Skip to main content
No Priors: Artificial Intelligence | Technology | Startups

Biohub: The Future of Biology is Open-Source with Co-Founders Mark Zuckerberg, Priscilla Chan, and Head of Science Alex Rives

56 min episode · 2 min read
·
Co-founders Mark Zuckerberg

Episode

56 min

Read time

2 min

Topics

Startups, Fundraising & VC, Design & UX

AI-Generated Summary

Key Takeaways

  • Hierarchical Biology Modeling: Build biological AI models from the ground up — proteins first, then cells, then whole systems like the immune system. Skipping layers produces weaker models. Biohub's ESM Fold already predicted structures for over 1.1 billion proteins, establishing the protein-level foundation before tackling cellular complexity at the next tier.
  • Frontier Biology as Data Strategy: Unlike language models that train on existing internet text, biology models require inventing entirely new scientific methods to generate training data. Biohub's Chicago hub engineers inflammation-sensing devices, New York develops cellular engineering techniques, and San Francisco runs cryo-EM imaging — each producing novel datasets unavailable anywhere else.
  • Protein Design as Emergent Capability: Rather than building task-specific models, train one general protein language model and gain design capabilities as an emergent property. ESM Fold, trained only to understand proteins broadly, produced nanomolar-binding single-chain antibodies — therapeutically relevant potency — validated experimentally in a 96-well plate screen without any antibody-specific training objective.
  • Predicting Drug Toxicity via Single-Cell Atlas: A comprehensive single-cell transcriptomic atlas can identify off-target drug effects before human trials by revealing which unexpected cell types express a target receptor. If kidney cells express a receptor assumed to be liver-specific, the model flags renal toxicity risk digitally, potentially eliminating a major cause of late-stage clinical trial failures.
  • Open-Source Accelerates Rare Disease Progress: Releasing biology models as open-source tools enables self-organized rare disease patient communities — who already run their own registries, biobanks, and trials — to access capabilities previously unavailable to them. Distributing tools broadly across a long tail of diseases generates scientific knowledge that feeds back into understanding common disease mechanisms.

What It Covers

Mark Zuckerberg, Priscilla Chan, and Alex Rives discuss the Chan Zuckerberg Biohub's $500 million Virtual Biology Initiative, which combines frontier AI with frontier biology to build hierarchical world models of proteins, cells, and biological systems, releasing all tools as open-source to accelerate scientific progress across the entire research community.

Key Questions Answered

  • Hierarchical Biology Modeling: Build biological AI models from the ground up — proteins first, then cells, then whole systems like the immune system. Skipping layers produces weaker models. Biohub's ESM Fold already predicted structures for over 1.1 billion proteins, establishing the protein-level foundation before tackling cellular complexity at the next tier.
  • Frontier Biology as Data Strategy: Unlike language models that train on existing internet text, biology models require inventing entirely new scientific methods to generate training data. Biohub's Chicago hub engineers inflammation-sensing devices, New York develops cellular engineering techniques, and San Francisco runs cryo-EM imaging — each producing novel datasets unavailable anywhere else.
  • Protein Design as Emergent Capability: Rather than building task-specific models, train one general protein language model and gain design capabilities as an emergent property. ESM Fold, trained only to understand proteins broadly, produced nanomolar-binding single-chain antibodies — therapeutically relevant potency — validated experimentally in a 96-well plate screen without any antibody-specific training objective.
  • Predicting Drug Toxicity via Single-Cell Atlas: A comprehensive single-cell transcriptomic atlas can identify off-target drug effects before human trials by revealing which unexpected cell types express a target receptor. If kidney cells express a receptor assumed to be liver-specific, the model flags renal toxicity risk digitally, potentially eliminating a major cause of late-stage clinical trial failures.
  • Open-Source Accelerates Rare Disease Progress: Releasing biology models as open-source tools enables self-organized rare disease patient communities — who already run their own registries, biobanks, and trials — to access capabilities previously unavailable to them. Distributing tools broadly across a long tail of diseases generates scientific knowledge that feeds back into understanding common disease mechanisms.

Notable Moment

When Zuckerberg and Chan first proposed curing all disease by end of century, Nobel Prize-winning scientists laughed at them. A decade later, Zuckerberg now considers that timeline too conservative — a reversal driven entirely by the pace of AI advancement compressing what once seemed impossible into a plausible near-term horizon.

Know someone who'd find this useful?

Episode Transcript

Just wanna give tools to the whole scientific community. We wanna understand how biology works. I wanna understand the genetics of this person. I wanna understand the risks they have to different illnesses. My goal is to be able to treat the individual as an individual, understand the mechanisms, and be able to intervene. We'll have a bigger impact by getting this in more scientists' hands quicker by doing it as open source projects instead. It's not just like there's some factory somewhere that you can pay to produce the data. You actually need to invent new novel scientific approaches. The theory isn't that we're gonna cure the diseases. We're not. It's that we wanna help accelerate the pace of progress for the whole scientific field. We folded over 1,100,000,000 proteins and predicted their structures and we didn't design a model for antibodies. We didn't design a model to be able to bind one particular target. We just designed a model that could understand proteins. If we could design a protein to actually change the physiology, then we can actually cure someone. Today on No Priors, we're joined by Mark Zuckerberg, Priscilla Chan, and Alex Reeves. We'll be talking about Biohub and all their various efforts to now start applying AI at scale to do world models of cells and different levels of interactions across biology. Mark, Priscilla, thank you for doing this. Yeah. Thanks for having us. Fun. Alex, congratulations on new missions. Thank you. You guys made Biohub your primary philanthropic effort and then committed $500,000,000 to this virtual biology initiative. Can you tell us a little bit about, you know, why do that, and how did you go from we should fund this to this is, like, who we are? So Biohub, in its current form, we're super excited about. We feel like it's a really good fit for who we are and what we bring to the table and what we can achieve together. But this work started ten years ago when we were thinking about how can we give back. And Mark had Mark wanted to build an organization that could cure, prevent, and manage all disease by the end of the century. And we had a series of hilarious meetings with scientists that, like, famous Nobel Prize winning scientists were just laughing at us. Is that was that your starting line? We're just gonna cure all disease. No. No. And to be clear, we don't think that we're gonna be the ones curing the diseases. Our our goal is always to build tools that could accelerate the whole scientific field. That way, the scientific field collectively could cure all the diseases. But still But still people laughed at us. By the end of the century, it was a stretch. Now I think it's, like, too conservative. And so we kept being, like, okay, well, we had these series of funny, awkward educational conversations where we're, like, okay, but, like, why? Like, why do you …

Get the full transcript (10,721 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all No Priors: Artificial Intelligence | Technology | Startups transcripts →

You just read a 3-minute summary of a 53-minute episode.

Get No Priors: Artificial Intelligence | Technology | Startups summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links.

Tools

  • by Chan Zuckerberg Biohub

    Biohub's ESM Fold already predicted structures for over 1.1 billion proteins, establishing the protein-level foundation before tackling cellular complexity at the next tier.

More from No Priors: Artificial Intelligence | Technology | Startups

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Startups & Product Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into No Priors: Artificial Intelligence | Technology | Startups.

Every Monday, we deliver AI summaries of the latest episodes from No Priors: Artificial Intelligence | Technology | Startups and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime