenograph_cluster .kmeans_metacluster n
#> <chr> <chr> <int>
#> 1 cluster2 1 1000
#> 2 cluster3 3 1000
#> 3 cluster1 2 995
#> 4 cluster1 3 5Here, we can see that our clustering procedure groups most cells from the same PhenoGraph cluster with one another (with a small number of mistakes).
To change which clustering algorithm tof_cluster uses,
alter the method flag.
# use the kmeans algorithm
phenograph_data |>
tof_preprocess() |>
tof_cluster(
cluster_cols = contains("cd"),
method = "kmeans"
)
# use the flowsom algorithm
phenograph_data |>
tof_preprocess() |>
tof_cluster(
cluster_cols = contains("cd"),
method = "flowsom"
)To change the columns used to compute the clusters, change the
cluster_cols flag. And finally, if you want to return a
one-column tibble that only includes the cluster labels (as
opposed to the cluster labels added as a new column to the input
tof_tbl), set augment to
FALSE.
sessionInfo()
#> R version 4.4.2 (2024-10-31)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.1 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=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: Etc/UTC
#> tzcode source: system (glibc)
#>
#> attached base packages:
#> [1] stats4 stats graphics grDevices utils datasets methods
#> [8] base
#>
#> other attached packages:
#> [1] HDCytoData_1.26.0 flowCore_2.19.0
#> [3] SummarizedExperiment_1.37.0 Biobase_2.67.0
#> [5] GenomicRanges_1.59.1 GenomeInfoDb_1.43.2
#> [7] IRanges_2.41.2 S4Vectors_0.45.2
#> [9] MatrixGenerics_1.19.1 matrixStats_1.5.0
#> [11] ExperimentHub_2.15.0 AnnotationHub_3.15.0
#> [13] BiocFileCache_2.15.0 dbplyr_2.5.0
#> [15] BiocGenerics_0.53.3 generics_0.1.3
#> [17] forcats_1.0.0 ggplot2_3.5.1
#> [19] dplyr_1.1.4 tidytof_1.1.0
#> [21] rmarkdown_2.29
#>
#> loaded via a namespace (and not attached):
#> [1] sys_3.4.3 jsonlite_1.8.9 shape_1.4.6.1
#> [4] magrittr_2.0.3 farver_2.1.2 vctrs_0.6.5
#> [7] memoise_2.0.1 htmltools_0.5.8.1 S4Arrays_1.7.1
#> [10] curl_6.1.0 SparseArray_1.7.3 sass_0.4.9
#> [13] parallelly_1.41.0 bslib_0.8.0 lubridate_1.9.4
#> [16] cachem_1.1.0 buildtools_1.0.0 igraph_2.1.3
#> [19] mime_0.12 lifecycle_1.0.4 iterators_1.0.14
#> [22] pkgconfig_2.0.3 Matrix_1.7-1 R6_2.5.1
#> [25] fastmap_1.2.0 GenomeInfoDbData_1.2.13 future_1.34.0
#> [28] digest_0.6.37 colorspace_2.1-1 AnnotationDbi_1.69.0
#> [31] RSQLite_2.3.9 labeling_0.4.3 filelock_1.0.3
#> [34] cytolib_2.19.1 yardstick_1.3.1 timechange_0.3.0
#> [37] httr_1.4.7 polyclip_1.10-7 abind_1.4-8
#> [40] compiler_4.4.2 bit64_4.5.2 withr_3.0.2
#> [43] doParallel_1.0.17 viridis_0.6.5 DBI_1.2.3
#> [46] ggforce_0.4.2 MASS_7.3-64 lava_1.8.1
#> [49] rappdirs_0.3.3 DelayedArray_0.33.3 tools_4.4.2
#> [52] future.apply_1.11.3 nnet_7.3-20 glue_1.8.0
#> [55] grid_4.4.2 recipes_1.1.0 gtable_0.3.6
#> [58] tzdb_0.4.0 class_7.3-23 tidyr_1.3.1
#> [61] data.table_1.16.4 hms_1.1.3 utf8_1.2.4
#> [64] tidygraph_1.3.1 XVector_0.47.2 ggrepel_0.9.6
#> [67] BiocVersion_3.21.1 foreach_1.5.2 pillar_1.10.1
#> [70] stringr_1.5.1 RcppHNSW_0.6.0 splines_4.4.2
#> [73] tweenr_2.0.3 lattice_0.22-6 survival_3.8-3
#> [76] bit_4.5.0.1 RProtoBufLib_2.19.0 tidyselect_1.2.1
#> [79] Biostrings_2.75.3 maketools_1.3.1 knitr_1.49
#> [82] gridExtra_2.3 xfun_0.50 graphlayouts_1.2.1
#> [85] hardhat_1.4.0 timeDate_4041.110 stringi_1.8.4
#> [88] UCSC.utils_1.3.1 yaml_2.3.10 evaluate_1.0.3
#> [91] codetools_0.2-20 ggraph_2.2.1 tibble_3.2.1
#> [94] BiocManager_1.30.25 cli_3.6.3 rpart_4.1.24
#> [97] munsell_0.5.1 jquerylib_0.1.4 Rcpp_1.0.14
#> [100] globals_0.16.3 png_0.1-8 parallel_4.4.2
#> [103] gower_1.0.2 readr_2.1.5 blob_1.2.4
#> [106] listenv_0.9.1 glmnet_4.1-8 viridisLite_0.4.2
#> [109] ipred_0.9-15 ggridges_0.5.6 scales_1.3.0
#> [112] prodlim_2024.06.25 purrr_1.0.2 crayon_1.5.3
#> [115] rlang_1.1.4 KEGGREST_1.47.0