Explainable multi-task learning for multi-modality biological data analysis

• Published in: Nature communications Vol. 14; no. 1; p. 2546
• Main Authors: Tang, Xin, Zhang, Jiawei, He, Yichun, Zhang, Xinhe, Lin, Zuwan, Partarrieu, Sebastian, Hanna, Emma Bou, Ren, Zhaolin, Shen, Hao, Yang, Yuhong, Wang, Xiao, Li, Na, Ding, Jie, Liu, Jia
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 03.05.2023; Nature Publishing Group UK; Nature Portfolio
• Subjects: Algorithms; Analytical methods; Artificial neural networks; Biodiversity; Biotechnology; Cell Cycle; Data Analysis; Deoxyribonucleic acid; DNA; Gene expression; Gene regulation; Machine learning; Modal analysis; Modal data; Neural networks; Sensory integration; Transcriptomics
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-37477-x

Current biotechnologies can simultaneously measure multiple high-dimensional modalities (e.g., RNA, DNA accessibility, and protein) from the same cells. A combination of different analytical tasks (e.g., multi-modal integration and cross-modal analysis) is required to comprehensively understand such data, inferring how gene regulation drives biological diversity and functions. However, current analytical methods are designed to perform a single task, only providing a partial picture of the multi-modal data. Here, we present UnitedNet, an explainable multi-task deep neural network capable of integrating different tasks to analyze single-cell multi-modality data. Applied to various multi-modality datasets (e.g., Patch-seq, multiome ATAC + gene expression, and spatial transcriptomics), UnitedNet demonstrates similar or better accuracy in multi-modal integration and cross-modal prediction compared with state-of-the-art methods. Moreover, by dissecting the trained UnitedNet with the explainable machine learning algorithm, we can directly quantify the relationship between gene expression and other modalities with cell-type specificity. UnitedNet is a comprehensive end-to-end framework that could be broadly applicable to single-cell multi-modality biology. This framework has the potential to facilitate the discovery of cell-type-specific regulation kinetics across transcriptomics and other modalities.