All videos
0:00 / 0:00
research

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

Latent Space30 June 2026Watch on YouTube

What you'll learn

  • You learn why diffusion turned out to be the missing primitive for 3D structure prediction in drug discovery.
  • You see how Genesis's PEARL model models protein flexibility instead of only predicting ligand binding.
  • You discover the role agentic AI systems like SAPPHIRE play across the full drug discovery process.
  • You hear how PEARL performed zero-shot on the new OpenBind benchmark against existing cofolding models.
  • You gain insight into trade-offs such as the tension between binding affinity and solubility when finding drugs.

Frequently asked questions

What is Genesis's PEARL model?
PEARL stands for Place Every Atom at the Right Location. The model does not just predict where a ligand binds, it also models how the protein itself flexes to accommodate it.
Why is diffusion important for 3D structure prediction?
Diffusion turned out to be the missing primitive the field had been waiting for, according to Genesis CTO Sergey Edunov. The most interesting architecture work in AI is therefore now happening in 3D structure prediction, not in language models.
What does the agentic AI system SAPPHIRE do?
SAPPHIRE is Genesis's agentic drug discovery system. It reasons about poses, forms hypotheses, reads literature, and proposes the next round of candidate molecules, acting like a chemist.
How did PEARL perform on the OpenBind benchmark?
According to Genesis, the PEARL system performed zero-shot on the new OpenBind benchmark and surpassed all cofolding models, including on a notoriously hard induced-fit target.

Topics

drug discoverydiffusion models3d structure predictionprotein foldingai agents

Read next

Description from the channel

Evan Feinberg and Genesis CTO Sergey Edunov join us to talk about solving drug discovery with AI. Sergey, fresh off leading Llama 2 and Llama 3 pretraining at Meta, makes the case that the most interesting architecture work in AI right now isn't happening in language models — it's happening in 3D structure prediction, where diffusion turned out to be the missing primitive the field had been waiting for. Genesis's new model, PEARL (Place Every Atom at the Right Location), puts that to work: it doesn't just predict where a ligand binds, it models how the protein itself flexes to accommodate it. We get into why that was so hard to do until now, and why Evan thinks the field's favorite benchmark — 2Å RMSD — is mostly "slop." (Full technical report here: https://arxiv.org/abs/2510.24670) We also dig into Genesis's agentic drug discovery system, SAPPHIRE, and what it actually takes for an AI agent to act like a chemist: reasoning about poses, forming hypotheses, reading literature, and proposing the next round of candidates. Plus: why finding a good drug is less "needle in a haystack" and more "hay in a needle stack," the tension between binding affinity and solubility, and how PEARL performed zero-shot on the brand-new OpenBind benchmark (https://www.genesis.ml/news/zero-shot-pearl-system-surpasses-all-cofolding-models-on-openbind) against a notoriously hard induced-fit target. Links: Evan Feinberg: https://www.linkedin.com/in/evanfeinberg/ Sergey Edunov: https://www.linkedin.com/in/edunov/ Genesis Molecular AI: https://www.genesis.ml/ | https://www.linkedin.com/company/genesis-molecular-ai PEARL announcement: https://www.genesis.ml/news/introducing-pearl PEARL technical report: https://arxiv.org/abs/2510.24670 OpenBind benchmark results: https://www.genesis.ml/news/zero-shot-pearl-system-surpasses-all-cofolding-models-on-openbind