VANCOUVER, BRITISH COLUMBIA -- Variational AI, the company behind Enki™, an advanced foundation model for small molecule drug discovery, announced the completion of its oversubscribed $US5.5 million Seed extension round. Enki™ empowers biopharmaceutical chemistry teams to efficiently discover and optimize novel hits and leads, accelerating early-stage drug discovery. The round attracted strong investor interest, exceeding the company’s initial funding target, reflecting confidence in Enki’s potential. Nimbus Synergies led the round, with participation from Merck Global Health Innovation Fund, Quimby Investments, Threshold Impact, and Defined Capital. Existing investors Flying Fish, A&E Investment, and Nepenthe Capital participated in the round.

The adoption of Artificial Intelligence (AI) for early-stage drug discovery has accelerated across the biopharmaceutical industry in recent years; however, small molecule drug discovery continues to rely on older, non-generative (discriminative) AI models focused on finding hits from within large libraries of virtual molecules. While effective, this approach often limits novel discoveries and still requires extensive optimization though multiple Design-Make-Test-Analyze (DMTA) cycles.

“Great drugs start with great molecules, but most drug discovery begins in the same place - screening molecular libraries or tweaking existing scaffolds,” said Handol Kim, CEO of Variational AI. “By comparison, we have trained the Enki™ foundation model on our proprietary dataset covering almost 600 targets that generates diverse leads with outstanding potency and selectivity. This empowers chemistry teams at biopharmaceutical companies to discover and optimize hits and leads with the best possible novel starting points far more efficiently than traditional methods” continued Kim. “Our partners synthesize and test around 20 novel molecules from multiple scaffolds that we generate per project over a few weeks and have achieved a sub-micromolar hit rate of over 50% with a 90% rate of synthetic success.”

Generative models are extremely effective in domains such as language and images but have yet to make a similarly deep impact on chemistry. “The Variational AI scientific team has spent years quietly building a foundation model constrained to small molecule drug discovery that uses orders of magnitude less compute and data than foundation models in other domains” said Jason Robertson, Managing Partner, Nimbus Synergies. “This foundation model marks a paradigm shift in drug discovery enabling better, more reliable, and cost-effective drug development, which ultimately improves patient outcomes and reduces healthcare costs,” expressed Robertson.

With this new funding, Variational AI is poised to bring its technology to a broader market, helping biopharmaceutical companies design novel drugs faster and more efficiently.