Latent Space: The AI Engineer Podcast
00:02:56 · Fabian Theis
[00:02:56] S0: I should disclose before I sort of go to the answer that obviously my opinion is quite academic in the sense that whenever I talk to my friends and colleagues that really sort of day by day sit in in the startups, they have like like what I sort of have as an overview and sort of a bit of intuition what the different research labs do, they have the same thing for the startups. And they know this is sort of the the hot big thing that, you know, this and these investments are happening. I don't really have that on on on that scale. But having said that, for example, you you you you mentioned a Biohubs initiative, which, by the way, is also heavily coupled to Human Cell Atlas, which is sort of this international, really worldwide consortium that sort of pushes this next level of data set generation. I do think that there's a whole bunch of reasons why we're going to see that sort of scale up from all these models working well in terms of being generative, but also sort of lab in the loop on the molecule level now being exported and sort of really working one level up on the cell level. And I think there's a bunch of reasons for that. And the first one, think, and maybe the most important one which you really hit here is the data generation. I think we had that concept of a virtual cell for a while. Like my lab, we started this perturbation prediction modeling and and using machine learning in 2019 with a paper we called scGen at the time, which was like... It was a nonlinear model, but essentially sort of in the latent space did some linear transformation, and it was actually quite okay. And even nowadays, many of these sort of pseudo linear type of things are still doing a good job, but the reason for that being that I think the data sets and the questions that we asked on top were just sort of still on the simplistic side, that's why also sort of it didn't yet take up. So whenever people talk about virtual cells, maybe ask you a question, I think what you actually ask is how does... Can you predict how a cell would behave under all kind of perturbations? And that's sort of, I think, a quite deep question.
00:04:43 · Fabian Theis
If you really think about it, that's maybe even a bit of a holy grail in computational biology or systems biology, sort of this this input output system that is a cell with memory and, like, with all these specifications and with all the different sort of levels of molecules and so on, not just RNA, I I think being able to map this out, what does even understanding mean? And I've been... This is sort of a bit of a meta problem, but I I think you understand at least your modeler system very well when you sort of predict its output behavior given different inputs. So I think it's a very good question, and this is why often people nowadays equate a Virtual Cell with perturbation prediction. I think it's a bit too simplistic, but I think this perturbation prediction type of models and that sort of being, maybe what you mean by Virtual Cell is taken off a lot, and the startup landscape, I think is a bit exploding there. We talk, I think, a lot about US Europe, but also in the Chinese ecosystem, there's a lot of these additional efforts now happening, and I hope that these are not just sort of now a kindling off of a flame because everyone sort of adds AI to their things, but be because pharma is really desperately needing to be cell type context specific in their screens, which at the moment they can't do yet on that screen.
00:05:51 · RJ Hanaki
[00:05:51] S1: Maybe you could expound a little bit on what does this... So perturbations right now that... Like, we talked to Xaira recently. They're doing these perturbation screens. What does that unlock? And then what are... What do you think the next generation of data is going to unlock in addition to that?
00:06:07 · Fabian Theis
[00:06:07] S0: I mean, for for me, if I may, you stop me when I'm sort of getting to put to put too much into these these these old stories. Like, you know, I'm sort of... I'm I'm I'm I've been trained machine learning scientist for the longest time doing all kinds of things, but, you know, I started with single cell early on, qPCR. Maybe initially, if I'm really honest, not so much because it was like the biology that was interested in, but because we had high sample numbers purely for that. Right? Because even early on, it was sort of clear that the number of QPCRs at scale, but then, of course, transcriptomes was just getting really big. And, you know, when I started my career early on, we had, a few bug RNA. Now we sort of had thousands of them or whatever. Right? So this is, early times. But now, you know, we we go into to a regime, and that was sort of one of these eye opening moments when when Parse Bio had, like, I think they call it the Gigalab or something like that. And, know, there's sort of similar ones from competing companies now. But when they had, like, a single experiment, 10,000,000 transcriptomes measured, right? I thought that was like next level stuff. And you know, this step from just getting more PBMCs as a control tool, like let's actually do something at scale to it, sort of having here the cell space, but then having here the perturbation space, which typically was very scarce. It was like control versus disease or so. So this sort of number of points, what you had here in terms of sampling on the perturbation space was typically much, much more scarce than the number of observations in terms of cells that you had. But now this is exploding. Now you sort of have, I don't know, 100 different cell lines where you do sort of full epitope seek, like full CRISPR, or you have, like, batteries of a thousand drugs or so added, and suddenly this space gets really rich, right, and then you can sort of start doing all these fancy perturbation prediction type of things, and this is currently happening. It's crazy what scale is happening.
00:07:45 · Fabian Theis, RJ Hanaki, Brandon Anderson
We ourselves involved in a whole bunch of things where we actually go beyond cell lines and do organoid perturbations, and maybe if you have time we can can talk a bit more about that, because I'm quite convinced that we need to go to multicellular systems to have actually really interesting readouts, but I think everyone is scaling these these these levels up, and at some point, you know, we're gonna go maybe even to human genetics as a perturbation. [00:08:07] S1: Can you just, like, explain what is a perturbation? What do you mean by that? Just for the people who are not familiar. [00:08:13] S0: Yeah. Yeah. [00:08:13] S2: Yeah. Actually, would you mind maybe backing up even one step more than that? Like, what do we even mean by, like, measuring transcriptomics? And you were talking about, like, PCR based and then also perturbed seq.
00:08:25 · Fabian Theis
[00:08:25] S0: And When I give sort of public talks, I typically say, you know, human genome project, we sort of have the genome for the body, but it's pretty much the same everywhere, right? So, like, why do we have all these different cell types, right? What's sort of happening specifically? And so first level, what we typically have, one of the first levels is that, you know, per cell different stuff is being read off of the genome, right, and these messenger RNAs, which then sort of encode the various downstream proteins, while these are sort of differently expressed as one says in in in different cells. And to say in a human maybe there's something like 20,000 different types of these, splicing many, many more, but there's sort of a rough level. So what you de facto have is per cell a 20,000 dimensional vector that has a whole bunch of zeros when stuff is not there, but then a whole bunch of sort of numbers, how many of these counts of these messenger RNAs you have. Because these things are called transcripts. Right? This is called the transcriptome. Yeah. And and and de facto, then you have this sort of 20,000 dimensional space that we very often encode in a sort of nicer latent space that sort of has like an... A sub manifold, like sort of this this subspace where these actual cell cloud lives. Right? And if the cell cloud then sort of like these sort of 20,000 dimensional vectors, each point then being one cell, right, if they sort of cluster up, then we call these things cell types or something like that. And if they sort of go into a sort of sausage or whatever, right, we call them in trajectories, like a cell differentiation, like the fertilized cell then making all the cell types in the body or something like that.