Performing scClassify using pretrained model
Introduction
A common application of single-cell RNA sequencing (RNA-seq) data is
to identify discrete cell types. To take advantage of the large
collection of well-annotated scRNA-seq datasets, scClassify
package implements a set of methods to perform accurate cell type
classification based on ensemble learning and sample size
calculation.
This vignette will provide an example showing how users can use a
pretrained model of scClassify to predict cell types. A pretrained model
is a scClassifyTrainModel object returned by
train_scClassify(). A list of pretrained model can be found
in https://sydneybiox.github.io/scClassify/index.html.
First, install scClassify, install
BiocManager and use BiocManager::install to
install scClassify package.
Setting up the data
We assume that you have log-transformed (size-factor normalized) matrices as query datasets, where each row refers to a gene and each column a cell. For demonstration purposes, we will take a subset of single-cell pancreas datasets from one independent study (Wang et al.).
library(scClassify)
data("scClassify_example")
wang_cellTypes <- scClassify_example$wang_cellTypes
exprsMat_wang_subset <- scClassify_example$exprsMat_wang_subset
exprsMat_wang_subset <- as(exprsMat_wang_subset, "dgCMatrix")Here, we load our pretrained model using a subset of the Xin et al. human pancreas dataset as our reference data.
First, let us check basic information relating to our pretrained model.
data("trainClassExample_xin")
trainClassExample_xin
#> Class: scClassifyTrainModel
#> Model name: training
#> Feature selection methods: limma
#> Number of cells in the training data: 674
#> Number of cell types in the training data: 4In this pretrained model, we have selected the genes based on Differential Expression using limma. To check the genes that are available in the pretrained model:
We can also visualise the cell type tree of the reference data.
Running scClassify
Next, we perform predict_scClassify with our pretrained
model trainRes = trainClassExample to predict the cell
types of our query data matrix exprsMat_wang_subset_sparse.
Here, we used pearson and spearman as
similarity metrics.
pred_res <- predict_scClassify(exprsMat_test = exprsMat_wang_subset,
trainRes = trainClassExample_xin,
cellTypes_test = wang_cellTypes,
algorithm = "WKNN",
features = c("limma"),
similarity = c("pearson", "spearman"),
prob_threshold = 0.7,
verbose = TRUE)
#> Performing unweighted ensemble learning...
#> Using parameters:
#> similarity algorithm features
#> "pearson" "WKNN" "limma"
#> [1] "Using dynamic correlation cutoff..."
#> [1] "Using dynamic correlation cutoff..."
#> classify_res
#> correct correctly unassigned intermediate
#> 0.704590818 0.239520958 0.000000000
#> incorrectly unassigned error assigned misclassified
#> 0.000000000 0.051896208 0.003992016
#> Using parameters:
#> similarity algorithm features
#> "spearman" "WKNN" "limma"
#> [1] "Using dynamic correlation cutoff..."
#> [1] "Using dynamic correlation cutoff..."
#> classify_res
#> correct correctly unassigned intermediate
#> 0.702594810 0.013972056 0.000000000
#> incorrectly unassigned error assigned misclassified
#> 0.001996008 0.277445110 0.003992016
#> weights for each base method:
#> [1] NA NANoted that the cellType_test is not a required input.
For datasets with unknown labels, users can simply leave it as
cellType_test = NULL.
Prediction results for pearson as the similarity metric:
table(pred_res$pearson_WKNN_limma$predRes, wang_cellTypes)
#> wang_cellTypes
#> acinar alpha beta delta ductal gamma stellate
#> alpha 0 206 0 0 0 2 0
#> beta 0 0 118 0 1 0 0
#> beta_delta_gamma 0 0 0 0 25 0 0
#> delta 0 0 0 10 0 0 0
#> gamma 0 0 0 0 0 19 0
#> unassigned 5 0 0 0 70 0 45Prediction results for spearman as the similarity metric:
Session Info
sessionInfo()
#> R version 4.4.2 (2024-10-31)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.2 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] stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] scClassify_1.19.0 BiocStyle_2.35.0
#>
#> loaded via a namespace (and not attached):
#> [1] gridExtra_2.3 rlang_1.1.5
#> [3] magrittr_2.0.3 matrixStats_1.5.0
#> [5] compiler_4.4.2 mgcv_1.9-1
#> [7] DelayedMatrixStats_1.29.1 vctrs_0.6.5
#> [9] reshape2_1.4.4 stringr_1.5.1
#> [11] pkgconfig_2.0.3 crayon_1.5.3
#> [13] fastmap_1.2.0 XVector_0.47.2
#> [15] labeling_0.4.3 ggraph_2.2.1
#> [17] rmarkdown_2.29 UCSC.utils_1.3.1
#> [19] purrr_1.0.4 xfun_0.50
#> [21] cachem_1.1.0 GenomeInfoDb_1.43.4
#> [23] jsonlite_1.8.9 rhdf5filters_1.19.1
#> [25] DelayedArray_0.33.6 Rhdf5lib_1.29.0
#> [27] BiocParallel_1.41.1 tweenr_2.0.3
#> [29] parallel_4.4.2 cluster_2.1.8
#> [31] R6_2.6.1 bslib_0.9.0
#> [33] stringi_1.8.4 limma_3.63.3
#> [35] diptest_0.77-1 GenomicRanges_1.59.1
#> [37] jquerylib_0.1.4 Rcpp_1.0.14
#> [39] SummarizedExperiment_1.37.0 knitr_1.49
#> [41] mixtools_2.0.0 IRanges_2.41.3
#> [43] Matrix_1.7-2 splines_4.4.2
#> [45] igraph_2.1.4 tidyselect_1.2.1
#> [47] abind_1.4-8 yaml_2.3.10
#> [49] hopach_2.67.0 viridis_0.6.5
#> [51] codetools_0.2-20 minpack.lm_1.2-4
#> [53] Cepo_1.13.0 lattice_0.22-6
#> [55] tibble_3.2.1 plyr_1.8.9
#> [57] Biobase_2.67.0 withr_3.0.2
#> [59] evaluate_1.0.3 survival_3.8-3
#> [61] proxy_0.4-27 polyclip_1.10-7
#> [63] kernlab_0.9-33 pillar_1.10.1
#> [65] BiocManager_1.30.25 MatrixGenerics_1.19.1
#> [67] stats4_4.4.2 plotly_4.10.4
#> [69] generics_0.1.3 S4Vectors_0.45.4
#> [71] ggplot2_3.5.1 sparseMatrixStats_1.19.0
#> [73] munsell_0.5.1 scales_1.3.0
#> [75] glue_1.8.0 lazyeval_0.2.2
#> [77] proxyC_0.4.1 maketools_1.3.2
#> [79] tools_4.4.2 data.table_1.16.4
#> [81] sys_3.4.3 buildtools_1.0.0
#> [83] graphlayouts_1.2.2 tidygraph_1.3.1
#> [85] rhdf5_2.51.2 grid_4.4.2
#> [87] tidyr_1.3.1 colorspace_2.1-1
#> [89] SingleCellExperiment_1.29.1 nlme_3.1-167
#> [91] GenomeInfoDbData_1.2.13 patchwork_1.3.0
#> [93] ggforce_0.4.2 HDF5Array_1.35.13
#> [95] cli_3.6.4 segmented_2.1-3
#> [97] S4Arrays_1.7.3 viridisLite_0.4.2
#> [99] dplyr_1.1.4 gtable_0.3.6
#> [101] sass_0.4.9 digest_0.6.37
#> [103] BiocGenerics_0.53.6 SparseArray_1.7.5
#> [105] ggrepel_0.9.6 htmlwidgets_1.6.4
#> [107] farver_2.1.2 memoise_2.0.1
#> [109] htmltools_0.5.8.1 lifecycle_1.0.4
#> [111] h5mread_0.99.4 httr_1.4.7
#> [113] statmod_1.5.0 MASS_7.3-64