DENVER, Colo., Jun 10, 2025 (247marketnews.com)- Evogene (NASDAQ:EVGN) launched version 1.0 of its proprietary generative AI foundation model for small molecule design, developed in partnership with Google Cloud. The model significantly advances the capabilities of ChemPass AI, Evogene’s drug and agrochemical discovery platform.
Targeting one of the most complex challenges in life sciences, the model enables the simultaneous design of novel small molecules that meet multiple, interdependent product criteria—a critical need in both pharmaceutical and agricultural applications.
Traditional discovery methods often address performance, safety, and IP requirements in a sequential manner, limiting innovation and increasing time-to-market. Evogene’s new foundation model leverages generative AI to overcome these constraints, accelerating discovery while expanding access to novel, synthesizable, and patentable chemical space.
Key Highlights:
- ~90% design precision, significantly outperforming traditional generative models (~29% accuracy), based on internal benchmarks.
- Trained on 38 billion molecular structures, using Google Cloud’s AI infrastructure, including advanced GPUs and scalable compute resources.
- Purpose-built to generate novel compounds that are potent, feasible to synthesize, and IP-defensible—vital in competitive product development environments.
“Completing our foundation model is a major milestone in our offering. It unlocks new frontiers for ChemPass AI, giving us the power to generate wholly novel molecules—ones that not only perform but also create new IP space. This is key to overcoming long-standing challenges in life-science R&D: from reducing late-stage failure in pharma to developing ag-chemicals that are effective, sustainable, and proprietary,” said Ofer Haviv, CEO of Evogene.
The model currently powers ChemPass AI’s compound generation engine and serves as a scalable base for future Evogene innovations across its subsidiary pipeline.
The post Evogene and Google Cloud Unveil Breakthrough Foundation Model for Generative Small Molecule Design appeared first on 24/7 MarketNews.