AI drug discovery company Elix, Inc. and the Life Intelligence Consortium (LINC) have announced that for the first time in the world, an AI drug discovery platform has been commercialized that incorporates multiple AI models trained using federated learning on data provided by 16 pharmaceutical companies.
The key to AI drug discovery lies in high-quality and sufficiently large datasets. Diverse and abundant data are indispensable for building superior AI models; however, pharmaceutical companies are generally limited to utilizing their own proprietary data and public datasets, resulting in significant data shortages that have posed major challenges to progress.
Federated learning technology provides a solution to this challenge. Elix, in partnership with the Department of Biomedical Data Intelligence, Graduate School of Medicine, Kyoto University, developed the federated learning library kMoL, enabling multiple companies to collaboratively develop a suite of AI models without disclosing their confidential data externally. Sixteen pharmaceutical companies participated in building these learning-based models, which are now implemented on Elix Discovery, Elix’s proprietary AI drug discovery platform.
By introducing Elix Discovery, users can leverage these newly developed models, and several pharmaceutical companies have already adopted the platform. The initiative marks the world’s first commercialisation of an AI drug discovery platform in partnership with numerous pharmaceutical companies utilising federated learning.
The development of federated learning-based AI models was achieved through “Development of a Next-generation Drug Discovery AI through Industry-academia Collaboration” (DAIIA), an industry-academia collaborative programme under the Project Promoting Support for Drug Discovery led by the Japan Agency for Medical Research and Development (AMED). Launched in 2020 with the aim of establishing a drug discovery support infrastructure leveraging AI, the project involved 17 pharmaceutical companies, research institutes such as RIKEN, Kyoto University, Nagoya University, along with about 10 IT companies with AI expertise. The project concluded at the end of March 2025.
Initially, the primary users will be the pharmaceutical companies that participated in DAIIA. However, as more companies join, the pool of available data will expand, further improving the accuracy and usability of the AI models for all users. The partners also plan to actively open the platform to companies that were not part of DAIIA.
Shinya Yuki, co-founder and CEO, Elix, said: “Data scarcity remains one of the biggest challenges in AI drug discovery. By jointly developing federated learning technology, kMoL, with the Department of Biomedical Data Intelligence, Graduate School of Medicine, Kyoto University, we have created a system that enables learning from the data held by 16 pharmaceutical companies while preserving the confidentiality of data such as compound structures.
“Commercialising the predictive models we have built and deploying them on an AI drug discovery platform is a world‑first initiative. This accomplishment was only possible through the collaboration of pharmaceutical companies, academia, AMED, LINC, and AI/IT enterprises involved in the project, and represents an important milestone that advances the use of AI in the pharmaceutical industry to a new stage. I believe that this will make Elix Discovery the de‑facto standard of AI drug discovery platforms.
“This federated learning-based initiative is just the starting point for further progress. By encouraging even greater participation and data contributions from pharmaceutical companies, we aim to further expand and strengthen this initiative, enhancing our contribution to the pharmaceutical industry as a whole and ultimately to patients.”
Yasushi Okuno, representative director, LINC; professor, Department of Biomedical Data Intelligence, Graduate School of Medicine, Kyoto University; division director, HPC- and AI-driven Drug Development Platform Division, Center for Computational Science, RIKEN; and co-investigator of the AMED DAIIA Project, added: “On the occasion of commercialising the AMED project, I would like to express my heartfelt gratitude to AMED and to all the pharmaceutical companies that have cooperated with us.
“This commercialisation has two points of significance. First, while many government-funded projects fail to reach practical implementation after their funding period ends, this initiative will be utilized by pharmaceutical companies, thereby contributing directly to real-world drug discovery. Second, multiple pharmaceutical companies will continue to share data across the industry through federated learning, aiming to develop highly accurate AI. In an industry where the pursuit of individual corporate profit often takes precedence, the effort by each of these companies to share data for the benefit of patients and to build and utilize high-performance drug-discovery AI is profoundly meaningful and a source of great pride.
“I sincerely hope that this project will become a cornerstone for enhancing Japan’s drug-discovery capabilities and, ultimately, contribute to the health of patients around the world.”
Jim Cornall is editor of Deeptech Digest and publisher at Ayr Coastal Media. He is an award-winning writer, editor, photographer, broadcaster, designer and author. Contact Jim here.
