Evogene Unveils Advanced AI Model for Small Molecule Discovery, Expands ChemPass AI Capabilities

Evogene has launched version 1.0 of its generative AI model for small molecule discovery, in partnership with Google Cloud. The model addresses the challenge of identifying novel small molecules that fulfill multiple, complex product criteria. Computational tests reveal it achieves approximately 90% precision in designing novel molecules, compared to only about 29% accuracy with conventional AI models. The company plans to release version 2.0 of the model and has reported Q1 2025 revenue of $2.4 million, down from $4.2 million in Q1 2024.

Evogene Ltd. (EVGN), a leading computational biology company, has announced the completion of version 1.0 of its generative AI model for small molecule discovery, developed in partnership with Google Cloud. The model addresses a significant challenge faced by both the pharmaceutical and agricultural industries: identifying novel small molecules that meet multiple complex product criteria [1][2][3][4][5].

The new model expands the capabilities of Evogene's ChemPass AI platform, which is designed for small molecule discovery and optimization. Built on a large dataset of approximately 38 billion molecular structures, the model leverages Google Cloud's advanced AI infrastructure, including high-performance GPUs and scalable storage [2][5]. Computational tests have revealed that the model achieves approximately 90% precision in designing novel molecules, compared to around 29% accuracy with conventional AI models [3].

The completion of this model marks a significant milestone for Evogene, as it unlocks new frontiers for ChemPass AI by generating wholly novel molecules that not only perform but also create new intellectual property (IP) space. This breakthrough is crucial for overcoming long-standing challenges in life-science research and development, including reducing late-stage failures in pharmaceuticals and developing effective, sustainable, and proprietary ag-chemicals [1][4].

Ofer Haviv, President and CEO of Evogene, stated, "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" [1][4].

In addition to the current version 1.0, Evogene is already developing version 2.0 of its generative AI model. This updated version will focus on enhanced flexibility for multi-parameter optimization, incorporating predefined, customized parameters tailored to therapeutic contexts or specific agriculture requirements [2].

The company reported Q1 2025 revenue of $2.4 million, down from $4.2 million in Q1 2024. Despite the revenue decrease, the announcement of the new AI model has had a significant impact on Evogene's stock performance. Shares of EVGN surged over 67% on Tuesday morning following the announcement, reaching seven-month highs [5].

References:
[1] https://www.wvnews.com/news/around_the_web/partners/pr_newswire/subject/new_products_services/evogene-announces-completion-of-first-in-class-foundation-model-for-generative-molecule-design-developed-in/article_141246ca-70dc-5000-b97e-b18e0dc89f6c.html
[2] https://www.marketscreener.com/quote/stock/EVOGENE-LTD-56536833/news/Evogene-Ltd-Announces-Completion-of-First-In-Class-Foundation-Model-Forgenerative-Molecule-Design-50202893/
[3] https://stocktwits.com/news-articles/markets/equity/evgn-stock-doubles-on-making-gen-ai-platform-with-google-cloud/chlaQCoRbCb
[4] https://fareasternagriculture.com/crops/agriculture/evogene-google-cloud-innovation-to-revolutionise-ag-chemicals
[5] https://www.rttnews.com/3545642/evogene-stock-surges-67-on-completion-of-generative-ai-foundation-model.aspx