# Virtual cells could make risky experiments cheaper to test

Markdown copy of https://realalpha.app/s/virtual-cells-could-make-risky-experiments-cheaper-to-test/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Mark Zuckerberg](https://realalpha.app/builders/mark-zuckerberg/) · Founder & CEO, Meta · Launched Facebook at Harvard with his roommates in 2004, and co-founded the Chan Zuckerberg Initiative.
- Host: [Erik Torenberg](https://realalpha.app/people/erik-torenberg/) · General partner, Andreessen Horowitz · Helped build Product Hunt; founded On Deck, Village Global and Turpentine.
- Show: a16z Podcast
- Episode: [Mark Zuckerberg & Priscilla Chan: How AI Will Cure All Disease](https://realalpha.app/v/YnV8pgHtO5Y/), Nov 6, 2025
- Moment: 21:34 to 25:36 of the episode (4 min), playing on https://realalpha.app/s/virtual-cells-could-make-risky-experiments-cheaper-to-test/; the episode from there: https://realalpha.app/v/YnV8pgHtO5Y/?t=1294

## Quote

> “Basically, you can describe a type of cell that you would like it to simulate, and it will just produce a kind of **synthetic model of the cell**.”
> — [Mark Zuckerberg](https://realalpha.app/builders/mark-zuckerberg/) at [24:30](https://realalpha.app/v/YnV8pgHtO5Y/?t=1470) · a16z Podcast

## Takeaways

1. Models need not be perfectly accurate to be useful.
2. In silico tests can help de-risk expensive wet-lab work.
3. Different models can simulate distinct cellular capabilities.

## About this segment

The speakers explain how virtual cell models could screen hypotheses before costly lab work, then describe models that predict CRISPR outcomes or simulate cell types. Even directional signals could help researchers choose experiments.

From “Mark Zuckerberg & Priscilla Chan: How AI Will Cure All Disease”, Nov 6, 2025. [Watch the full episode](https://realalpha.app/v/YnV8pgHtO5Y/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[21:40](https://realalpha.app/v/YnV8pgHtO5Y/?t=1300) Yeah. And, you know, you guys think about risk all the time in terms of when you make investments. Like, I think the promise of being able to do virtual biology using a virtual cell model is you can actually take on riskier ideas. Right now, like, grant funding can be hard to come by, and the wet lab work is expensive and slow, and it's not just, you know, money, it's also time. And so you have to choose something that you think is going to have some likelihood of success to keep your lab career going.

[22:13](https://realalpha.app/v/YnV8pgHtO5Y/?t=1333) And so it naturally lends people to take on like some risk, but not a lot of risk because they need to make sure that they are hitting like a certain percentage of the time to make tenure or publish or whatever they need to do. But if you had a virtual cell model where you could simulate really high-quality biology, you could actually then start testing and tinkering on the computational side and, like, ask riskier questions, things that would have been expensive and costly in terms of time and resources to do in the lab, and actually see if there is promise doing the experiments in silico before you make the time and money investment in the wet lab.

[22:53](https://realalpha.app/v/YnV8pgHtO5Y/?t=1373) Do you think of it kind of like a model organism? Yeah. Like it's the new fruit fly? Yeah, I was going to ask, given the complexity of a cell, like how close, like how accurate do you think you'll get the model to? I mean, just assuming, I mean, maybe you get it to like a perfectly accurate representation of a cell, but like how accurate to be useful would the virtual cell have to be? I think it will obviously iterate and get better and better because right now we're still just talking about transcriptomics.

[23:23](https://realalpha.app/v/YnV8pgHtO5Y/?t=1403) we're expanding into different ways of looking at the cell, but you get more and more accuracy. But I don't think it needs to be 100% accurate to be useful because you just want to be able to de-risk the idea on the front end a little bit. And the more and more you de-risk it, the more efficient it gets, obviously, but it'll be useful if you even get directional signal. And yes, we do think about it as a model organism, but in a way that's like has fidelity to the human body like you know like I don't want all models are wrong some are useful yeah This hopefully has utility on certain acts.

[24:03](https://realalpha.app/v/YnV8pgHtO5Y/?t=1443) Exactly. And just like the language models, you build in specific capabilities. So for example, one of the models that we're publishing is variant former. It basically makes it so that it's trained on a bunch of effectively pairs. If you have a cell, you apply CRISPR to it in a place. You see what comes out at the other side. So it basically is able to make that kind of a prediction. Like, okay, if you have this edit that you're doing to a cell, what is likely going to happen?

[24:34](https://realalpha.app/v/YnV8pgHtO5Y/?t=1474) Another one of the models is it's this diffusion model. Basically, you can describe a type of cell that you would like it to simulate, and it will just produce a kind of synthetic model of the cell. Again, I mean, it's kind of interesting because to Priscilla's point before about how everyone is different and different cells have kind of, you want to be able to simulate these kind of rare configurations, having at least a synthetic version of what that could look like is interesting and then you can test against that.

[25:06](https://realalpha.app/v/YnV8pgHtO5Y/?t=1506) The cryo model, I think, is interesting because it's spatial. So it kind of gives you a sense of there are all these different models that you can have that allow you to basically look at different kinds of things and then you just train them in to be increasingly general over time. Wow, very interesting. And is the modeling technology basically LLMs or like is there a reasoning model? Is it like a just – Oh, that's actually – yeah, no, that's a fascinating one too.