🔬The BioAI Phase Shift - Matthew McPartlon & Neil Patil, Chai Discovery
August 11, 2026
AI Summary
5 min readThe protein design company Chai Discovery raised $400 million in its most recent round, and its product has already produced moments like a scientist in tears because, after a decade of trying to get an initial binder for a target, the platform delivered one. The company’s co-founders Matthew McPartlon and Neil Patil sat down to explain how they got there, what their models actually do, and why they believe drug discovery is finally crossing from science into engineering.
From structure prediction to generative design
Chai’s first model, Chai One, was a structure prediction model in the lineage of AlphaFold. Given a protein’s amino acid sequence, it would output the 3D shape. The architecture combined a transformer-style tokenizer with a diffusion model that emitted coordinates in 3D space. The key point is that structure prediction alone is useful for understanding biology, but it does not directly create new medicines. Chai Two was the real leap: a design model that co-generates both the sequence and the structure of a new antibody. It is an all-atom diffusion model that iteratively refines both what atoms are present and where they sit in space, converging on a self-consistent molecule. The analogy McPartlon gave is that Chai One tells you there is a cat in an image; Chai Two generates a new image of a cat in a field that you prompted.
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
Never miss an episode of Latent Space: The AI Engineer Podcast
Get every new episode summarized in your inbox — free, ~5 minutes to read.
No spam. Unsubscribe anytime.
What you'll learn
- 1 Timestamped Navigation Outline
- 2 (00:00) **The Design Suite Vision** - Opening analogy comparing Chai's protein design interface to Photoshop, Solidworks, or Figma, with paint tools for epitopes and content-aware fill for binder generation
- 3 (01:15) **Introductions and Backgrounds** - Matt McPartlon (co-founder, AI-biology PhD, entered field during AlphaFold 1 era) and Neil Patil (platform/product lead, varied background from security startup to Chai)
- 4 (03:28) **Partnerships and Business Model** - Chai has landed partnerships with Eli Lilly, Pfizer, Novartis, and Genentech; positioned as a "neutral software factory for medicines" rather than a drug developer
- 5 (05:05) **Why Chai and Why Now** - The bet on being the software and modeling layer was controversial two years ago; models needed to reach a tipping point for design to work
- 6 (08:26) **What Are Antibodies and Why Design Them** - Lock-and-key problem where antibodies are flexible Y-shaped proteins; only the tips (CDR loops) engage in binding, making them tractable design targets
- 7 (12:45) **Traditional Antibody Discovery vs. Computational Design** - Before AI, antibodies were discovered via mouse immunization or massive yeast displays screening billions of molecules for one-in-a-billion hits
+ Full timestamped outline available in the app
Show Notes
This January, four big AI Ă— Pharma tools deals were announced at the huge JPM Pharma conference that takes over San Francisco every year. OpenAI-backed Chai Discovery (now worth $4B) was somehow at the heart despite being all of 2 years old.
The Science team is proud to bring you the first podcast with cofounder Matt McPartlon and product lead Neil Patil to tell the full story!
Editor’s note: not to be confused with Chai AI, which was another top pod of ours.
Pharma suddenly doing big AI tools deals
For the non-pharma people, JPM is JP Morgan’s annual conference for pharma deal-making that takes over San Francisco for a week in January with hundreds of side events, etc. It’s a big thing.
Tools deals for pharma are also a big (new) thing: companies that start as AI for Pharma usually end up building their own drug pipelines instead, and the reason is something like this: convincing pharma to use your tool requires proof that your tool works. Proof means good targets, maybe with good clinical validation. If you have that, then it’s easier to raise money (with a known, if long path to commercialization) or sell (e.g payment in biobucks) for a specific target than it is to sell to lots of companies on a promise that it will work across their portfolios.
The “we’ll just partner / build our own drug” optionality proved to be the only good path up until January. What changed? In short, the tools got good enough for drug design teams to trust.
Good-enough-to-trust unlocks the ability to scale discovery: get more, better candidates into the lab and animal trials faster. More screening for toxicity, better delivery, etc. This means that what you push to the clinic is more likely to succeed.
Tools also unlock new capabilities: mechanisms that are very hard or impossible to develop using lab-based discovery. Designing an antibody that precisely triggers a very specific molecular cascade takes many years of trial and error. Designing bi-specific antibodies (that bind to two different proteins) is similarly difficult. Good design tools can unlock this.
RJ: The fact that the quality of the model has jumped means you’re enabling things you just plain couldn’t do. So it’s a step change. It’s not an efficiency argument at all, or not so much.
Matt: Yeah, exactly. It’s kind of interesting, ev
More from this podcast
Latent Space: The AI Engineer Podcast →