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

My cofounder Andrew Blevins and I were at Recursion looking at, a small molecule on a screen. And then a medicinal chemist walked by us, this guy named Mike Cucarizzi. And Mike was like, hey.

Looks like a Stuart Treiber molecule. And then we were like, oh, no. You can tell just by walking by?

Would you 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.

And so Well, did learn something. They learned like this. Yeah.

They they they don't learn physics. We downloaded all chemicals from all chemists at Kimball, which is the biggest repository of these things and their activities. Every chemist who published more than...

I think it was 30 papers in 600 molecules. So you get all molecules and all the stuff. It's 1,815 chemists.

And then we tried a 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 probability of creator.

So 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 chemical. 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 on the exhaust, you might be in trouble.

is there anything about us that you want to tell us before we get started? No. Thanks.

That was very kind. Yeah. We we founded Leash historically after 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 kinda try to go after it. Yeah. Yeah.

So reasonable scale.

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, 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 kinda takes forever.

And then a 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, kinda 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 is 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 Dell's, the largest one that has been produced is 40,000,000,000,000 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 That is correct. Yeah. Yes.

Yes. And 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 gonna 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. But 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 we're gonna 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.

Right. Yeah. I would definitely say that it is a party line at Leash that if you're gonna 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, and 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, Incedra does that.

Then almost everyone else with the spatial omic stuff or or other approaches, they'll do some mixture of of pictures and, you know, and sequencing, which is is also pictures. Yeah. There'll be some proteomics people out there who are gonna, you know, disagree with me, but I I I...

I'd still argue the scale's not there yet. Hot take number one.

well established technique. Like, we're very is good at it. It is very, very cheap.

It is getting cheaper all the time. There was a little while where it kinda 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 costs dropping and it has implications for how we think about data collection at the scale that we're doing.

Yeah. It's really nice. That's cool.

So 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 gonna 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, let'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 and electronics that they're gonna bind into this very distinctively shaped hole. 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.

So amplifying 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.

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 gonna pull out certain chemical libraries, chemicals from the library. And so you've gotta think pretty hard about all those things and make a reasonable comparison to the thing you're actually trying to to get binders for.

one protein? Great question. For one small molecule.

For one small molecule. So there's a couple things. One thing if we wanna get into the kind of a 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 in the DNA that might make them amplify faster than others, and so you wanna 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 gonna 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 or 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.

Yeah. And so that can be risky. And that can cause false positives.

Right? Very much so. Yeah.

A lot of people complain about this. Yeah. This is kinda to the earlier comment about folks having del...

Del 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. Because here's one small molecule. That'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 then its neighbor, which is the same chemical formula, will have a different barcode Right. And then so on for So if there's any differential there, then you know that you That is correct. That you're binding to the DNA instead of the That's right.

The cell molecule. And so and so for, like, the the DNA protein aficionados in the audience, one 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 the...

You recover the DNA sequences back from this experiment. It's like, great. We found the consensus binding motif.

Right. So I think our protein probably got made right.

Barcode tags, like, hanging off your molecule? It doesn't impact the Yes. They are happy.

They are happy. This is another complaint that people bring up about Dell's. There's a couple different answers here.

I would say, but the very 10,000 foot philosophical answer is that there are two different or there are multiple different reasons why you might wanna 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 gonna progress into drug programs. And so if that is your main goal, then you wanna 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 gotta 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 are 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 truth signal, feel quite good it.

Okay. You 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 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 we put...

We very much put in a placeholder that that that marks like the position of the DNA. If you're going to synthesize this for a drug, will you leave that No. Like I said, that's that's where you get those attrition rates.

Right? Okay. And then you've gotta make it, and and sometimes they behave differently.

Okay. I see. But...

Yeah. Yeah. Let's unpack action.

Got it. Got it. Got it.

So Sorry. No. No.

No. Just needed to understand that. No.

Actually, that was a... Those are really good questions. Those are really good.

Yeah. Yeah. Like, there there are lots of objections, and the...

And, like, there's one re... There's... These are many of the reasons why folks are trying to do the thing that we're trying to do.

Yeah.

when Dells were invented, it 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 and 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 wanna 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 and and they have maybe tried a bunch of other techniques, and they haven't worked out. So, okay. Let's try DELISCREEN 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 DEL 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 gonna run some functional assays to convince themselves that, oh, it's really gotta be this good for us to go off and run this screen.

And then when they run the screen, they're gonna try to maximize their chances of getting pretty good chemical material. And so then the incentive drives into a place where we want 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 in hopes. And that... And that's their motivation, and and it makes a lot of sense.

What we have done that's very, very different is we, you know, 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 wanna get tons and tons of active chemical material across large numbers of proteins.

And so there we can identify how our DELs behave very, very well because every one of our chemical libraries gets screened against many hundreds of targets. So you're characterizing the The chemical library. 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 the 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 people at the company come from real, like, genomics methods development backgrounds as compared to chemistry backgrounds.

And 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 cofounder, this guy named Andrew Blevins, and a number of other people on our team.

And we all made, you know, honestly, like, 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 for thinking about, oh, well, you know, there's these sources of noise this way. We're gonna have 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.

I would say that there are four that I... I I 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 Invader with Vishwa Kaluru and and August Allen and and Hannah Gordon and all these great people, Dave Healy. And then there's also Known Medicine that was run by Katie Ryszkailey that got picked up by PATHUS 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, oh, we're pretty good at noisy measurements. Let's try to see if we can get...

Can signal a lot at this particular corner. You know? And so for us, it's a small microchemistry problem.

For Invada, it's it's mixtures of natural products. They use... They do do a lot of, like, you know, of mass spec kind of stuff.

And then there's Ron, and then and then there's Katie Reyes' group. So, yeah, we're all very similar.

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 and 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 that's not familiar, what is a small molecule?

Why do we care?

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 gonna try to interact, 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 that 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-one treatments, you're gonna have to have kind of an injection. 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 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, have a little tiny chemical. And tiny chemicals, small molecules here, are things that can be in pills. They 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 life scientists in the twenty first 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 Nobula. There'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 for protein behaviors that that make it reasonably effective, you know, for 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.

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 and 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 to stop causing those problems, does it affect it doing the thing that I want it to do?

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. So And that's something that we are very much pushing forward to is, oh, let's also make those proteins.

Let's also screen those proteins with our chemistry. It seems useful if you have a giant assay of That's right. Different proteins and a library that you can Yeah.

It is it is not at all an exaggeration to say that it is our aspiration to have screened every protein. Mhmm. And then also move on to those outside of humans.

Mhmm. Both for reasons to get variation of the proteins, but also to identify maybe you don't wanna 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.

Interesting. Right. So you wanna do that stuff.

But yes, going after large numbers of these things allows you to think, alright. 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.

Mhmm. 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, if it does 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.

We'd But to think that models that have a good understanding of the biophysics themselves can be useful and maybe fine tuned on smaller datasets in the future. Popping back one more maybe and get... Maybe getting a little into the model.

Why why Dells? Dells 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 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 might 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, the word might be arrayed libraries, or libraries that are in one chemical at a time, in a tube, or in a well, in 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 Adell's, maybe worse. Adell's 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 3,000,000 physical interactions. And so we released a dataset that was about 4,000,000,000 physical interactions, and it was all measured by a single person in the basement of my house.

not by a long shot the first group to try to evaluate whether you could use computers to 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 X Chem and Google some years before before we founded Leash that that 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. So we wanted to put together this contest and design the evals in particular in a way that could really test it across a range of eval difficulties. We're...

Because we were thinking about, okay, we're gonna have a lot of people, hopefully, a lot of people compete in this. Some are gonna be very good. Some are probably gonna be beginners.

We wanna 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 at the very top end of what would be difficult here, what we imagine difficulty might And so to kind of unpack that, we've talked a little bit already about how these libraries are combinatorial, so you're gonna have some smaller number of building blocks, but a large number of combinations. We got our hands on a chemical library from a a wonderful sponsor, this guy named Xiaojie Liu, who who runs a shop called Alpha Ma in Shanghai. And the chemical library was about a 130,000,000 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. It's a 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 dataset. Let's have a a couple different ways to split this. One way is that we could say, alright.

The chemicals might have one shared building block, one shared spoke, and then the other two spokes are different. Okay. That's one thing we could do.

So let's do that for some, and that was the easy stuff. Another one we can say is, alright. Well, maybe we're not gonna have any shared building blocks, but we do know that if they're gonna 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 gonna be a little bit harder. Sounds great.

And then for the third most difficult eval, we had a completely different chemical library that 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 gonna do...

We're gonna have these three in different proportions. We're not gonna tell anyone that's what we did. We're just gonna say, here are the evals, and let's go see how it goes.

And so we launched the Cloud 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 on... Did, you know, o...

Okay on on the stuff that were... They were shared building blocks. Depending on the target, we saw some boosts in performance for where there were no shared building blocks, but the core hub was still the same.

The triazine 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, 2,200 just random person who submitted a a Jupyter notebook. Right? It's a thing for Yeah.

So the so the winner was this guy named Victor Schlapov who put together a slightly different approach, but... And and his his was good, but again, like everyone else, no better than Chance. Three of the top five were the noisy tutorial notebook.

recent advancements and kind of, like, cold folding approaches would mean that it would obviate our company entirely. Like, we Didn't happen. No.

It didn't happen. No. But we we were like, you know, there's like a small chance.

Like, we are really messing up here. And that didn't happen. We suspected more likely that folks weren't very good at it and that the data might help, and so we're hoping to see that.

One thing that we And anyway, you'd wanna know that. You'd wanna know before you started years of your life. Absolutely.

And 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 three d graphs.

There's, like, weird spherical, like, spherical convolutional nets. Like, people have tried kind of goofy things to try to represent molecules in a useful way. And there'll be lots of people on 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, and let's see how it goes. And we were grateful to find that, you know, like, 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.

Yeah. Translated into a a text string. And so you can start the graph at different points, and so there's, you know, what they call canonical and noncanonical 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 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 full force into this?

follow ups, but I I'm just curious to hear. Yeah. Yeah.

This is a great question. So, like, we we are extremely bitter less than 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. Yeah. Because if this problem is like all the other ones that we're aware of, if 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.

Yeah. There are a couple things that were... That...

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 this, you know, for lots of reasons, but 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 100,000,000 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.

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 to... We wanted to make sure that we're getting a lot of variation across both axes as compared to, like, one axis and, a handful of proteins.

Sorry. Which two axes? So that would be like the number of chemicals against the number of proteins.

Okay. Right? Yeah.

Yeah. It's a... When you have the technology, just do it.

Yeah. Two two building blocks. Yeah.

Yeah. Right? Yeah.

You can do whatever you want. Yeah. Yeah.

So that's the nice thing is you have enormous control over over, 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 thought into, you know, kind of bells and whistles in our own Dells to to really boost of like a performance and signal over noise and all this stuff.

But getting back to the of like the Kaggle competition lessons, it 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, you know, when Hassett that it's pretty far away, they... I mean, at the current regime, at that regime, they 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 Dell competition?

Like, maybe everyone's just bad. Maybe it's all first year grad students. And so as a result, we just released all of the data entirely.

And so if anyone out there thinks they're awesome, then like please show us, because like we want this problem solved.

All the evals, everything. It is it is all on Polaris, which is like a nonprofit group that was run by Recursion. It's it's there for anyone to use.

Please use it. You know? Like, we we intentionally released it as as, you know, hoping the community would would make good use of it.

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 and 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, well, know, I've got this time split on the PDB, for example.

And, you know, you know, our model's never seen these these molecules or 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, one's seen those before.

That's cool.

evaluated that, I think, and all the care you... Which went into that model. Hermes is a model that is the original brainchild of the data scientist at a niche named Mike Kleinstasser, Max Kleinstasser, and also Sean Francis Lyon, and 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 in different, like, 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. Was, you know, we wanna try stuff fast. And so we built Hermes, and then the basic architecture of Hermes is two different embeddings.

One of them is evolutionary scale modeling, an ESM embedding that's a protein embedding that comes from a group that was at Meta, then went off to start their own company, and then they got and they got picked up by Chan Suckerberg more recently. And so We had Alex Reeves on the podcast. Yeah.

Yeah.

So we did that for the protein side, and then we had a different embedding called Camberta, which is basically like a next token predictor chemistry kind of embedding to this side. Something which predicts Smiles... Or That's right.

Yeah. Yeah. Just predicts, yeah, Smiles tokens.

And 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's incredibly simple. Very, very small.

And then we trained some of our own data on it. Actually, you don't... Not the simplest.

The thinking with the attention was... Had to do with some other experiences that we'd had kind of with graph convolutional... Or like graph models for protein structure.

And one thing that we noticed is if you've got these sort of graphs, and there's a couple models that do this, and other work that we had done, we had scrambled the positional coordinates of those, and performance for some of those models more or less stayed 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 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.

in some sense, forces certain molecules to interact with certain residues in a protein. Yep. Or at least maybe not forces, but provides the opportunity for you to think about it.

It's it's an inductive bias. Yeah. 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 COG competition where we had, you know, training sets on data that we generate internally, and then we'd looked at chemical libraries that were further away. But then, also, we wanted to think about splits to kind of probe Hermes' behavior.

And so because Dells have this combinatorial approach, you could 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 is 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, then then you might have things that are, like, are close enough that that memorization or some other cheat mode might, you know, convert 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. And 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.

we did these different split regimes to try to evaluate how well things would do relative to, like, SG boost performance. And so one thing that was really really gratifying to see is that you see SG boost drop steadily as you get further and further away with these building block cluster approaches. Like, if you share two building blocks, it's at a certain level.

If you only share one, it gets worse. If you share one one, you know, only in none, it's worse. Then 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 gotta 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 published.

We haven't yelled about it too much. Wait. Do I thought you...

Do you have block post like XGBoost is all you Yeah. Yeah. We did that.

Yeah. That's why we did that. Yeah.

many years ago, my cofounder Andrew Blevins and I were at Precursion looking at a small molecule on a screen. And then a medicinal chemist walked by as this guy, this guy named Mike Cucarizzi. And and Mike was like, hey.

Looks like a Stuart Treiber molecule. And then we were like, oh, no. You can tell just by walking by?

And we were like, 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, you know, I don't know, every 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 gonna try to train models to understand chemistry.

So you're gonna 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. And so Well, they did learn something.

They learned you said. Was. Yeah.

They they... They don't learn physics. Right?

They're not learning the thing they're trying to get them to learn. Yeah. And so we were really afraid of this.

They learned that cervicimists are better than other ones. Yeah. We learned all kinds of stuff, but maybe to set to set this up for the audience, so we went out and, like, we, you know, we published this, you know, 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 Kimball, 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 molecules and all the stuff, It's 1,815 chemists.

And then we trained a classifier to predict a chemist from looking at the molecule alone, and we got a top five 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 work 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 have students or trainees, then they adopt some fraction of that, you know. And so that seemed pretty clear to us.

And so that was horrifying enough of on its own.

the field. Yeah. Like, you were not generating your own data, you're using this.

And then if you are generating your own data, then you are probably victim to this because your organization probably has multiple chemists who have their own distinctive chemical styles and that they're 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.

you're learning the style instead of the problem. You're learning the style, you'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, ordering a molecule to be manufactured and tested is kind of a pain, Right?

And then not making that choice is a fingerprint that that is going to land on what does get made. And then, you know, when you talk to some of the distal chemists, some of them are... You know, bless them.

They're superstitious people. And some of them will say, like, oh This is brand new Yeah. I bring this up, like, every single time.

Yeah. Medicinal chemists are some of the most superstitious people I've ever met. Right.

And so and so it's like, oh, well, this building block worked in this in this program that made it to the clinic. I'm really fond of it. Maybe it helps with solubility, so I'm gonna 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 model to identify who the chemist was, and then we chose to represent the molecules not with any chemical structures or formulas at all, but just a vector of the probability of Creator.

So now it's this 1,800 element 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 Kimball. And it does as well as if you use chemical formulas.

And if you combine them According to sociology only. Yes. If you combine them, it doesn't mean you meaningfully better.

And so, yeah, we 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 and the fingerprints of the people who are trying to develop these 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 two drugs by making the fewest number of chemical series possible. Of course, they're gonna do it like that. But when you train models on the 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.

No. Like, I mean, I think a good way of intuition is like, if a thing's working, they're gonna do more stuff to it because they like it. Yeah.

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.

Yeah. You know, things that you wouldn't do if you didn't think it was working. Right.

And so it's all these signatures that the models would just kinda pick up. And so, yeah, it's quite terrifying. So...

Yeah. This is this is like the horse something... Clever Hans?

Clever Hans. Yeah. It was the horse.

Can tell the story about Clever Hans? Yes. Yes.

Yeah. 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 eighteen hundreds.

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 like a a chalkboard that's got a math problem, and then the horse would stamp the horse's foot on the ground and then stop when the correct answer, you know, was was arrived at. And everyone was amazed that these horses are brilliant, and then someone had the good idea to go get a questioner who did not know the answer to the math problem. Yeah.

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 seven, then the owner gets, like, real giddy when it's at six.

Right? Yeah. And the horse stops stamping.

And there's this, like, wonderful paper put out by by a German psychologist who actually evaluates the the actual micro expressions and postural changes that he had observed on the horse's owner is is quite extensive. Okay. So, yeah, like, if you're dying for a silly read, you can go look it up.

So then the the analogy is that you're reading the face and not the math. Right. Yes.

Do not understand math. The models do not understand chemistry at all. They are just, you know, remembering the sociology of of the creators.

Got it.

To do something useful in the real world. Yep. So how do you...

How 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 seemed very obvious to...

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.

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. 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 of external molecules, and then we predicted them to see how well we would do across many different proteins, lots of different positives and negatives that we chose very carefully. It was, I wanna say, was like the total number of tests in the Hermes paper. I think it's like 13,000,000 or something across like many...

It's like 500 protein targets or something. It's some huge number. And then we benchmarked it against the existing, what was at the time, the state of the art structural model, which is done by the Boltz team, which is a very good model, and ours cannot do a lot of the things that that model can do.

But what we were able to do was about as well as those guys on those public datasets in terms of this binding problem prediction. When you compare to Boltz, it required some sort of tricks to kind of have a variation comparison. I think Boltz also trained on this data.

Was that right? Sort of. So there are a couple large collections that we we weren't totally clear on, like, the different subsets that they had trained on.

And so there... 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 a lot more molecules in there to go see how it would go.

So yeah, like I think I think there... And also, if you look at the different performances between Hurwitz and Bolts, you know, like, we're better on some proteins and protein families that that Boltz 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. Or, know, honestly, maybe, like, memorize a little bit more, and they're able to extend that a little 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 BRD four, where there's an identical molecule from our screen that was also in the PDB, the protein databank training set that Bolt had almost certainly seen. Our models did kinda 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 a crystal structure already as part of the training set. So they were awesome. Was like, 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 in the space more broadly? Or We hope so.

Yes. We hope so. Mhmm.

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 kinda to 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 in behavior? So a real classic example of this that medicinal chemists will talk about is this idea, 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 this one 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 the 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, two out of three building blocks might be similar across large numbers of examples and have variations of behaviors.

right, many at... 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 ignoring like the hydrogens, but you can imagine that they're building blocks that themselves are very similar with like a single atom substitution. Oh, I see.

Okay.

That's right. That's right. And maybe that thorn just changes position.

Then and 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 want super fine grained changes that are very, very subtle, try to really teach the models these very, very subtle differences.

And so as we think about designing our own chemical material, like, we have to, you know, 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. Both it also matters on the protein side too.

Right? It matters very much the protein side. And so as you look at current co folding models, a couple different groups have shown this, you can take a protein, and it's got this amino acid sequence, and it codes some protein that's got a big pocket in it, and maybe that protein's 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, or a small molecule or chemical in there.

So you got this pocket, the 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, 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 what the model will do. It will shove the small molecule in where the pocket used to be. Okay.

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 gonna be a small number of amino acids that will have hydrogen bond positions that are going... They're sticking out, and there's gonna 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 very, very important.

And and they are very important in the 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 it can't shove a molecule on there. And that...

That's the thing. It's 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 thing.

Right? You know, they don't have a lot of these variations that really, you know, disrupt these behaviors. And no one's gonna make crystal structures with a bunch of these mutants like we, you know, like we're currently doing for ourselves.

But how do you get negatives? The way that we get negatives is that we 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 drop out.

But this is a one off experiment. This is not Adele. No.

This is Adele. Oh, no. So you're just...

You're not saying you broke 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 the pocket is intact. Yeah.

Sounds great. Yeah. Okay.

We get a bunch of hits. Yeah. Let's let's go even further.

Let's say that we know someone else has already identified a chemical that goes in that pocket. Mhmm. Let's buy it.

Let's stick it in there and 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 that we have.

Oh, you have a competitive asset. Oh, we do that all the time. Okay.

Okay. We do this all the time. Yeah.

Okay. And then you say, okay. Well, that looks pretty good.

I believe that. And then you say, alright, 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.

you know, like we stare at... We have a structural biologist and staff that kinda look at these things like, oh, yeah. Know, this guy, Edward Craft, is amazing.

And so... Alright. So, you know, now we're gonna 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 when we broke the 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, Yeah.

And they come So you didn't just break the protein. You didn't just break it. Right?

And so... And then you think, okay, well, you're gonna be out screening a 100 protein constructs a week, which is what we do on big weeks, like Wait. Sorry.

So you've broken the pocket somehow. Yeah. Then how...

Do you also find that there are other things that do that start to connect to bind to So the when you change things around, you might change the shape in a way that does encourage other things to bind. We have definitely seen it. 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 Dell's is you can you can imagine, if you're not thinking in in large numbers, that, oh, I've got this one chemical that was binding, and now 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 on on the podcast or whatever. But the... It'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.

It's beautiful. It's very, very clear. Yeah.

Yeah. Go ahead and tell us about this plot. We pulled this thing up, 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.

And a reason that we think this is you wanna be able to get the... You know, a model trying to learn medicinal chemistry to really start to put together... You're having these hydrogen bond interactions between, like, this part of this molecule and this part of the protein.

We've seen other work that I talked about earlier about how you can... If you digitally break a pocket and you 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 us suggest that 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 rescreening. And so what that looks like Physically doing that. Physically take doing you take the DNA of the wild type protein that you've already screened, and then you use microbiology techniques to change 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 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 of, you know, wingers at each one. And so then you run the screen, and now when the pocket 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 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, and maybe you try to break all of them independently. And then you redo the screens each time, and get a good feel for what part of the small molecule is interacting with the part that you had changed.

And then when you do this with a large Dell, then you'll have lots and lots of repeated examples of similar molecules that are 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 is super common is this one little bit on the small molecule.

So I have a suspicion that it 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 made.

Along the axes are how well the small molecule's bound. So if it's 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 the one mutant that we made. So in this plot, there's on the bottom, the wild type target.

most of these to bind better. That's correct. Yeah.

There's a second mutation in that pocket that I can also share with you where all of the... All of those population, all those blobs get kicked out entirely, 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 correct. So you can give this for post production? Yep.

Yep.

So one thing that we've sort of written about is using these attention mapping approaches to have a look at where Hermes is looking at amino acid space. When we first did this work, we were expecting for it to either look at the binding pockets that was the first intuition and then maybe a more measured intuition was like, Well, maybe what we'd hope for it to do is maybe 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 nonbiology 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 then often gets shuffled among other proteins as well. Have this conserved region that's called a domain, or a conserved protein domain.

That part looks pretty similar across many proteins. It's something that biologists will use to infer protein families and relationships and functions. If they hold the same kind of piece, they're probably doing something similar.

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 typically do a whole lot. They're a little bit different.

They're non conserved. There's a lot more variation in those. We realized that Hermes was probably coming up with a nickname for the protein.

It's not thinking about, Oh, this is the functional part. It's like, I don't need to learn that. I can remember 10 or 12 amino acids that are different here than everyone else, and I can just memorize it.

And we thought that was bad.

similar, then maybe... And the variation in the pocket mostly don't matter, but some of them do, then you might... The model might learn, oh, I can just 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 the 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 and different behavior, it's gonna do a bad job.

Yeah. And so we went back and did model... You know, trained models with these additional mutations, like the one on this pot that you guys are seeing, and then, you know, looked back at the attention maps, and now Hermes will look at all of these things much more evenly.

in the pocket to kind of encourage it to pay attention to the pocket instead. Yep. Yep.

And it's not necessarily just to be across any one gene.

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 we're using 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.

tell us about what you're doing. Yeah. So we started this project a little while ago because one thing that we realized is that we had this 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 reasoning agents to go explore it and use it in a lab and 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, we did some Quinn's and GLM and, you know, this stuff that other people are using, 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 molecules in natural English. And then we got it to the point of where we say, okay, here are some molecules that are binders, here are some that are not binders. Can you tell us why you think the binders are binding?

Mhmm. And then you can also give it hard negatives. So you have these two collections that think, oh, okay.

Well, I think this chemical series has this, you know, and it will write these things down in in readable English, which we think is great. And then we said, okay. Now that you sort of know these basic concepts, we're gonna give you 10 binders and 10 nonbinders that are closed, ask you to decide why you think the binders are binding, and now we're gonna give you the opportunity to run your own experiments.

Here's a catalog of millions of molecules. Why don't you pick five or 10 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, it will 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 But you're do 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 rollouts.

It is a reinforcement rollout Yeah. Of of a large scale that's growing all the time that's full of these activity cliffs and full of 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 dataset. We just give them 10 binders and 10 non binders.

You give them a budget of a 100 molecules, and they'll go through, you know, probably like a 102 calls 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.

you know, attention thing. 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 all these mutants, Like, as you add more parameters to a model, like, they're gonna 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 is 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 and loop stuff where you're going off and making robots and going off to these problems, they will also necessarily require, 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 allowed the agents to play in it.

We think it's probably gonna go a lot faster for this particular problem. That's interesting. Yeah.

rhymes with this, but It does. Like all these guys are really smart and pushing like these automation things. Yeah.

Yes. So right now, the way that we like to think about it is if you're a medicinal chemist and you're working at a pharmaceutical company, 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.

You go through what's called an SAR campaign. That's early drug development. Let's make the molecule better.

You might see a couple dozen of these, maybe 50 of these in your career. And so right now Yeah. 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, we'll be restricted to the space of things that we have screened, and then at the 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.

I mean, it's like running these coding sandboxes. You just have, like, really rapid reinforcement reward signal. 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 gotta have the counterfactuals, it's gotta make mistakes.

Yeah. And you need to make sure that the mistakes are present in the data, or future potential mistakes are present in the data in ways that are not really biased for it to learn chemist sociology fingerprints. Yeah.

That's that's really fascinating. So through all of the, you know, language pretraining corpus, it 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. Would say that the reasoning skills might even be more important.

Right? The ability to say, 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, you know, our our experimental corpus grows at, you know, like two x, 10 x, you know, like, a 100 x the rate that it currently does because then, like, the amount of of space for these agents to explore, like, expands dramatically.

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 you will be somewhat constrained by designs in terms of like, oh, I'm gonna get some number of building blocks, usually two to three, and then stitch them together in some way. And so, like, when we do chemical library design choices Yeah. Typically, it's like like one...

The one that we run a lot right now is a fork 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. And then you have to think about where is the DNA gonna go and, like, how is that gonna 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 gonna 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 gotta think about the different proteins I'm gonna 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 and might be really crappy for these other types of targets.

And so then you get to think about, alright. What am I... What what corners of protein space am I optimizing for?

Do we wanna move on to the last phase? Yeah. You can.

Go for it. Let's see how it goes. Alright.

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. It was it was it was horrifying and inspirational.

I think a lot of it is going to be somewhat dependent on, like, building block availability and, like, one's willingness to go into custom synthesis. So if we're... Especially for the fine grain mapping stuff, you know, being able to, say, move a nitrogen all the way around the ring and all one of those positions is something that's very, very desirable.

But it's also something that's pretty unlikely that you're gonna get, like, commercially for all sorts of building blocks that you're currently generating. So, like, is that gonna 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. But right now, trying to get those is challenging. One critique that Claude might be thinking about in terms of molecules easy to put together and disassemble, for many years, it was the most common way to attach building blocks between telchemistries is amide bonds or protein bonds, and so those are quite digestible, you know, in in the body.

But in the past few years, they're really... Really past, like, years, there've been, like, a really nice 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. I'm I'm more worried about building block diversity than there's sources for that.

Yeah. What about admit properties in general? Like, you know, you...

You've been focusing very much on binding. We have. Yeah.

So of projects that we've done, trying to look at reasonable admit and, like, PKPD properties, for what it's worth, we've gone directly from chemical library hits to good PKPD in a mouse in six months with a very small number of med chem cycles. So at least chemical material that we currently have, or at least that, you know, those few series that we did that for, you know, they turned out pretty good in our I guess, you know, we will continue to see, like, how that modeling looks. And also, of course, we wanna do more of these, like, AdNet 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 The drift...

So we... When we designed this chemical libraries at the beginning, we very much optimized that space for drug likeness. 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, we have this of like Thompson sampling level approach where we come up with an optimization function. You say, okay. Well, I want the libraries to have these properties.

And so some of those properties are gonna be, I wanna bind these things. I wanna avoid these things. And then some of these properties are gonna 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. I have all the chemicals that I could make given my geometry. I don't wanna make that many.

I wanna make a smaller number. And so you you get... You basically set up and generate a bunch of synthetic libraries, and then you score them on this optimization function.

And so we did that with this library, and the starting material looked pretty good. So I'm sure that we'll continue to do that.

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 can you dose a mouse with the thing and then see how it gets into the mouse's body and tissues.

drug through or how does the metabolism move drug through the body? Yep, and then are there biomarkers of the drug's intended activity? And so what that means here is this is like a a drug...

This is a compound we're working on for a little bit of inflammation, and so we were following 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.

I mean, for those we talk to, we have a couple of these things that we're talking to folks about partnering up to spin up new entities to go chase them down. Okay. And so...

Yeah. And, of course, like, these things take... Like, sometimes you've gotta do...

Like, there are these traditional things forward, which you'd declare what's called, like, a development candidate, then you've gotta do a bunch of other work about manufacturing and additional safety work before it can get into people. So all these things take a little while longer. Yeah.

And so you're gonna spin out... The idea is to spin out a... So people, maybe even internal, they will say, like, I really wanna 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 kinda think about it is, you know, we built this really great engine for, like, data generation and and model training, and and now as we've talked about, like, these reinforcement learning reasoning approaches.

And most other domains, when you build an engine to go do that stuff, to go, like, help on those problems, 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. Like, there are gonna be little bits of gold that we have generated as a consequence of doing all of the screening.

Because you're actually reasoning about not only that this model is good or... Sorry, this molecule is good, but that 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 in, you know, protein target classes that others might find hard to 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, I think, like 700 targets. Like, it's an enormous number.

You don't wanna chase all those down. But as opportunities, they are all opportunities with different levels of economic value capture and desirability. And so you think, alright, well, we cut all this stuff.

Let's we get out see of it.

And so I think there are a number of early discovery problems that are worth that much, you know, 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.

You know, a pretty straightforward example is for a lot of these 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, like, cold chain, you know, transport 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 wanna get these if you wanna get these antibody based drugs to some of these folks, like, this is, a very hard problem.

Yeah. And very expensive. And very expensive.

And so and so folks are, like, really quite excited about can you find a small molecule therapeutic that does the same thing than antibody against these Right. So there's some antibody, it's... It works.

Yep. And so we know it works. And you...

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 gonna be much more 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 gonna ruin the antibody market, basically. I mean, if you can, and it's good for some stuff, it's great for some stuff, and there's a lot of energy being thrown at those groups because we're good at protein folding.

And so they're making a lot of progress. And maybe more broadly I would say is 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 gonna get better at that stuff.

We're gonna start to, like, go up these different layers 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. Yeah. And I would argue also that you can...

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 have some new target that, know, some new evidence that covers, and then the org could give you small molecule material instantly that you would feel comfortable running straight to like a mouse study. Right. Right?

So but this... 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. 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.

Alright. Well, we're on, you know, everyone's favorite pet question. My favorite pet question is what I call the Kusuri paradox of machine learning and Oh, here we go.

Yes.

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 screened it an 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 starting to wonder if it would enable a much larger 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? 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 go work off material science, and you don't have to... If you're really good at it, then 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 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 really good starting material. Like the novel guys did it with this basically like a receptor on cells that has like a little tiny piece of a mutated cancer gene that's like really hard to do, and they managed to pull it off. And so you can imagine, oh, there could be a world where we do this with small molecule material as well.

And so, like, I don't think three is wrong in terms of finding, like, start... You know, if you're just trying to drug this one thing and you scream a lot and then you already had the thing, you don't need a model for the thing, 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 in engineered activity cliffs that you will actually be at a point where you can do all things, in which case...

At which point, you don't need to screen it all ever again. And when arguably you guys... I don't I don't know exactly how much you raised.

So, I mean, you're...

Yeah. I mean, maybe to put some real perspective on it. So we have developed and screened about 2,000 different protein constructs, a total of probably about 5,000 screens in the history of the company across at least six and a half million molecules each, which I don't wanna get into like a a huge numbers game, but it's certainly almost as much as anyone else on earth.

Maybe more than everyone else, probably not. There's probably a couple groups that like if...

So the the the pleasant answer is, you know, I I said earlier that we have trained models on internal data only and that we're able to extend and make generalized predictions into chemical, which is very different corners of chemical space. So, yes. Do we think it's enough?

Not remotely. You know? And so part of our roadmap moving forward is making, you know, larger numbers of of chemical libraries in different 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.

Then the other side, it's like these big coarse changes to try to capture new proteins and and sort of protein shapes.

Like, can you do KD curves, like where you 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 is something that folks do.

One thing that we see is when we when we do replicates of screens, we get back the same hits in roughly the same order, which makes us, you know, kinda optimistic that you could get these kinds of things. We started to move more into SPR biophysics related measurements, try to figure out if we can maybe come up with, like, a potency ladder that we could then be as part of the chemical material that we're screening 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 something? 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 that, like, the DNA barcode itself, there there are proteins that are not described as DNA binders that we had 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 be able to get, like, some reasonable, you know, kind of like sloppy translation.

But I wouldn't say that we're there yet. Okay.

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 lot 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, alright, we have to track all these things. We have to build tools to track all these things. We have to make those tools frictionless that the people doing the work actually will record these things.

And then you have to go back and look at all the data back into this founding history of the company to make sure that 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 a 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 expression process, and then we have all these other proxies that we use to evaluate how well the protein went and if it's good or it's bad and these other filters.

And it's just... 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 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 gonna be pretty...

It's gonna 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 when they're going sideways. And there might be things that you can write automated filters for and maybe not early on.

And so, like, you know, like one pretty good example I'm happy to talk about is 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 we have noticed that when proteins misfold, and we're able to identify misfolding in very crude cases, like if you put the protein, run it out of gel, which is this protein trick where you try to figure out how big it is, and it misfolds, then you can kind of detect that.

But if it misfolds a little bit, it could be hard. There are drugs whose job it is to refold misfolded proteins. Correct.

They're called molecular chaperones. Oh, okay. You can call them cartridges too, that's what we would call them.

Yeah. There's a very famous one that treats cystic fibrosis patients called Luma Kraftwer. We have a bunch of chemicals in our chemical library that looks like Luma Kraftwer, this thing whose job it is to refold misfolded proteins.

Guess what kind of proteins it hits when we screen them? Cycocyst... Fibrosis?

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 accident. Like, we saw this, you know, these chemical series keep popping up across all these different protein types.

It's like, man, like, what is that? Is that Lubacaffitor? 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 we get a bunch of little catheter heads, that protein probably didn't fold right.

We probably don't wanna use that as training data. We probably wanna rerun it with slightly different conditions that make them more friendly to the protein. Then we'll see what those hits look like.

And so, like, unless you're paying that 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 a... Yeah.

It's it's a hard problem. Yeah. Going back to everyone who touches Dells comes out traumatized.

also traumatized, but in a good way. Yeah. I know.

It's really hard. And that's... And, you know, and that's why.

It's it's... And and 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, then you're not gonna 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.

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 wanna do?

We want more chemicals and we want more measurements. 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.

There were stretches where it was dropping faster than Moore's Law. Yeah. Was was it?

I'm sorry.

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... Right now, when you make them, you you put some stuff in a pot, and then you you heat it up, produce 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 kinda clean it up. So people use, like, 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, what do we wanna 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'd be really clean and purified and easy to work with, 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, course, everyone complains about, like, GPUs and stuff. Like, I'm Yeah.

GPU... Well, that's the that's the one that you do. What everyone says, like, besides GPUs, Yeah.

what would you like people to take away from the episode? I would like people to take away from the episode that, 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 in 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 wanna talk to partners. And so, you know, we're building this thing that we think will be transformative.

So come talk to me. Amazing.