🔬Causal Models Need Causal Data - Xaira’s X-Cell model (Bo Wang & Ci Chu)

And what really blew my mind away is when I saw the model make prediction just print out the heat map of the gene expression changes. Look at the actual raw data and line up the linear baseline prediction, the ground truth, and the XL prediction altogether, it's visually very clear to see that XL prediction is much more similar to ground truth than the linear baseline.

This is a wow moment I was talking about in the beginning. It is the first time that someone can put together not just one perturb-seq, but 7 genome-wide perturb-seq campaigns together. Something that jumped out to us biologistsright away is that some of the perturbations are context universal.

Hi, I'm R.J. Honeckey, CTO of Mirroromics. This is Brandon Anderson, who builds RNA therapeutics at Atomic AI, and this is the Latent Space AI for Science podcast. One of the themes that has run through the podcast is how the lab, experimentation, and the real world have probably the biggest impact and have the most relevance to whether something is AI for science or something like B2B SaaS.

We're really happy to have in the studio with us today Bo Wang and Ci Chu from Xaira Therapeutics. At Xaira, they're building with a bunch of other people an AI drug discovery platform. They're using a high-throughput experimentation system to collect very large datasets and then training AI models that can predict the way that your cells in your body will respond to drugs and therapeutics.

Really happy to have you. Big fan of your work. Why don't you two introduce yourselves to the listeners?

Hello everyone. My name is Bo Wang. I'm SVP and head of biomedical AI at Xaira Therapeutics. I joined Xaira about 8 months ago, and before that I was Associate Professor at the University of Toronto in Canada. And I'm Ci Chu.

My first name is incredibly difficult to pronounce unless you speak Mandarin, so I go by Chu, as in Chewbacca or Pikachu. I think you're a favorite fictional character. I'm the SVP of AI-enabled discovery at Xaira. I joined about more than 2 years ago when I was still in stealth mode, and here I lead the high-throughput biology group, generating the kind of data that will feed our AI models and also think about their applications.

Before this, I spent about a decade at the intersection of AI and big data and biology. So I previously worked at insitro, leading the in vitro discovery platform there, and before that I was at Verily, which spun out of Google X.

Okay, so you're at Xaira, the company which is on the paradoxical frontier of confusing names and mega rounds. So Xaira is, I think, kind of came out of stealth like a few years ago and just really big org kind of out of nothing.

So I'm curious if you can explain a little bit about what is Xaira's mission, what is their thesis statement, like what is, you know, special about Xaira, and, you know, kind of where you're going in the future.

Yeah, Xaira is an AI-enabled drug discovery company, and at the core of our mission, we're using AI platforms to generate better therapeutics to advance patient care. And so we will be making drugs using different AI capabilities. There are 3 main AI platforms that we're building here.

The first one is protein design, work that spun out of our co-founder, Dr. David Baker's group from UW. A lot of the current generation of protein designers are here in the company. So their thinking is to use advanced AI technology to develop

molecules against previously undruggable targets. The second AI platform, I guess we'll spend a lot of time talking about today, is the one that Bo and I have been working on for quite some time and just released a preprint on.

That's the virtual cell or foundation model of biology work. Their hope is to build an AI model to predict biology, exactly like you said, and predict what genes and drug molecules will affect cell biology. And the third piece, which we're beginning to build now, is patient representation models.

And the goal there is to have AI models that can understand which patients will respond to which therapeutics. So hopefully together, these platform technology will help us make better drugs, faster, and with a higher success rate than previous technologies, to transform what used to be artisanal, tried and error in the past, into more and more into an engineering discipline.

Yeah. I think what sets Xaira different is not just the 1 billion turning around, but also I think Xaira is one of the very few AI-native companies for drug discovery that works from end to end of all sections of drug discovery, from as early as, you know, target ID and then protein design, small molecules, and to phase 1, 2, 3 clinical trials.

We aim to use AI to accelerate every part of the drug discovery so that not only we increase the success rate of developing drugs, but also greatly, you know, reduce the cycle time so that we can have, you know, new drugs instead of every 10, 20 years.

So hopefully we can half the cycle time so that we have more useful drugs for patients.

That's really interesting. I know there's a lot of interestright now in that third thing, maybe called translation, from the lab to the clinic. Where are the bottlenecks? So you have these 3 models. What are the bottlenecks that you're addressing and, and sort of like, how are you doing that?

Why are you doing it that way?

Xaira is an AI-native company. Almost every part of the sections of drug discovery, we're trying to use AI to revolutionize how we develop drugs. So the early part, we build causal foundation models, or sometimes we call it virtual cell proteins.

We have, you know, state-of-the-art protein engineering models, and we have also patient representation learning models. And I think what Xaira is trying to do is not only we develop AI models, but also we create theright datasets to empower these models.

And I think what's really makes me excited to work at Xaira is we always aim to connect 3 AI models together instead of letting them work individually by their own. So when we design virtual cell models, we look for connections to that.

Can we find targets that it's easier to, to apply the protein engineering models? And then even when we design the cellular causal models, can we connect to patient representations? What are theright patient data to connect the cellular models so that we have something to show clinical utilities?

So I think what really makes me excited is, before I joined Xaira, I'm kind of a professor in the computational biology department or computer science department, where we're mostly working on computers. We look at the data, look at the arrays, et cetera.

But once coming to Xaira, what really excites me is that I get to talk to people like Chu, lots of drug hunters, you know, extremely experienced drug hunters, to really understand their pinpoint. So when we design AI models, we think about questions that really excite biologists.

So later maybe we can talk about how one of the rewarding signals I received after we developed X-Cell is that, like, it's a wow moment from biologists that this is the first time biologists actually find the model can predict exactly how these unseen cell lines kind of respond to different perturbations.

So that's kind of the part that really excites me is the integration of kind of dry lab or AI models to wet lab or the biology or even eventually to the clinical side.

With this clinical model, I know you guys are aiming to, you know, take a drug all the way to, to FDA approval and beyond. Where do we stand now? I don't know if you're able to talk about this, but like, are you able to collect data from clinical trials and tie that back yet?

As Bo said, I think if you think about drug discovery process, it's easy,right? You just need to find theright target, make theright molecule, and find theright patients to give them to. Of course, each of those steps are incredibly difficult to getright.

And so far, like I said just now, it relies a lot on trial and error and guesswork. And the main issue, I think, is that we don't have theright biological data, really the power, the training of a predictive model.

And in protein design space, I think that's where we have seen the most rapid progress so far.

Yeah.

That's partially because we have a lot of data, high-quality data, over 70 years curated by the entire community. People deposit protein structures into a database,right, called PDB.

Yeah.

We also have a lot of sequence data,right, collected over the years from different genomes that can help inform the model as well. And it's these high-quality data that are collected and accumulated that are certainly in this revolution in protein design and AlphaFold and other folding models.

In the other domains, such as clinical model prediction, such as virtual cell, we are nowhere near the same kind of massive data that are high quality. And I think it's mainly a data limitation issue. So to your question, that's why we're very invested in generating these data, particularly causal data in cell biology in a lab.

And that's, I think, what made it possible to innovate on the algorithm side as well to usher in virtual cell models. On the patient side, it's a very interesting question. Perhaps that's one of the hardest data to get because getting access to high-quality patient samples is difficult in itself.

Getting it matched to theright clinical annotation so that you can actually learn the difference, the bridge between molecular data and clinical response, that's even harder. And you might be able to do that across different disease severities, but it will be harder to collect theright data to predict which drug treatment will or will not respond in a particular patient or not.

And so that takes a lot of thought and a lot of careful curation to generate data out of. And so we're beginning to go into the area, but hopefully we'll be able to share more soon.

Awesome. Maybe we should switch gears now. You just released X-Cell. Why don't you guys describe? I won't, I'll butcher it.

X-Cell is Xaira's first virtual cell models. It is an AI model that can predict the response to genetic perturbations. Certainly we can extend it to other types of interventions, such as drug perturbations, chemical perturbations, et cetera.

So can you just describe for the non-biologists in the, that are listening, what, what is a perturbation? What do you mean by that?

In our cells, when Bo talked about genetic perturbations, our cell, human cell, typically have 20,000 genes. Not all cells express every gene equally. That's why your eye cell, your skin cell, your heart cell, even though they share the same genome, they function very differently.

A lot of that's determined by, you know, selective gene expression that determines the type and the state of the cell. So what we do is to build a model that you can in silico ablate certain genes from the cell.

That is an in silico perturbation. That's to say, if I reduce the expression of this gene in a cell, what is the implication for the rest of the cells? What's the biological consequence?

So you basically turned a knob down on one gene.

That'sright.

And then that, what happens to all the other genes in that cell?

Correct. And the hope is, of course, to predict the effect on all the other genes, but maybe even more things than gene expression, such as the function of the cell.

Okay.

And that's important that that's therapeutically relevant because a lot of drugs are inhibitors and they function through exactly that, turning down the activity of a protein or gene. And so we can start with gene perturbation prediction. The hope is that we can also go to pathway inhibition prediction, so on and so forth.

So a pathway is just a set of genes that all kind of talk to each other by this, this gene expresses a protein, that protein has some impact on another gene, and so forth and so on. There's this long chain reaction of, of genes and proteins.

And then, so that, that's called a pathway. And so if you interrupt that or somehow change it, then that has an impact on the, the larger phenotype of the cell, what the cell looks like does, et cetera.

That's exactlyright.

Yeah.

Yeah. So you have what you call a virtual cell or you're, you're creating a virtual cell. And virtual cells are very popular. It's, a lot of people are interested in this concept, but I think your approach is somewhat unique or separate from what other people are doing.

Can you explain what do broadly people mean when they say virtual cells? What are some of the distinct other strategies? And then like, what is your specific strategy that you're going for?

Certainly virtual cell is a very high-level term to describe an AI model that is able to predict or describe what cell looks like or predict the cell expressions or cell functions after certain interventions. It's a very high-level concept.

It, it was, first of all, it was not a novel idea. We had virtual cell project almost 20 years ago, but back then, sometimes we call it virtual cell 1.0, is that people trying to derive differential equations to trying to use mathematics to describe what's the response for certain pathway interventions, as you just mentioned, and by fitting these equations to different observations.

And largely speaking, that was a failed attempt in the sense that the biology is just way too complicated to write in a few predefined set of differential equations. Moving forward, with the rise of language models, I think that the idea of using AI models to mimic how cell responds to different interventions by data-driven approach started to get popular.

And I think 3 years ago, almost just 4 months after ChatGPT was released, our lab at University of Toronto published one of the early foundation models of single-cell genomics called SCGPT. You can kind of interpret it as a GPT-like model for single cells.

And it quickly became very popular in the sense that for the first time we have a foundation model that is able to tackle different downstream tasks using the same model, such as we can use the same model to integrate different batches of single-cell RNA-seq.

We can use the same model to predict multi-omic integrations.

Let's define those things. So batches, integrate different batches of RNA-seq. So you have different equipment, you're all collecting.

Or data collected from different labs.

Yeah. Different labs, different time of day.

Correct.

Different phase of the moon, whatever. And those actually have a big impact on the data that you collect.

Correct.

And so there's a big problem of how do I even compare this dataset to that dataset when there's all this other differences that have nothing to do with the gene expression, just how I measured it.

We call that batch effect. We certainly want to remove the batch effect while preserving the cell types, which are more important biology we want to preserve.

So this is sort of like analogous to the tank problem in image classifiers, for example, is a, is a sort of the models pick up on these crazy, spurious features, which have nothing to do with what you actually care about, the underlying biology.

Exactly. Certainly the core idea of integrating different batches is to kind of keep the biological signals while removing the batch effect. And before these foundation models, what, what happens in single-cell domain is that for every task, biologists have to choose the so-called specialist state-of-the-art approaches.

And

with, with foundation models such as SCGPT or GeneFormers, what we hope to bring is that one model that solves all the tasks in single cells. And with the popularity of foundation model, lots of researchers come together under CZI, Chan Zuckerberg Institute, and we published a perspective paper at journal Cell to coin, for the first time, coin the term virtual cell, almost virtual cell 2.0, in the sense that let's use data-driven approaches.

If we cannot describe, let's learn it. So that's the idea of virtual cell so that generally speaking, can we build a language model or language type of model to predict what the cell types look like, how the cell respond to different interventions, and eventually we kind of, we can replace all the cellular experiments by simply running simulations on computer without even running the actual experiments.

Maybe for a bit more context, you can think about this as, so a virtual cell is just a general concept, but you think cells have 20,000 genes in them. And in most human cells, I think what roughly, you know, 4,000 to 5,000 are usually active at any given time or expressed at reasonable levels.

So you look at a normal cell, you might have 4,000 to 5,000 genes doing things. And so your, your question is, in many cases, the way medicine works is you, you know, you target a protein or you target some sort of, you know, something which makes proteins more common or less common, or they stop the protein from doing something.

And your goal is, given this, you know, some number of genes which are in a cell, every cell has a different composition of genes, what is going to change? You know, will some, some pathway die off? Will some pathway grow?

And how does this, you know, from this, you could predict how medicine is going to work by just understanding how changing one specific gene or some cluster of genes could change everything. Is that, is that a correct understanding?

Yeah, that's a correct high-level understanding about virtual cell. What's happening for this field is that we are lacking a concrete definition of virtual cells. And people almost equate foundation model with virtual cell. I, but in my view, virtual cell is probably a much broader concept than just foundation models.

Foundation models mostly provide a reliable, semantic, meaningful representations of cells. But I think virtual cell is more dynamic in the sense that can we build AI models even predict the, the development of different, the cell states across different times, or even can, can we even describe the spatial changes at the cells, different cellular resolutions?

In my understanding is that we are really at the early stage to develop such comprehensive virtual cell models. And the foundation model is really just the starting point.

AI models always begin with the data. You are building a high-throughput experiment or have built and are continuing to develop a high-throughput experimentation system. Can you, that sounds really cool and really complicated. Can you tell us what that entails?

Like how, what are you doing? What are the experiments that you're running? How does that inform the building of an AI model? And why do this rather than pick up the Cellex gene database, which is a collection of gene expression data that has been aggregated over the public datasets?

Yeah, great question. I want to pick up where Bo left off. I think Bo said something pretty profound, going from a representation model, the foundation model of biology, to a virtual cell. And the key difference there is perturbation prediction or dynamic, dynamic processes in biology.

That's a causal concept. For that, I think we need causal data. And if you look at cell by gene, that's a fantastic dataset that curated at the, in the beginning, more than 33 million cells, now a lot more than that.

And at the time when SCGPT was trained on that dataset coming out of Bo's lab in Toronto, that was mostly a observational profiling dataset. It's a descriptive data, not causal, and mostly profiling healthy human donors. And so the model that was trained on this dataset is very, very good at doing descriptive tasks, such as harmonizing across batch effects, removing effects from different labs, different technologies.

But I think Bo, us, and many others in the field have found that these models that are trained on descriptive data do not yet outperform linear models on causal tasks, perturbational tasks, what we call counterfactual tasks. If I did this to the cell, then what would happen?

That makes intuitive sense to a biologist because the correlation data in the descriptive dataset can be fit with many, many possible causal structures. In a very simplistic case, let's say you observe gene A, B, C all go up and down together in your descriptive dataset.

You can infer that A regulates B and C. That's why when A goes up, B and C also go up. You might also say that B regulates A and C, and that will be perfectly reasonable as well. You could also say that A regulates B and C is completely regulated by something different.

You see the problem there. And there's n number of ways to fit a causal regulatory network into descriptive data. Fundamentally, we believe observational data are underpowered to learn causality truly. And this is why we realized pretty early on that we need to really start training cause, building causal dataset to train a causal model.

So what are the ways to do that? I think the, the field has come of age to do these at scale, technique that we call high throughput biology. And there are many ways to generate these causal data at scale.

The technique that we have focused on is something called Perturb-seq. So for the listeners who are not familiar with that technology, it combines high throughput pulled CRISPR perturbation together with single-cell RNA-seq technology to build 2D datasets. Let me, let me break that down.

Yeah. Please.

So we just talk about in a cell, there are at least 20,000 analytes to measure. These are the genes. These are both the features to measure. These are also the lever to perturb the cells with. So for clarity, let's call them perturbations and gene expressions for perturbation, perturbation on one axis and the features on that you measure that describe the cell on the other axis.

Perturb-seq is a technique that leverages the latest breakthrough in lab biology, CRISPR-Cas9. These are bacterially derived enzymes that allows you to disrupt gene expression in mammalian cells, in human cells, for example. And we can do so in one at a time fashion.

So I can take out one gene at a time. Of course, that would be incredibly difficult to scale if I want to do all 20,000 gene expression knockout in one single experiment. I probably need a huge factory, a lot of robots to do that.

Or you can do them in a pulled fashion. And I love pulled experiments. These are hyperscalable. And so we have lab tricks that allow us to disrupt one gene per cell, but do all 20,000 genes across many, many cells in one single pulled experiment, perfectly scrambled.

So there's no batch effects, there's no play-to-play differences. So that solves the perturbation throughput.

Basically use some sort of combinatorial trick to first perturb all the different genes in different combinations, and then you can read them out and do some math on it, and you basically pull out a whole bunch of different experiments in one experiment.

Correct. It requires barcoding technology. And that barcode is actually achieved by directly reading out what kind of CRISPR guide RNA is present in which cell. So for CRISPR-Cas9, this bacterially derived machinery to work in mammalian cells, you just have to deliver two things to each cell.

You have to deliver the protein, the Cas9 protein that does the, does the job, and you have to deliver an address barcode encoded by a short piece of RNA called guide RNA. And the guide RNA tells the protein where to go in the cell purely via lots of quick base pairing, ATCG.

So it matches a part of the gene. It's sufficiently long to say this will match the correct gene. And then that guides it to connect to theright and, and, and reduce the expression of that particular gene in the cell.

Correct. We design these guides to go to the promoter part of the gene. That's the beginning stretch of every gene before the transcription starts. And if we bring the Cas9 protein to there, armed with theright effector, the silencer, that promoter will get shut off and that gene will never be transcribed out of again.

So effectively, we tune down the expression level of that gene. And so all you have to know is figure out which guide RNA is in which cell. And that can be done using genomic readouts. That's the barcode. And you can then infer which gene is being silenced in which cell.

So that's the way you scale throughput on the perturbation side. On the readout side, it's a 2D dataset,right? So we just talk about one of the dimensions. On the readout side, we leverage single-cell RNA-seq technologies. So these are also recent technologies in the last decade that have been scaled that can let you read out the expression level of all 20,000 genes simultaneously from each cell.

So armed with both high throughput CRISPR perturbation and high throughput single-cell RNA-seq technologies, all of a sudden we can generate these 2D datasets where we systematically perturb or knock out, knock down every single gene in the human genome in the cell type.

And we read out this impact on every other genes in the, in the same cells. So we generate these 2D rich dataset, not that different than the size, the type of PDB data that trained alpha-fold models,right? If you think about that, that's hundreds of thousands of protein entries.

If those are the rows, columns are the XYZ coordinate of every single amino acid. That's also a 2D dataset. And I think it's these type of rich 2D datasets that power the training of foundation models of biology.

I find it really fun how you have turned a fairly straightforward assay in using, I guess this is NGS sequencing,right? Next generation sequencing, very high throughput. You've used this to scale a simple perturbation response, which is indivinquently maybe not all that interesting to this massive scale of over a, basically an arbitrary number of cells.

I think you did 25 million or something.

So it's actually a lot more than that. So 25 million is what came out of the most stringent quality filtering. It's actually as much of a scientific challenge to figure out how to do CRISPR and single-cell RNA-seq as it is an engineering challenge.

In the first part of the experiment, oftentimes we have to harvest tens, if not hundreds of millions of cells, and they go through various quality funnels to arrive to give Bo and team the highest quality data at the end.

That's incredibly difficult to do because, as you can imagine, all of these techniques have been published by academia before, and they work very well in small-scale experiments. But when you think about scaling them to a genome-wide perturbation, we're talking about handling hundreds of millions of cells.

Techniques that are published in academia used to be all about handling fresh cells. Cells are still alive. And that may be okay if your entire experiment takes only an hour or two. It's not quite easy to handle cells across a 14-hour day that's hundreds of millions of cells.

And so by the end of the day, I used to joke with my team, you can easily detect stress signals from the cells and from your scientists in the lab.

Yeah.

And quickly we realized that's not the way to do this data generation. Machine learning is very quality dependent, and we want to give the, the highest quality data to our AI teams. So we're putting a lot of engineering thought and industrialize the whole workflow step by step, introduce chemical fixations so that we lock the state of the cells in at the beginning of this experiment, but figure out ways that it doesn't disrupt all of the biology, molecular biology steps afterwards.

It doesn't impact data quality so that we can do all of these data generation in a time-shifted operational manner that's very not prone to batch effects.

One thing that you didn't mention is that you're using some sort of stem cells. And so, and obviously like you don't have, you know, like brain cells or, or, or blood cells, or if you did, then you would have a big combinatorial effect on that.

So how are you, why are you convinced that working on stem cells, which are, you know, my understanding is that there are actually blood cells that have been sort of the stem cell behavior has been unlocked on them, and, and that causes some, some sort of stress on the cell as well.

So you have these like sort of not quite blood cells that are stressed. And then how, why are we convinced that that is a good proxy for a brain cell or a whatever you're studying?

Yeah, not quite. So we didn't actually start with stem cells. That was more, more of a later development.

Okay.

When we started data generation, so we put out the method that I talk about, as well as the first two datasets, which is the world's largest Perturb-seq data released at the time last June in the preprint, we call it dataset X-Atlas Orion.

That was actually generated from two cell lines. A lot of this field's early work started with cell lines. These are cells.

Cancer cell lines.

One of them is a cancer cell line. The other is just a cell line. These are immortalized cells. Some of them are derived from cancers, hence cancer cell lines. Others are just derived from primary cells, but have been immortalized, many times grown for many, many years in various labs.

People start with these cell lines in the beginning, as you can imagine, because those are easy to do. It's easy to scale, easy to grow a lot of cells out of. Turns out the ability to grow millions of cells is actually critical for doing these large experiments.

So we started there first, and they actually still capture the characteristics of the cell types that are derived from colorectal cancer, as well as hematopoietic cells. But later on, in the most recent preprint, we actually expanded to many more cell types.

Now, some of these are still cell lines, our T cells. We chose to use cell lines, but some of these have now gone into primary cells. So we did one experiment in IPSC. These are induced pluripotent stem cells.

And another experiment in, and we think this is the most ambitious and coolest screen that we've done to date. This is a pen differentiation multi-cell type stem cell project. So effectively, we differentiate IPSC into 10 different cell types in one single experiment without restriction.

And we did a genome-scale perturbation across them. So you can imagine instead of just generating 10,000 different biological experiments, we did 10,000 by 10 cell types. That's almost a library on library experiment. Why are we doing this? We think that in the beginning phase of data collection, as Bo said, I think we're just in the early days of virtual cell building, context and diversity and richness of the data matters.

It's not just the total number of cells or total number of sequencing reads. It's about bits per dollar and information content. So we want to scale not only in the genetic perturbation landscape, but we also want to scale across biological context so that we can give our AI teams the best rich dataset to build a generalizable model on.

Is there any thinking about, so you say context, but obviously these cells in these experiments have been sort of de, I forget the term, but they've been separated from their cohorts,right? Is there thinking about using spatial transcriptomics or other, you know, sort of technologies, imaging-based technologies to build models with perturbations, but within, in the context of the cells that it lives near?

Great question. So we're thinking about that in a couple ways. Number one, that's actually exactly why we want to build a virtual cell model in the first place. You might think that, well, you can already do exhaustive screening in these cell lines.

Why do you still need a model? You can just do the experiment and generate the data. Certainly, if your query is just about cell biology in cell lines, you'reright. We don't need a model,right? At least if for genetic screening, we can just do the experiment.

But you're also correct that oftentimes good targets, biological insights are not about cell lines. These are about primary cells, about cells in their native physiological context in organs or even multi-organ coming together and have some emergent properties. A lot of immunological disease are that way.

You cannot do exhaustive high throughput experimentation in animal systems or in organs or in all of these complex translational models. You can do some experiments, and these are expensive and high stake. The ability to build a model that can be trained on massive data where it is possible to scale and be trained in a way that can be fine-tuned and transferred to make high-quality causal predictions in these complex models so that we can go into the lab and have the highest quality hypothesis possible to validate.

I think that's the whole point about building a virtual cell model.

But from AI side, I think you're absolutelyright that I believe the future virtual cell model should be able to incorporate multiple modalities, not just RNA expressions. Spatial, spatial single-cell RNA-seq is already a popular technology, even for SCGPT. We actually have an extended version.

We call it SCGPT spatial that is specifically designed for spatial single-cell RNA-seq. And we also have papers on early attempts to trying to take the HNE images, trying to predict the gene expressions. There's already some signals you can find.

So eventually what I predict is that a virtual cell model will be able to integrate not only RNA-seq, can integrate more functionally related, for example, protein RNA-seq or other regulatory side of RNA-seq such as ATAC-seq to overall combine all your descriptive RNA-seq datasets to predict the, the future states of the cellular functions.

I think that's probably the, the future for virtual cell model.

We had Ron Alpha and

Dan Baer from Noetic as guests recently. And viewers who want to hear a little bit more about that, I think they, they go, we go quite in depth there. So if you want to, so background, you can go to that, but can you explain a little bit about what spatial transcriptomics and spatial proteomics are?

So maybe a bit of a history lesson here. Before we had single-cell RNA-seq, we had RNA-seq, and before that we have microarray technologies. What RNA-seq and microarray used to do is take a chunk of my tissue, grind it all up, put it in a blender, imagine, make a smoothie out of it, and take the, all of the RNA from different cells in that piece of tissue and measure all of their expression levels.

It is great. For the first time, you can measure gene expression all 20,000 at a, at a time. We used to do them, we used to have to do them one at a time, but it is not great in that we don't know which RNA came from which cell.

And this is particularly a problem if you're dealing with a multicellular piece of tissue. You want to attribute RNA to the immune cell, to the skin cell, to the fibroblast, to the keratinocytes, but you can't because you ground everything up in a smoothie.

What single-cell technology allows you to do is analyze them cell by cell. So now I can attribute RNA gene expression to the cell that they originate from. But there's still a problem. I don't know spatially where these signals come from.

And for many diseases, it matters,right? In immuno-oncology, for example, you want to know when T cells are close to a tumor cells or when a T cell is not able to penetrate the solid tumor, what is the difference between them?

Or when a T cell is attacking the tumor cell, when a T cell is not, what is the difference about, about that? And for that, you need spatial information. You need to observe cell in situ in their context.

And so now there are different technologies that solve that problem. Essentially, take that chunk of tissue. I don't have to grind it up anymore. I just make a cross-section, lay it down in a piece of slide, and I can measure its morphology using standard techniques like HNE staining.

I can then also measure many protein expression using multiplex IF assays, immunofluorescence assays. Ultimately, I can also look at the gene expression up to genome-wide in all of these cells in their native spatial coordinates by using some of the latest spatial RNA-seq assays.

So you have the XY coordinates of every cell, but also all of the molecular analysis that we talked about earlier. And that's an exciting new direction for genomics field.

That's something, can you imagine that the spatial RNA-seq adds more difficulty to AI modeling because you have, instead of looking at the individual cells, you have to look at the neighboring niche cells to better kind of learn the representation that is spatially cohesive.

That is the challenge the current spatial foundation model are facing.

But that context is going to be crucial for, I mean, understanding, let's say cancer where the interaction of immune cells and cancer cells and non-immune or cancer cells.

Yeah, that is absolutely crucial for you to extract spatial-aware biomarkers to predict some of the clinical response. I think that would be extremely important to build such models.

Getting back to X-Cell, this, you know, presumably can inform a spatial model as well,right? Because you, you can, you have like one cell in one place. If you can imagine, okay, I can just throw away the coordinates and just get, do inferences on one cell at a time, and now I can create, I can create a more complicated model that does that, but it also knows who its neighbors are or something.

You're absolutelyright. But the current version we were releasing, we're not dealing with spatial RNA-seq. However, definitely our ongoing work and the next version of X-Cell will be able to infer the spatially aware representations for different cells.

I see. We've talked about the data collection a bit. Let's talk about the architecture. Get some red meat for the, for the AI engineers listening in.

Sure. Let's get to the history of virtual cell modeling, particularly virtual cell 2.0. I think our SCGPT kind of sets the foundation for most of foundation models of single cells is that we adopted kind of autoregressive training, extremely similar to how ChatGPT is trained on languages,right?

We use its next word, next token predictions. So we mimic the way how ChatGPT is trained on languages to train the single-cell foundation model on cells. By doing that, it has to assume an inherent order of genes,right? The way we assume the order of genes is by attention mechanism.

There's many other methods that are using different orders of genes. Some, some as simple as just rank the genes based on the expression values. There's also more complicated kind of methods to rank different genes, but inherently you have to have assume an order of genes.

And just to be clear, so when you talk about genes, those are intrinsically ordered,right? They're a sentence spelled out in ATGC,right? So genes themselves have this, the nucleotides and there's this long chain, and that makes a lot of sense to have an order to them.

But what we're talking about is something different. That's the expression data, the expression levels. So the expression level means how it's just a count for each gene of how many of these genes did I see when I was measuring.

For gene sequences, the order of ATGC makes total sense to us,right? But for expression data, they're literally just matrices. So it's really hard to assume an inherent order of genes. Even if we shuffle the, the order of genes, I think the biology doesn't change much.

However, because of the way kind of language model is trained, everybody has kind of preset tricks to train such models. So it's easy to adopt. That's how all the foundation models are started for single cells. And then I quickly realized that with diffusion language models, we actually don't need to assume the order of genes.

Instead, we can have a bidirectional diffusion process to generate such long, high-dimensional gene expression datasets. So just to think about it, what's the difference between autoregressive training versus diffusion language models? Is that you kind of, you can think of autoregressive training as typing.

There's, for example, I like coffee, you have to type I and then like and coffee. There's inherent orders. But diffusion language model, you can treat it as editing. You iteratively generate a sentence from a very vague, very rough sentence, and then you can iteratively refine it.

So same thing with gene expressions. You can generate a very rough representation of the gene expressions and then iteratively from noisy representation to more refined representations. So you kind of iteratively edit the gene expression predictions until it minimizes the losses.

So this is a very different philosophy to generatively predict the response after perturbation. And turns out it actually fits more to single-cell RNA-seq. So that's why we switched from SCGPT-like model to the current X-Cell model, which is using diffusion language models.

When I think of transformers, like they're fundamentally objects which operate on sets. The community spends a lot of time trying to make them things which have some sort of causal ordering to them. But if you just naively take your transformer, it's, it's a set operation,right?

So given that, why think about this in terms of diffusion or, you know, autoregressive LLMs? Why not have your initial prediction strategy be something like take a, a just a set of genes, each of which has its own kind of one hot encoded identity, and then use that as sort of a prediction.

That seems like a much more natural architecture to me. And I, it's not just, you know, your work, a lot of people work on things like this, and I have been somewhat confused why there's this bias in the community about this.

Yeah. That's, that's a, so I think what, what you were referring to is more related to representation learning, where you can take sets of genes and trying to project to low-dimensional latent space. But what we care about for building generative modeling for, for virtual cell, because you want to predict the dynamics of cells.

So we want to have a generative models. So that's why we're mostly using decoder-only architectures in order to generate the full transcriptomics instead of just predict a predefined small set of genes, because you want to model the whole gene, gene, gene regulatory networks, which are extremely kind of high-dimensional,right?

So just to be clear, input is genes plus a perturbation, output is new gene expression levels. Is that gene expression levels plus perturbation is input, output is.

Plus times cells, number of cells.

Like for each cell.

Correct. Correct. That is correct. Yeah.

Right. Okay. And so the, the way that I think about, the way I think about diffusion language models, and you can correct me here 'cause I don't know a lot about them, but the way I think about them is they're like BERT, but you do it over and over again.

Is that, is that kind of a good idea?

That is a, yeah, that is a rough understanding of how diffusion language model works.

Yeah. So, so you just apply the diffusion, the diffusion process is like basically unmasking or editing once to over and over again. The, the similar to how like an image diffusion model kind of refines the image over and over again.

In this case, I'm using BERT. So it is a transformer basically.

It is a transformer architecture.

But it's like repeatedly updating the, the sort of sentence in this case, which is a bunch of expression levels over and over again.

That is correct. Actually, in our paper, we show that as the number of diffusion steps goes on, the, the loss function keeps decreasing, the, the, the fitness of the prediction to the ground truths keep increasing. So this, which means the model starts to understand how iteratively refine the predictions.

I see. We're talking about diffusion versus autoregressive. What, what there, I noticed in the paper, there's a bunch of discussion of preconditioning using a whole bunch of stuff. Can you want to talk a little bit about that?

Yeah. Another major innovation we made in X-Cell is the way we incorporate prior knowledge into the model. So incorporating biological priors has always been a good idea in biology in general, because biologists spend, you know, decades to, to understand some of the biologies already.

How do we tell the model some of the prior knowledge, some metadata about the cells? Before X-Cell, what people do is they, they try to incorporate a single type of priors. For example, GEAR using gene regulatory network as a prior to predict the perturbations.

SCGPT sometimes trying to incorporate PPI as a prior as well. X-Cell, to my knowledge, is one of the first models then trying to incorporate an extremely diverse sets of biological priors. So in our preprint, we incorporate five types of priors, including literatures as simple as just ask ChatGPT, tell me everything about this gene, and then we embed the output as an embedding to.

That's a GNPT.

Exactly. That's a GNPT. And we also incorporate PPI, protein-protein interaction networks. We also incorporate DEPMAP, which is cancer-related essential gene informations, morphology informations. We even try to incorporate SCGPT embeddings, which is basically cell types. So we use a set of prior knowledge as conditions to the model.

The model starts to have more accuracy in terms of context-specific predictions. And what's more interesting to us is that by looking at the weights of different priors, we can actually understand which prior knowledge are more important to these particular cell types.

So it adds more interpretability to the models. So we find that combining diffusion language model plus a very diverse set of prior knowledges, X-Cell does much better in generalizing to unseen contexts. So this is some of the AI innovations we made for X-Cell.

Do you now need to provide all of that context in order for the model to work, or that those are like preconditioning that it can also do without if you want?

We don't need to incorporate these prior knowledge anymore because these are already learnable parameters inside the models. However, what you suggest is more prompt or in-context learning for virtual cells. We can do that as well, basically by adding more conditions into the prior knowledges so that to prompt the model to predict towards certain directions.

In other words, you took it, you, the model now takes advantage of the learning using the, the priors that you provided during training and doesn't need them, but it, but it has some advantage because you provide them during training.

But you can even get more advantage if you are able to provide those priors during inference.

Yeah.

Okay. Wow. Nice. Yeah. How much does that matter? I mean, whenever I see big machine learning papers with tons of things thrown in, I'm always wondering, where's like the big alpha and where's the little alpha? How much are, you know, is this just some, are these adding this little bit of incremental performance boost or, I mean, are all these actually crucial to general generalization?

So there's multiple factors we have to consider. How much contribution the data contributed, how much of the contribution the AI architecture is contributed. Even for the architecture, what's the outcome from switching to autoregressive training to diffusion language model?

What's the outcome from the prior knowledges? Certainly all of these needs very specific ablation studies. From empirical experiments, we find that the qualities, the amount of the datasets matters the most. This is why we were extremely excited to, to, to publish the PISCES datasets, which has 16 different cell types and across 25 million cells, and it's genome-wide.

You have kind of a huge tensor if you really think about from computer perspective, genome-wide perturbation, genome-wide transcriptomics, plus number of cells, plus at times number of conditions. So it's a massive tensors. And those, and because of the post-screening technology, we don't have batch effects.

So, so you don't, you don't need the model to climb the hill of batch effect. So that's already an advantage. So we find that trained on perturbation datasets, high-quality perturbation datasets already give a big boost to the models.

We also did ablation that if we train all the virtual cell models out there, including state cell to sentence original SCGPT on the same datasets, what's the outcome we are observing? We, we reported the results there as well.

We find that switching from autoregressive training to diffusion language models give a significant improvement over some of the harder tasks, particularly generalized to unseen tasks. And the prior knowledge more or less condition-specific. For certain cell types, some of the prior knowledge make a huge difference, but for certain cell types, the delta seems to be marginal.

We are thinking about, you know, how to better incorporate the, the prior knowledge. We still believe that let the model know a big chunk of existing biology should be helpful, but maybe it's the way we incorporate the prior knowledge through cross-cross attention limited the, the scope of the metadata.

But I think it's certainly a, a research topic. But overall, if we have to give an order, my order would be the quality amount, scale of the datasets, and then the, the architecture, and then the prior knowledge. But certainly this is only applies to our X-Cell.

I'm, I'm sure there's different choices of architecture have different ranks of contributions.

First of all, this is really fascinating. Very cool model. I hope everyone has a chance to look at the paper. There's a lot of, obviously a lot of resources that were put into doing this. I don't know if you guys can disclose how much.

It's a lot of money, whatever it was. Operating wet lab, probably very complicated training runs. I think there's a couple 4 billion parameter model. Is thatright?

4.9 billion.

Yeah. 4.5 billion parameter model. So much larger model. Probably took a lot of GPUs to train. What's the lift that you get from this effort versus let's just put the money into like wet lab work and the sort of traditional pipeline that, that, you know, basically has been the status quo up until now?

Biology is a multi-skill discipline. There are cells, there are DNA sequences on the most fundamental level. There are cells, there are multicellular pieces of tissues, co-cultures. You have tissues, you have animal systems, and finally you have human. I think we would like to be able to do causal prediction towards theright of the spectrum, ultimately do causal prediction in human, know what drugs will work in which patients, but that's very difficult to collect high-throughput data on.

And so the whole vision of virtual cell is to generate data where it is possible so that we can transfer the causality prediction towards theright, towards the more translational, the more complex systems. The, certainly you can mine the data already.

We generated a lot of data, as Bo said, seven screens, 16 different biological contexts, genome-scale perturbation. There's a lot of good ideas in that already. There's a figure that we put out in a preprint that just look into inactivation of T cells.

We already saw some, you know, we saw known biology, TCR complex. We also saw some putative new biology, which we're very excited to validate in the lab. Some of that were actually also caught out in a very recent screen last December published from Alex Morrison Lab, also in the Bay Area.

So very excited to see that. But the hope is to not just mine the existing data. The hope is that the model can generalize and we will be able to do in silico experiment into the future. Nobody knows before how much data and what kind of data are needed to do that.

The whole field is waiting for the demonstration that the model can beat linear baseline in perturbation prediction, and it can generalize out of context, not just within a cell line you have training data on, but out of that context.

That's where, that's why you need a model. So what's very exciting for us is that in this preprint, we saw that generalization capability. A few demonstrations. We first did in T cells. We actually generated the data expressly for this purpose.

We generated a resting T cell perturbation screen. So these are T cells in their baseline condition, not activated. And then we have a activated T cell perturb-seq.

So I just, T cell activation means I'm going, I'm trying to kill something.

No, these are, these are regulatory T cells, but yes, we activate their receptors so that they're starting to proliferate.

Okay.

They become more active. They can do their physiological job. And we only, critically, we only train the model on the resting T cell. And we told the model, hey, this is how the active T cell look like. Now go and predict what all of the perturbation are going to do in this active T cell.

And the model have not seen how perturbation work in active T cells. And we set up a couple of rigorous tests. One, linear baseline. Took the perturbational delta in the resting case, just transpose that linearly onto the active T cell, and that's our linear baseline.

Essentially, think about this as a combinatorial perturbation prediction problem. One of the perturbation is activation of the cell. The other is all of the genome-wide perturbations. Can I just linearly add the two effects together? That would be a linear baseline.

And second, we apply other models from the field. And last, but we applied X-Cell. Critically, X-Cell has not seen active cell, T cells. And it's able to make accurate prediction not only on the known biology, the TCR complex, predicting their effect accurately that these are going to inactivate the T cells, which is exactly what we would expect to see, but also it predicted the putative T cell inactivities that we found in the screen correctly as well.

So that's very exciting to us, and that suggests a possibility that we might be able to use these virtual cell models completely out of context in the unseen context and predict new biology. And so we're very excited to follow up on those hits and validate them in the lab.

Just very briefly, a couple other cases that we saw exciting generalizing capability of this model. Remember we did a multi-cell type differentiated IPSC experiment. There we specifically held out one cell type from training. So the model has not seen that cell type.

Trained on the other cell types as well as the rest of the datasets, the model made very good prediction across thousands of genes, thousands of perturbations in that unseen cell type. So again, suggesting the model's ability to generalize out of cell type.

And the last experiment I think we're very excited is that we trained this on T cell cell line, but there was just very recently a primary T cell perturb-seq published from Alex Morrison's lab. That's a impressive amount of work.

It's not easy to do this scale screening in primary cells. Very few labs have that kind of capabilities. Much easier to do that in T cell lines. Again, the model is able to generalize out of cell lines into primary cells and make accurate predictions there.

So they actually perturbed primary cells, not, not cell lines.

Primary T cells harvested from donors. And we were able for multiple donors. And X-Cell trained on just one T cell cell line is able to make predictions in across multiple donors from primary T cell experiments.

This is a validation of the whole theory,right? That you can train on these slightly weird cells and that it will be good because, you know, you're covering the, the domain well enough or whatever it is that you're able to actually predict in real, real cells that come directly from real people.

That'sright. Yeah. I think building virtual cell is not to replace biological experiments, as you mentioned. What we're trying to do really is a holy grail of virtual cell is to have a model to generalize to unseen context that is harder or even impossible to, to, to conduct biologic experiments on,right?

So far, X-Cell focusing on cellular cell lines, and eventually we want to extend to more complicated biological systems such as animals, organoid, and eventually, as we mentioned before, to patients, to human, human biology,right? And bear in mind a few numbers.

90% of disease has no cure, and most of the drug failed at the phase three clinical trials on patients. And the success rate of phase three trials is as low as 5 to 10%.

And phase three means?

The final stage on the patient trials.

So that's when you generalize from toxicity in phase two to efficacy in phase three,right?

From a small cohort.

From a small cohort.

To a much larger cohort.

Oh, sorry. Toxicity is one,right?

Phase one. Toxicity is phase one.

Small cohort. And so a lot of.

To a large cohort.

So the generalization problem, okay, this drug, I've very carefully selected my patients and it works pretty well, and now I get a bunch more patients and suddenly it doesn't work very well. And that's the big problem that you're.

Yeah. So certainly the promise of virtual cell is that can we build such a model that learn all the causality of biology so that can be grounded to predict the response on, on eventually on patients so that we can for certain drugs, we can select theright patients to conduct the clinical trials on,right?

Certainly this is a long-term vision, but we are already see some early hopes that X-Cell trained on diverse set of causal datasets can already generalize to some, some unseen cell types. So certainly there's a lot of experiment to be done to validate this model.

So even continuously fine-tune this model. But I think that we certainly see some early hopes.

So you were talking about linear models, and this brings up this famous or infamous ARC challenge about, you know, perturbation. And there's this been this theme about complicated foundation models oftentimes not beating linear baselines. And I'd like to get your take about that as terms of what is this, you know, first of all, is this different?

I mean, I think some of maybe your own models might also have had trouble beating linear baselines in the past. Is there something different about your current data strategy or where you're going and where's the field going? And what is the role of foundation models versus virtual cell models versus, you know, these simple baselines?

Yeah, a few things. First of all, those benchmarks, as you mentioned, are conducted on reprobable datasets, which are very small datasets. And the metrics people report are mostly MAE. Certainly you can imagine if the, because single-cell datasets are so sparse, the average profiles of all the cells certainly you kind of, you can imagine it's a great minim kind of local optimum to minimize the MAEs.

This is why sometimes the average profile of cells has lower MAEs even than technical replicates, which are considered of ground truth for, for kind of perturbation experiments. So that itself shows that that metric is not reliable. However, most of these benchmarks are still comparing foundation models that train on static expression datasets such as cell by genes.

SGBD is often benchmarked against. Internally we also find that when it comes to MAE, sometimes SGBD kind of fail to outperform linear models just because of the reasons I just stated. And what sets X-Cell different from these static expression models such as SGBD or GeneFormers is that we actually, instead of training on gene expression datasets, we train on causal datasets.

We train on massive amount of genome-wide perturbation datasets so that it learns better about the dynamics of the interventions. And in our preprint, we extensively compare with linear model as well. And as Chu mentioned, linear model totally failed to extend to unseen cell types.

You can quickly imagine why. And I believe that foundation model or other more complicated AI models that train on theright data will outperform these linear models in harder tasks, particularly in generalization tasks. And that's why I keep mentioning theright dataset with theright AI model will lead to huge improvements.

But I think the field still needs to see more biological validations to be more convincing that the virtual cell direction is theright one. Yeah. I think the field suffer from a lack of consistent and uniformly accepted benchmarks. What gets measured will get improved.

And in our paper, we measured, I think the one of the metrics that we put a lot of thought into and saw the model really shine is metrics around gene expression changes. So, you know, Pearson delta, the similarity between predicted changes and ground truth changes upon a perturbation.

That's very hard to cheat on. You have to really get the changesright. And what really blew, blew my mind away is when I saw the model make prediction, just print out the heatmap of the gene expression changes. Look at the actual raw data and line up the linear baseline prediction, the ground truth, and X-Cell prediction altogether.

It's visually very clear to see that X-Cell prediction is very much more similar to ground truth than, than the linear baseline. This is a wow moment. I was talking about in the beginning.

That'sright.

And it's not hard to understand why when we put. So this is the first time that someone can put together not just one perturb-seq, but seven genome-wide perturb-seq campaigns together. Something that jumped out to us biologistsright away is that some of the perturbations are context universal, meaning that the genes do the same thing in regards of the cell types you experiment in.

Might not be surprising to you that these are your housekeeping genes,right? Of course, they do the same thing every cell. And then there are all of these other clusters of genes that have very context-specific functions. They do different things in different cells.

Again, not hard to imagine why. In IPSC synarr stem cells, we saw developmentally relevant genes, genes that are important for neuronal differentiation. They only light up in IPSC experiments, of course,right? That makes sense. So think about biology. It's so complicated that you have to capture these, you know, context universal perturbation effects.

You also have to somehow learn the context-dependent perturbational effects. It's not hard to then see why a very sophisticated nonlinear model is able to capture and learn all of those biology much better.

Are your perturbations always single gene perturbations or do you have more? Because my understanding of regulatory networks is oftentimes, sometimes it can be a single gene does a ton of things. For example, I think males are just differentiated due to one gene being enabled at like day seven of embryo development or something.

And that differentiates everything. It's this one gene. But then sometimes you have large networks of genes, which all are very redundant, which allows for more subtle feedback mechanisms and so on. So I could imagine a lot of single gene perturbations as being kind of irrelevant and that you might want to start having a more combinatorial strategy here.

Yeah, that's a, that's a great question. And Bo and I have thought about this a lot. Actually, it's interesting that you brought up reproductive biology in, I study a lot of in female cells, the compensation, the dosage compensation mechanisms.

There are female cells have two X chromosomes. Male cells have one X chromosome. To match the dosage output from the X chromosomes, strategy that the mammalian cells employ is one gene that produce a RNA that does not encode for any protein, just a non-coding RNA.

That RNA wraps around one of the female X chromosomes and turns down most of the gene expression from that chromosome, shove it away in a corner of the nucleus, and it's called a barb body. It is never heard from again.

And so absolutely agree with you. One gene can do a lot. But in biology, you also have redundancy. You have compensation. You have all kinds of mechanisms where knocking down one gene is not sufficient to always see a phenotype.

What if four genes redundantly do the same thing,right? Taking out one is not going to be sufficient. So where we started with one cell type at a time, loss of function, single gene perturbation, and look at only RNA expression as the output, we're expanding the platform along all of those axes.

So that's what we do today to build a scaffold of the data for training models like X-Cell. We are now beginning to grow in all three axes of the platform, going beyond transcriptomics alone to look at multimodal data, going beyond just one gene perturbation alone to look at also pathway activation and inactivations, turning on and off entire cascade of gene train reactions.

And also going beyond just cell lines, monocultures into more and more complex translationally relevant systems, into primary cells, into organoids, and doing even direct in vivo perturbation screens. So we believe with all of that expansion, the data will be all the more exciting to train models on.

This is also why we incorporate PPI networks as a prior knowledge into our model. And, and although the modelright now are trained on single gene perturbations, but once the model is trained, you can actually predict combinatorial perturbations just on the model in only silico,right?

So in the sense that you can just perturb the tokens of two genes at the same time and see what's the response. Certainly without training the actual combinatorial perturbation datasets, the accuracy may not be there, but at least with the existence of such models, we can start to generate hypotheses using insilico perturbations.

How do you see the role of the scientists changing in the age of AI? And you, you may, because you're, you're not using, your, your focus is not language models themselves and agentic science and things like that, then you may have a different, slightly different take.

You're building, you know, these very specific models. But still, one, how are you and your students able to maintain such a high pace? And I suspect it may have something to do with generative AI partly, but also, and how do you see the role of the scientist, the academic changing?

Yeah, that's a great question. So my official split of time is 80% on Xara, 20% on my university affiliations. But turns out the reality is 100% on Xara, 100% on the university office.

You admitted a time machine. That's the answer.

So the way I try to keep up is certainly we, my lab use lots of agentic AI trying to monitor all the AI papers every day and which every week we have lab meetings. We try to discuss different topics in AI for biology, AI for healthcare, et cetera.

And it's, it's to be very frank, even as a professor, I find it's extremely hard to catch up. The pace of AI is just so incredibly fast and to the point that sometimes I feel anxiety waking up says, oh my God, this paper already, so many papers published and what happened to our existing unpublished work?

And certainly you can imagine students probably face 10X anxiety. So sometimes I try to encourage students to really kind of using different tools, trying to stay focused, you know, finding the niche areas that we become an expert on,right?

But with the era of generative AI, now agentic AI, I find the way people, at least academics does science, are extremely different now. Overall, most of professors or students in academia start to be very struggling in terms of fundings, in terms of the pace of publications.

And that's why you can see lots of major breakthroughs come from industry,right? Like AlphaFold, for example. So how academics survive or even thrive at such era of agentic AI is certainly something everybody is thinking about. We see lots of faculties left university and join industry for simply for the reasons of resources,right?

If you are doing research on AI, do you have enough GPUs at your school? It's the first question you should ask when a student join a professor's lab. The first question they often ask is, how many GPUs do you have?

Right? So certainly in that sense, industry has a major advantage over academic labs. But I think what academics labs have advantages on is really the kind of the pace of innovations and also the niche areas as this specific academic lab can be extremely expert on.

So also having the, the freedom of thinking sometimes also make you easier to innovate on ideas that maybe industry people didn't even think about. Overall, I think the whole field needs to be a lot more innovative to catch up.

And hopefully with, with the help of different tools and, and hopefully the government start to invest more into academia because I still deeply believe that academic is the main sources of innovation for the whole field and particularly when it comes to biotech.

So hopefully we, we see more investment into academia so that we stay afloat.

I agree with you, but, but why? Why do you think that it, why, why shouldn't the money just go to industry? Why should the government put any money into academia?

I still believe the power of, you know, academic freedom. This is actually the, the original motivation we have such the existence of academic professors who not only we teach, but also we do research. And there's also benefits of teaching and research at the same time in the sense that when you teach a subject, you actually have to become the experts on and that force you to keep updating your knowledge base and then find easy ways to convey your knowledge into students.

And by doing that, you actually start to innovate on different ideas. And, and myself, for example, I teach a big class in University of Toronto about deep learning and neural networks. It's a gigantic class with 600 students every year.

And by teaching that, it forces me to update, update the slides, lectures every year. And myself reading lots of materials, trying to update myself so that I can find ways to convey some of the knowledge into to students,right?

So that's how I keep updating myself whenever there's chance. I remember vividly we have GPT-2, we updated the lectures and then different language models, how the multi-thread GPU communication is used in training larger scale neural networks, et cetera.

So I force myself just update the models. And by talking to different students, we really generate lots of novel ideas to apply the cutting edge AI models to very specific niche areas in biology or in healthcare. Maybe it's unique to Canadian academic system.

By being a professor in academic, we also have access to lots of healthcare datasets, which are very hard for industry to access due to many legal reasons or regulatory reasons. And that's why you see some of the papers we publish through academic hospitals in Canada where we developed some of the state of the arts foundation model for ultrasound images.

So that's what I mean that there's certain level of freedom of academic thinking that really drives lots of innovations. And I still believe, maybe it's biased, but myself still believe that having certain level of freedom of academic thinking will lead to lots of kind of innovations that is unthinkable in industries.

I 100% agree with Bo there. So, you know, just thinking about the lab workflow that we do, a lot of these are building upon innovations that were first pioneered in academia as well. CRISPR, of course, was discovered in academia.

CRISPR applied to mammalian high throughput screening, also demonstrated in academia first. Single cell RNA-seq, this kind of droplet encapsulated single cell RNA-seq first demonstrated in academia. Then different companies tried to build it up into commercial offerings. Putting all of these together to do perturb-seq at first, also pioneered in academia,right?

Chris Box Lab, Jonathan Weissman's lab, Evi Regev's lab, many of the pioneers in academia. And then I think these, especially on the lab side, these innovation takes so long and the discovery process can be so accidental,right? That it's perhaps not ideal for pure industry to take on.

But once they show early promise, scaling them and robustifying them and generating data that's not only massive but high quality, especially for AI scale, I think that's something that can be very well done in industry. Both the mindset as well as the kind of the resources that we can support, that sometimes can be hard for academia labs to match.

Xaira has been very generous with releasing your datasets and your models. You've been, seem to be very committed to open science. Given some of the things you were just talking about and, you know, the discussion about like what is the best, most important data strategies for virtual cells or understanding human biology, where do you think academia should go next, now and next?

Since, you know, Xaira has probably a budget comparable to, you know, probably dozens or hundreds of bio labsright now. What do you think that if you are an academic, a professor, especially in a wet lab, what would you want to be focusing on?

First of all, myself is a deep believer of open science. That's why all the models we talk about here, data are open source. You can find all the data weights from my lab GitHub.

It's very thorough.

Yeah, thank you. And the reason I believe open science is that, as Ciu mentioned, most of the time academic lab, we started an idea and we proved it. It's not scalable. It's not even a good product. And industry can take it to scale things up.

This is also why SCGPT quickly become one of the most widely used single cell foundation model in pharma companies. So that's very encouraging to us. And this is why Xaira is also start to open source some of the datasets, some of the models.

Part of the reason is that we believe virtual cell is such an early field and it doesn't help to withhold certain datasets or certain models because it's so early. A better win-win situation is everybody gets to in this field start to contribute data together, start to contribute models together to exchange ideas so that this field can move, move forward in a much faster pace.

We see successful examples in protein space,right? Because of the availability of open source datasets in PDBs, therefore we have models such as AlphaFold, Rosetta Fold, again, AlphaFold to also open source. Therefore we can quickly iterate different models. That's why you see kind of a booming situation in protein space.

We want to do the same thing for virtual cells. Let's put all the datasets together. Let's have the same standard protocols to generate high quality datasets. Let's put all the resources together to generate next generation of virtual cell models.

When it comes to academic labs, certainly Ciu can comment on wet lab, how wet lab academics can survive. But from dry lab perspective, I do encourage all the, you know, dry lab AI researchers in universities start to collaborate with industries so that they can get more resources to develop their own ideas.

And with the era of agentic AI, now everybody can code. So it's more important to have aright taste about your project so that you don't just let, just burn tokens without purpose,right? So we want more academic students, academic professors to have higher taste of research so that we, we, we makes theright utility of agentic AIs.

As a professor, your job is to have taste, obviously, but as a student, how do you develop taste as in a world where so much of the thinking scientific process could be essentially outsourced to an LLM or a, you know, some, there's not a world where you're forced to bang your head against something and learn taste by the hard way.

This is why we need academic training where you get into a field you know nothing about. And hopefully after you graduate, you become the expert about this particular topic in the world,right? This is why you have to go through different programs to talk to your peers, talk to your professors to get an idea about what's a good research taste to, to begin with.

And, but more importantly, I always teach students that the best way to learn something is to just program it. By programming, you kind of know what's the details hidden in, in all the mathematical equations in the paper, which often you omit.

But in the era of agentic AI, since slight different in the sense that we used to spend lots of time coding, a little bit of time just debugging, but now we let the agent do most of the coding, but we spend most of time debugging, which seems to be definitely interesting to me.

And we had lots of discussion with the students in the lab, what's the best way to spot bugs by, by AIs? So how do you find places where AI is particularly good at? Also, how do you find places AI are still limited at?

It's kind of, you need lots of trial and error as well. And in the end, you still need to kind of validate your model using real world evidence,right? So that's why collaboration with wet labs, collaboration with clinical teams to validate your model, provide a feedback signals to, to your taste, as, as we discussed, is certainly a very important training program.

On the wet lab side, academic has extremely important roles to play. I think we'll enter a field of an era of symbiotic innovation and cross-pollination of ideas. Just like in AI field, I think we have great ideas coming out of academia still all the time, but industry now increasingly are contributing new ideas on architecture, on all of that as well.

In the wet lab side, certainly industry seems to be able to scale this type of data generation quite well. But biology is so much more than just cell-based perturb-seq. Beyond RNA-seq, we would like to measure many other analytes,right?

Proteins, metabolites, lipids, protein-protein interactions. How do we do that at scale? Beyond individual cells, we would like to be able to measure cell cell interaction, spatial, cell in their native context, or even whole animal level in vivo perturbations.

Again, how do we do that at scale? Lots of great innovation coming out of academia. Actually, just one great paper last week. And so how do we connect all of these together? I think we have many years of work ahead of us to fully crack data generation for all biology.

And that, I think we need the scale, the industrialization, the innovation from industry. We also need that from academia. I think we'll together move this field to the next level.

One question that we've been trying to ask everyone is in your field, which you could say maybe is AI and, you know, sort of high throughput experimentation or however you want to define that. If you could wave your magic wand and have a bottleneck removed for you or a key problem solved, what would that be?

Protein.

Okay.

If there is a way to do protein sequencing or high throughput protein measurement, the same scale that we can do genomics, that would be amazing. You know, I'm training genomics field, but if I can do that, I would incorporate that technology in a hard speed.

RNA is amazing. It foreshadows which proteins are going to get made. But protein, by and large, are the functional units in a cell. Not only does their abundance matter, their post-translational modification matter, their localization in the cell matter.

If you can measure all of those things, their conformational states, their modifications, their abundances, their localizations at scale, single cell or even spatially, I think such data sets would be incredibly useful to train the next generation of financial models.

I know there's a lot of innovations in that direction. Can we just see that become, come of age? My hope is, I hope to see a breakthrough in sequencing technology, not just the reduced cost, but sequencing technology that can sequence the same cells at different time points.

I think this is much lackingright now because you have, in order to sequence the cell, you have to kill the cell,right? So can we have a technology that can measure the cell states at different time points for the same set of cells?

I think that will bring a very different dimension to the dataset so that we can start to measure the temporal dynamics of cells. So far, everything we measure, everything we model is extremely static. So can we have a technology that measured different cell response at different time points for the same set of cells will unlock massive opportunity to kind of model the dynamics of cells.

To me, that is the real virtual cell.

That's a really interesting idea. I never would have thought about that. Wow. Would you be okay with even just partial, like small snippets of genes or maybe three prime regions of a small number of transcripts?

Yeah, we can start with a small, small set of gene panels to begin with,right? But eventually, if, if, since we are talking about the magic wand here, eventually, if we can have a system that observe how cell evolve at different time points and we have enough data to actually model such development, I think that would be real virtual cell modeling.

There's small attempts in, oh, sorry, earlier attempts in just, for example, sucking out portions of the cells, taking almost biopsies from the cell to do, you know, a fraction of the cytoplasm measurements. So that might be similar to the idea you talk about.

There's also work from Paul Plantley's lab to have the cells secrete little vesicles and they harvest that in the cell, in the cell culture media to measure what the cells are, you know, producing longitudinally. But there hasn't been technology that can let you measure the entire cell transcriptome while still keeping the cell.

You can't have the cake and eat it.

Yeah. Cool. Yeah. Thank you for taking the time to chat with us. It's been great. Learned a lot. It was a lot of really interesting discussions. And I think, and I especially really appreciate your commitment to open science and all of the cool models and data you've released.

Is there any last, like, thoughts you have or anything you'd like the audience to know, follow up with?

Overall, I think virtual cell is such a new and fast moving field. We hope to have more and more people join us and our excel paper is out and we look forward to receiving your comments and feedbacks. And also we are hiring.

Yeah, we are always looking for talented engineers, technologists, biologists, drug hunters, AI scientists, computational biologists. So look on xaira.com, look for the open roles. We'll be happy to chat with you.

Thank you.

Thank you very much.

Great. Thank you.