Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data
| Autor: | Huiyu Cai, Zuobai Zhang, Jian Tang, Yue Li, Yifan Zhao |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Topic model
Computer science Science General Physics and Astronomy Computational biology Machine learning computer.software_genre General Biochemistry Genetics and Molecular Biology Article Transcriptome Set (abstract data type) Functional clustering Gene Interpretability Multidisciplinary business.industry RNA General Chemistry Gene signature Autoencoder Generative model ComputingMethodologies_PATTERNRECOGNITION Face (geometry) Scalability Key (cryptography) Artificial intelligence business Encoder computer |
| Zdroj: | Nature Communications, Vol 12, Iss 1, Pp 1-15 (2021) Nature Communications |
| ISSN: | 2041-1723 |
| Popis: | The advent of single-cell RNA sequencing (scRNA-seq) technologies has revolutionized transcriptomic studies. However, large-scale integrative analysis of scRNA-seq data remains a challenge largely due to unwanted batch effects and the limited transferabilty, interpretability, and scalability of the existing computational methods. We present single-cell Embedded Topic Model (scETM). Our key contribution is the utilization of a transferable neural-network-based encoder while having an interpretable linear decoder via a matrix tri-factorization. In particular, scETM simultaneously learns an encoder network to infer cell type mixture and a set of highly interpretable gene embeddings, topic embeddings, and batch-effect linear intercepts from multiple scRNA-seq datasets. scETM is scalable to over 106 cells and confers remarkable cross-tissue and cross-species zero-shot transfer-learning performance. Using gene set enrichment analysis, we find that scETM-learned topics are enriched in biologically meaningful and disease-related pathways. Lastly, scETM enables the incorporation of known gene sets into the gene embeddings, thereby directly learning the associations between pathways and topics via the topic embeddings. Computational single-cell RNA-seq analyses often face challenges in scalability, model interpretability, and confounders. Here, we show a new model to address these challenges by learning meaningful embeddings from the data that simultaneously refine gene signatures and cell functions in diverse conditions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink