Workflow
Generative AI foundation model for small molecule design
icon
Search documents
Evogene Announces Completion of First-In-Class Foundation Model for Generative Molecule Design, Developed in Collaboration with Google Cloud
Prnewswireยท 2025-06-10 11:00
Core Insights - Evogene Ltd. has completed its generative AI foundation model, version 1.0, for small molecule design, developed in collaboration with Google Cloud, addressing the challenge of identifying novel small molecules for pharmaceutical and agricultural applications [1][6] - The new model enhances the capabilities of ChemPass AI by enabling simultaneous consideration of multiple complex product requirements, which is crucial for innovation and securing intellectual property [3][4] Company Developments - The foundation model achieves approximately 90% precision in novel molecule designs, a significant improvement over traditional methods which have around 29% precision [4] - The model is built on a dataset of approximately 38 billion molecular structures and utilizes Google Cloud's advanced AI infrastructure, ensuring scalability for future enhancements [5] - Evogene is already working on version 2.0 of its generative AI model, focusing on enhanced flexibility for multi-parameter optimization tailored to specific therapeutic and agricultural needs [6] Industry Implications - The generative AI model is expected to reduce late-stage failures in pharmaceutical R&D and facilitate the development of effective, sustainable, and proprietary agricultural chemicals [6] - The model's ability to create novel, patentable molecules positions Evogene to significantly impact drug discovery and agricultural product development [3][6]