Lab-in-the-Loop at Compute Speed — Ian Quigley, Leash Bio

Molecule chemistry and the hidden sociology of data

0:00My co-founder Andrew Blevins and I were at Procursion looking at a small molecule on a screen. And then a medicinal chemist walked by us that's named Mike Cucarisi. And Mike was like, hey, looks like a Stuart Shribert molecule. And then we were like, oh no, you can tell just by walking by? You're like, who made this? That's horrifying. And if the models can identify the chemist by looking at the molecule alone, then maybe the models can infer chemist intent, which means maybe they don't learn anything at all. Well, they did learn something. They learned what the chemist was. Yeah, they don't learn physics.

0:30We downloaded all chemicals from all chemists at Chemble, which is the biggest repository of these things and their activities. Every chemist who published more than, I think it was 30 papers and 600 molecules. So you get all the molecules and all the stuff. It's 1,815 chemists. And then we tried to classifier to predict a chemist from looking at the molecule alone. And we got a top five accuracy of 60%. We chose to represent the molecules, not with any chemical structures or formulas at all, but just a vector of the probability of creator.

1:00So now it's this 1,800 element, you know, vector, and it's got some probability of who made it. And you can use that representation and then train a model to predict activity from Chemble. And it does as well as if you use chemical formulas. We really think that it's learning a lot of sociology. It's not learning ground truth. When you train models on the exhaust, you might be in trouble.

Introducing LeashBio and DNA-encoded libraries

1:20Welcome to Latent Space AI for Science podcast. I'm RJ Haneke, CTO of Mirror Omics. And I'm joined by my co-host, Brandon Anderson. He develops RNA therapeutics at Atomic AI. Super excited to have Ian Quigley in the studio with us. Today, this is a, this episode is going to be a treat. Very excited. Ian is the co-founder and CEO of LeashBio, which in my personal opinion is one of my favorite young tech bios in the last, like, few years, you know, at a high level. Leash is combining epistemic rigor, data collection at, like, a crazy scale,

1:55and has a strong commitment to open science, and has an incredible series of blog posts, a lot of which we'll cover today, which I think really tells you how to do machine learning in a very hard domain in kind of the right way. I think I'll have some fun anecdotes. Hopefully, it can trickle in through the episode. But, yeah, to start with, thanks for being here. And, you know, what's your, is there anything about us that you want to tell us before we get started? No, thanks. That was very kind. Yeah, we founded Leash historically

2:26after being confronted by a particular problem of trying to predict small molecules binding to protein targets and then finding that the data that was out there was kind of wanting. And so we went out and built this thing at a reasonable scale to kind of try to go after it. Yeah. Yeah. So, reasonable scale. So, you're founded upon the idea of doing something called a DNA-encoded library. Every person I've ever met who's touched a Dell has come out severely traumatized. I don't know any person who has ever said, Dells, that's a great idea. Let's do hundreds or thousands of these things.

2:57So, why? What? And also, please explain what a Dell is before you get started. Yes. So, when you're going after a small molecule drug discovery, the ultimate goal is to get a small molecule or a dinky chemical to bind to the protein that you think is causing the problem in a disease and then go from there. And some of these proteins are pretty easy to find chemical material that sticks to you and some are harder. One way to go about this is to have a lot of different chemicals in different tubes and you then dunk the protein in one tube at a time and it kind of takes forever.

3:29And then a different solution that was proposed some years ago now was maybe if you had a lot of chemicals in the tube at once and then one tube and then you've got a small DNA barcode that's physically attached to each small molecule. You dunk your protein in the tube kind of like a fishhook. You pull out different ones that bind and then you sequence the DNA of those. And so, the idea is that you could then pool this large number of molecules and then you wouldn't have the logistical overhead of trying to go across large numbers of tubes or individual wells and plates. And so, what's happened downstream of that

4:00is that you've got chemical libraries that if you do one tube at a time, the biggest ones in the world are in the low single-digit millions. With Dells, the largest one that has been produced is 40 trillion molecules. There's some problems when they get that big, but that is the kind of scale that you could try to attempt with this technology. So, the way you create these things is you use this combinatorial chemistry where you have these building blocks and then you build the library piece by piece, but you build it combinatorially. So, that is correct. Yes, yes.

4:31And so, to unpack that a little bit, if you've got, you know, some number of millions of molecules, what this really means is it is a combinatorial mixture of building blocks and the number of building blocks is going to be a lot smaller than the final product of all of those. So, you might be squared or cubed, right, in some different examples. So, it's not uncommon for there to be maybe thousands or tens of thousands of building blocks that would then generate a chemical library of many millions of molecules. And this is restrictive in some ways because, you know, you're stuck with a smaller number of building blocks,

5:02but one thing that's really nice about it for machine learning is that you've got all these different combinations of things that look very similar to each other except for maybe one or two changes. And so that, you know, I'm sure going to get into this later, but that does really enable comparisons so that you can identify, oh, it's this part of the small molecule that's driving the binding because I see a lot of variations in this other part that's not affecting the behavior too much. And that turns out to be incredibly useful. The other aspect of this is how you do the readout, which is the DNA sequencing. This has been a big theme on the podcast. We've had many guests

5:33who have had some variation of we do something crazy and then we convert the reading into a DNA sequencing readout. So how does this work and why is this so useful? Right, yeah. I would definitely say that it is a party line at least that if you're going to go off and try to do life science stuff and couple it with machine learning approaches, there's really only, really only one scalable technology in town and that technology is taking pictures. Sequencing DNA is another way of taking pictures.

6:04And so it's basically pictures and DNA sequencing. And if you can shovel your challenging problem into that using one of those approaches as a readout. So for, you know, like recursion takes actual pictures of cells and a bunch of other groups do that, like InSitra does that. And then almost everyone else with the spatial omic stuff or other approaches, they'll do some mixture of pictures and, you know, and sequencing, which is also pictures. Yeah. There'll be some proteomics people out there who are going to, you know, disagree with me, but I'd still argue the scale is not there yet. Hot take number one. Yeah.

6:36And one of the really cool things about sequencing is that it is dirt cheap. You can, you know, extremely scalable, very well-established technique. We're very good at it. It is very, very cheap. It is getting cheaper all the time. There was a little while where it kind of plateaued in terms of the price dropping, but now a bunch of new companies have started up and they're driving it down again. And so like we very much look at like the trajectory of sequencing cost dropping and it has implications for how we think about data collection in the scale that we're doing. Yeah. It's really nice.

7:06That's cool. So you have these components that you are mixing together to form different, this combinatorial mixture of molecules and each of those components is barcoded. Is that right? That's correct. And so they, and then they, so they kind of bind together because they're these proteins chain or these amino acid chains that will click onto the ends of each other and fold together and then they either bind or don't bind to your target.

7:37So first of all, how do you know that they bound to your target? Yeah. So first of all, it is very much like this sort of fish hook analogy where if you were to, so right now the target, you know, is some protein or a protein complex that you're going to try to find chemical material to bind to. It's attached to a solid support. And so some folks do it a variety of different ways, but the way that we usually do it is it's attached to a magnetic bead and so you dunk this bead in this complex mixture of all these small molecules and in a very easy case,

8:08let's pretend that the protein has a very distinctively shaped hole in it. You dunk it in there and then the chemicals in that pool, some tiny fraction of them, have the appropriate shape in electronics that they're going to bind into this very distinctively shaped hole. So then you pull this protein back out and you only pull out the things that are in that hole. You rinse it a couple times in some way and then you sequence the DNA of those things that come out that are in that hole. Okay, and then when you say sequence of DNA, you're basically amplifying the barcodes that are in there. That is correct. And so then you can,

8:40so amplify meaning PCR or something like that. You do a little bit of PCR and then, yeah, then you toss it into the sequencer. And then one thing that you're probably thinking right now is, okay, well, we need to compare it to something to get a good measure of relative enrichment. And so you do have to engineer a bunch of good negative controls to say, oh, well, if I just stuck the bead in there by itself or are there pan-protein stickiness signals that are going to pull out certain chemical libraries, chemicals from the library. And so you've got to think pretty hard about all those things and make a reasonable comparison to the thing you're actually trying

9:11to get binders for. For the things that bind, you sort of have these combinations of barcodes that all sort of, okay, if this one bound then I have like these, how many barcodes are we talking about for one protein? Great question. For one small molecule. For one small molecule. So there's a couple things. One thing, if you want to get into the kind of PCR-based weeds, and so for the audience here, if you're making lots and lots of copies of DNA, there's little subtle biases

9:41in the DNA that might make them amplify faster than others, and so you want to control for that. So you put in a little bit of unique sequence in there, so when you have lots of copies, you can then collapse it so that they all came from this one that you know very much, you know, it's very much just from this one event. And then there's a bunch of other things about barcodes that we worry about at Leash, which is that when you are trying to stick proteins in there, some of those proteins are going to stick to DNA because that's their job, right? There's lots of proteins whose job it is to interact with the genome and cells and turn things on or turn things off

10:12or affect them in some other way. And then you've got this assay where you've got a ton of DNA and you're throwing them in there. And so that can be risky. And that can cause false positives, right? Very much so. A lot of people complain about this. This is kind of to the earlier comment about folks having Dell nightmares. This is one of those problems. There's a variety of ways to address it. One thing that we do is we have large numbers of barcodes that each encode one particular type of small molecule. Here's one small molecule.

10:42That's great. Now we have 32 or 48 different barcodes all encoding this one small molecule. Oh, I see. Right? And so then, you know, so like, you know, there'll be, you know, a single example. One single molecule has got this barcode and then its neighbor, which is the same chemical formula, will have a different barcode and then so on. So if there's any differential there, then you know that you're binding to the DNA instead of the small molecule. That's right. That's right. And so for like the DNA protein aficionados in the audience,

11:13one really nice thing about this is that because there's DNA in there, you can see if there's a single DNA encoding barcode that's like way, binds way better than everything else, even though it's all the same small molecule. And then you can look at the sequence that you have enriched there and you can recover the described DNA binding preferences of those proteins. It's like, oh, here's a transcription factor. It binds this series of nucleotides that is very well described. You know, it's like six or eight of them. And then you look at the,

11:43you recover the DNA sequences back from this experiment. It's like, oh, great, we found the consensus binding motif. Right. So I think our protein probably got made right. You have this barcode that you've identified and you've kind of gotten rid of the false positives using the technique that you just said. And so now I know that for a given combination, so for a given small molecule that I'm in, I bind to my target and it's, but don't you have

12:13all these DNA tags, barcode tags, like hanging off your molecule? You do. Doesn't that impact the... Yes, they are happy. They are happy. This is another complaint that people bring up about DELs. There's a couple different answers here. I would say, but like the very like 10,000 foot philosophical answer is that there are two different or there are multiple different reasons why you might want to run one of these experiments. One reason is that you're trying to get a small molecule material that behaves a certain way that you're going to progress into drug programs. And so if that is

12:44your main goal, then you want to make sure that you're getting some kind of fidelity between having the DNA barcode on there and then having it off there. And that's true and when we try to pursue interesting chemical material at least, like you do have to go through the work of manufacturing the chemical off DNA. You've got to run them in these functional assays. There's a certain level of attrition for things that are easy in our hands. About 90% of them work. For things that are hard it's about 50. So there's some loss. Other people have different experiences. But I would also say that if you're thinking about doing this for machine learning training purposes, all these chemicals with their DNA barcodes

13:15are in the tube. You ran the experiment. Some of them bound and some of them didn't. And that is real signal that you are physically measuring from the world. And so then you just condition your models on the existence of this barcode and then you just keep moving on with your model training. And so in our hands when we rerun experiments, so make fresh protein batches, make a new batch of the chemical library over many, many months of time, we get back the same hits in the same order for the most part. And so it's extremely reproducible and robust. And so in terms of like ground true signal, we feel quite good about it.

13:46You could be blocking the pocket or something with your DNA so then you get a false negative there. But you don't because you know that the DNA is there. It did not bind. The way that you're thinking about it is like, oh, I'm thinking about how the molecule will behave missing the DNA. But we know it's there and we don't pretend that it's not. Oh, I see. So does your hit include the DNA then? Yeah, like when we train models, we very much put in a placeholder that marks like the position of the DNA. If you're going to synthesize this for a drug,

14:17will you leave the DNA on there? No, like I said, that's where you get those attrition rates, right? Then you've got to make it and sometimes they behave differently. Okay, yeah, yeah. But it's on track. Got it, got it, got it. Sorry. No, no, no. Just needed to understand that. No, actually, those are really good questions. Those are really good. Yeah, yeah. Like there are lots of objections and like there's one, these are many of the reasons why folks are trying to do the thing that we're trying to do. Yeah, I was going to say, going back to my original statement, I again have never met someone who has worked on Dells and said, we should do more of these. Oh, yeah.

14:48So, I mean, I think, I mean, hopefully we will get to, I think, why I'm actually excited that this route seems to be working. You know, hopefully the audience will agree with me before this is over. In fact, actually, maybe even a personal anecdote. We have a mutual friend who was, I think, an angel investor in Leash and when he told me he was an angel investor in a Dell company, I jokingly said, okay, well, that's money you'll never see again.

15:15I'm like here in front of our entire audience to say I was, I was wrong. I wish I had, I wish I had listened. I'm curious about, first of all, why are Dells so hard? I think we just covered a lot of these. Like, what in the historical community of people doing Dells was making it so dramatic as an experience? And then, why did you think you could overcome that? One thing I do want to say is that when Dells were invented,

15:45it was definitely at a time when sequencing was kind of more expensive and it really felt like taking, doing sequencing experiments was kind of like a big logistical

Scaling measurements across thousands of protein targets

15:55and financial swing. And then, when you built the technology at the time and then pointed it at the problems that it was pointed at, it was very much, oh, we want to find new chemical material binding to targets that are very challenging. And so, that brings up a couple kind of tactical issues. One of them is that classically, folks don't screen large numbers of protein targets. They're usually interested in finding chemical matter for something that's like really hard and they have maybe tried a bunch of other techniques and they haven't worked out. So, okay,

16:26let's try Dells screen because we don't have anything. Then, they'll go off and make the protein that they're going to try to screen and they'll put a lot of work into it because it feels like kind of a lift to do a Dells screen. And so, maybe they might spend two to six months growing big batches of the protein that they care about, doing a bunch of purifications. Maybe they're going to run some functional assays to convince themselves that, oh, it's really got to be this good for us to go off and run this screen. And then, when they run the screen, they're going to try to maximize their chances of getting pretty good chemical material

16:56and so then the incentive drives into a place where we want a big Dell. Like, we want a lot of diversity. And so, if you go looking at folks who are offering CRO services or internal Dell groups, a lot of times they'll push into these very large Dells and HOPs. And that's their motivation and it makes a lot of sense. What we have done that's very, very different is we screen tons and tons and tons of proteins and we are less driven by trying to find individual binders for a particular protein target that might be of high interest for a program. We just want to get tons and tons

17:27of active chemical material across large numbers of proteins. and so there we can identify how our Dells behave very, very well because every one of our chemical libraries gets screened against many hundreds of targets. So you're characterizing the chemical library better. We know it very, very well. And so we start to encounter lots of these motifs that are quirks of the chemistry that we designed or maybe the manufacturing process. Like, oh, well, even, I mean, a great example is we have one chemical library that we've had made a couple times and even though it's

17:59the same chemical library, it does behave differently and we did not know that until we screened hundreds of proteins against it. And then you have to stare at those results and say, oh, well, now we're seeing these motifs show up a little bit more and then as you characterize the library more and more, it really helps you evaluate and troubleshoot even your protein production process. And so the one reason that we felt that this is pretty tractable overall is that I and a couple of the people at the company come from real like genomics methods development backgrounds. as compared to chemistry backgrounds.

18:30And so we knew what it might take to tweak experimental protocols to really get good signal out of these funky assays. And I would say it was that plus many years at recursion that's where I was last with my co-founder this guy, Andrew Blevins, and a number of other people on our team. And we all made, you know, honestly, like a lot of mistakes in high-dimensional biology, bumping around in the dark figuring out what different modes, failure modes there might have been that would allow models to cheat on, you know, the high-dimensional imaging data that recursion produces. And so we had this real eye

19:00for thinking about, oh, well, you know, there's these sources of noise this way, we're going to chase those down, and oh, can you predict, you know, the instrument that this was run on, and if you can, that's really bad. And so we incorporated all that thinking into going after this particular assay, and we had a feeling that folks hadn't really stared at it, you know, in that amount of detail before. Yeah, this goes back to the Ron Alpha noetic episode where I found it. Recursion Mafia. Yeah, Recursion Mafia. I found there's some real spiritual parallels between

19:30both of your companies, this like real epistemic rigor, checking very carefully everything you're doing, doing things in different ways, and sort of like semi-overlapping ways. And I'm just curious, we asked Ron this, yeah, very data-focused like at scale. And automation. And yeah, and I'm curious, like, was there something like at Recursion, like, was this just like core to Recursion's culture that is sort of like. It is, yes, yes, especially in the early years. I would say that there are four that I,

20:03I think, I think there's four ex-like Recursion Mafia companies, and they all kind of rhyme. So there's us, there's Noetic with Ron Alpha, there's Invada with Vishwa Kuluru, and August Allen, and Hannah Gordon and all these great people, and Dave Healy. And then there's also Known Medicine that was run by Katie Rose Skelly that got picked up by Pathos a couple years ago. And so all these companies are basically looking at different interesting biology problems with extremely noisy measurements. And then they pulled in people from Recursion to figure out like, oh, we're pretty good at noisy measurements. Let's try to see if we can get

20:33consignal out of this particular corner. You know, and so for us, it's a small microchemistry problem. For Invada, it's mixtures of natural products. They do do a lot of like, you know, kind of mass spec kind of stuff. And then there's Ron, and then there's Katie Rose's group. So yeah, we're all very similar. So let me, let's pause for just a second. What do you guys actually do?

Small molecules versus biological therapeutics

20:58That's great. Sorry, I like, I'm so excited about this. I just jumped in. That's great. Yeah, we are a machine learning small molecule company. And so what that means is we go off and we collect massive numbers of small molecules binding to protein targets. And we use that to drive advancements and machine learning understanding of this kind of stuff. And we also push, you know, small molecule material into partners and move it forward towards, you know, towards patients. Just for the audience

21:28that's not familiar, what is a small molecule? Why do we care? Or what, how is it different than other therapeutic adnees? This is great. So when you're trying to drug something, I talked a little bit earlier about how you've got a protein of interest in your body and you're going to try to interact, you know, affect its behavior in some way. There are a couple different things that are currently on the market that people use. One thing that's common is antibodies, which are made by cells. They're large molecules. And by large, they're big enough

21:59that they have a really hard time getting inside cells. They also have a really hard time being in a pill. So if you have like antibody treatment or one of these protein treatments like GLP-1 treatments, you're going to have to have kind of an ejection. It can affect certain proteins that are easy for them to get to. But there's other ones inside the cell that drive a lot of disease that are quite challenging for those. It is kind of more appealing in a lot of ways to instead have this big thing that's a protein to have a little tiny chemical. And tiny chemicals, small molecules here, are things that can be in pills.

22:30They can go inside your cells and affect behaviors. They do make up most of drugs. If you've got any pills in your house, they're almost certainly small molecules. And of the different machine learning drug discovery groups that are going after treatments in a general sense, we have made, we as in all of, you know, life scientists, you know, in the 21st century, have made pretty good progress on being able to predict and enable the behaviors of protein type drugs. So you've got a bunch of antibody companies like Isomorphic does this or like Chai or Nabla.

23:01There's all these groups of very good, very smart people pushing on these particular problems. And I think part of that is because we understand or have enough data for protein behaviors that make it reasonably effective, you know, for these companies to do these designs. Our thesis is that those capabilities are really not here for small molecule approaches. And so that was one reason why we built this company is we felt that we could go after it in a meaningful way. And small molecules, one of the key characters, they go everywhere, right, in your body. So that's good and bad.

23:31Yep, that is good and bad. They can penetrate into the cell and they can also get through defenses of tumors and cross the blood-brain barrier more easily. But at the same time, they do all those things and therefore they can be more prone to toxicity and other side effects. Very true. So the kind of path through the regulatory barriers for small molecules can be a little bit more fraught than those for antibodies. And so antibodies, we know pretty well right now about how they behave in the body and what they're likely to cause problems

24:01and what they're not. And for small molecules, there's a bunch of well-described problems that some of them might affect. They might cause liver problems, for example. They might cause heart arrhythmias. And as a medicinal chemist, a person whose job it is to develop these molecules, to get them from something that looks okay in a tube to something that you would feel confident enough to give to a human being, there are a lot of these pitfalls and they have to do a lot of work to avoid these pitfalls. So make sure that my molecule doesn't cause heart arrhythmias and then if I change it

24:31to stop causing those problems, does it affect it doing the thing that I want it to do? How do your models help with this larger problem of developing these and then, you know, maybe with, you know, sort of these downstream problems? So one way to think about it is that some number of these problems, these sort of off-target toxicities are going to be driven by your small molecule binding to other proteins in ways that you might be able to predict or identify. And so that's something that we are very much pushing forward to is, oh, let's also make those proteins.

25:03Let's also screen those proteins with our chemistry. It seems useful if you have a giant assay of different proteins and a library that you can... Yeah, it is not at all an exaggeration to say that it is our aspiration to have screened every protein and then also move on to those outside of humans, both for reasons to get variation of the proteins but also to identify maybe you don't want to run a mouse model, maybe you should run a rat one because your chemical material behaves differently in those different species because those proteins might be slightly different. Right, so you want to do that stuff.

25:34But yes, going after large numbers of these things allows you to think, all right, well now I've got my chemical material and then I know of all these chemicals which ones and what variations are ones likely to bind these things will cause other toxicity problems. Got it. Yep, yep. And then downstream of that, there's a bunch of other assays that lots of people do that are more kind of emergent behaviors where it's maybe not a single protein but it's how well it gets across cell membranes, how it interacts in a more complex way that you require a cell to evaluate or it might be like a cardiac cell, for example,

26:04for this heart arrhythmia stuff. And so those things, you know, right now there are lots of groups that are pushing on technologies to measure these at the cellular level which is, you know, one level of biological abstraction away from what we're focusing on right now. But we like to think that models that have a good understanding of the biophysics themselves can be useful and maybe fine-tuned

The Kaggle competition and the limits of prediction

26:20on smaller data sets in the future. Popping back one more maybe and maybe getting a little into the model, why DELs? DELs really are, at least in our view, the most scalable technology for measuring small molecule interactions because you can put many millions of them in a tube. Now, one thing that we haven't touched on in terms of like these chemical libraries is that when you make them in a pooled process, there are probably going to be some that react imperfectly and that the label translation of what you think you have

26:52might be a little bit off. And so we've designed a lot of controls into constructing our chemical libraries to mitigate this. When you're using these, you know, the word might be arrayed libraries or libraries that are in one chemical at a time at a tube or in a well on a plate. When folks study to figure out how good those labels are, like you hope that they're good, but when folks examine this, they're typically off by 20 to 30%. It's an enormous mislabeling problem. We think it's probably comparable to mislabeling in DELs, maybe worse.

27:23And DELs themselves are just enormously, enormously scalable. And maybe I can, like I'll tell a quick story that I'm sure that we'll get into at some point anyway. We ran a Kaggle competition a couple years ago and we decided to generate the data for the Kaggle competition and we released it. There's existing, there's a database that was at the time two years ago called BindingDB, which was the biggest aggregated collection of small molecules binding to protein targets as compared to cells or something else. And it was about two, a little under three million physical interactions. And so we released a data set

27:54that was about four billion physical interactions and it was all measured by a single person in the basement of my house.

28:01Yeah. The early blog posts are really funny. You like literal picture, you have an, it's not quite a garage startup, but it's in a basement. It is a basement apartment with like a seven foot ceiling. Yeah. It looks claustrophobic. Yeah. I've never seen a biotech startup started in a basement. Can't be done. Can't be done. The number ones are like that, right? Yeah. Anyway. Okay. So the, so this Kaggle competition, I think is just a fascinating story because you had such high hopes going into this. We did. You were like,

28:32and I think this is one of those cases of like very nice epic rigger where you didn't just provide, oh, like, you know, here's a train test with random split or something. You, you thought carefully about how to organize this Kaggle competition, how to run it and how to kind of evaluate fairly. Can you talk about that process, the decisions you made and then also the results? Yes. Happy to do that. So we were not by a long shot the first group to try to evaluate whether you could use computers

29:03to make reasonable predictions of small molecules binding to chemicals and then test those predictions. There are lots of papers that are doing this. Like there's a real classic paper that came out of Xchem and Google some years before we found it that does this. We had run a lot of our own experiments on public data and we had suspected that no one was really very good at it. And so we wanted to put together this contest and design evals in particular in a way that could really test it across a range of eval difficulties because we were thinking about okay we're going

29:34to have a lot of people hopefully a lot of people compete in this. Some are going to be very good some are probably going to be beginners. We want to make sure that there are some nice easy wins then like a bunch of stuff in the middle that's like kind of hard and then some things at the very top end of what would be difficulty or what we imagine difficulty might be. And so to kind of unpack that we've talked a little bit already about how these libraries are combinatorial so you're going to have some smaller number of building blocks but a large number of combinations. We got our hands on a chemical library from a wonderful sponsor this guy named Xiaojie Liu

30:04who runs a shop called Alpha Ma in Shanghai and the chemical library was about 130 million molecules and the center part of the molecule you can imagine it kind of like a hub with three spokes and then the center hub was the same for every molecule and it's a particular chemical motif called a triazine and so what we did was we said okay so we got the center hub then we got these three spokes for the evaluation data set let's have a couple different ways to split this. One way is that we could say all right the chemicals

30:35might have one shared building block one shared spoke and then the other two spokes are different. Okay that's one thing we can do so let's do that for some and that was the easy stuff. Another one we can say is all right well maybe we're not going to have any shared building blocks but we do know that if they're going to come from this chemical library there's going to be the shared hub and so we can imagine that some of the spokes might be similar but they won't be exactly the same and they won't be shared so we think this is going to be a little bit harder. Sounds great. And then for the third most difficult eval we had a completely different chemical library

31:05that we had designed at Leash there was no common hub no common building blocks different attachment chemistries different everything and so we thought okay we're going to do we're going to have these three in different proportions we're not going to tell anyone that's what we did we're just going to say here are the evals and let's go see how it goes and so we launched the competition it was two years ago and you guys can look it up if you want we've written a lot about it and then after 2,000 teams competed the winner did you know okay on the stuff that where they were shared building blocks depending on

31:36the target we saw some boosts in performance for where there were no shared building blocks but the core hub was still the same the tri-seam was still there and then when you go to the most challenging eval no one did better than chance yeah the like winner was like the like 1,200 just random person who submitted a jupiter notebook right or something yeah so the winner was this kind of who put together a slightly different approach but and his was good but again like everyone else no better than chance three of the top five were the noisy tutorial notebook so but

32:06just to be clear they're usually with Kaggle competition there's like a public eval for you to train to test your algorithm I guess and then there's the private one that's held out that's right and the competition runs that and all you know is the score yep so was your library included in the public eval okay no it was it was hidden back to be to make it spicy right okay yeah and it was spicy it was very spicy so so what did you take from this what was the lesson and I mean first of all what did you hope to get from this you kind

32:37of talked about that but then how did that sort of affect your thinking about like how do you proceed forward yeah yeah we had a couple hopes and some were fears one thing I will be candid about is you know we had released this data set that was a thousand times bigger than anything anyone had ever seen and we gave it about a five percent chance that recent advancements and kind of like co-folding approaches would mean that it would obviate our company entirely like didn't happen no but we were like you know there's like a small chance like we are really messing up here and that didn't happen we

33:08suspected more likely that folks weren't very good at it and that the data might help and so we were hoping to see that and anyway you'd want to know that you'd want to know that absolutely and like another thing that we wanted to know is there's lots of different ways to represent molecules and give them to computers you could use these things called smiles that do it some way you could do 3D graphs there's like weird spherical convolutional nets people try kind of goofy things to try to

33:39represent molecules in a useful way and there'll be lots of people in the field who will argue that like oh I think this way is better than this way or whatever and we did really encourage competitors especially those who had a chemistry background like let's try like some of these different representations so let's see how it goes and we were grateful to find that the thing that we were doing which is just basic smiles kind of beat everything else like it wasn't it wasn't like a resounding thumping but it was better enough for us to continue to using that approach and smiles just if I recall correctly is just basically a sequence a textual sequence of strings it doesn't

34:09encode any 3D structure it does not it's all emergent it is a graph traversal translated into a text string and so you can start the graph at different points and so there's what they call canonical and non-canonical smiles depending on where you start but yeah it's an extremely simple representation and so yeah we were thinking that you know or you know we wondered if some of these fancier ways of representing molecules might beat at least this particular problem and they super didn't so was your takeaway that you should go

34:42like what was the collective emotional reaction at least after that I've always wondered that I mean he kind of wrote about you had several follow ups but I'm just curious to hear yeah yeah this is a great question so like we are extremely bitter lesson pilled over here and so our thought was some of it was kind of delight which is like wow this is much harder than we thought that's kind of great that's kind of great because if this problem is like all the other ones that we're aware of

35:13if you can get pretty good signal out of a scalable measurement regime then you should just try to go get that yeah yeah no we're I mean for us it was it was pretty validating like oh man like we this is an opportunity here especially if your scalable measurement regime is hard and you have specialized knowledge to do that absolutely absolutely it was like oh man like this is the time to like pour gas on this all right great wow yeah I mean that's awesome so then you were just like okay let's full force we're gonna just start collecting data collecting data collecting data correct

35:44yeah and so you did that for a while and then what came what came next and maybe first also what were the lessons you learned in the process and then building to kind of your your first useful like yeah yeah there are a couple things that were from the process that we felt were very was very very useful one thing that we realized is that the count competition was based on three protein targets that were fairly well studied it became clear to us that we really wanted to you know for lots of reasons

36:14but including these that you know getting performance across novel proteins probably meant that we'd have to do a whole lot more so okay so that you know we were always motivated to do that but that really underscored like oh man we're gonna have to go we're gonna have to make a lot of proteins aren't we here and so that was part of it part of it was thinking that we had this very large number of small molecules like this hundred million compound library that didn't help as much to us as better characterizing a smaller one and so that was also like a strategic choice that we made this is actually quite important because

36:45you have a fixed budget and so you can either let's say sequence or sequence you spend more money on sequencing getting high resolution for what you already have for a smaller set or you can get more molecules and then hope that the noise sort of averages out or something yeah that's correct like having a fixed budget really does affect like your strategic choices and for us we wanted to make sure that we're getting a lot of variation across both axes as compared to like one axis and like a handful of proteins sorry which two axes so that would be like the number of chemicals against the number of proteins okay right and so

37:16you know you can imagine like oh I'm gonna do three proteins and a billion chemicals or maybe I should do like thousands and single digit millions yeah you know or some other combination of those single digit millions being probably one of the tiniest stells ever constructed it's pretty small the smallest one I've seen is 50,000 molecules oh okay yeah I guess you can make a custom Dell if you want to do like SAR you can do whatever you want yeah yeah yeah well you have the technology just do it yeah two building blocks yeah yeah right you can do whatever you want so that's the nice thing is you have enormous control over

37:46over like you know both like the library size and its characteristics and like this barcode issue that I talked about you can expand that kind of stuff and we put a lot of

37:59ways and all this stuff but getting back to the kind of like the Kaggle competition lessons you know was also clear to us that models could think about memorizing individual building blocks and that would boost their performance that was something that seemed pretty clear it seemed pretty clear that they might be able to get an idea through probably through memorization that if you have a very similar building block it might behave similarly so that also some of those performance metrics and then also that it's pretty far away they I mean at the current regime at that regime

38:30they simply could not do it and when we released these results basically saying hey you know no one did better than chance we did get some blowback where folks were like well did anyone good compete you know in your competition like maybe one's just bad maybe it's all first year grad students and so as a result we just released all the data in entirety and so if anyone out there thinks they're awesome then like please show us because we want this problem solved but we haven't seen anyone do great you know perform great on that stuff yet all the data you have including all like the raw

39:02read counts and everything so you can go through and say oh it's not just you know a processing error like you can go from the raw data and use it you could take our yeah you could take our binary labels you could do it yourself all the evals everything it is it is all on Polaris which is like a non-profit group that was run by recursion it's there for anyone to use please use it you know like we intentionally released it as you know hoping the community would make good use of it do you think though the structure of this data set was fundamentally limited in a way that maybe without some external augmentation you're not going to be able

39:32to do any better than what people have pretty much already done I think if you had really perfect structural understanding or like really good structural models then you ought to be able to do okay on this right because if we we all have models that really understand truly understand like the physics of the interactions between the amino acids of the small molecules then it doesn't really matter what the distribution of the small molecule training set would look like if they're really good at this you know and I think when we see when we see structural model predictions and folks say oh well you know I've got this time split on the PDB for example and you know our models have never seen these molecules

40:03or this protein before and then hopefully we can you know kind of use this understanding to make reasonable folds like that's that's very much in the spirit of being able to make the predictions on this stuff because no one has seen these especially our internal molecules like no one's seen those before that's cool so Kaggle competition you went ahead and you learned you learned some lessons you went full force data collecting regrouped committed to scaling yep all right so then you I think something like six months later you released or you had a blog post about your model Hermes

40:33yep which is yeah can you tell us about that sure some of the learnings there and I think both and especially how you evaluated that I think and all the care which went into that model

Hermes and the cross-attention architecture

40:46Hermes is a model that is the original brainchild of a data scientist at least named Max Kleinsasser and also Sean Francis Lyon and Andrew Blevins of course is the CTO there what the thinking was originally was that we had a bunch of data and we were thinking about how to split it and different training regimes and so we wanted to come up with a model that was really really dead simple so that we could do lots of potential experimental iterations it wasn't the purpose of it wasn't to be a state-of-the-art model it was like ah you know we want to try stuff fast and so we got Hermes and then the basic architecture of Hermes

41:17is two different embeddings one of them is evolutionary scale modeling ESM embedding that's a protein embedding that comes from a group that was at Meta and then went off to start their own company and then they got picked up by Chan Zuckerberg more recently we had Alex Fries on the podcast so we can throw back to that episode if you want to hear more we'll go back a few weeks thank you Alex if you're listening so we did that for the protein side and then we had a different embedding called Kemberta which is basically like a next token predictor chemistry

41:47kind of embedding to the other side something which predicts smiles that's right just predicts smiles tokens and so that's these very very two simple embeddings and then we just put them together with cross attention and that was it and then we used it to predict a binary label simplest possible thing it is incredibly simple very pretty small and then we trained some of our own data on it actually not the simplest you could have done MLP after those right instead of cross attention so why attention the thinking with the attention was had to do with some other

42:17experiences that we'd had kind of with graph convolutional like graph models for protein structure and one thing that we noticed is that if you've got these sort of graphs and there's a couple models that do this other work that we had done we had scrambled the positional coordinates of those and performance for some of those models more or less stay the same and that made us think that like attention was super critical and so we ended up just making sure that the model was at least at least what we hoped is that it would be looking at the different parts of the proteins as small molecule structures that could be useful here so this is I think oftentimes known

42:48as the Picasso problem in like image generation where let's say CNNs for example would were famous for a while where you could scramble just the features of a picture like Picasso like flip the nose around or just like rotate the eyes or something and the CNN would still depict oh this is a Picasso because it just picked up on individual local features rather than some sort of global structure and this has been a problem in small molecule drug discovery for a while where oftentimes it picks up

43:18on local motifs and then it doesn't have any global understanding of that topology so especially for something like Adele where you have this combinatorial structure of individual building blocks you could imagine the model learning each building block independently and then essentially just decomposing into the sum of three building blocks or something or I mean it's a simple concept yeah so cross attention in some sense forces certain molecules to interact with like certain residues in a protein or at least maybe not forces but provides the opportunity

43:49thinking about it it's an inductive bias yeah kind of what you're getting at is you know we were thinking about how to evaluate this and so we had done some of the similar tricks that we did over with the CAG competition where we had you know training sets on data that we generated internally and then we'd look to chemical libraries that were further away but then also we wanted to think about splits to kind of probe Hermes behavior and so because DELs have this combinatorial approach you can do the same thing where you might share certain building blocks and so we do that and of course performance is better which we suspect

44:19is for memorization but the other thing is you can imagine that there are building blocks that are very similar to one another that if you're just trying to split on the identity of those and then you might have things that are close enough that memorization or some other cheat mode might confer predictive power and so we came up with a scheme where we then did basically clustering of these different building blocks we had building block clusters on similarity and that way we would just avoid entire clusters from being overlapped between test and train

44:50and so when you do that then you know the performance does drop and so one thing that you might be alluding to is we have we use lots of lots of reasonable baselines here that we're really worried about and so for almost everything that we do we'll use like xgboost right you should do something like that just to see how it's going yeah yeah every the classic young machine learner practitioner they spend six months optimizing the favorite model and then someone walks by and does like you know xgboost a random forest

45:21and they're like oh yeah yeah that just beat like six months of work oh yeah yeah and so we and so we did these different like split regimes to try to evaluate how well things would do relative to like xgboost performance and so one thing that was really gratifying to see is that you see xgboost drop steadily as you get further and further away with these building block cluster approaches it's like if you share two building blocks it's a certain level if you only share one it gets worse if you share one you know only none it's worse

45:51and if you do the building block cluster it's even worse than that and then we compared that to the Hermes performance which was pretty steady across all these different regimes I see yeah so it made us think like oh yeah you know you've really got to get pretty far out of distribution for xgboost to really tank yeah and that's something that we haven't you know we haven't it's in a couple plots and some work that we publish we haven't yelled about it too much wait I thought didn't you have a block post like xgboost is all you yeah yeah that's why we did that yeah yeah running those splits is something that we've put a lot of thought into into trying to figure out like okay how do you stop your models

46:22from really you know memorizing and remembering things this might be a good time for a little bit of a detour but referencing another one of your blog posts which I found absolutely hilarious from my own personal experience I have seen machine learning models like pick up on so many weird detractors uh-huh and your one your blog post about molecule ownership or authorship was uh

Clever Hans and chemical authorship fingerprints

46:44oh god

Clever Hans and chemical authorship fingerprints

46:45I think a really fun story the clever Hans post yeah so many years ago uh my co-founder Andrew Blevins and I were at Procursion looking at um a small molecule on a screen and then a medicinal chemist walked by us this guy uh this guy named Mike Cucarisi uh and and Mike was like hey looks like a Stuart Schreiber molecule and then we were like oh no you can tell just by walking by you're like who made this that's horrifying and then that haunted Andrew in particular for like many years like it was like six or seven years and we joked uh you know I don't know

47:15every couple of months we're out for beers like man we really should figure out like how bad this problem is why is that a problem okay so it's a problem where it's very easy to imagine you're going to try to train uh models to understand chemistry so you're going to get the data from lots of groups because it's very tempting to get data from lots of groups and if the models can identify the chemist by looking at the molecule alone then maybe the models can infer chemist intent which means maybe they don't learn anything at all well they did learn something they learned who the chemist was

47:46yeah they don't learn physics they're not learning the thing you're trying to get them to learn and so we were really afraid of this they learned that certain chemists are better than other ones yeah we learned all kinds of stuff but maybe to set this up for the audience so we went out and like we published this over Christmas you could look it up we have a leaderboard we have a goofy online game you can play but we downloaded all chemicals from all chemists at Kemble which is the biggest repository of these things and their activities every chemist who published more than I think it was 30 papers and 600 molecules so you get all the molecules

48:17and all the stuff it's 1815 chemists and then we tried to classifier to predict a chemist from looking at the molecule alone and we got a top 5 accuracy of 60% it's a very very easy problem yeah yeah it's super easy for the models to do where they get confused is where you have two chemists who run the same publications and were at the same institution and so what we think is very likely is that there is a distinctive chemical signature style that individuals have when they make molecules and then when those individuals

48:48have students or trainees then they adopt some fraction of that you know and so that was that seemed pretty pretty clear to us and so that was horrifying enough upon its own and this is a data set that many many academic projects many PhDs have trained on tried to predict on find patterns and this is really like a major data set for the field yeah like if you are not generating your own data you're using this and then if you are generating your own data then you are probably

49:19victim to this because your organization probably has multiple chemists who have their own distinctive chemical styles and that they are using their styles to go after different types of projects but the key here I think is that those chemists also tend to solve similar problems like I'm might have a career here and I have a style but I also am working on a class of problems and so that your style is also you're learning the style instead of the problem you're learning the style

49:49you're learning the sociology of the problem and the other thing that you're learning is that when you're a chemist at these organizations you know ordering a molecule to be manufactured and tested is kind of a pain right so what will happen is you will make many many choices of things you will not pursue and you do not write those down oh yeah it would be dumb to do that and it's like yeah that's their motivation our team just wouldn't make it like we could do this but then it would cost too much or the lab team will say the chemistry team

50:19will say no we can't make it now or we don't have the building blocks on I don't think it's going to work like there's all these reasons why you might not make a choice and then not making that choice is a fingerprint that is going to land on what does get made and then you know when you talk to some additional chemists some of them are you know bless them they're superstitious people and some of them will say like oh yeah I bring this up like every single time medicinal chemists are some of the most superstitious people I've ever met right and so it's like

50:50oh well this building block worked in this program that made it to the clinic I'm really fond of it maybe it helps with side building so I'm going to put it in things that I like and so then your model will learn like oh the chemist likes this because they put so that means it's probably working and so it learns all this weird stuff and so like we were very afraid of this and so we took you know we ran this this model to identify who the chemist was and then we chose to represent the molecules not with any chemical structures or formulas at all

51:20but just a vector of the probability of creator so now it's this 1800 element you know vector and it's got some probability of who made it and you can use that representation and then train a model to predict activity from Kemble and it does as well as if you use chemical formulas and if you combine you're coding the sociology only yes if you combine them it doesn't be meaningfully better and so yeah we are you know we really think that it's learning a lot of sociology it's not learning ground truth it's just learning like the choices

51:50and the fingerprints of the people who are trying to develop these molecules and it's not a knock on them right I mean that's that's not what they're trying to do they're trying to you know get to drugs by making the fewest number of chemical series possible of course they're going to do it like that but when you train models on the exhaust you might be in trouble so this means that this is not a great machine learning training set we do not believe so it's funny in my own in my own life you know I've had many of these similar lessons it's well known that things like molecular weight will just you know all you have to do is sort by molecular

52:21weight that's like one of the single biggest predictors you can possibly have like wasn't it cast 16 where it was tied for first place yeah for second place like it was really close it was really close yeah yeah so all these people pulling out their fancy machine learning models you just sort the molecules by heaviest molecules better binders yeah yeah yeah so yeah but this is not an intrinsic property to chemistry this is a property of the data set yes yes this is a property of the sociology of what gets made what gets tested yeah and like

52:52the way medicinal chemists work heavier molecules more likely to bind a lot of times it's because they're seeing improvements to affect other properties that's part of it and you probably got some parts too it's like basically you have a chemist to they find a hit and then they start optimizing it and they're like oh I have a hypothesis that this is the binding site so let me add this functional group to bind here okay and then they're like okay well that was a stronger binder and then so they're like oh what if we add this other functional group to bind to this thing and what ends up happening is they just keep adding things yeah until it gets really good

53:22and then yeah until it's sufficiently good and then you know instead of using a combinatorial approach or as Ian said also then you have these other properties you're like okay well now we have this really good binder but it's not soluble so let me throw on you know some you know hydrophilic functional or some functional groups on the other side of the molecule which is not in the binding pocket to like make it you know and you just sort of you just keep tacking these things on and next thing you know you get this big good binder and so you just sort

53:52by molecular weight and it's like the single biggest predictor that you can have in most public data sets but that has nothing to do with chemistry no like I mean I think a good way of intuition is like if a thing's working they're going to do more stuff to it because they like it yeah so you just do more stuff to it it gets more baroque or you have more like complicated expensive reactions or you know you get like weird building blocks that are hard to get you know things that you wouldn't do if you didn't think it was working and so it's all these signatures that the models would just kind of pick up and so yeah

54:23it's quite terrifying yeah this is like the horse something Clever Hans Clever Hans the horse can you tell the story about Clever Hans yes so for so a little history lesson here is there was a there was a horse trainer in Germany I think it was like the late 1800s I mean I read about this I should remember it and there's a horse named Clever Hans and what Clever Hans seemed to be able to do was complicated math so you would show the horse you know like a chalkboard that's got a math problem and then the horse would stamp the horse's foot

54:55on the ground and then stop when the correct answer you know was arrived at and everyone was amazed that this horse is so brilliant and then someone had the good idea to go get a questioner who did not know the answer to the math problem and then the horse completely fails and then it turns out that the horse is just looking at like the posture and the micro expressions mostly of the owner so that when it got to you know let's say the answer's 7 then the owner gets like real giddy when it's at 6 right and then the horse just stops stamping and there's this like wonderful paper

55:25put out by a German psychologist who actually evaluates the actual micro expressions and postural changes that he had observed on the horse's owner is quite extensive so yeah like if you're dying for a silly read you can go look it up so then the analogy is that you're reading the face and not the math that's right yes you do not understand math the models do not understand chemistry at all they are just you know remembering the sociology of the creators got it going back to Hermes and your epistemic rigor and you know

55:56you're in trying to build something useful out of all the data you trained so you find you know public data sets are untrustworthy and you have a bunch of data which you trust internally but you don't really have a good way of or but now you need to understand how do we accurately and carefully use this to understand to do something useful in the real world so how do you

Testing generalization on external data and mutations

56:18how did you bridge that gap for us to think about this like we did a bunch of these splits like I kind of described earlier but then the next thing that seems very obvious for us to do is like well you know we've trained models on internal data and we kind of don't like to train models on external data so maybe we should try to predict on external data instead without ever training on external data without ever seeing it and so that does put us in a nice position because I haven't seen any other group train models for this task exclusively on internally generated data

56:48I think it's very tempting to go get these other sources especially because there's so many possible protein targets out there because people don't screen as many as we do typically and so we took large collections of external molecules and then we predicted them to see how well we would do across many different proteins lots of different positive negatives that we chose very carefully it was I want to say it was like the total number of tests in the Hermes paper I think it's like 13 million or something across like many it's like 500 protein targets I think it's some huge number and then we benchmarked it against the existing

57:18what was at the time like the state-of-the-art structural model which is done by the Bolts team and so which is a very good model and like ours cannot do a lot of the things that that model can do but what we were able to do was do about as well as those guys on those public data sets in terms of like this binding problem prediction when you compared to Bolts it required some sort of tricks to kind of have a fairish comparison I think Bolts also trained on this data was that right sort of so there are a couple large collections that we weren't totally clear on like the different

57:49subsets that they had trained on and so I could think of one example in particular where it was very very clear and I'll talk about that in a minute but a lot of the evals that we used were ones that were also surfaced by the Bolts team only we put a lot more molecules in there to go see how it would go so yeah like I think there and also if you look at the different performances between Hermes and Bolts you know like we're better on some proteins and protein families that Bolts is worse at and vice versa and we suspect this is because of like different distributions of those in the training sets so that they understand a little bit more

58:19or you know honestly maybe like memorize a little bit more and they're able to extend that a little bit one thing that was very validating for us is one of our test sets was like another orthogonal chemical library that our models had not seen that we had used internally but it was a copy of a chemical library that had been out in the literature and so there was one target in particular it was called it's a protein it's called BRD4 where there's an identical molecule from our screen that was also in the PDB the protein data bank training set that Bolt had almost certainly seen

58:49our models did kind of bad on that molecule it was a distant chemical library they weren't very good at it and Bolt was perfect at it and it's because we suspect that Bolt had seen this protein and this individual molecule in a crystal structure already as part of the training set so they were awesome that oh yeah that checks out feels pretty good so does this mean that I mean in your opinion this validates your scaling hypothesis add more proteins more more diverse chemical libraries and now you can basically fill in the space more broadly or we hope

59:20so yes we hope so yeah like we think that going after large amounts of diversity and in particular going after intentionally chosen what you might call activity cliffs is the way to do this and kind of unpack that a little bit it's either on the protein side or the small molecule side do you have two things that look very very similar except for a tiny change and that tiny change drives like outsized changes in behavior so like a real classic example of this that medicinal chemists will talk about is this

59:51idea and it's kind of mythical it's not exactly real but this thing called a magic methyl and the idea is that you've got a molecule and then maybe you've got like this one like little thorn that is or is not there and that presence or absence of that thorn means like either it works great or it doesn't work at all when you have those situations then maybe your model will start to learn like man like having a thorn could be really meaningful and so maybe I need to think about like these very small changes and so one thing that we do a lot and it's baked into DELS because you've got you know

1:00:21two out of three building blocks might be similar across large numbers of examples and have variations of behaviors and then on the protein side we very intentionally engineer mutations in those proteins to do the same kind of thing I'm a little confused here because if you have these building blocks and the size of your variation is multiple atoms right many how big is like a building block in terms of atoms right right it might be it might be like six to like 30 or something if we're not ignoring like if we're ignoring like the hydrogens but you can you can imagine that they're building blocks that themselves

1:00:52are very similar with like a single atom substitute oh I see okay so maybe there's two building blocks that have one one a thorn and not a thorn and then you and then so you can see that in the in the sequencing that's right that's right and maybe that thorn just changes position and then as you're thinking about this you're like okay well I might have tension between my goals I might want lots of like rougher more coarse diversity because I'm trying to find binders across large numbers of protein targets that may be very different or I may

1:01:22want like super fine grained changes that are very very subtle and you know to try to like really teach the models like these like very very subtle differences and so as we think about designing our own chemical material like we have to span this kind of tension so yeah we think about it a lot and both of those matter both of those matter both of those matter and it also matters on the protein side too right it matters very much the protein side and so as you look at current like sort of co-folding models a couple different groups have shown this you can take a protein and it's got this amino acid sequence and

1:01:53it codes some protein that's got a big pocket in it and maybe that protein is represented in the training set so the model has a pretty good idea about what it looks like when there's a molecule in there there's a small molecule chemical in there so you got this pocket a thing that goes in the pocket you can just change the amino acid sequence that you give to the model to consider and you can use that to break the pocket you could fill the pocket in like you're filling it with cement or you could remove it entirely so that there's nothing there or it's gone or it's much bigger you do any of these things and you get at least what we've seen so far if you use current state of the art models to go see

1:02:24what the model will do it will shove the small molecule in where the pocket used to be because it just remembers where it is yeah and that's bad so it's like looking at the large scale structural things not some or like the hypothesis anyway is that it's doing this yeah the hypothesis is that it doesn't quite understand you know when you when you have a pocket and a protein there's going to be a small number of amino acids that will have hydrogen bond positions that are going they're sticking out there's going to be maybe a little bit of pie stacking these other things that you know sort of drive this chemistry and those things really ought to be

1:02:54very very important and and they are very important in the physical world when you're measuring them and so if you break them and the model understands the physics then it probably should know that it can't shove a molecule in there and that's the thing is like a lot of these structural training sets like there aren't great negatives because what makes it into there is yeah I was gonna ask that's got the thing right you know they don't have a lot of these variations that really you know disrupt these behaviors and no one's going to make crystal structures with a bunch of these mutants like we you know like we're currently doing first but how do you get negatives the way that we get negatives is that

1:03:25we have a really good understanding of the distribution of the number of those molecules in a baseline condition okay so like when we do the screen we know oh okay these bound a lot because now we're enriching for them when we pull the protein out and now let's break the pocket and they are no longer enriched okay they are no longer going that one amino acid substitution that we made is making a bunch of these chemical series dropout but this is a one-off experiment this is not a dell no this is a dell oh no so you're just you're not saying you

1:03:55broke it you're saying i find the case where it was broken no i we break it so we break the so we take the so let's say we screen a protein and the and the pocket is intact yeah sounds great yeah okay we get a bunch of hits yeah um let's let's go even further here let's say that we know someone else has already identified a chemical that goes in that pocket let's buy it let's stick it in there run the screen again yeah that means all the chemicals that normally go in the pocket will be displaced by a high concentration of the one them definitely not oh you have a competitive assay oh we do all the time okay

1:04:26okay do this yeah okay and then you say okay well that looks pretty good i believe that and then you say all right now we know that this chemical that someone else has characterized goes in this pocket because maybe they made a crystal or some other thing yeah great let's look at the the amino acids in that pocket and then we will change the dna construct that makes the protein for us we will now mutate physically this one residue so now like this hydro this you know this this particular amino acid now we put a big bulky one in there and the pockets full or like the different side chain or something all these things you can do

1:04:56yeah yeah and this is really easy now because we have alpha fold and you know bolts or all these structure models you can you can use this to design your proteins as you you can use this you can use and for things that aren't as well characterized you know like we use conservation you know like we stare at we have a structural biologist and staff and kind of look at these things like oh yeah you know this guy edward craft is amazing and so all right so you know now we're going to make this one mutation let's do get another screen and oh look all the chemicals that got booted out when we hit it with the with that one thing that's plucking the hole they're also gone we broke

1:05:27the pocket so now we have really good evidence that they're all going into that pocket right right and then here's the point where you know like the protein chemists come in and they say well if you made a mutation how do you know that you didn't just break the whole thing right reasonable question you say okay well we only lose the chemical series that got kicked out by that competitor all the other ones that are binding everywhere else in the protein are intact then they come back yeah so you didn't just break the protein you didn't just break it right and so and then you think okay well if you're going to be out screening a hundred protein constructs a week which is what we do on

1:05:58big weeks like sorry so you've broken the pocket oh yeah oh yeah and how do you also find that there are other things that do that start to connect to bind to the protein so when you change things around you might change the shape in a way that does encourage other things to bind we have definitely seen and is that an information source for you it is it is and so another thing that's really nice about this and the nice part about dells is you can you can imagine uh if you're not thinking in large numbers that oh i've got this one chemical that was binding and

1:06:29now i broke the pocket and now it's gone yeah but because of the combinatorial nature of the dells maybe i have five different chemical series it's like it's like hundreds of molecules and there's another group that's the same hundreds of molecules with a single change in the building block so like you have these repeated examples where it's like oh this one tiny thing shifted the population behavior enormously and it's a big population and so it's like oh i am now really convinced i can show you guys a plot that we i don't know if you you know put pictures on the podcast or whatever uh but

1:06:59it's very obvious like oh this one side group on this building block is clearly interacting with this one amino acid residue because we have like five independent examples of population behavior shifting because of it is beautiful it's very very clear yeah go ahead and tell us about this plot we pulled this thing up um and the reason that we pulled it up is we think it's really important for there to be a lot of variation in the proteins as well as the small molecules um and a reason that we think this is you want to be able to get the you know a model trying to learn medicinal chemistry to really start

1:07:30to put together you're having these uh hydrogen bond interactions between like this part of the small molecule and this part of the protein um we've seen other work that i talked about earlier about how you can uh if you digitally break a pocket and use the current state of the art models that they have a really hard time understanding the physics and they'll just shove the molecule back in that thing anyway so it makes this suggestive they're memorizing and so we thought one way to go around get around this is to experimentally engineer mutations in binding regions of these proteins and then re-screening and so what that looks like physically doing that

1:08:01physically doing that you take the dna of the wild type protein that you've already screened and then you use microbiology techniques to change uh one or more than one amino acids in that protein so that the functional part where the small molecules are binding is no longer the same it's different in some way we have a different methods to try to identify which amino acids are the smart ones to break sometimes you break ones that you're confident will do things sometimes you don't know and so you but we can do this at a pretty big scale so it's not a big problem to us to take a couple you know wingers at each one and so then you run the screen and now when the

1:08:32pocket is broken when the molecules go what do the molecules do do they still go in there do some of them go in there is there something common among the ones that stick around is there something common about the ones that get dislodged or or pitched out and then you have lots of different examples of these where you might have three to five-ish amino acids in a given pocket that are driving the binding behaviors maybe you try to break all of them independently and then you do redo the screens each time and get a good feel for what part of the small molecule is interacting with the part that you have changed and then when you do

1:09:03this with a large dell then you'll have lots and lots of repeated examples of similar molecules they're all following the same behavioral trajectories and that way you get a really good feel for oh I've got lots of examples they're all pretty similar but the one thing that's super common is this one little bit on the small molecule so I have a suspicion that is interacting with the pocket that I just broke what are we looking at on this diagram so what we're looking at on this plot is all those little dots are small molecules from a chemical library that we have designed and

1:09:33made along the axes are how well the small molecules bound so if it's like really down the axis it's binding well if it's more towards the origin it's not really binding at all and then we've colored a couple different blobs and those blobs are different chemical series the chemicals look very similar to each other but the difference is where we pointed that kind of chemical looking structure and so if you're squinting and you look at these they're all pretty similar but there's a couple subtle differences and that whole population we believe is driven by interactions of those differences to

1:10:04the one mutant that we made so in this plot there's on the bottom the wild type target and then on the on the horizontal or the vertical axis you have the mutant type target and so there's this red one and the red one is pointing basically up it is binding better it is binding better so that particular one is like the new mutation made that particular one bind better that's which is speaking to the question that I asked a few minutes ago yeah and then maybe some of the

1:10:35most of these seem to be above the axis so most of this mutation caused most of these to bind better that's correct yeah there's a second mutation that pocket that I can also share with you guys and where all of the all of those population all those blobs get kicked out entirely and they do not bind so then the pocket was broken in a meaningful way and then here the binding is increased and so and so that basically everything will be along the bottom that's correct okay that's great so you can give us post-production yep awesome so doing this you can map out both well you

1:11:06can you can treat the activity cliff issue both in compound space and in protein space that is correct and this is particularly useful if you're let's say working at kinases where you there's like a hundred kinases which differ only by like in the important binding site you might differ by one residue at a time or something so this could be incredibly powerful for certain classes like that in addition to your own insanity yep that's right yeah that's right yeah and we do this you know as I mentioned we do this we do this a lot yeah yeah many many hundreds of these types of screens one of the things you

1:11:37can do with this is Hermes sees this cross attention so you can actually interpret where Hermes thinks the binding pocket is so it's learning the binding pocket through these type of maps yes so one thing that we've sort of written about is using these attention mapping approaches to have a look at where Hermes is you know looking an amino acid space and when we first did this work we were expecting to for it to either look at the binding pockets that was like the first intuition and then maybe like a more measured intuition was like oh well maybe what we'd hope it for it to do is

1:12:09maybe look at all those residues because it probably doesn't really know what's going on yet and then when we looked it was not looking at either of those things it was looking at really short sequences of amino acids that were away from the functional part of the protein and also away from part of the protein that looks similar across many proteins and so for maybe the non-biology people in the room the way a lot of molecular evolution has worked is that there's a stretch of a protein that does a pretty good job and that often gets shuffled among other proteins as well so that you

1:12:40have this conserved region it's called a domain or you know conserved protein domain and so that part looks pretty similar across many proteins it's something that biologists will use to infer protein families and relationships and functions so they all the same kind of piece they're probably doing something kind of similar and so we expected the models to look at that but they don't they look outside that and they look at these little stretches that people don't think typically do a whole lot they're like a little bit different they're non-conserved there's a lot more variation in those and we realized that hermes was probably coming up with a nickname for the protein it's not

1:13:11thinking about oh this is the functional part it's like I don't need to learn that I can remember you know 10 or 12 amino acids that are different here than everyone else and I can just memorize it and we thought that was bad because maybe many of the like if you have variations in the pocket or whatever but but they all have the these other parts that are similar then maybe in the variation the pocket mostly don't matter but some of them do then you might the model might learn oh I can

1:13:41just pay attention to these yeah the concern was that the model again was not really learning any physics it's like oh I could just memorize this stuff it's very much in keeping with when you try to break the pocket with the co-folding models and they shove it in there anyway it's like oh it doesn't know what's going on it's just made this nickname yeah it's like oh man so how do you fix that and then that's when we hit upon trying to do these these mutations at scale and so what happens is if you have a protein that looks almost exactly the same but there's one tiny difference and then the behaviors change a lot as a consequence of that one tiny difference you're kind of encouraging

1:14:12the models to look at all the amino acids again it can't do that for the section that's non-conserved because if it does that with these two things a different behavior it's going to do a bad job yeah and so we went back and did you know train models with these additional mutations like the one on this pot that you guys are seeing and then you know look back at the attention maps and now Hermes will look at all of these things much more evenly so you're basically using the attention map to find these cases where it's memorizing nicknames and then enrich the mutations in the pocket to kind of encourage it to pay attention to the

1:14:43pocket instead yep yep and it's not necessarily just to be across any one gene it's more like the general problem of like oh i can't use this nickname strategy effectively anymore you want to teach the model that no don't do that you don't do that no no that's that's lame don't do that so i love this because we've seen or i think that the most pragmatic use of mechinterp has been in biology and in probably others related sciences where

1:15:14in the reason why i think it's qualitatively different is because you go backwards from you're learning about biology from the model rather than the just trying to interpret what like what is like what is it thinking in this case maybe it is actually that forward case but i've just seen so much mechinterp being applied to biology because you're really trying to understand you don't have the language in these machine learning models there is no language to lean on so you really have no clue what is thinking

1:15:45unless you're inspecting the model

Using reasoning models for lab-in-the-loop discovery

1:15:47well it's really interesting so yes and one thing that we have found very fruitful in the very recent past is actually transitioning to language models okay and what we are currently doing is um we're using um readable interpretable english to represent the small molecules and the proteins and their behaviors wow okay and that turns out to work pretty good yeah i mean this is no so this is because yeah i want to just frame this a little bit before you tell us about this because yeah this there is actually a really interesting paper in the single cell uh domain

1:16:20called gene pt in which people so i can't remember the authors are from stanford and it was somebody who was a statistician not even really in bio maybe they are now but that person they took the textual embeddings of the descriptions of genes yep and then they use those and so like you're using the esm embeddings uh for hermes yeah so you were using the esm they were just like let's just use the textual embeddings and the beauty of this is because now you

1:16:52have like a gazillion years of human time put into understanding each of these genes and that's all captured to some extent by these textual embeddings that knowledge of the embedding so like yeah so please tell us about what you're doing yeah so we started this project a little while ago uh because one thing that we realized is that we had this like growing collection of activity cliffs and profiles of the same chemical material across large numbers of proteins and we wanted to know if we could actually use

1:17:23reasoning agents to go explore it and use it in a lab-in-a-loop kind of situation and so that demanded that we started working with reasoning models and language models in order to kind of let them go play and so what that looks like is we took some open source language models like we did some quins and glm and you know the stuff that other people are using uh and we taught them medicinal chemistry in ways where you say here is a structure describe it in natural english give me the diff between two very between two molecules in natural english and then we got it to the point of where we say okay here are

1:17:53some molecules that are binders here are some that are not binders can you tell us why you think the binders are binding and then you can also give it hard negatives so you have these two collections that they go okay well i think this chemical series does this you know and it will write these things down in readable english which we think is great uh and then we said okay now that you sort of know these basic concepts we're going to give you 10 binders and 10 non-binders that are close ask you to decide why you think the binders are binding and now we're going to give you the opportunity to run your own experiments here is a catalog of millions of molecules why don't

1:18:25you pick five or ten and test your hypothesis about why they're binding and so then the model will go into the data that we have already collected it will pull out what it thinks are the most informative choices and we'll get back the answer instantly like it's a coding sandbox and then it will update its hypothesis about the binding and then the ultimate goal is to get the best binder in as few steps as possible very much like a medicinal chemist would do and then we just you're doing this based on your a priori run experiments but it's looking up in a database that's right right so now so you're basically created reinforcement rollout it is a reinforcement rollout

1:18:57of a large scale that's growing all the time that's full of these activity cliffs and full different protein variations and so now we have and so you can use this and since we know that when you change the molecules in these small activity cliff ways it is a causal change like we know that when you put this thing on there the behavior changes in this reproducible measurable way and so you can also use these trajectories to come up with reasoning traces kind of at a pretty good scale and so right now we have these agents running through the data set we just give them 10 binders and 10 non-minders give them a budget of 100 molecules and they'll go

1:19:28through you know probably like 102 holes where they're just going through this long many-step reasoning problem and then come up with what they think are the answers to the best at the end so why do you think this is superior to something like hermes or maybe like something you know sort of scaling up the hermes approach where you're you know sort of building some you know attention yeah we think so we think it's much more resistant to the memorization problem and so like while we are very happy with where the attention goes with hermes when you throw in

1:19:59all these mutants like as you add more parameters to a model like they're going to memorize the mutants too right like and we want this thing to really understand like these causal changes and it seems like using natural language it's like a pretty good regularizer for the problem and like we are unaware of other problems where you have a reinforcement learning loop that is physically grounded that is this scalable this fast like you can imagine for you know when you're doing lab in the loop stuff where you're going off and making robots and going after these problems they will also necessarily

1:20:29require like limited resources they will still make some choices about what to make in the first place what not to make in the first place and then doing those loops will take a little bit longer and if there's a scalable way to measure that landscape and then continually make that bigger and bigger and bigger it's allow the agents to play in it we think it's probably going to go a lot faster for this particular problem that's interesting yeah i mean you i would say it's close it's excel from zera is getting there but they're not actually language there but they are encoding as a sequence so it's in some ways

1:21:01the perturbation is similar but this is yeah this is different and then lila also rhymes with this but it does like all these guys are really smart and pushing like these automation things yeah but but but they're but they're they're not um doing these pooled screens and then using that as they haven't as far as they know haven't figured out how to make that into a just a database lookup so you can do huge number of rollouts yes yes so right now the way that we like to think about it is if you're a medicinal chemist uh and you're working at a pharmaceutical

1:21:32company you do this thing called a structure activity relationship and what that means is oh when i change the molecule in this way it changes the behavior and so i'm trying to optimize for these different properties and you go through what's called an sar campaign that's early drug development it's making the molecule better um you might see a couple dozen of these maybe 50 of these in your career and so right now you know last weekend we pulled out over 10 000 of them and we're not even trying that hard right so yeah and so now is the opportunity now it will be restricted to the space of things that we have screened and then at

1:22:04the end you can ask the models to make additional choices from say catalogs and then you can go you know in the future go order those and retest them like you might for like a traditional lab in the loop approach but right now we give these agents 10 binders give them a budget of 100 and they'll get the best binders out of six and a half million in that budget and so it seems like it's working yeah so like tell us more about why you think this is i get the argument about it's a better regularizer it's but also why why do you believe that this is effective

1:22:35right so like um you can imagine well it doesn't get things wrong so badly but it also doesn't get things that right but it's i think it's because you give it the opportunity to make all those choices i mean it's like running these coding sandboxes you just have like really rapid reinforcement reward signal and but the thing is you also have to include the choices that a human being would not have made because we're measuring all the molecules across all the proteins yeah so it has to be able to make the counterintuitive decision and get a feedback on that it's got to have the counterfactuals

1:23:07it's got to make mistakes yeah and you need to make sure that the mistakes are you know present in the data or future potential mistakes are present in the data in ways that are not really biased for it to you know learn chemist sociology fingerprints yeah that's that's really fascinating so through all of the you know language pre-training corpus it kind of has an intuition for some basic chemistry that i think most medicinal chemists might have an idea of and now you're giving it sort of like an infinitely fast lab in the loop that's correct so maybe reasoning too i would say that the reasoning skills might even be more important right the ability to

1:23:38say oh in my reinforcement campaign i've learning campaign i've learned things and now now that allows me to reason about the next harder question and then just keep making choices yeah you know and and you know right now we like we're really excited about the early signal and also you know like we're a tiny shop right there's only 10 of us like i'm really looking forward to when uh you know our experimental corpus grows you know like 2x 10x you know like 100x the rate that it currently does because then like the amount of space for these agents to explore like expands dramatically let's talk about that space because

1:24:10so my understanding and this is from me like you know talking to claude and googling and whatever but my understanding is that dells are they're like limited in that they are they tend to be create flat molecules or flatter molecules it depends on the building blocks okay it depends on the building blocks yeah so there are you can imagine that um you will be somewhat constrained by designs in terms of like oh i'm going to get some number of building blocks usually two to three and then stitch them together in some way and so like when we do uh chemical library design choices typically it's like like one one that we run a lot right now is a

1:24:43forked design it's like a y-shaped molecule and then there's other ones that are linear shaped molecules there's yet other ones that are kind of like circular kind of macrocycle shaped things um and then you have to think about where is the dna going to go and like how is that going to cause me problems and then also the the commercial availability of building blocks and the chemistries required to stitch this together you can go for custom stuff takes longer it's kind of more appealing to us to go faster yeah and there's certainly going to be corners of chemical space that we're probably bad at and then you have to think about oh well future libraries should have this kind of geometry and then i got to think about the different proteins

1:25:14you're going to throw at it and there'll be like a pretty uneven distribution of like a whole chemical library made this way might be really good for these types of targets it might be really crappy for these other types of targets and so then you get to think about all right what am i what corners of protein space am i optimizing for and those kinds of tensions yeah so so it sounds like the argument is well we know that we're not optimizing the whole space but it's a lot more than it was before so that's better and then we are as we get better at this and understand or we have bigger budget or whatever it is then we'll

1:25:47expand to these corners that we know that we're lacking in but or maybe we don't even know we're lacking in but we will find that out right exactly exactly do we want to move on to the uh last phase yeah you can go for it let's see how it goes all right so uh for the audience context um ian uh requested i want to confirm that this was his idea not mine it was what you might call it a don't ask me or uh come at me bro section where we we ask the hardest problems we can cut we can come up with which is we probably tell is not very hard for me

1:26:19yeah but we i think i've asked my hard questions already we only had about uh 24 hours to prepare so i think most of these will be claude's hardest questions but uh anyway we'll see how this goes yeah the context for this is i was at um i was at a cancer molecular therapeutics meeting last week and uh and the the format of the meeting is half of the time is for content presentation and the other half is for very aggressive grilling uh and it was uh it was it was horrifying and inspirational and so uh here i am willing to do it in public let's do this dells as uh rj was just alluding to

1:26:51oftentimes have very specific properties um and you can get very good at optimizing in dell but ultimately they frequently fail at certain things which are hard to translate to actual medicine yep so certain failure modes being such as anything which is easy to assemble is easy to disassemble bad for you know admin properties you only have so much room to kind of build on because you've already sort of used some of the combinatorial building blocks and so on anyway how is this limiting in terms of like long-term out of library generalization i think a lot of it is going to be

1:27:24somewhat dependent on like building block availability and like one's uh willingness to go into custom synthesis so if we're especially for the fine-grained mapping stuff you know being able to say move a nitrogen all the way around the ring at all one of those positions is something that's very very desirable but it's also something that's pretty unlikely that you're going to get like commercially for all sorts of building blocks that you're currently generating so like is that going to be a failure mode for sure yes yes i would i would love to be able to get more of those and like beef up our custom synthesis that's something that we're looking at uh but right now trying to get those is challenging one critique that claude might be thinking about in terms of molecules easy to

1:27:57put together and disassemble for many years it was uh the most common built a way to attach uh building blocks you need to tell chemistry is amide bonds or protein bonds and so those are quite digestible uh you know in in the body uh but in the past few years uh they're really really past like four ish years um there's been like a really nice um fluorescence of chemistries that are friendly to dna that don't destroy it during the attachment process because that's very important that will give you carbon carbon bonds carbon nitrogen bonds these kinds of things so it's actually pretty good for work a day simple chemistry yeah so like i'm actually not too worried about that part

1:28:31i'm more worried about building block diversity uh and there's sources for that yeah what about admitt properties in general like you know you've been focusing very much on binding we have yeah so uh of projects that we've done uh trying to look at reasonable admitt and like pkpd properties for what it's worth we've gone directly from uh from chemical library hits to good pkpd in a mouse in six months with a very small number of medchem cycles so at least chemical material that we currently have or at least that you know those few series that we did that for uh you know they turned out pretty good in our hands i guess you know we will continue to see like how that modeling

1:29:05looks and also of course we want to do more of these like admit target models and then think about how to incorporate other types of you know more emergent models along with our designs was that speed driven by your ability to create custom like local combinatorial libraries or was that speed driven like what allowed you to get there in six months like um the drift so we when we designed this chemical libraries at the beginning we very much optimized that space uh for drug like this and so we think that's part of it is that was like a really good starting point you know when we do our chemical library designs uh we have this uh kind of like thompson sampling

1:29:37level approach where we come up with a optimization function you say okay well i want the libraries to have these properties and so some of those properties are going to be i want to bind these things i want to avoid these things and then some of these properties are going to be oh there's other admit model approaches that you can use to make predictions about how your chemical material might turn out and so you put that as part of the optimization function and then what you do is you say okay of all the chemicals that i could make given my geometry i don't want to make that many i want to make a smaller number uh and so you you can you basically set up and generate a bunch of synthetic libraries

1:30:08and you score them on this optimization function and so we did that with this library uh and the starting material looked pretty good so i'm sure that we'll continue to do that along those same lines is has anything that you've done like made it to so it made it to animals yeah so pkpd in a mouse is that's yeah so what that what that means is uh can you dose the mouse with the thing uh and then see how it gets into the mouse's body and tissues yeah so pkpd is pharmacokinetics pharmacodynamics meaning yes how does the body move the the drug through the or how does the metabolism move the body

1:30:41the drug through the body yeah and then are there biomarkers of the drugs uh intended activity and so what that means here is this is like a drug this is a compound we're working on for inflammation and so we were following uh cytokine levels in mouse blood and they and they did what we wanted them to do and expected them to do based on the targets of the drug so uh sean uh likes to ask when money i want to ask when people yeah i mean for those we talked to we have a couple of these things uh that we're talking to folks about partnering out to spin up new entities to go chase them down

1:31:12okay and so yeah and of course like all these things take like sometime you've got to do like there are these traditional things forward once you declare what's called like a development candidate then you've got to do a bunch of other work about manufacturing and additional safety work before you can get into people so all these things take a lot longer yeah and so you're going to spin out the idea is to spin out a so people maybe even internal they will say like i really want to take this this thing to market or try to get it like take it to the next step yeah i mean one way that we kind of think about it is um you know we built this really great engine for like data

1:31:44generation and and model training and now as we've talked about like these reinforcement learning reasoning approaches um and most other domains when you build an engine to go do that stuff to go like help on those problems um the subset that you're generating along the way is not itself intrinsically valuable no one wants to sell reasoning traces about like political theory but like there are going to be a little bits of gold that we have generated as a consequence of doing all the screening because you're actually reasoning about not only that this model is good or sorry this molecule is good but

1:32:17that this here is why that's good here is why that's good and here is chemical material that's proprietary to us that has you know activities that are you know protein target classes that others might find hard to drug right and so you've got starting material for you know right now we have starting material that looks pretty selective to us for uh i think like 700 targets like it's enormous number uh you don't want to chase all those down uh but you know as as opportunities they are all opportunities with different levels of you know kind of economic value capture and desirability and so you think all right well we got all this stuff like let's see what we can get out let's see

1:32:50what we can get out of it discovery is like a small percentage of the total cost of developing a drug and you can argue that well you have lots any given discovery is cheap maybe but that you know because of the failures you have a lot of them so but even then you know to get one drug one drug like all the steps of a single drug candidate that is successful is maybe you know on the low side 200 million on the

1:33:21high side a billion um depending on who you have to test on and lots of other factors but and then you know the discovery is a couple million so so are you tackling the right problem here um and so i think there are a number of early discovery problems that are worth that much you know like like reasonable amounts and so what does that mean there's a bunch of targets right now with like really good genetic evidence that are very challenging to drug with small molecules um you know a pretty straightforward

1:33:53example is uh for a lot of these um uh kind of cytokine inflammatory indications folks are using antibodies to drug them and going after a small molecule therapeutic that you could take as a pill instead of an infusion one that doesn't require uh like cold chain you know transport uh to get to different patient populations like having those things is enormously desirable meaning you have to have refrigerated trucks yeah right yeah like and like if you want to get these if you want to get these antibody-based drugs to some of these folks like this is like a very hard problem yeah and very expensive and so and so folks are like really quite excited about can you find a small

1:34:26molecule therapeutic that does the same thing uh that antibody against these like so there's some antibody it's it works yep and so you're like well why can't we just go after the same target with a small molecule and it turns out that those proteins are very hard to drug for a variety of reasons but we like to think that you know the technology that we're developing can can get good material and so we do in fact have selective material for a lot of these cytokines and so that's one example of something that's like a very desirable target where of course like there's going to be much more uh capital requirements to like get it across the line to actually get it to market but the interest is sufficiently high enough so you're going to ruin

1:34:59the antibody market basically i mean if like if you can like and it's good for some stuff like it's great for some stuff and like there's a lot of energy being thrown you know at those groups because we're good at protein folding yeah and so like they're making a lot of progress and maybe more broadly i would say is like going after the right problem it is a little bit of a lamppost problem where the things where we can make enough scalable measurements in the life sciences are these early problems we can't really run a million mice experiment right like we can't run many millions of phase one trials and so we're going to get better at that stuff we're going to start to like go up these different

1:35:33layers of biological abstraction with like better data and better reasoning and physics models but like right now like the the technologies that we have to really make the number of measurements that we need are going to be like these early approaches i think yeah yeah and i would argue also that you can if you have a oracle some ai oracle that says oh this like all the admit properties will be good and this generalizes to exactly this population so you have this oracle filter then all of your failures in clinical trials go away yeah you can imagine a world where you can come up with an org you

1:36:04have some new target that you know some new evidence that covers uh and then the oracle could give you small molecule material instantly that you would feel comfortable running straight to like a mouse study right right so but that requires training on data from mouse studies clinical trials whatever i mean maybe i mean i could say definitely like admet properties if you're confident in the target and you need to make sure that it's not hitting all these other off targets uh but even then like that's you probably don't need clinical results to feel the confidence to run off and run a mouse study right away all right well we're on you know everyone's favorite pet question my favorite

1:36:35pet question is what i call the kosari paradox of machine learning and yes yes um okay so uh shrie kosari bless him great tweet i love this guy it was uh yeah yeah i mean he he was honest a few weeks ago we hopefully will release his episode in the next few weeks um sadly i actually didn't even bring this up on the episode i'm so disappointed anyway uh but yeah the tweet is basically what is the business model in machine learning for drug discovery because in order to build a good machine learning model you need lots of data in good high quality data at scale you clearly have

1:37:09that but then if you need that to train the model like what do you need the model for because you just go collect the stuff and you clearly can collect this stuff quite well so yeah we talked a lot about data collection we talked a lot about machine learning and i i'm actually kind of curious in some ways like where does the actual machine learning is it necessary for your business model so i mean of course it would depend on the business model i think if your only rationale is to go off and get good chemical material for a particular target then of course re is right right you would have it you

1:37:40could get started if you had enough chemical material broadly cast across all these other targets in a way that can uh you know kind of drive a deeper machine understanding of the chemical behaviors then the way by which you optimize those early materials have the potential to go much faster especially if you can do it at the scale that we've done it especially if you can do it at like the low capital infusions that we've been able to do this we have not raised a lot of money at leash and we screen it in a enormous amount and then i think getting even you know kind of even stepping back you know one of the reasons that i brought up this language model stuff is because we are

The business model of machine learning in drug discovery

1:38:13starting to wonder if it would enable uh you know a much larger sort of like scope of capabilities than just identifying novel chemical material like if we get really good at chemical reasoning then we can get really good at lots of different industries and their applications without having to physically go and screen in all those different domains like what's an example of that uh so let's say we get really good at making these predictions then we can run off and go work in agriculture like immediately right you could go work in veterinary science you can work off material science and

1:38:44you don't have to if you're really good at it that you don't have to screen all those proteins too because you have like a good fundamental understanding of this right and the same thing could be argued for like all the protein folding companies right it's like now that these models are good there are teams that are going after protein targets that have not been screened yet or are very challenging to screen and getting like really good starting material like the novel guys did it with this uh basically like uh a receptor on cells uh that has like a little tiny piece of a mutated cancer gene that's like really hard to do uh and they managed to pull it off and so you can imagine

1:39:15know there could be a world where we do this with small molecule material as well and so like i don't think street is wrong uh in terms of finding like start you know if you're just trying to drug this one thing you screen a lot and then you already had the thing you don't need a model for the thing uh but that's not exactly the same as generalizing across all things and you know we are hopeful that if you have enough of this variation engineered activity cliffs that you will actually be at a point where you can do all things at which case at which point you don't need to screen it all ever again yeah well and arguably you guys i don't i don't know exactly how much you raise so i mean you're

1:39:45for a campaign you're talking that's like a couple campaigns you that would cost the same amount so uh yeah yeah i mean maybe to put some real perspective on it um so we have uh developed and screened about 2 000 different protein constructs um a total of probably about 5 000 screens in the history of the company across at least six and a half million molecules each um which i don't want to get into like a like a huge numbers game but it's certainly almost as much as anyone else on earth maybe more

1:40:16than everyone else probably not there's probably a couple groups that like if you know but like the number of mutations i think it's probably more than everyone else that seems likely to me uh and so yeah like we just put a huge amount of work into making this like very cheap and very scalable and if i was doing one at a time yeah if you went to a cro and you did one at a time it would probably cost you 100k each depending on you know how much handholding you got right yeah you just said five million six was it six and a half million molecules yep that's not a lot of molecules especially since it's combinatorial space you know everyone will say 10 to the 40 or something 10 to 60 uh big numbers yeah i mean obviously you don't need to understand all the

1:40:51chemical space no you just need to make drugs consistently repeatedly that's that's your goal but is that actually enough chemical space to meaningfully do anything outside of your chemical space great question um so the the the pleasant answer is um you know i said earlier that we have trained models on internal data only and that we're able to extend and make generalized predictions into chemo which is very different corners of chemical space so yes do we think it's enough not remotely you know it's so part of our roadmap before it is making you know larger numbers of chemical libraries in

1:41:23different corners of chemical space and kind of spanning kind of what i talked about earlier where some are like these very fine-grained changes to more appreciated activity cliffs and then the other side it's like these big course changes to try to capture uh new proteins and sort of protein shapes this isn't sorry not not a hard question just i'm genuinely curious are you able to predict like potency like relative potency meaningfully like can you do kd curves like where you you know titrate like large more and more larger libraries or so people have wrestled with this a little bit in terms of trying to get the kds directly out of dells doing things like maybe varying protein concentration

1:41:56is something that folks do one thing that we see is uh when we uh when we do replicates of screens we get back the same hits in roughly the same order which makes us you know kind of optimistic that you could get these kinds of things we started to move more into uh spr biophysics related measurements try to figure out if we can maybe come up with like a like a potency ladder that we could then be as part of the chemical material that we're screening uh to try to capture those things but i won't say that like we're good at it yet like you can't use like you can't just use reads as a proxy for kd or

1:42:26something um i think the relative ranking yes but i think reads for kd rates reads for kd not really and then you start running into weird stuff so like there's lots of proteins that we've encountered where it turns out like the dna barcode itself there there are proteins that are not described as dna binders that we have discovered are and so you can imagine that that might affect the kds of things and you have to figure out how to mitigate those problems and that kind of stuff so like yeah it's i think the relative ranking is something that's quite doable i think translating it into kds is something that we're actively working on and we think we might really get like some reasonable you know kind of like sloppy translation but i wouldn't say that we're there yet okay this one this one was

1:43:00pretty brutal the bitter lesson that yeah i'm just gonna read this this one is pure clod i had no thought in this the bitter lesson is really the law what stops a better funded lab from outscaling your dell engine oh yeah of course people can ask us this um so and the reason like you know here's what i would really say is that uh both at leash and at recursion uh my team has made so many mistakes in accidentally bumping into the cheating modes that just kind of come out of the consequence of doing laboratory work there are so many of these and and so like you have to chase these down and a

1:43:34lot of it has to do with tracking batch effects with metadata for example and so then you have to build a culture at your organization where it's like all right we have to track all these things you have to build tools track all these things we have to make those tools frictionless that the people doing the work actually will record these things uh and then you have to go back and look at all the data back into this founding history of the company to make sure you're getting really consistent results and then when you see big changes you have to identify what drove them then you have to mitigate those and it's just like it's like a huge huge amount of work and we also rebuilt kind of from scratch the selection process we rebuilt from scratch a lot of the protein

1:44:07expression process and then we have all these other proxies that we use to evaluate how well the protein production when and if it's good or it's bad and these other filters and it's just um it takes kind of a unique culture and patience and willing to make these mistakes and then have the team like really think very deeply uh about how to address them and i think unless you've got folks who you know really have a nose for these kind of experimental mistakes it's going to be pretty it's going to take some time to replicate process mode yeah i really think so there's just so many things where it can go sideways and you have to be paying enough attention all the time to identify them

1:44:42when they're going sideways and they might be things that you can write automated filters for and maybe not early on um and so like you know like one pretty good example i'm happy to talk about is um people ask us a lot how do we know our proteins are any good we have lots of ways to figure this out i think one of my favorite ones right now is um we have noticed that when proteins misfold and we're able to identify misfolding in very crude cases like if you put the protein you know run it on a gel which is this protein trick where you try to figure out how big it is um and it misfolds then you can kind of detect that but if it misfolds a little bit it could be hard there are drugs

Removing bottlenecks and scaling future sequencing

1:45:16whose job it is to refold misfolded proteins called molecule chaperones okay you can call creatures too that's what we would call them yeah uh there's a very famous one that treats cystic fibrosis patients called luma caftor we have a bunch of chemicals in our chemical library that looks like luma caftor this thing whose job it is to refold misfolded proteins guess what kind of proteins it hits when we screen them cystic fibrosis uh misfolded proteins oh yeah that's what it's for it's all like and it's in our libraries and so you know like and we discovered this by

1:45:50accident like we saw this you know these chemical series keep popping up across all these different protein types like man like what is that is that luma caftor and then you start looking at the protein expression and then like how it went it's like oh it it goes when when things aren't going well and so now we can use it as one filter for if we think if if we get a bunch of luma caftor heads that protein probably didn't fall fold right we probably don't want to use that as training data we probably want to rerun it with slightly different conditions that make it more friendly to the protein then we'll see what those hits look like and so like unless you're paying

1:46:20that kind of attention like it's really i mean it's really hard yeah and you have to build tools so that you can just look at these things and have people who know to look for these things and recognize them it's uh yeah it's it's a hard problem yeah going back to uh everyone who touches dells comes out traumatized somehow you've uh you figured it out you're also traumatized but in a good way yeah no it's really hard that's you know and that's why it's it's and you know when you have the motivation to just finding like one or two really awesome hits to start off a drug program like

1:46:52then you're not going to chase down like all of these different aspects of the assay and so i get it but like if you're motivated for it to be machine learning fodder then like yeah you have to pay attention to all this stuff one of the questions that we always ask at the end is if you could buy fiat remove a bottleneck what would that be no when i think about buy fiat and it's one of these things that is actually currently happening which is watching the sequencing costs drop like a rock like i'm thinking about okay what do we really want to do we want more chemicals and we want more

1:47:24measurements those are the things that i want to make my life a little bit easier like at the problems that are immediately on the ground so you want sorry i don't understand cheaper sequencing more molecules okay yes in sequencing like can you give some context for how much it's dropped oh my god like many many many orders of magnitude it is uh i think the first genome cost a billion dollars and now we can do a human genome for a thousand i think it might be a hundred a hundred it's really cheap yeah there were stretches where it was dropping faster than moore's law yeah was sorry yeah and what so wait why then why do you want to even cheaper sequencing oh i just i'm

1:47:59just i'm just happy with the trend okay yeah what would you remove it by fiat if you like that hasn't been removed yeah here's a good thing what i would want is there are different gizmos that you can use to kind of purify small molecules okay so when you uh right now when you make them you you put some stuff in a pot and you heat it up or do some other conditions and you get the output and and that will work at some level of efficiency might be great might be crappy and so in either case especially if it's crappy there are these other gizmos that you can use to kind of clean it up so people use

1:48:31like hplc or some of these other tricks none of them are super parallelizable that are really really good and so being able to like clean up stuff at a massive scale would be really really nice because like we you know well what do we want to do we run all these molecules in this funky assay that we've already described has given people lots of trauma it would be great to then get you know large numbers of molecules in a different assay that would be really clean and purified and easy to work with uh and then go do that next because then you could really orthogonally validate all those measurements that you're making so yeah that'd be really really nice and of course everyone

1:49:04complains about like gpus and stuff like everyone says like besides gpus all right so and then the other question is um what would you like people to take away from the episode i would like people to take away from the episode that like you know at least for us we we believe that we're building something that's really really exciting and you know like what feels like physically grounded substrate for all sorts of interesting reasoning and biomedical applications and so if that's of interest to them like please reach out to us like we're you know we're hiring machine learning people we want

1:49:37to talk to partners and so you know we're building this thing that we think will be transformative so come talk to me amazing cool that was great so much fun thanks thank you for coming thank you yeah yeah