Cellcano: supervised cell type identification for single cell ATAC-seq data

• Published in: Nature communications Vol. 14; no. 1; pp. 1864 - 10
• Main Authors: Ma, Wenjing, Lu, Jiaying, Wu, Hao
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 03.04.2023; Nature Publishing Group UK; Nature Portfolio
• Subjects: Algorithms; Availability; Benchmarks; Chromatin; Chromatin - genetics; Chromatin Immunoprecipitation Sequencing - methods; Computational efficiency; Computer applications; Data analysis; Datasets; Epigenetics; Epigenomics; Heterogeneity; Machine learning; Robustness (mathematics); Single-Cell Analysis - methods; Supervised learning
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-37439-3

Computational cell type identification is a fundamental step in single-cell omics data analysis. Supervised celltyping methods have gained increasing popularity in single-cell RNA-seq data because of the superior performance and the availability of high-quality reference datasets. Recent technological advances in profiling chromatin accessibility at single-cell resolution (scATAC-seq) have brought new insights to the understanding of epigenetic heterogeneity. With continuous accumulation of scATAC-seq datasets, supervised celltyping method specifically designed for scATAC-seq is in urgent need. Here we develop Cellcano, a computational method based on a two-round supervised learning algorithm to identify cell types from scATAC-seq data. The method alleviates the distributional shift between reference and target data and improves the prediction performance. After systematically benchmarking Cellcano on 50 well-designed celltyping tasks from various datasets, we show that Cellcano is accurate, robust, and computationally efficient. Cellcano is well-documented and freely available at https://marvinquiet.github.io/Cellcano/ .