Evogene and Google Cloud Launch AI Platform for Pharmaceutical and AgTech Molecule Discovery

Evogene, an Israeli biotech company, has completed version 1.0 of its generative AI foundation model for small molecule design, trained on Google Cloud's AI infrastructure. The model delivers 90% precision in generating novel molecules, compared to 29% for traditional GPT-based models. The tool aims to accelerate and streamline drug and agrochemical discovery, potentially reducing R&D costs and regulatory demands. EVGN is up 80% as of writing, with a Moderate Buy rating and an average stock price target of $3.50.

Evogene Ltd. (EVGN), an Israeli computational biology company, has completed version 1.0 of its generative AI foundation model for small molecule design. The model, developed in collaboration with Google Cloud, is designed to address the challenge of identifying novel small molecules that meet multiple product criteria, an essential requirement for both pharmaceutical and agricultural applications [1].

The new model, built on a large dataset of approximately 38 billion molecular structures, delivers around 90% precision in generating novel molecules, compared to approximately 29% for traditional GPT-based models. This significant improvement is a result of Evogene's proprietary foundation model, which was developed in-house by the company's algorithm teams [1].

The model aims to accelerate and streamline drug and agrochemical discovery, potentially reducing research and development (R&D) costs and regulatory demands. The ability to generate highly potent, synthesizable, and patentable molecules simultaneously meeting essential parameters is a breakthrough that could significantly impact the life-science industry [1].

Shares of Evogene Ltd. (EVGN) are surging, up nearly 133% as of the announcement, reflecting investor optimism about the potential of this technological advancement [2]. The company has also announced plans to develop version 2.0 of its generative AI foundation model, with a focus on enhanced flexibility for multi-parameter optimization [1].

References:
[1] https://www.prnewswire.com/news-releases/evogene-announces-completion-of-first-in-class-foundation-model-for-generative-molecule-design-developed-in-collaboration-with-google-cloud-302477449.html
[2] https://www.rttnews.com/3545577/evogene-shares-surge-on-completion-of-generative-ai-foundation-model-developed-with-google-cloud.aspx?type=bn