Evogene and Google Cloud Develop AI Model for Molecule Design

Evogene Ltd. has completed its first-in-class generative AI foundation model for small molecule design, developed in collaboration with Google Cloud. Announced in a press release, the model enhances Evogene's ChemPass AI by addressing the challenge of identifying novel small molecules that meet multiple product criteria, crucial for pharmaceutical and agricultural applications.

The new model allows for the simultaneous consideration of complex product requirements, facilitating the creation of novel molecular structures that are patentable and meet essential parameters. Built on a dataset of approximately 38 billion molecular structures, the model was trained using Google Cloud's advanced AI infrastructure, achieving about 90% precision in molecule design.

Evogene is already working on version 2.0 of the model, which will focus on enhanced flexibility for multi-parameter optimization, incorporating predefined parameters tailored to specific therapeutic or agricultural needs. This development aims to improve the ability to generate molecules optimized for clinical, commercial, and regulatory success.