MOE Key Laboratory of Bioinformatics, Beijing Advanced Innovation Center for Structural Biology, Center for Synthetic and Systems Biology, Tsinghua-Peking Center for Life Sciences, School of Life Sciences, Tsinghua University, 100084, Beijing, China.
Beijing Advanced Innovation Center for Genomics (ICG), Biomedical Pioneering Innovation Center (BIOPIC), Peking University, 100871, Beijing, China.
Nat Commun. 2019 Oct 8;10(1):4576. doi: 10.1038/s41467-019-12630-7.
Single-cell ATAC-seq (scATAC-seq) profiles the chromatin accessibility landscape at single cell level, thus revealing cell-to-cell variability in gene regulation. However, the high dimensionality and sparsity of scATAC-seq data often complicate the analysis. Here, we introduce a method for analyzing scATAC-seq data, called Single-Cell ATAC-seq analysis via Latent feature Extraction (SCALE). SCALE combines a deep generative framework and a probabilistic Gaussian Mixture Model to learn latent features that accurately characterize scATAC-seq data. We validate SCALE on datasets generated on different platforms with different protocols, and having different overall data qualities. SCALE substantially outperforms the other tools in all aspects of scATAC-seq data analysis, including visualization, clustering, and denoising and imputation. Importantly, SCALE also generates interpretable features that directly link to cell populations, and can potentially reveal batch effects in scATAC-seq experiments.
单细胞 ATAC-seq（scATAC-seq）在单细胞水平上描绘了染色质可及性图谱，从而揭示了基因调控的细胞间变异性。然而，scATAC-seq 数据的高维性和稀疏性常常使分析变得复杂。在这里，我们介绍了一种用于分析 scATAC-seq 数据的方法，称为通过潜在特征提取进行单细胞 ATAC-seq 分析（SCALE）。SCALE 结合了深度生成框架和概率高斯混合模型，以学习能够准确描述 scATAC-seq 数据的潜在特征。我们在使用不同协议在不同平台上生成的数据集上验证了 SCALE，并且具有不同的整体数据质量。在 scATAC-seq 数据分析的所有方面，包括可视化、聚类、去噪和插补，SCALE 都明显优于其他工具。重要的是，SCALE 还生成了可直接与细胞群体相关联的可解释特征，并且可能揭示 scATAC-seq 实验中的批次效应。
