Statistical method scDEED for detecting dubious 2D single-cell embeddings and optimizing t-SNE and UMAP hyperparameters
Top Cited Papers
Open Access
- 26 February 2024
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-21
Abstract
Two-dimensional (2D) embedding methods are crucial for single-cell data visualization. Popular methods such as t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP) are commonly used for visualizing cell clusters; however, it is well known that t-SNE and UMAP’s 2D embeddings might not reliably inform the similarities among cell clusters. Motivated by this challenge, we present a statistical method, scDEED, for detecting dubious cell embeddings output by a 2D-embedding method. By calculating a reliability score for every cell embedding based on the similarity between the cell’s 2D-embedding neighbors and pre-embedding neighbors, scDEED identifies the cell embeddings with low reliability scores as dubious and those with high reliability scores as trustworthy. Moreover, by minimizing the number of dubious cell embeddings, scDEED provides intuitive guidance for optimizing the hyperparameters of an embedding method. We show the effectiveness of scDEED on multiple datasets for detecting dubious cell embeddings and optimizing the hyperparameters of t-SNE and UMAP.Keywords
Funding Information
- U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences (R35GM140888, R01GM120507)
- U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences
- Johnson and Johnson (WiSTEM2D Award)
- W. M. Keck Foundation (UCLA David Geffen School of Medicine W. M. Keck Foundation Junior Faculty Award)
- Silicon Valley Community Foundation (2022-249355)
This publication has 46 references indexed in Scilit:
- EMBEDR: Distinguishing signal from noise in single-cell omics dataPatterns, 2022
- No evidence that plasmablasts transdifferentiate into developing neutrophils in severe COVID‐19 diseaseClinical & Translational Immunology, 2021
- Fault diagnosis of industrial process based on the optimal parametric t-distributed stochastic neighbor embeddingScience China Information Sciences, 2020
- A Quantitative Framework for Evaluating Single-Cell Data Structure Preservation by Dimensionality Reduction TechniquesCell Reports, 2020
- Comprehensive Integration of Single-Cell DataCell, 2019
- Dimensionality reduction for visualizing single-cell data using UMAPNature Biotechnology, 2018
- A general and flexible method for signal extraction from single-cell RNA-seq dataNature Communications, 2018
- A single-cell survey of the small intestinal epitheliumNature, 2017
- Automated mapping of phenotype space with single-cell dataNature Methods, 2016
- Comparing partitionsJournal of Classification, 1985