Federated learning for molecular discovery |
| |
| Affiliation: | 1. Department of Biochemistry and Biophysics, School of Basic Medical Sciences, Peking University, Beijing, 100083, China;2. Department of Structural Biology, Van Andel Institute, Grand Rapids, MI, 49503, United States;1. Department of Integrative Structural and Computational Biology, The Scripps Research Institute, La Jolla, CA, 92037, USA;2. Department of Chemical Physiology and Biochemistry, School of Medicine, Oregon Health and Science University, Portland, OR, 97239, USA;1. Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden;2. Molecular AI, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK |
| |
| Abstract: | Federated Learning enables machine learning across multiple sources of data and alleviates the risk of leaking private information between partners thereby encouraging knowledge sharing and collaborative modelling. Hence, Federated Learning opens the ways to a new generation of improved models. Domains involving molecular informatics, like Drug Discovery, are progressively adopting Federated Learning; this review describes the main projects and applications of Federated Learning for molecular discovery with a special focus on their benefits and the remaining challenges. All the studies demonstrate a real benefit of Federated Learning, namely the improvement of the performance of models as well as their applicability domain thanks to knowledge aggregation. The selected publications also reveal several remaining challenges to be addressed to fully exploit Federated Learning. |
| |
| Keywords: | Federated learning Molecular discovery Drug discovery Artificial intelligence Machine learning |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
