🔬 "The Most Innovative Diffusion Research Is Happening in Drug Discovery, Not Image Generation"

With R.J. Haniki, Brandon Anderson, Evan Feinberg, Sergey Udov · Sunday, July 5, 2026

This episode explores how Genesis Molecular AI is leveraging advanced AI, particularly diffusion models, to revolutionize drug discovery by achieving unprecedented accuracy in protein-ligand structure prediction. Guests Evan Fineberg and Sergey Udov discuss their Pearl model, the critical 1 angstrom resolution threshold, and their vision for AI agents automating drug discovery. They also delve into the challenges and opportunities of integrating wet lab data and reinforcement learning into their cutting-edge AI pipelines.

Watch on YouTube ↗All Latent Space summaries →More from AI →

Key takeaways

The highest leverage for AI in healthcare isn't identifying new disease targets or optimizing clinical trials; it's in the drug discovery and design process itself. Read more →
The 1 Angstrom Cliff: Genesis Molecular AI's Pearl model demonstrates that for drug discovery, 1 angstrom (Å) resolution isn't just nice-to-have; it's the absolute minimum threshold to reliably predict protein-ligand interactions. Anything less, and your drug fails. Read more →

2 articles from this episode

AI's Real Rx: Best-in-Class, Not Just First-in-Class

Genesis Molecular AI's Evan Fineberg argues AI's highest leverage isn't finding new targets, but designing superior drugs for 'undruggable' conditions and best-in-class therapies.

Read article →

Genesis AI: Why Your "Good Enough" Metrics Are Broken

Founders, how precise are your core metrics? Genesis Molecular AI shows why sub-angstrom accuracy (1Å) is non-negotiable for drug discovery, and what that means for your business.