Biohub started with an ambitious goal of curing, preventing, and managing all disease by the end of the century. A decade later, thanks to the convergence of frontier AI and biological data, that goal may have been too conservative. In this episode, Elad Gil and Sarah Guo sit down with Biohub co-founders Mark Zuckerberg and Priscilla Chan, alongside Biohub Head of Science Alex Rives. Together, they discuss Biohub’s $500 million virtual biology initiative, which integrates frontier AI with wet-lab work to build predictive world models of cells, proteins, and systems. They also talk about their newly announced open-source engine for digital protein and antibody design, ESMFold2; why Biohub is a nonprofit rather than a venture-backed startup; and how hierarchical simulations will soon allow doctors to treat patients at an individual, mechanistic level. Sign up for new podcasts every week. Email feedback to [email protected] Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil | @Biohub | @finkd | @alexrives | @ChanZuckerberg
Chapters: 00:00 – Cold Open 01:02 - Mark Zuckerberg, Priscilla Chan, and Alex Rives Introduction 01:26 – Why Biohub and Their Mission 08:27 – Integrating Frontier AI and Frontier Biology 09:45 – Micro to Macro Biological Modeling 14:22 – Mechanistic Interpretiability 16:58 – Why Biohub is a Non-Profit 21:41 – Understanding How Biology Works 24:23 – Timeline for Curing All Diseases 26:25 – Translating Research to Patient Impact 28:04 – Launch of ESMFold2 32:13 – Tackling Off-Target Effects and Edge Cases 38:39 – Putting the Tech in Individual Hands 41:06 – Talent at Biohub 44:25 – What’s Next After ESMFold2 46:10 – Connecting ESMFold2 to Agentic Systems 46:51 – The Virtual Cell 49:33 – Defining Success for Biohub 51:52 – Biohub Strategy Update 56:20 – Conclusion
AI Generated·May contain errors
Video Summary
AI Generated
Mark Zuckerberg, Priscilla Chan, and Alex Reeves discuss the mission of Biohub to transform biology from a discovery-based science into an engineering-based science. By integrating frontier AI with open-source biological datasets and \"world models,\" they aim to create a virtual representation of human biology to accelerate the cure for all diseases.
We just want to give tools to the whole scientific community.
We want to understand how biology works.
I want to understand the genetics of this person.
I want to 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 going to cure the diseases. We're not.
It's that we want to help accelerate the pace of progress for the whole scientific field.
We folded over 1.1 billion proteins and predicted their structures,
and we didn't design a model for antibodies.
We didn't design a model to be able to find 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.
Great to be here.
Alex, congratulations on new missions.
Thank you.
You guys made Biohub your primary philanthropic effort
and then committed $500 million to this virtual biology initiative.
Can you tell us a little bit about 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 10 years ago when we were thinking about how can we give back?
And 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 famous Nobel Prize winning scientists were just laughing at us.
Was that your starting line?
We're just going to cure all disease?
No, no.
And to be clear, we don't think that we're going to be the ones curing the diseases.
Our goal is always to build tools that can accelerate the whole scientific fields
that way the scientific field collectively could cure all the diseases.
But still, people thought that by the end of the century was a stretch.
Now I think it's 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 why?
Why do you think it's impossible?
And just being the person in the room was just like,
well, I don't know why you tell me.
Finally, we got people to like, they're like, fine, if you really must know.
And we're like, no, we do.
It seems important.
They were like, well, we work in silos.
And when you publish, information doesn't get shared.
It gets locked up for long periods of time.
And we don't have tooling.
They gave the example of like, we build a great tool by one postdoc in a lab,
and it lives on their computer.
And when they graduate, the tool is gone.
And what we heard was very hard to build shared tools to move science faster,
build a shared knowledge base to quickly move science faster.
And that's sort of where we begin in thinking about, okay,
like if those are the problems, like what can we contribute?
Yeah.
I mean, so the original Biohub model was basically focused on long-term tool
development by bringing together engineers and scientists across multiple
universities to focus on long-term tool development.
And basically it worked.
And we started off with CZI doing a number of different things.
And I think over time, we just felt like, okay, the science piece is really working.
And we just kept on investing more and more and more in it until now,
it is basically the primary and main thing that we're doing.
And we've expanded the original San Francisco Biohub to a handful now.
At this point, there's New York, there's Chicago.
The real focus and the unifying theme at this point is the virtual biology initiative around
taking the unique datasets that are able to be generated in order to model effectively,
starting with the smallest pieces of proteins, but then eventually cells and whole biological
systems.
But that's kind of how we've evolved is this idea that we talk about around
that some of this is an AI problem and you want to build a frontier AI lab,
but you need to couple that with a frontier biology effort that can do the work of basically
being able to understand and get the data that you need to actually be able to build these models.
Because unlike language models, where there's just a lot of data out there on the internet,
that's not really the case with biology.
I mean, there are obviously a bunch of different datasets that
exist that academia and scientists have generated over the decades.
But a lot of the stuff that I think we want to put into this, it doesn't exist.
It's like you want to be able to visualize things that people haven't been able to see
before, which is why we're doing the imaging work.
You want to be able to record things that are going on inside the body, which is why
we're doing the cellular engineering work.
You want to be able to measure things like inflammation in ways that haven't been possible,
which is why the Chicago Biohub is focused on building those kind of devices and being
able to do that.
That will fundamentally create new types of datasets that will allow new types of models.
I think it's just a very exciting thing that, going back to what you're saying, if the scientific
field primarily needs tool development that now is going to empower scientists across
the field to be able to do their work faster, that's what we think we can provide through
this long-term focus on tool development.
I think there's a fun through line on where we started, and bringing us to our work that
Alex is driving now, is that our very first request for application, RFA here, was around
single-cell sequencing.
We wanted to look at the RNA that is transcribed in individual cells.
That was possible, but it was still pretty early on in understanding how different cells
were expressing their DNA, to the point where, at the beginning, we were just funding methods,
getting people to describe how to do it so that others could share that methodology.
Then that became us funding the Human Cell Atlas, which is now one of the largest databases
of single-cell transcriptomes.
It was getting hard for scientists to annotate the data, so we built Cell by Gene, which
was a very simple annotation tool that scientists could use to make use of that data.
Then a community came around Cell by Gene, built around Cell by Gene, and started contributing
more and more data that we had nothing to do with creating or funding or making happen
in the world.
Now Cell by Gene is a corpus of knowledge that a lot of the transcriptomic-based models
are based off of, and is used regularly by the scientific community.
But still, there are always critiques, like, this is just stamp collecting.
You're just gathering bits of knowledge—sorry, bits of data, and we're not going to be able
to pull scientific knowledge and wisdom and insights out of.
And we're like, well, we didn't have an answer for a while.
And then imagine our delight when large-language models became a huge topic of conversation
that could make sense of large amounts of data.
For me, it was like, what if we could actually understand how biology worked?
Move it from a discovery-based science to an engineering-based science, where we could
systematically understand how living beings, living cells worked, and be able to understand
why things go wrong.
And so when we saw that moment, we were like, this is it.
Something really big could happen here.
Alex, you started at MetaFair, but you were on the path to—you'd assembled a team at
evolutionary scale, and you'd raised Venture, and you were making progress in your models.
What was the pitch from Mark and Priscilla where you said, like, that's actually the
right way to go after the mission?
Well, I think for me, it was really kind of the moment when I understood that they really
saw this as an integration of frontier AI and frontier biology.
And I think I had developed conviction that this is really a new era of science that's
just beginning, kind of what's going to be possible with artificial intelligence.
And we're in the age of information theory at scale, and we have these systems that can
basically kind of predict the next token, and they can learn world models from that.
They can learn biology from the data.
And so I think that it was really clear that to build that next institution for the next
era, you would really need to have frontier artificial intelligence.
You would have to have frontier biology.
You would need to start to put those things in feedback and really have models that are
learning from the biology.
And you'd need the right scale and the right people.
And so this just really felt, I think, like the way to do that.
There's a variety of different models that you all have been working on.
And I think it's kind of interesting because some of the earliest breakthroughs in biology
were things like AlphaFold, where there was a Google model that showed that you could
do protein folding at scale in a really interesting way that people didn't realize was very
tractable, and this was pretty sort of the really big transformer waves that came later.
And then you're working on a variety of different things at different scale, right?
You're doing incremental molecular modeling and protein folding.
You're doing cell-based stuff.
You're thinking about interrogating larger-scale systems in biology.
How well do you think that extends from sort of the micro to the macro?
You mentioned almost starting with building blocks and building up, but modeling cellular
behavior is very different from modeling protein folding.
The data is very different.
The modeling is different.
I'm just curious, like, do you think it's all similar in terms of just data and you
train stuff, or do you think it's actually, there's some differences in terms of how you
actually have to deal with these systems?
I mean, there are probably some differences.
I mean, you can probably talk more to the specifics around this, but like, I mean, I
think each layer is going to end up being somewhat qualitatively different, right?
I mean, but you need to be able to understand the protein interactions in order to be able
to understand how cells work.
So you can't just go straight to cells in a way without understanding the protein modeling.
And then if you're trying to understand something like the, you know, the way the
immune system works or a bunch of cells interact together, then it's tough to do that without
first understanding cells.
I mean, you might be able to add like a very high level of abstraction, simulate a system,
but if you really want to like understand how it's going to work, you kind of want to
build the simulations at each level hierarchically.
So that's basically the approach that we're going through, starting with the building
blocks and the protein.
But yeah, I mean, I think that there's going to be different types of data that you want
to collect for each.
The modeling techniques, I think we'll see.
I mean, that'll all keep on advancing across the board.
But I do think that a big part of the strategy is this view that you need to build it up
hierarchically.
And, you know, one of the things that's unique about us in the space is we were very intentional
that the AI efforts and the wet lab efforts were a single effort.
And we've done a lot of work to bring them together.
And the really neat thing that we can do is really try to pull and gather data that helps
us connect across sort of the hierarchy.
You know, you can look at transcriptomics with space within a cell and look at where
it's localizing.
We can look at translucent zebrafish and look at the development across different cells
and when the brain develops.
We have sensors that allow us to look at cell-cell communication in different molecules.
And so we can be strategic about the types of experiments and data we want to collect
that helps us bridge across these, that makes it so that there's some connective tissue
that helps drive the modeling that, you know, the modeling magic that happens.
Yeah.
The reason I asked the question, by the way, is I used to be a biologist.
I have a PhD in biology and I worked in wet labs for almost a decade and everything else.
Are you looking for a job?
We can talk about that later.
I'm like Danny Glover, you know, and I'm almost at retirement.
But I think, you know, one of the things that was always lacking was this integrative nature
across the different layers of biology and the developmental biologists would work on
their own and the molecular biologists would be doing different experiments.
And so that's what I was curious about.
Yeah.
Typically there's a reductionist view of biology and there's a systems view
and those people didn't really work together deeply.
And so one of the exciting things about what you're doing, actually,
is how you're bridging that.
And so that was kind of the basis for the question as well.
Yeah.
And if I could add something there, you know, it's, I think that, you know, we're in the age
of this kind of information theory in biology.
And so, you know, there are levels of complexity and hierarchy in biology and kind of each level
is made up of and, you know, constituted by the lower levels.
And so as you want to have that kind of more complete description and you want to have systems
that can really generalize and begin to actually answer, you know, experimental questions digitally
that you could ask in the lab, you know, you need to have kind of the right basis for modeling
at every level.
And so I think what's really unique about what we can do is to, as Priscilla and Mark were saying,
you know, really build information at each of these different layers, collect them,
collect kind of those connection points, but then also really kind of do it at the scale that will
reveal that underlying information architecture.
And that's going to be really critical to actually be able to build
digital representations that can answer new experimental questions.
One of the things that inspires me most about this effort is really what Priscilla said,
which is like, well, there's so much we actually don't understand about biology and what if we
could, which I think is actually very different from lots of other incredibly interesting and
useful AI problems we attack.
We're like trying to replicate human behavior.
And I'm like, a lot of that data is, you know, on the internet or captured and
without pretending to understand all human behavior, you can predict a lot of it.
I thought one of the most interesting things in your release was actually, you know,
the mechanistic interpretability stuff you alluded to, which is, can we actually extract
new knowledge from, you know, what the model believes is happening?
Right.
Can you talk a little bit about that?
Yeah.
I'm really excited about that.
So I think, you know, in mechanistic interpretability, kind of traditionally, it's been
applied to large language models with the goal of understanding, you know, kind of what is the
representation space of a large language model?
How does it compute things?
And does that really connect to, you know, what we understand about our intuitive
understanding of the world?
And so there's, I think, this really rich toolkit that has been developed to start to
be able to ask those questions.
So kind of what does that mean for biology?
One of the classes of models that we train are these protein language models.
So they're really, you know, it's trained on the codes of proteins.
And so anything they learn about biology is kind of emergent.
And we've seen that they can learn things like biological structure and biological
function.
And that's just kind of emergent from this, you know, token prediction training task.
So, you know, as we think about like mechanistic interpretability in those models, you
know, we're really seeing the unknown because the models have been trained on billions of
protein sequences.
They've been trained on, you know, both known and unknown biology.
And yet they're developing these representations that start to kind of capture things that
we can really see correspond to that reductive picture of biology that's been built up over
the centuries.
So kind of you can start to connect the dots between proteins where we kind of really don't
know anything about them with proteins where we do know something because there's that
kind of underlying structure, grammar that's linking them in the representation space of
the model.
And at the extreme, it could be, you know, we're going to understand systems in the body
that we didn't before or the mechanism of action for a new treatment because we can
ask the model, right?
Interrogate that representation.
That's right.
The hope is that you kind of really learn the underlying basis for how it's making the
predictions.
And so you open up the black box and you can actually understand kind of the biology that
the model is representing.
So asking for a friend, you know, you guys all believe in venture-backed companies as
a way to have impact on the world.
Was it like collecting data on zebrafish or the span of the data or the wet lab work or
just the scale?
What makes this a better fit for this big non-profit, you know, ecosystem effort versus
a venture-backed company?
Well, I think we just want to give tools to the whole scientific community.
And I mean, like, so I think in order to have the biggest impact, I mean, part of it is
just we're, I mean, it's not actually clear that we couldn't run it as a business if we
wanted to.
I just think that we'll have a bigger impact by getting this in more scientists' hands
quicker by doing it as open source projects instead.
So yeah, I mean, I think that's kind of the approach.
But I don't know.
It's an interesting question.
I'm not sure that, I mean, obviously you were doing it as a for-profit company, a bunch
of the modeling before.
Then you run into certain issues.
I mean, you have to raise a large amount of money in order to build the compute clusters.
You know, I mean, I think in a lot of ways, the data is actually even more of a constraint.
And because if you look at the scale of these models compared to language models, they're
smaller, but they're smaller because the amount of data is less.
In order to get the data, it's not just like there's some factory somewhere that you can
pay to produce the data.
Like you actually need to invent new novel scientific approaches to be able to do the,
you know, for example, the type of cellular engineering we're doing in New York or the
types of devices in Chicago, which is why, you know, when we're talking about this concept
of frontier biology and frontier AI, the frontier biology is you need to do real science
to advance different biological methods in order to be able to observe the things that
create the data that go into the model.
So it's not just like an off-the-shelf thing that you can create.
Now, that's a pretty big effort.
I don't know that there are like that many things like that that are done as biotechs.
I think it's just the scale of the ambition of what we're doing, the horizon over which
we're committed to doing it.
I think part of the theory is like, if you're building tools that are this complicated,
you kind of want to have a 10 to 15 year time horizon on building out these efforts.
And then the scale of capital required.
I mean, I guess there's no rule that said that you couldn't do it as like an incredibly
well-funded startup, but I think that this just made more sense.
And then it also is simplifying strategically to not have to think about how you're going
to make money with the different things.
I mean, we just, we want to get the models in people's hands.
We release them as open source.
I think that that's like a very valuable thing to do.
And again, I mean, the theory isn't that we're going to cure the diseases.
We're not.
It's that we want to help accelerate the pace of progress for the whole scientific field.
As the person least experienced with making money here, I would say that the sort of neutral
nonprofit nature of our work actually helps harness more people to enter this effort and
to actually achieve the mission of understanding the totality of human biology and to cure,
prevent, manage all diseases.
You actually do need the entire academic biotech industry to come together and to work on this
in a sort of unified way.
In part, because there's a lot of talent out there and it's not helpful to leave any talent,
exclude any talent from the effort.
And there's a super long tail of diseases.
There are the common ones.
And even the common ones, I think if you unbundle heart disease, cancer, neurodegenerative diseases,
even if you unbundle dementia or depression, there are many, many, many subcategories
that become more and more niche.
And that's not even looking at the long, long tail of rare diseases.
Those often get orphaned and don't get brought along when we're sort of looking at the most
efficient way to impact the lives of many.
But if you sort of decentralize the effort and put the tools in many people's hands,
you start getting people who are like, you know what?
I am super interested in spinal muscular atrophy.
And that's something I care deeply about.
And if you put the tools in that person's hands, they're going to be able to make progress.
In a way, if you had to focus your efforts and make big bets, you probably wouldn't because
it's just a niche, individual, small group disease.
That actually will in turn, if we can understand that disease process, helps us unlock knowledge
about a lot more about how the human body works.
Do you have any thoughts or predictions in terms of what disease areas this work will
impact first?
I know it's very hard to be predictive about these things, but just given the nature of
the work and the nature of the models, are there areas you're most optimistic about in
the short to medium term?
That's actually not how I think about it, at least.
The way I think about it is like, we want to understand how biology works.
The ideal world is you would say, I understand the genetics of this person.
So I want to think about people at the individual level.
I want to understand the genetics of this person.
I want to understand the risks they have to different illnesses.
I want to understand the mechanistic connection between, say, a gene variant, a protein, and
a disease process.
Because if you understand that through chain, then you can design a protein, design a drug,
bespoke to them, and actually make an intervention.
And right now, I'm sure we've all had experiences being sick.
And if you have something that's even remotely non-standard, you go into PubMed, you look
up a paper, you look up the supplement, and then you start going through the methods.
And you're like, am I represented in this paper?
And we're just making guesses.
We really have no mechanistic understanding.
We're saying, OK, you're kind of like these people that we studied.
And this drug kind of impacts the pathway that we think is implicated.
Let's try and see if anything happens.
And time passes.
And sometimes it works, and sometimes it doesn't.
So my goal is to be able to treat the individual as an individual, understand the mechanisms,
and be able to intervene.
And there are different diseases that are at different stages of filling out that whole
through line.
And so for some diseases, you just want to understand which gene variants actually cause
disease and which don't.
And that in itself can be super empowering to patients.
And beyond that, there are some diseases where we understand the chain.
We just can't intervene and change a specific protein function.
That's super exciting, too.
If we could design a protein to actually change the physiology, then we can actually cure
someone.
But to me, that is just as exciting as contributing to our understanding of how someone gets sick
in the first place.
That's a very exciting vision, because you're basically saying you can bring generalizable
tools to provide very personalized things for each individual person.
And that's the power of the approach, is you have these big models that you build that
can then apply anywhere.
I know that you mentioned earlier that you're going to try and cure prevent all diseases
within 100 years.
And you mentioned, hey, it could actually be sooner now, given all the advances in AI.
Do you have some thought of when we think we'll be closer to that goal?
I mean, I'm optimistic it'll be sooner.
I think the thing that's complicated is that it's a dynamic system, right?
So if you fix something, there will obviously be future things that you need to work on.
So I don't think that the current set of things that we're aware of are going to be the only
things that need to get worked out.
But I think that the progress with AI is obviously very exciting on this.
The other thing that I'd say, just adding to what you were saying a second ago, is we
really look at more systems than specific diseases.
So for example, one area that seems really important to understand is inflammation.
We talked about this a bunch.
This is a big focus of the Chicago Biohub.
There's a lot of data on that.
It seems quite clear that it's connected to a bunch of different diseases.
But rather than studying the specific diseases, we think that by trying to understand inflammation
more broadly, that will make it so that other companies that can then use these tools can
work on specific therapies.
Another example is, I think that the immune system is a very good case to study for some
of the work that we're doing in cellular engineering.
And when we ladder up from proteins to cells to whole dynamic systems within the body,
I think that that one makes sense.
I mean, it's sort of privileged that the cells can travel around through the body, all that.
So obviously, that has a big part in addressing different diseases.
How do you make the immune system function better?
But exactly how do you connect that last mile, I think, is going to be more something that
biotech or other academics individually studying things will be better suited to do.
So this is kind of how we think about building out the tool set that just helps accelerate
all these other folks.
Whether the timeline is 10 years, hopefully less than 100 now, I think it's useful for
maybe your average doctor or patient, human being, everybody's a patient, to think about
what's externally visible in the progress here.
You worked with patients for a long time at UCSF.
What should doctors look out for?
What should people look out for if you're actually accelerating?
This is the part, you know, I'm super excited about the progress, especially with this launch
that Alex and his team have put forward.
And I think it's very clear that science is going to start moving pretty quickly.
And I think the thing that's less clear to me is exactly how we translate to the clinic
and what that looks like.
And I think what has to change is actually the way we do clinical research.
And my hope is that we're really shortening the distance between bench research and patient
impact.
But there's a lot of steps there that we need people who actually take care of patients
to think creatively and think about how to deploy safely.
And that's a gap that we have some work in.
We partner with Jennifer Doudna on a CRISPR-Cures program at UCSF.
So we're dipping our toe in understanding how the deployment of research needs to change,
given how quickly research will be progressing.
But that one is still, I think, is still shaping up.
Maybe I could say something about our most recent launch, because I think it also kind
of illustrates something about this.
I guess it was just a week ago, about now.
So we announced the new ESM fold.
And so this is basically an open system for scientific discovery in protein biology.
It's a world model of protein biology that's been trained.
It's a language model base.
So it's been trained on billions of protein sequences, kind of learns these emergent
representations of protein biology.
And then we can use it to make predictions of atomic resolution protein structure.
And we can use it to, and it's really fast.
So it's blazing fast.
So it's kind of illustrating this Pareto optimal frontier of kind of speed and accuracy
in structure prediction.
And so this allows us to kind of characterize really vast kind of stretches of the protein
universe.
So we folded over 1.1 billion proteins and predicted their structures and identified
kind of features connecting all of them through mechanistic interpretability.
But I think the thing that I thought was most exciting about this model is it's this really
general model of kind of protein biology.
And so you can use it as a world model.
You can actually really start to search the space of the world model to design new proteins.
And it's really hitting state of the art across pretty much every structure prediction
benchmark.
And especially on protein-protein interactions and protein-antibody interactions, which is
really critical for therapeutic design.
And so what we found is you can actually now use the model to design proteins and design
actually single chain antibodies.
And so you can do all of this digitally.
And then really in a small number of experimental trials, basically like a 96-well plate, select
from hundreds of thousands of trajectories digitally, actually synthesize 96 proteins,
test them in the lab in a really kind of short, easy experimental cycle.
And we found nanomolar binders there.
And so that's really the level for therapeutic activity.
So it's really, I think, showing that you can have these kind of general purpose models
that can, you know, we didn't design a model for antibodies.
We didn't design a model to be able to bind one particular target.
You know, we just designed a model that could understand proteins.
And you kind of get protein design as an emergent property.
And then I also think it illustrates this kind of the power of open science and open
source, because, you know, we released this as basically an open discovery engine.
And so really anyone can build on it.
And so it takes what are these really intensive laboratory experiments where, you know, you
have to screen through hundreds of thousands or millions of antibodies and high throughput
screens in the lab.
And, you know, you can really just kind of spin up an instance and compute and now, you
know, be able to generate antibodies.
You should say more about sort of like we took that data when we looked at an antibody
screen, and then we validated, we looked at PDL in cells, and then we looked at it
under the cryo-EM and sort of how all that complemented, validated what you were seeing
in the models.
That's right.
Yeah.
So, I mean, I think it's really critical, you know, to actually go and characterize
these molecules in the lab.
And it's, you know, we have a structural biology center here.
We have incredibly powerful cryo-EM microscopes.
And so we're really able to kind of look at these proteins biophysically and functionally.
And so, you know, we designed proteins for several therapeutically relevant targets,
and we're able to confirm their function.
It's delightful when it works the way it's supposed to.
Yeah, it's pretty amazing.
We're able to look at the structure also, so you can see atomic resolution kind of at
the binding interface as well.
I know a lot of your work is really focused on basic research and kind of building other
fundamentals.
If I look at actual translation into drugs or drug development, often a clinical trial
will be 15 years, so it'll cost $1.5 billion.
About $50 million of that often is the molecule and preclinical work, and it's a few years
of work.
And then the other $1.45 billion and decade plus is actually the drug development side
of it.
A lot of that seems to be gated on some regulatory issues, some of it's recruitment, it's a
variety of things, but a lot of it also has to do with the failure of drugs and trials
around things like absorption or toxicity or things like that.
Have you considered at all tackling that other chain of molecular design and thinking, or
is the primary focus more on the basic biology and the initial molecules?
I mean, at least my hope in building this comprehensive model of how cells work is actually
also being able to predict off-target effects.
I think you can do some of that actually with biological models, because right now some
of the off-target effects are we just didn't know your kidney cell also expressed this
receptor.
And then when we test it in human, we see it happening and we see renal toxicity.
And if you have a single-cell atlas that looks at all the different cell types, some of which
actually were not predicted before we modeled them, you can start looking at which cells
actually do have receptors for the target you thought you were exclusively targeting
and be able to predict some of these downstream effects before we get into the human trials.
And I think that that's actually one of the more exciting applications of a transcriptomic
model to understand actually how the different cells will react when you intervene and do
something.
But I think when you think about delivery mechanisms and patient care, that's where
you start having to be creative about when you ask, what disease do you want to care
first?
There are certain diseases that will be easier to deliver a therapeutic to, or the risk-reward
makes more sense.
And I think we were all inspired by baby KJ, I think last year now, when the team at CHOP
was able to deliver a CRISPR therapeutic to edit a mutation that he had that would have
inevitably led him to significant neurotoxicity and altered his life.
But we were able to, that disease was very carefully chosen because we needed to target
his liver cells.
And if we could easily deliver a product that would work in his liver.
And I think that's when the creativity, the wherewithal to choose the right applications
can help us unlock the first application.
Maybe something just to add to that also, because you described the conventional drug
development process, right?
And I think these kind of tools have the potential to have a lot of impact on that process.
But what's interesting is to really start to think about the new paradigms that can
open up.
And what does it mean if you can, the barrier to develop a drug, to design a molecule, to
kind of get through all of those stages is so much lower.
And so you have programmable biology and you can really start to create a medicine for
every individual patient.
I think that has enormous implications for how we do drug development and what the future
of medicine looks like.
It'll be an exciting day when the FDA accepts like a virtual clinical trial for the phase
one or something, or, you know, it's based on some person's view of that person.
Yeah.
But even short of that, like thinking about the specific like mechanisms where you see
this acceleration, like I imagine if people feel like they can predict impact in kidney
cells or have a stronger perspective on tox because they have this broader understanding,
they'll be willing to try many more programs.
Yeah.
The recruitment could also change.
And we have this program, Rare is One.
And the basic idea is that a lot of people focus on the most common diseases, but there's
this long tail.
And the economics don't quite work out for companies to focus on those diseases.
But if you could make it so that the groups of patients can kind of come together and
organize and say, hey, we would take an experimental drug on this, then it actually, because of
the cost that you're talking about and how that's a huge amount of the overall cost,
if you can flip that, then it actually makes it so that the economics make a lot more sense
to then if you can generate something more easily and you can pair it with a group of
people.
I think one of the interesting things from science and engineering is that often you
can hit your head against the wall on the common problems and in this case, diseases.
But a lot of times you like learn a lot more about a system from finding some kind of rare
or like weird side thing that's happening, edge case.
So I don't know.
I think that's like always been kind of an interesting part of this that actually connects
pretty well to this because now you're going to be able to enable a long tail of new kind
of ideas to get tried and enable them to potentially get tested more easily.
Yeah, that's a really good point on rare.
In our rare disease cohorts, first of all, they're incredibly inspiring and powerful,
but patient groups are self-organizing patient registries, natural history registries,
biobanks.
They're organizing their own clinical trials.
There's gene therapy that one disease group has moved forward over the course of like,
I want to say like three to five years rather than decades.
And the speed is so fast because the patients themselves have organized
the resources that a scientist or a clinician might need.
And it's incredible.
But I think to some degree you're going to need something like this because
there are going to be many more new things that can get created.
But that doesn't mean that for like the general population that you're not going to want the
same level of vetting that we've had historically.
But making it so that people who want to be on more of the frontier
have the ability to do that is I think also going to be pretty helpful.
Letting people opt in to be part of trials, I think is one of the big shifts that
is starting to happen, but could really help accelerate biology in general.
All three of you have mentioned at different points, like the power of open ecosystems
in such a large space.
I think some of that logic around open source and the breadth or diversity of data collection
you were describing, it should also apply in the language model world and the multimodal AI world.
Do you think that's right?
Does any of the work you're doing here change how you think about AI and meta?
I mean, I think it's sort of a similar philosophy overall.
And Priscilla was talking about this, that a lot of our focus is building tools that
empower individuals to do things.
And that's sort of a common theme across a lot of the things that I work on is
just kind of putting the technology in individuals' hands.
We don't believe in this very centralized future where there should be a small number
of institutions that basically are advancing all of this stuff.
Our vision is not that there's going to be some central superintelligence that solves
all of science.
I think people are really important, and I think we'll be more important in the future.
And giving people more tools to be more productive is going to be a critical part of any kind
of positive future.
And that's how progress has always been made historically, right?
It's not through centralization, it's through empowering individuals to try things that
are somewhat out of the mainstream that other people didn't think were good ideas because
they thought they were good ideas that already have been done.
So I think that's very central to the whole ethos of, I mean, to some degree, it's like
why you create something like social media, right?
To give people a voice.
It's, you know, I think a lot of the stuff that I care about in terms of empowering people
with individual AI, open source is one instantiation of it.
It's not the only way to do it.
It certainly is one way that you basically are saying we're going to take this technology
and put it in everyone's hands.
In terms of science, I think it really makes sense.
And we're deeply committed to open source.
There are obviously interesting considerations on this that are important too, because there's
a lot of considerations around biosafety and things like that that we're going to need
to balance and think through how to handle.
But I think overall, this is like very deep in the ethos of the work that we're doing
both at Biohub and probably a theme for a lot of the stuff that I do is just like, we
believe that a positive future is one where you build a technology as a tool, you put
it in individuals' hands, and that's kind of how society makes progress.
You have this, I think, incredibly ambitious mission at Biohub, and yet, you know, the
AI scientists that work here could also go work in commercial enterprises.
How do you think about the talent and how to bring people to Biohub?
I mean, where do I start?
Yeah, I mean, it's a very hot market for AI researchers.
But I think that part of what that means is that there's a lot of demand and they're
very in demand and can work on the things that they want to work on.
And I think this gets back to this point again about frontier AI and frontier biology.
So yeah, I mean, I think the AI researchers who work here could go work on language models
or things at any of the main labs, but those labs don't have the frontier biology part
attached to it.
So I think that there's also just a very large mission component of this, which is
like, there's an ability to do this unique work here that you just can't really do at
the other places.
So if that's what your focus is, then I don't actually think that there's any other
organization in the world that's doing both the frontier biology and the frontier AI.
Yeah.
Why are you here, Alex?
I mean, I think it's really simple.
Our mission is to take care of disease.
And I think, you know, it's just such a powerful—
And you say it with a straight face in a less than 100-year timeline.
It's very serious now.
There's no more.
Yeah.
It's a really powerful mission.
And I think, you know, you—
Yeah.
I mean, it's just, you know, scientists, I think, are very motivated by that.
It's something people are deeply motivated by.
And I think, you know, we're at this moment in time where that actually seems like something
that can be achieved.
And I think, you know, we're building a really unique place where we're tackling that
problem.
And, you know, we have the resources.
I think kind of the right things to actually really go after that and do that.
Yeah.
I mean, that resonates with me as somebody who, you know, talks to and hires a lot of
research scientists.
They want to know if you have the data, if you have the tools, if you have the compute,
if you have the talent, and then what the mission is.
And so I actually think that's super competitive.
The other thing is that you don't need a very large team, right?
So I think it's like an interesting thing about the world is that people care about
different missions.
And that's good.
I mean, part of why building these tools and giving people the ability to explore what
they care about, whether it's across science or just across everything, is such a powerful
way to make progress in society is that people care about different things.
And in order to make progress in AI, you don't need many, many hundreds of AI researchers
or thousands or anything like that.
I think you can really make progress with a very strong group of a dozen or a couple
dozen people.
And yeah, I mean, finding people who care about this mission is not a particularly hard
thing.
I mean, this is like a super important thing in the world.
So I think that that's, yeah, it's just kind of a cool thing about the world is that people
obviously are drawn to different missions.
So I think the simplest mental models that folks have, even if they're paying attention
to the space, are essentially like, okay, you know, structured prediction models for
proteins and protein-protein interaction models.
And then, so there's this one piece, which is fundamental understanding.
And then there's this like theory of someday we're just going to be able to like zero-shot
things into either the clinic or the clinic with much, much better hit rate.
What needs to happen for us to go from ESM Fold 2 to this other piece?
And is that feasible?
I think that's a great question.
I mean, I would say that I'm really optimistic on that.
So I think, you know, on the one hand, you know, these are problems that historically,
you know, people could spend kind of an entire career working on.
Like, how do you figure out how to effectively optimize a drug?
How do you get it through preclinical?
How do you do the early safety?
I think that, you know, when you have a new scientific paradigm, kind of, you know, questions
that were once hard kind of become simplified through the new paradigm.
And so I'm very optimistic that kind of many of these core problems will be solved kind
of in an emergent way through these models.
And I think one great example of that is toxicity.
Whereas if you can kind of really digitally simulate everything and be able to predict,
you know, where a drug is going to distribute and bind across the human body, you know,
like you kind of have the beginning of a solution to that kind of problem.
So I think that once you have these kind of accurate representations at the molecular
level, you know, we're going to start to see really rapid progress on a lot of these core
problems.
What is the most exciting use or experimentation with the models you've seen in the last week
since release?
Yeah, I mean, it's just been great to kind of see it get integrated in all kinds of things.
I think one of the really interesting things that we've been seeing is people kind of
connecting it with agentic systems to just kind of do automated design and kind of just
automate that whole process.
So it's really, I think, another example of how you can kind of see bringing together
agentic and frontier AI with the ability to have a world model for biology and actually
reason about biology and really kind of start to automate the entire design process.
Are you taking, you know, how do you decide what the next step in the research agenda
is?
It's like world model for biology.
And then I could, I'm just going to be very coarse here.
Like I could scale it up.
I could add more data.
I could, like adding data is a non-trivial thing in terms of new methods and domains.
Like what is, do you take input from the larger ecosystem about, you know, how people are
using it and what would make it more useful?
Or is it really like we, we understand like the next step of structures or coverage that
we're looking for?
I mean, I think there's two things.
So like we have a view on kind of the next big challenge, which I think is, you know,
the virtual cell and, you know, really being able to kind of ladder up the hierarchy of
biological complexity to the cell.
And sorry, very basic question.
Yes.
Virtual cell model.
Like what is the input and output I should expect?
Yeah.
I mean, I think there's a different views on that, but I think kind of what you ultimately
want is a system that can really model each of the levels of complexity.
So, you know, the proteomic layer, the genetic layer, the transcriptomic layer, and connect
that to the phenotype.
And you need enough generality so that you can ask the model questions about a new intervention
in a context that it hasn't been trained on and kind of get an answer from it.
And, you know, the gap that we need to close as a field is being able to really make those
predictions that can generalize.
So that's going to require, you know, enormous effort to generate data.
Yeah.
And then, I mean, in terms of what you decide to do next, I think this is like, you know,
a pretty normal process of constraint management, right?
I mean, it's like, like, I think every lab and every field across the world probably
feels compute constrained.
I think that that's probably true here too, right?
So, I mean, I know, like, you know, there's all these questions like, okay, should we
double down more on advancing the protein piece?
Should we do more of the cellular stuff?
Those are kind of ongoing debates in terms of how you sequence that.
And then, yeah, within that, there's kind of being at the Pareto frontier about how
much you want to train the different models in order to, like, and the size of the models
is also dependent on the scale of the data that you have for obvious reasons.
So, yeah, I mean, I think it's, there's some of that is just where you want to be on the
curves and the normal constraints.
But I think that this is, like, probably the same process that, like, any research organization
goes through of, like, you want to go in all these different directions and you're just
trying to constraint optimize and make enough progress to do world-class work at one thing
at a time while planting some seeds that can blossom over the next couple of years as well.
Yeah, this has been the most dynamic period of technology, at least I've seen over my
career.
I mean, it's so exciting in terms of everything that's happening with AI.
And every week there's something new that's changed.
Are you tired or invigorated?
I'm both.
I feel like everyone's in this manic phase.
Yes, it's a combination of invigorated and exhausted.
Yeah, it's wonderful.
And so, I guess, you know, things are very unpredictable right now.
It's really hard to know what's coming.
We have this almost, like, early signs of exponentation on the model side with agentic
flows that we're starting to see in really interesting ways.
Models starting to help more and more with models, although it's still very, very early
days for that.
If you're thinking back five years from now and you were to define what success was relative
to your efforts, and I know things are very dynamic, things changed a lot, but you have
this common thread of tooling for the Biohub.
You have a common thread of empowering scientists at scale.
You're looking back five years from now.
Is there a specific thing that you really want to make sure that you've accomplished
or achieved or a primary goal?
Well, I mean, I think we have a pretty clear view of this hierarchical set of world models
that we want to build around biology.
And the other part of that is that we want to do the highest quality work in the world,
right?
I mean, I think we're basically set up to do that between having a world-class AI research
team and this collection of Biohubster world-class life sciences research organizations.
I think that's fundamentally a setup that no other organization in the world has.
But you can have a lot of great ingredients and that doesn't guarantee that you succeed.
So I mean, to me, five years from now, looking back, I'm sure other labs or efforts will
try to produce things that approximate what we're trying to do.
And I just think that we should be able to do something that is meaningfully better and
a unique intellectual contribution to the world, right?
I think that that's kind of what you, whenever you do any kind of research, that's what you're
trying to do, right?
So, yeah.
So if we do that, I think we'll all feel very good.
I would also expect that at some point we'll just start seeing a lot more idea generation
from the people using the models.
But I have enough faith that that part will materialize.
That for me, it's more just about making sure that we do world-class work.
And I think if we do, the rest almost will take care of itself.
Very last question for you.
Snapshot of it's mid-2026, what's the biggest update in your own thinking about
Biohub or the domain from the last year?
Well, from the last year, I mean, you joined in the last year.
I mean, I think the biggest thing that we basically rotated, and I think in the last
year, we basically kind of formalized that Biohub is the main focus of our philanthropy.
So I think this is like, I've been a very big shift.
But Alex and the team coming in, I think has been interesting, not only because it's a
world-class group, right?
I mean, you guys have worked together for a while.
I think also, I mean, you talked about how stuff is changing so much in the field.
I think one thing that's underrated is this is an extremely talented group of people who
also know each other and work well together and are stable and good.
And I think that that also is underestimated in terms of the compounding benefit of people
being able to work well in a stable environment over time.
So I think that that's a really important piece.
Part of what we wanted to do was, prior to Alex leading the effort, the previous leaders
of the Biohub were basically primarily biologists who were interested in technology, right?
And now I think this is the point where we really flipped that, right?
Where, I mean, obviously you have a background in biology as well, but you are primarily
an AI researcher who has a background in biology.
I think that that's like a deep reflection on the way that we expect that this is going
to drive more value in the future.
So those are probably the biggest updates in the last year in terms of the work that
we're doing.
It's a new leader, not just the leader, but a team that I think is really good.
And then, yeah, I mean, I think on the rest of the industry, it's on track.
I mean, I think it's kind of this crazy thing because when you have an exponentially growing
curve, I think the way that an exponential curve feels is it's growing so quickly that
the kind of emotional feeling is it can't possibly keep going, right?
But I mean, the nature of an exponential curve is it doesn't just keep going, it keeps accelerating,
right?
Exponential growth is accelerating.
So I think that that has all of these emotions and psychology attached to it.
But I think fundamentally, when you look at the curve in the industry, the kind of fundamental
thing is it is on track.
It has remained on that curve, which I think has all these very profound implications for
all of these domains.
But certainly, it validates and makes one feel very good about making a very big investment
in the things that will play out if you stay on that track.
And it seems like we are.
So that, I think, is very good news.
I think the most important aspect of what you're doing there is you're actually closing
the loop with the actual biology.
Because with code and research, it's closed-loop systems.
And so they're very fast to iterate.
This is an open-loop system.
So you're closing a loop.
And that's really crucial to progress.
Yeah.
For me, one of the biggest changes with the strategy we're driving now and Alex at the
helm is, before, we had amazing teams moving generally in the same direction and understanding
the potential collaborations and interconnectedness of our work.
But now, we are at arm's length moving together.
It feels very directed.
It's very directed.
And it's very exciting.
It's a little bit scary, but it's truly a team playing off each other and trying to
make progress towards this goal.
And that has taken a lot of work, but also the maturity, our teams being able to have
their work at a level of maturation where it actually does make sense to interlock.
Amazing.
Well, to teams being on the curve, thank you guys for doing this.
Thank you for joining us.
Thank you.
Find us on Twitter at NoPriorsPod.
Subscribe to our YouTube channel if you want to see our faces.
Follow the show on Apple Podcasts, Spotify, or wherever you listen.
That way you get a new episode every week.
And sign up for emails or find transcripts for every episode at no-priors.com.