EmbedSOM is a simple and fast dimensionality reduction algorithm, originally developed for its applications in single-cell cytometry data analysis. We present an updated version of EmbedSOM, viewed as an algorithm for landmark-directed embedding enrichment, and demonstrate that it works well even with manifold-learning techniques other than the self-organizing maps. Using this generalization, we introduce an inwards-growing variant of self-organizing maps that is designed to mitigate some earlier identified deficiencies of EmbedSOM output. Finally, we measure the performance of the generalized EmbedSOM, compare several variants of the algorithm that utilize different landmark-generating functions, and showcase the functionality on single-cell cytometry datasets from recent studies.

Department of Software Engineering Faculty of Mathematics and Physics Charles University Prague Czech Republic

Institute of Hematology and Blood Transfusion Prague Czech Republic

Institute of Organic Chemistry and Biochemistry of the CAS Prague Czech Republic

Zobrazit více v PubMed

Kratochvíl M, Koladiya A, Balounova J, et al. : SOM-based embedding improves efficiency of high-dimensional cytometry data analysis. bioRxiv. 2019. 10.1101/496869 DOI

Van Gassen S, Callebaut B, Van Helden MJ, et al. : FlowSOM: Using self-organizing maps for visualization and interpretation of cytometry data. Cytometry A. 2015;87(7):636–645. 10.1002/cyto.a.22625 PubMed DOI

Weber LM, Robinson MD: Comparison of clustering methods for high-dimensional single-cell flow and mass cytometry data. Cytometry Part A. 2016;89(12):1084–1096. 10.1002/cyto.a.23030 PubMed DOI

Rauber A, Merkl D, Dittenbach M: The growing hierarchical self-organizing map: exploratory analysis of high-dimensional data. IEEE Trans Neural Netw. 2002;13(6):1331–1341. 10.1109/TNN.2002.804221 PubMed DOI

Van Der Maaten L: Accelerating t-SNE using tree-based algorithms. J Mach Learn Res. 2014;15(1):3221–3245. Reference Source

Becht E, McInnes L, Healy J, et al. : Dimensionality reduction for visualizing single-cell data using UMAP. Nat Biotechnol. 2019;37(1):38. 10.1038/nbt.4314 PubMed DOI

Amid E, Warmuth MK: TriMap: Large-scale dimensionality reduction using triplets.2019. Reference Source

Moon KR, van Dijk D, Wang Z, et al. : Visualizing structure and transitions in high-dimensional biological data. Nat Biotechnol. 2019;37(2):1482–1492. 10.1038/s41587-019-0336-3 PubMed DOI PMC

Borodin PA: Linearity of metric projections on Chebyshev subspaces in L 1 and C. Mathematical Notes. 1998;63(6):717–723. 10.1007/BF02312764 DOI

Ding J, Condon A, Shah SP: Interpretable dimensionality reduction of single cell transcriptome data with deep generative models. Nat Commun. 2018;9(1):2002. 10.1038/s41467-018-04368-5 PubMed DOI PMC

Dittenbach M, Merkl D, Rauber A: The growing hierarchical self-organizing map. In: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: NewChallenges and Perspectives for the New Millennium, IEEE,2000;6:15–19. 10.1109/IJCNN.2000.859366 DOI

Samet H: The quadtree and related hierarchical data structures. ACM Computing Surveys (CSUR). 1984;16(2):187–260. 10.1145/356924.356930 DOI

Wong MT, Ong DE, Lim FS, et al. : A High-Dimensional Atlas of Human T Cell Diversity Reveals Tissue-Specific Trafficking and Cytokine Signatures. Immunity. 2016;45(2):442–456. 10.1016/j.immuni.2016.07.007 PubMed DOI

van Unen V, Li N, Molendijk I, et al. : Mass Cytometry of the Human Mucosal Immune System Identifies Tissue- and Disease-Associated Immune Subsets. Immunity. 2016;44(5):1227–1239. 10.1016/j.immuni.2016.04.014 PubMed DOI

van Unen V, Höllt T, Pezzotti N, et al. : Visual analysis of mass cytometry data by hierarchical stochastic neighbour embedding reveals rare cell types. Nat Commun. 2017;8(1):1740. 10.1038/s41467-017-01689-9 PubMed DOI PMC

Belkina AC , Ciccolella CO, Anno R, et al. : Automated optimized parameters for T-distributed stochastic neighbor embedding improve visualization and analysis of large datasets. Nat Commun. 2019;10(1):5415. 10.1038/s41467-019-13055-y PubMed DOI PMC

Characterization of the input material quality for the production of tisagenlecleucel by multiparameter flow cytometry and its relation to the clinical outcome

Unique roles of co-receptor-bound LCK in helper and cytotoxic T cells

OMIP-080: 29-Color flow cytometry panel for comprehensive evaluation of NK and T cells reconstitution after hematopoietic stem cells transplantation

GigaSOM.jl: High-performance clustering and visualization of huge cytometry datasets

ShinySOM: graphical SOM-based analysis of single-cell cytometry data

Zobrazit více v PubMed

figshare
10.6084/m9.figshare.11328035