Ensemble deep learning of embeddings for clustering multimodal single-cell omics data

• DOI: 10.1093/bioinformatics/btad382
• Publication Date: 2023-06-13T21:26:00Z
• Authors: Lijia Yu; Chunlei Liu; Jean Yee Hwa Yang; Pengyi Yang
• Keywords: Python; Ensemble Learning; Modalities

Recent advances in multimodal single-cell omics technologies enable multiple modalities of molecular attributes, such as gene expression, chromatin accessibility, and protein abundance, to be profiled simultaneously at a global level individual cells. While the increasing availability data is expected provide more accurate clustering characterization cells, development computational methods that are capable extracting information embedded across still its infancy.We propose SnapCCESS for cells by integrating using an unsupervised ensemble deep learning framework. By creating snapshots embeddings multimodality variational autoencoders, can coupled with various algorithms generating consensus We applied several datasets generated from popular technologies. Our results demonstrate effective efficient than conventional learning-based outperforms other state-of-the-art embedding generation The improved will pave way cell identity types, essential step downstream analyses data.SnapCCESS implemented Python package freely available https://github.com/PYangLab/SnapCCESS under open-source license GPL-3. used this study publicly (see section 'Data availability').