A new partnership between computational chemistry company Evogene and Tel Aviv University's Blavatnik Center for Drug Discovery aims to solve a persistent problem in medicine: turning brilliant academic research into actual drugs that reach patients. The collaboration combines AI-driven molecular design with rigorous experimental validation, creating an end-to-end pipeline that researchers and entrepreneurs can access to accelerate small-molecule drug discovery, particularly for challenging targets like complex proteins and molecular glues.

Why Are Academic Discoveries Stuck in the Lab?

Israeli academic institutions generate world-class scientific discoveries and identify novel therapeutic targets regularly, yet many researchers and entrepreneurs struggle to transform these insights into viable drug development programs. The gap between identifying a promising biological target and actually developing a drug candidate is enormous, requiring specialized computational chemistry expertise, experimental validation capabilities, and access to advanced technology platforms that most academic labs simply do not have.

This collaboration addresses that exact problem. By combining Evogene's ChemPass AI computational engine with the Blavatnik Center's experimental validation capabilities, the partnership creates what amounts to a translational bridge. Researchers can now submit their biological targets and receive comprehensive support in identifying and optimizing small-molecule candidates without having to build these capabilities from scratch.

"Israel's academic institutions generate world-class discoveries and novel therapeutic targets. However, many entrepreneurs and researchers face significant hurdles in transforming these scientific insights into viable drug development programs. Through this collaboration with the Blavatnik Center for Drug Discovery, we are creating a unique framework that combines advanced AI-driven computational chemistry with world-class experimental validation capabilities," said Ofer Haviv, president and CEO of Evogene.

Ofer Haviv, President and CEO at Evogene

How Does the AI-Powered Discovery Pipeline Work?

• Computational Design: Evogene's ChemPass AI platform uses generative design to rapidly explore chemical space and identify promising small-molecule candidates, accelerating the hit identification and optimization process compared to traditional methods.
• Target Profiling: Recent integration of Google Cloud's agentic AI systems generates richer early target profiles, allowing researchers to anticipate downstream developability constraints and identify potential problems before committing significant resources to a candidate.
• Experimental Validation: The Blavatnik Center provides rigorous laboratory testing and validation, ensuring that computationally designed molecules actually work in biological systems and meet real-world therapeutic requirements.
• Prioritization at Scale: The combined system can prioritize high-potential candidates earlier in the discovery process, reducing the resource-intensive attrition that typically plagues drug development.

This approach is particularly valuable for challenging biology that has historically resisted drug discovery efforts. Molecular glues, for example, are proteins that bring two other proteins together in ways that can be therapeutically useful but are notoriously difficult to target with small molecules. Complex proteins with intricate three-dimensional structures also present obstacles that traditional computational methods struggle to overcome.

What Recent Advances Enable This Partnership?

The timing of this partnership reflects significant recent progress in AI-powered drug discovery. In June 2026, Evogene announced a major milestone in its collaboration with Google Cloud: the successful integration of agentic AI systems into its ChemPass platform. Agentic AI refers to AI systems that can autonomously plan and execute sequences of actions to achieve a goal, in this case designing and optimizing molecules without constant human intervention.

"This milestone advances our vision to redefine molecular discovery and optimization through AI. Google Cloud's technology provides a robust foundation for scaling these capabilities across our pipeline and future collaborations. By integrating advanced AI agents into ChemPass AI, we believe we can generate richer target profiles earlier in discovery," stated Ofer Haviv.

Ofer Haviv, President and CEO at Evogene

These agentic systems can test hundreds of thousands of molecular iterations per learning cycle, a scale of exploration that would be impossible through traditional chemistry alone. The integration of Google Cloud's Gemini models provides the underlying language and reasoning capabilities that enable this autonomous exploration.

Meanwhile, Moderna has taken a different but complementary approach to accelerating drug discovery. The company unveiled Lucy, an internal machine learning platform designed to run closed-loop experimental cycles that connect data across lab notebooks and files into a continuously improving learning system. Lucy operates without human intervention between cycles, linking experimental results directly to AI-driven hypothesis generation.

Moderna's Lucy platform has access to the company's entire library of human mRNA clinical trial data spanning more than a decade, giving it a learning advantage that newer entrants cannot easily replicate. The system can simultaneously test up to one thousand drug candidates in a single mouse or primate using barcoding technology, then deconvolute the results to assess each candidate's individual performance.

What Does This Mean for the Future of Drug Development?

These partnerships and platforms represent a fundamental shift in how drugs are discovered. Rather than relying primarily on human intuition, trial-and-error chemistry, and expensive high-throughput screening, the industry is moving toward AI systems that can learn from vast datasets, generate novel hypotheses, and autonomously explore chemical space at unprecedented scale.

For academic researchers, the Evogene-Blavatnik partnership removes a critical barrier to translating discoveries into therapies. Researchers can now focus on identifying novel biological targets and understanding disease mechanisms, while the AI platform handles the computationally intensive work of finding molecules that can modulate those targets. This democratization of drug discovery technology could accelerate the pace at which academic insights reach patients.

The broader implication is that AI is shifting drug discovery from a bottleneck limited by human expertise and computational resources to a process constrained primarily by the quality of biological targets and the ability to validate candidates experimentally. As these AI systems mature and accumulate more training data, the speed and efficiency of drug discovery should continue to improve, potentially reducing both the time and cost required to bring new therapies to market.