What’s holding drug discovery back?
Drug discovery is increasingly expensive, slow, and uncertain.
Costs have doubled approximately every nine years since 1949, and even with modern tools, the discovery phase remains a major bottleneck. The standard approach, screening existing libraries and iteratively optimizing known compounds through the Design Make Test Analyze (DMTA) cycle, can take years per program.
Despite decades of innovation, only half of discovery programs advance to preclinical development. The problem is not that chemical space lacks potential. It is that our ability to search it is fundamentally constrained.
We’ve barely scratched the surface of chemical space
The chemical space is unimaginably large, estimated at 10⁶⁰ drug-like molecules. Yet current methods have explored far less than a billionth (0.0000001%) of it.
This is not because we lack tools to model molecules. It is because most searches begin with what we already know: familiar starting points, well-characterized scaffolds, or prebuilt libraries. These approaches optimize within the known instead of discovering the new.
The question is no longer whether more molecules exist, it is “how many life-saving drugs are still waiting to be discovered, and how do we reach them?”
A generative shift in small molecule discovery
At Variational AI, we believe the way forward is not to screen more, but to generate better.
We have developed Enki™, a generative AI foundation model that enables a different approach to early discovery. Instead of relying on known scaffolds or fixed libraries, Enki™ generates novel, diverse, and synthesizable small molecules tailor-made from the start to meet multiple therapeutic objectives such as potency, selectivity, ADMET, and more…
By removing the dependency on known chemical starting points, our approach enables true exploration, navigating previously unreachable regions of the chemical space with speed and precision. This is not a marginal improvement to the DMTA cycle. It is a radical change in how we approach small-molecule drug discovery.
Enki™ operates within a smooth, physics-informed latent space that reflects pharmacological behavior. By capturing key molecular properties in this space, Enki™ generates (not just ranks) molecules optimized for success across more than 50 criteria.
New molecules = New possibilities
Enki™ expands the search beyond what is already known, proposing candidate molecular structures that are both novel and practical to make. It generates compounds that align with your target product profile and balances multiple properties at once so you can progress with fewer iteration cycles.
With synthesis-aware generation and clear rationales behind each proposal, Enki™ accelerates decision-making from the first design cycle to lead series selection. The result is a pipeline seeded with higher-quality starting points and a faster path from idea to experiment.