Rare Compute, Fighting Rare Disease with AI & Web3

Transcript

GMGM welcome to be welcome to what's going to be another great Devantel. So if you didn't know Devontel is a 30-minute podcast held every Friday allowing founders, hackers and anyone in between a showcase or stage to showcase their product. And today I'm ecstatic to welcome back on the show uh Stanley Bishop who's the co-founder of Rare Compute. Uh, Rare Compute is a decentralized biotech platform that aims to revolutionize rare disease research by leveraging blockchain technology and computing credits. If you stick around for today's episode, you'll see Stanley give us an overview of Rare Compute, the story behind its origin, and their latest research in the fight against rare disease. All right, let's get into it. But before that, a word from our

sponsor. Today's episode of Devantel is brought to you by our friends at Arbitrum. Arbitum is a technology suite designed to scale Ethereum. You can use Arbitum chains to do all the things you do on Ethereum, but your transactions will be cheaper and faster. With over 3.8 million ET saved, 1.69 million active wallets, and over 1.7 billion total transactions, why would you want to settle for any less? Get started today by exploring Arbitum's comprehensive docs and tutorials linked in the description below to help you get started launching your next DAP today.

Now on to today's show. [Music] GMGM, welcome back on the show, Stanley. Happy to have you here again, man. Oh man, I'm so happy to be back. How you doing? I'm doing well. Doing well. Uh excited to learn about all the the great work uh you guys are doing at at rare compute. Um as we know uh the fight against rare disease has been uh all too hard to fight. So hopefully um there is some great progress you and your colleagues have made uh in the area. But um I guess before we get into all that good stuff um if folks didn't catch you

um while you're here the last time around uh showcasing Lily Pad, did you want to give a brief introduction about yourself? Yeah, absolutely. Um, my name's uh Stanley Bishop and um, yeah, seriously, man, so happy to be here. Um, always like just even when we do a one-on-one call, I always have the best time. So, I think this will be a lot of fun. Um, and yeah, my name's uh, uh, Stanley Bishop. Um, I'm a mathematician and a computer scientist. Um I unfortunately think I have to say also a patient have a kind of a rare slashcomplex disease and I'll tell you not having uh the best day

today. So do forgive me if I uh you know stumble or fumble as I'm uh speaking but um yeah I'm I'm a person who um you know had some uh roles in in leadership in in machine learning and in kind of the early days of uh using uh GPUs to accelerate machine learning and it I think gave me an interesting and early insight into um what was going to happen and and what's been happening with AI and particularly um how AI can be a a positive part of an existing system but then also um how AI can disrupt existing systems often in ways you weren't expecting. Um so you

know that very much given my experience as a patient like you know brought me to the idea of like how can technologists you know bring some of our tools to that world um integrate them positively with uh you know healthcare providers as as partners and yeah hopefully improve uh the outcomes and experience for for patients you know that's uh kind of what I've decided to be dedicated to. Amazing man. And I guess um you have quite the background in in AI. Um you used to work at Google um I believe in the machine learning um vertical and you also uh founded a couple startups of your own. Um I guess did did you want to

kind of lean into that a bit? um if there was any inspiration from uh from from perhaps your your your rare disease going into those fields or or whatnot. Yeah. No, super happy to and um you know I think in particular an experience I had building um computational linguistics technology for for for Google was very formative. Um I was the principal scientist uh working on a platform called uh Falcon. Uh it was a language translation platform and this was like 15 years ago. So in the days of like you know you wouldn't want to use Google translate for anything real kind

of thing right. Um so at that time you know we were building technologies uh to accelerate translation to support translation and localization um also to get the right jobs to the right translators and and localizers. So in in that sense you could think of the system as uh Uber for language translation. And kind of a fun like little statistic, I I think at the time I was working, our group was responsible for I think something like 20 to 30% of the world's total daily translated language. Um, so yeah, really was so fun as someone with a background and an interest in computational linguistics to kind of

have that bird's eyee or I guess you'd say that falcon's eye view of just kind of how the flow of of language works. It was really a special uh thing to be involved in. Um but yeah, I'll tell you it was actually a population of about uh 75,000 translators um all over the world that the Falcon system, you know, flew between. And so uh uh really uh like I I said a really interesting thing to see when when you have an existing system with with so many humans carrying out so many actions every day putting out so much effort. You know what happens when you add these machine learning um pieces to the puzzle and and can you always predict what they do? And yeah, it turns

out you can't. Um but yeah, there really is a kind of a science you might say to how you kind of implement those systems. Um, sometimes this is called uh cybernetics. You know, we we often hear about cybernetics and we think about like putting robot gear on your body, but it's it's also it's like being in a system that is, you know, containing human and non-human intelligences. And let me tell you, I think we're seeing we're all now part of a cybernetic system right Nar? Yeah. Yeah. 100%. We're leading that way. Um, and I mean it's just going to get even more um like proficient like us being one with

um all the AI and whatnot that's getting developed. Like I think we're moving at a really rapid rate. Um I'm I'm sure you've seen it. Um I know I've seen it around man. We'll have to talk later about Claude code which is such a takeoff point but keep up with even you know my little slice of my of one little slice you know um right uh uh interesting um seeing it all play out and and yeah it was like I saw some really interesting things like uh kind of just uh how humans react to being involved in machine learning how how people react emotionally to the idea of you know interacting with AI and um uh yeah became really interested in in sort

of exploring the frontier of how those technologies would be applied. So um yeah after leaving the project at Google I founded a really interesting uh alternative uh startup studio in Venice Beach that was called uh Space Post Labs and our theme was impact venture. So, we had this idea um that sort of like a um you know, being in a venture isn't just a really exciting and often lucrative uh position, but it's a chance to be uh yeah, at the frontier of exploring how new technologies are going to interact with communities, human experience, human health. Um, and so it really I

think should be a responsibility to people in venture to kind of like you know when it's possible like do good and do well and then I'll I'll tell you a secret uh in in the venture world that's like oxygen for people. You know, I think people are so used to a very different way of doing things that, you know, you can kind of set that dual motive and accomplish some really, you know, positive impact milestones, but also, you know, people will react to you differently. Like there's advantage to be found in that part of the community. So, um, yeah, was was really so fun and and we, um, you know, operated for about 10 years. We were, uh, part of a really special, uh, art patronage network. we were like their kind of technical

provider uh called the Budman Studios and then um yeah about a year or two ago uh Jim Budman the founder uh retired and so um kind of happened to be at that time um you know had this really interesting experience uh at something called the uh the Stanford rare disease AI hackathon which you know I think that would be such a cool thing to you know start the rare disease story the rare comput story with because yeah man that that was literally what it all grew from.

Oh yeah. Yeah. We'll we'll definitely get into it. And uh I guess from your venture days um was there any particular type of company uh company profile they were looking for when you were investing? It seems that you were looking for a very particular um uh type of of company there. Yeah. um uh would would totally say that it was uh companies but I always thought of it as founders like I was a very founder centered uh builder um founders I I believed in and founders I I thought I could help you know because I'm not perfect I only have the cards that I have so I I think being realistic and

judicial about where you can add value is is something anyone in in venture should uh something anyone in venture should should do. Um but but yeah, I guess I would say like definitely machine learning. Um you know, like frontier data technologies were a big piece of it, but I I was particularly passionate about finding founders who like I guess you'd say normally wouldn't be hearing about that stuff or wouldn't be exposed to those things. So um you know, I think actually if I really went down the list like we, you know, I think we built the architecture for the world's most successful digital art gallery chain. Um, you know, we also helped uh develop a bunch of like neurological treatment courses for some

some diseases. So, uh, you know, really everything from from entertainment to STEM and any any everything in between. And, you know, branding wise, I think that's what we called ourselves, a steam incubator. And so, you know, if anything, the theme was really bringing diverse voices to a ta to the table and kind of seeing, you know, what those voices that might not otherwise have a chance to talk get to say. Amazing. That's That's awesome, man. And like you said, um you found yourself at a Stanford hackathon. I I am I'm really curious. I I I I don't know the origin story of Rare Compute. So, uh let's get into that if you don't mind.

Yeah. Well, um also ties into my broader origin story as like Stanley the DI guy. Yeah 100%. Uh you know, it's a What would it be? It's like wish.com Bill Nye uh character I try to do. But I I do have fun with it. So that's a plus. Um but yeah, I used to be um I guess in addition to like the work I I did in venture, I I am a a researcher and have continued my my life as a researcher and I work in um you know hypers scale computing uh specifically for kind of post training and application engineering in AI. Um so yeah I'm really interested in like how do you properly set up and operate you

know thousand 10,000 plus clusters and you know get them working for for scientific uh computing purposes. So uh yeah have have always kind of like uh worked on um projects as a a research collaborator or contributor. um uh particular project got a shout shout out because it was a big part of uh uh me entering this world was a deep cam a really special uh project that grew out of the pande but it's I I think probably the most high quality and um you know performant open-source machine learning technology for medicine discovery and and molecular engineering and um yeah like kind of u

uh got involved involved in in sort of medicine discovery and biioinformatics as like someone doing the computers at uh deep but then yeah have a background as a physicist and love to learn and I think uh more than anything I really love working with experts and sort of helping them communicate collaborate you know activate large computer systems you know work together to get them doing uh useful work. So uh yeah, my my work at Deep Cam grew into uh work with a lot of different places cuz cuz it sort of happened that there was a big realization and a rush uh to kind of get access to these machine learning technologies like actually particularly in the wake of Alphafold uh which you

know might not need an introduction but happy to talk about it anyway although you'll you'll have to cut me off because I can go on forever about uh Alphafold um but but yeah so it's like sort of um uh had had this career and practice going on for uh quite a while. uh started to get interested in in DII and passionate about DI and then um I I think it was like three or four years ago uh was like serving as a research architect for the Snyder labs at uh Stanford medicine that's the Stanford genetics department and had like really a cool role uh uh with a a particular group that looked at uh frontier technology application in rare genetic

disease and oncology. So uh we were often working with patients who completely exhausted traditional course of care or who had diseases where there was no course of care and um you know in in many cases like with the rush of AI models with you know many new incredible technologies like there are you know things where you can really change the outcome for a patient if you kind of build them fast enough teach the doctors how to use them fast enough. So, uh, yeah, was was sort of a kind of triage technology architect role and and really a lot of fun, you know, just day-to-day building cool stuff having really, uh, I I hope uh, positive, uh, impact on on patient outcomes. Um, but, uh, yeah,

kind of funny story starts with an external hard drive. Uh, we had a particular patient who had a condition called EDS and this patient was having the classical rare disease story. uh uh struggling to find doctors who knew anything about his disease. Um struggling to interact with administrative and insurance layers of our medical system and even things like you know um his medical records. Yeah. Like literally filled a 4 terbte hard drive. I think it was 3.8 terabytes of medical records, different formats, PDFs, like just a mess, you know. and the guy was going to doctor's appointments and he would spend the

whole time you know when he should be interacting with his doctor and getting feedback like trying to find that one form. Um so yeah this was what just in the moment when um you know rag systems were available like retrieval augmented uh generation technologies. Uh this was the first moment when people were connecting multiple agents to serve purposes. So, uh, we kind of got started like just building a rag system for this gentleman. But, yeah, we realized like as soon as this thing was built and everyone was excited about it, you know, I think the doctor we built it for said, you know, she didn't have a a migraine for the first time, right? Because, uh, it sort of her and the patient were able to just kind of find what they needed.

And anyway, we we ended up getting a lot of demand on on the side of other physicians like curiosity. How do how do I use something like this? What does this thing do? Um, a lot of it was positive curiosity. Um, I'll tell you that in ARB, we we did have one funny thing where uh an oncologist uh discovered hallucination of of LLMs uh sort of in a in a funny way. uh this this scientist asked for a bunch of uh papers on the interaction between uh viruses and and oncology and a paper popped up that she had been writing with a colleague the exact same title but the colleagueu's name and not her name and

uh this was actually a total coincidence um I mean not like a coincidence right because when models hallucinate they hallucinate things that sound like dangerously reasonable so the model actually like based on the previous work of this scientist predicted she might write that paper and put her name on it and then so it's just anyway I think there was an angry phone call that was probably very confusing on both sides but um anyway that that's all to say like I I think you know uh many of us are like familiar with hallucinations familiar with some of the complexity these systems but yeah this was really the first moment when uh the medical system was thinking about this

Um, and then another really cool thing happened when we started telling people in the technology community about like having, you know, done this service for a patient, everyone was like, is there anything we could get involved in? Um, we we really had like just when you shared the story, everyone literally was like, how can I help? You know, so we decided to see if we could sort of scale that. Um, and and so we, you know, created some structure. I uh designed a research methodology where you know we would be kind of standardizing the tasks the data sets and the models um and then providing validation you know so providing uh medical leaders to review the systems um uh validation and model postraining is kind of my whole field

and so um one of the things we built NARB I I think you would have thought was particularly cool um was almost like a arcade where our doctors could play the models in the sense that you know these models that the teams were building they could log in talk to them and then correct them and bro let me tell you if there is anything doctors really like it's correcting stuff so we actually got some really good user engagement there but but yeah then we we actually used the modified statistical system um uh have you ever seen a a chatbot arena no I've never seen it at all oh you got to check it out it's it's so much fun and and it's the really set of benchmark marks that I trust most for

model performance because it's totally human validation. So, um, you go on there and and just like I was saying, our doctors did. You say, uh, I'm asking this question. Here's answer for model one. Here's answer for model two. You know, it's Tinder. It's like swept left or right. Which model do you like? And, uh, uh, if if you've ever played like chess or or maybe Starcraft um, uh, is also a place where there's a numerical rating and basically each time you win a match, you gain some points. Each time you lose a match, you lose some points. And then the number of points you gain or lose is proportional to the difference between you and the person you you you beat or are defeated by. Um so this is actually a system called ELO uh ELO and it's a

yeah really beautiful statistical system for providing merit-based tracking of uh performance between things that can undergo head heads up competition. Um and yeah. Yeah. So it's so cool and and was really interesting to kind of see how doctors interacted with it. Um see what the behavior was of the models within the system and yeah we did kind of find that like the medical use case was very different. For example um uh medical models can give answers that are disqualifying right like if they say something that is potentially dangerous to a patient then that model has to actually be removed from the system until it's triaged. Uh similarly uh and and very similar actually I would say to the human practice of medicine uh kind

of alluding to some of the cybernetic concepts here um uh doctors are very specific and rigorous and when they change their procedures and practices it's it's very rigor it's a rigorous process they they do very deep and systematic review and so um on the model side that looks like kind of making the system a little stickier. So if a if a model is starting to win, we we actually tweaked the system so it climbs the ladder a little more slowly, right? Um so so anyway, this was just like the kind of idea of this hackathon, a decentralized hackathon where all of the people with knowledge and wisdom about rare disease all over the world could kind of contribute their their spice to the stew. Um and oh my god, Narv, it was

really beautiful. The response was like insane. Um you know I I think in the end we had over 250 like doctors involved in different ways. uh we we had maybe 500 volunteers and created over 30 teams from over 20 countries and uh man uh was quite a bit of unexpected activity 100% but uh really was a a beautiful thing to see and and then just all on all sides of of this situation you know like um rare disease uh advocates and patients who kind of struggling to find support um you know doctors who who need uh assistance processing all the data of rare disease. Um, and then also like

technology companies and engineers like who, you know, are all humans and all have families. But then, you know, quite frankly, I I think all of us are pretty concerned about what AI is going to do. So, it's like really a beautiful thing. You know, it's like I think really easy to say that like, you know, the world is in a place of uh, you know, people not caring and, you know, things not working. But then, you know, maybe it's just we need to think about how to create those opportunities and get them in front of people because like Yeah, it was so incredible. Like again, like we said, like we got a jump for the patients and everyone was just like how high, you know?

Yeah, that that's awesome, man. And I guess from all of that, um, it sounds like that was kind of the the major springboard for bringing together a a group of people to start rare compute if I'm not mistaken. Right. Yeah. Well, um, it just, uh, yeah, get carried away talking about how how fun was and how how how much excitement, positivity it created. Um, and one Narb, I got to tell you just one last like cherry before I do turn to the dark side. And I'm just kidding, but you know, um, uh, the OpenAI co-founder, uh, Greg Brockman,

I've heard of him. Yes. Oh, I mean like as a machine learning scientist, one of my, uh, biggest heroes is like a leader. Um, you know, not just a very brilliant scientist, but you know, machine learning scientists are smart people but complex people. and like being able to lead and build organizations. That's like such a special guy. And anyway, uh we found out like just a week or two before our demo day, which was uh at the GitHub headquarters that uh Mr. Brockman's uh wife had EDS. Um actually, she'd just been recently diagnosed with a particular variety of of EDS called HDS.

and she had had the exact same set of experiences as every other EDS patient I've ever worked with. Um, you know, chronic issues with health, uh, throughout her life. Um, uh, no doctors who ever really gave any indication of what it could be. A lot of doctors who who maybe didn't take it seriously. And then eventually uh she found a a caregiver who had seen EDS before and worked with EDS patients and immediately said, "You have EDS, you need to get checked out for EDS." And um um yeah, and then that led to a knowledge of the diagnosis, which is for so many

patients, like even sometimes when you get a bad diagnosis, when you've been working on it for four years, it's it's one of the best days of your life. You know, that's a funny thing we hear from patients. But but yeah, also you know EDS is a disease where if you have knowledge of your condition, you can really drastically improve your quality of life. And so it just goes to show like we all are human. We we all have the sort of shared heritage of this biology with all its goods and all its bads. And um yeah, it was was just a really really cool special experience. Um the thing I would say though and and can kind of start it with a joke. Um if you think uh doctors need to have a good bedside manner, uh machine learning scientists who work with doctors have to

have like really good bedside manner. Um and and yeah, no, just kind of half kidding but but half serious that there were some real human communication and coordination problems. The the world of medicine organizes itself very differently from the world of tech. there's you know different values there's different understanding um there's also a thing where a lot of the work that is done on the technology side is kind of invisible on the uh medical side and uh vice versa quite frankly so it it really is something we realized there is some extra intentional and important work to do in like kind of

building cultural bridges and building you know shared knowledge like shared motivation shared mission And yeah, like we kind of just came away from it having seen uh you know playing this role talking to engineers about rare disease um talking to rare disease scientists about machine learning like talking to doctors about the idea that like we're here to help you know we're not looking to replace doctors like we know doctors are overworked we want that to stop you know um so it yeah just kind of like uh came to feel to me and a number of other contrib contributors that there was just an enormous amount of good to do. And and then to bring like one more kind of punchline that I

think segus really nice into other things we want to talk about. Uh it is a very I I would almost say easily solvable problem. Um it is a problem of coordination and resource allocation. Um right now there are many diseases that with the kind of current state of incilico tools we could uh make serious attempts at curing. Um and uh uh there is enough compute at any given time about 20 to 30% of the world's total compute is idle and could be allocated for trivial amounts of money to cover the data center cost. Um and there just are not systems structures and incentives to get companies to do that.

Um what we found though is that when you go through the process of talking to the humans who compose those companies um that can change. So we we found uh quite a few companies to have been you know extraordinarily generous when when these uh opportunities are presented. Um think you know in particular have to shout out uh Dell computers. I I have to say they've been angels. They've really been saints. Um I I would even say like they have made uh patients and researchers cry with joy for for some of their their extreme generosity. And um um you know they're not the only ones. Um but uh uh uh yeah, it sort of is a thing where uh starting from that original goal of

activating, you know, a couple hundred engineers, you know, we're uh at this point getting resources to um you know, like thousands of projects and and you know, trying to build a community and and our hope is that like we can build a system uh that will be democratically administered that will allow um the world's medical experts to allocate that idle compute. Um we we estimate that about 5% of the world's total compute uh let's call it a tithe uh could make sure that there's never a rare disease researcher who does not have access to those critical systems. Um and and yeah, that's kind of like the the northstar we're following is a moment where, you

know, when it comes to uh getting those resources in the hand of people who need them. Uh it's not insurance companies making the decisions, it's, you know, uh doctors, uh patients, and patient advocates. That's awesome, man. And yeah, I mean that that's a crazy stat. just like 5% and like every rare disease researcher can have compute to help them and and you spoke about it or touched on it briefly about um the different types of diseases you're researching. I have a question from the crowd I want to bring up um on the topic um particularly for Parkinson's and if there's anything that um you've seen or you've been your you

and your team have been researching around it for Tula. Yeah. Oh man, I'm um I'm so sorry to hear that. Um I uh um got to say you know Narb I am like a big softy. Uh I I think I love contributing to medicine. And it's it's I think been something I've wanted to do my whole life, but uh really like have an admiration for doctors cuz like it hurts me like even thinking about what a lot of patients go through and you know being a patient myself like it it brings up my experiences and yeah Parkinson's is is such a tough one. A very close uh person to me has been struggling with that and is a person who um actually has a pretty

famous career like working with their hands. So, um, anyway, man, I'm I'm just sending love to you and and thank you for the question. Um, Parkinson's is a tricky condition. Um, Parkinson's, uh, sort of, uh, happens inside the the nerve cells. Um, the nerve cells are just a very complicated world. And when you're, uh, kind of looking at the dynamics, it's almost like a murder mystery. Like there's so many things like floating around. So, for example, um there's a something nar that can form in a cell called a a lipid droplet. And a lipid is a type of protein that can serve as like a fuel. It's kind of like a fatty kind of thingy uh for for

different cellular processes. So, in many cells, it's a natural and and normal thing for lipid droplets to form. And it's, you know, kind of like putting some stuff in the pantry for the cell. uh neural cells like normally don't have lipid droplets. Um and so like uh it is an unusual thing we observe in in Parkinson's patients. So large number of lipid droplets. But yeah, we're kind of like I I think there's controversy like do the lipid droplets cause the disease? Are they a byproduct? And so you know that's all to say like uh right now you know our uh foundation is uh working on a compound. It's an autoimmune condition. Uh compound to treat an

autoimmune condition and and that condition happens because there's like two or three different uh kind of proteins or compounds that are interacting in a negative way. And and yeah, it's it's pretty likely that Parkinson's involves a large number of biomolelecules like and potentially like extended processes that are interacting in a fairly uh complex way. And and then again, all of that is is me speaking as like the computer guy. Um uh I uh personally actually hope and am am expecting that our next research sprint will be on Parkinson's and a couple related uh neurog degenerative diseases.

Um in particular we're going to be looking at uh so this is a kind of a crazy thing. Narp, have you ever heard of a a human fly chimera? Uh no I can't say that I have. Sounds something out of uh uh out of fiction. No, I I know, right? And it's so funny. A fly in front of my face just as I was saying that. And listen, everyone in the audience, like next time you're going to swat a fly, don't like you owe that, bro. Because yeah, like we kind of got very lucky. Uh flies have a nervous system that is remarkably close to ours.

Um and you know if we want to test medications, explore treatments, uh having a model organism where you can test a treatment and then see what happens and you know if the life cycle of that organism like the fly is is short then you can actually go through many generations quickly. Um so uh yeah like flies are very important model organisms but they do not have uh uh human exact nervous systems. Um you can give them human exact nervous systems.

So uh you know it's sort of funny Narb like you're probably used to navigating a big GitHub repo and you see the diagram of like all the different modules and that that's like actually a thing that exists for our genomes too. So when you kind of look at something called the interact map of a fly cell, you get this thing where there's kind of like this component of the cell is in a box. This component's in a box. Each component has different genes that code and produce different proteins. And so it's almost like yeah, it's like the GitHub repo for how the the cell works.

And what they can do is actually use like a technology like crisper to remove the fly genes and put the human genes in the fly. And uh actually they can actually give a fly a human bioexac nervous system for for testing medications. And um yeah we our next project will be uh looking at using those human humanized fly models to to do some neurodeenerative disease research. Um and then last thing I'll I'll say on on that research and and uh before actually giving something that might be helpful like on a more immediate basis for your father. Um uh we're at this early moment where AlphaFold 3 and similar models are giving us our first kind of like you

know think of it as a grainy black and white picture of what would be called the interact. So not just what a single protein is shaped like but how does a protein a molecule another biomolelecule how do several things actually fit together. Um and then that technology is is just in its early days. that will continue to scale. Uh going to need a lot of compute, going to need a lot of data, but but I uh uh sincerely believe like to a sort of would bet on it level that we we will soon be able to peak into the the cells of a Parkinson's patient and figure out what what's happening and stop it. So, you know, for

for you and your father, just please um you know, have hope and and seriously, thank you so much for um you know, here being here, being part of the conversation. Um last thing I I would share though is there is a new uh treatment modality that a very good friend of mine um helped pioneer at UCLA. Um and it's kind of interesting. It's actually using focused ultrasound on certain brain tissue. So like literally using sonic waves to sort of like they they have like emitters that go on some different parts of your brain so that the sonic waves only like intersect with a certain intensity at like certain tissues and it has provided really remarkable symptoms relief. Um

patients who have not been without movement for years like will often have six-month periods with no movement. And um uh I I think the uh kind of uh name for the treatment would be like neurom modulation uh acoustic bio acoustic neurom modulation. Um you know again like not a doctor just just the computer guy. So like you know would say this is more something to maybe uh you know talk to your father's physician about but have have seen it uh to be really a modality that's growing and seems to have like enormous uh impact on Parkinson's patients. Awesome.

Uh yeah, wonderful answer and and hope that that helps a little bit too and yeah, wishing your father all the best and um I guess uh we are running a little short on on time and I wanted to give you an opportunity to speak on um any other research um Rare Compute might be doing that you um would like to touch on. I know uh Rick Compute has recently gotten a big uh grant from Poseidon Dow to fund some of the fun stuff uh you guys are researching. Um is there anything you wanted to bring up touch on?

Oh, you're on mute S. Thank you, sir. Um well, yeah, first of all, like I mean I should have remembered if we thank Dell, we got to thank Poseidon. Uh they're really special group. Um there's a field it's it's I guess the field that I'm in uh pre precision medicine and precision medicine kind of starts with the idea that we should ask more of of how well we see our our patients. Um so it's a very datadriven approach. Uh we we try to generate as as much data as we can about the patients and then we kind of put the pieces together. And the thing is it turns out when you do that for one patient you you

do get better outcomes for the patient but you also uh increase the health of the total ecosystem of data. Um because we all share so much of our biology that things we learn in one area apply to other areas. And then um this is a place where for DEI it it's like there's places where the ecosystem of health can be improved with precision medicine but it might not make sense for a hospital to pay for it. And so you know many things that are important that would save us money in aggregate across all of society that would be good for our patients um they don't get funding and then Poseidon is like specifically existing to target that problem. So they're looking to, you know, allocate

resources to projects that are exploring, you know, decentralized and uh non-traditional ways to bring solutions to patients. And um yeah, we we were so excited to be a recipient of their their first grant. And we are I think uh just about to successfully complete the research. Um we have our uh I think uh it's going to sound weird, but our uh our first 100,000 molecules were successfully generated. Um these are molecules that will be attempting to treat a condition called uh myinia gravis. Uh this is an autoimmune condition where your your antibodies start attacking your neuromuscular junction. And uh Narb it's so funny my friend because like often I have to

explain a lot of stuff about the neuromuscular junction but I I know you were a fellow bodybuilder. So I'm I'm sure you have that creatine container on your kitchen with the little diagram and so Indeed indeed. That's the neuromuscular junction. So that's like one of the things creatine does is it helps the interface between our our muscles and the supporting neurology to kind of communicate fluidly. And then in myia gravis like you almost could consider it the anti-reatine. Uh one of your antibodies like starts attacking those uh key proteins and your muscles kind of go haywire in in quite a few different ways that are really really terrible.

um uh we we think we have a a molecule that that should actually grab onto uh just those antibodies and deactivate we hope enough of them to alleviate uh symptoms in the patients. Um uh and and yeah in in about uh a month we'll be uh uh well first we have to filter those 100,000 down to about 40 or 50. Uh then we'll uh test them in the lab which will produce a lot of data about how they worked, which ones worked. Uh that data will be uh fed back into the system that generated them and they'll be you know regenerated and then we'll actually go through this process a few different

times. And um we're we're hoping that you know they're already looking pretty good but but after a little bit of shaping uh with with this kind of new uh paradigm which is called a wet dry active learning is is what they're calling it. So the the wet is the biology lab with the petri dishes and the dry is is me over in the data centers and and yeah the idea is that a key part of this paradigm is there has to be kind of integrated communication between those those two stakeholders. Um so yeah it's a really cool uh milestone.

Um additionally uh the traditional uh paradigm in drug discovery starts with like uh these these very large databases of compounds that the pharma companies have. Um and they are very like jealous guardians of these data sets. So there is unfortunately a lot of really important research that like doesn't start because the pharma companies just won't won't open won't open the pantry so to speak. Um and and yeah our method is is very different. You know we uh if you want to learn a little bit about what we're doing if you look at the Nobel Prize from last year uh one of the recipients was uh David Baker at Baker Labs University of Washington. um his

contributions to protein informatics like you know can't be uh overstated both in terms of specific research impact but you know as I alluded to getting the stakeholders that need to contribute to these projects like pull in the same direction ain't easy and and Dr. Baker is just, you know, you you you hear from everyone who interacts with him that he's not just a brilliant uh scientist, but he's a kind leader, you know, and and I I just love to hear that. Uh but anyway, he created this thing called RF diffusion. And if anyone's used like midjourney or stable diffusion or or you know, Dolly, uh those are diffusion models. So, you know, they learn the connection between some uh textual data and some images.

But turns out the structured data of the images, you can learn whatever structure. So you could actually learn protein structures. So you could actually like have a model where it creates the protein you tell it to create. Now the way you tell it to create the protein is a little non-trivial. You're not just kind of prompting it. You're using other biological data. Um we we actually like in in and more broadly the field has grown from just using one model to like really using multiple models that are each shaping and configuring a different part of the protein. And you know there again it's like pretty interesting coordination cuz like you know we often have to start like cuz we need the biologist to help us configure all the models explaining to the biologist what a model is right like it's it's a pretty

fun like teamwork kind of kind of thing. Um uh punch line though is uh um uh yeah we're we're very close to uh successful completion of this first molecule with this new technique that doesn't look for the needle in the hay stack. it makes the needle. Um, and yeah, we we've done it on I I think what would be a bit of a a shoestring budget. Uh, the Poseidon grant was about 100K. Uh, pretty funny. We we actually got roasted pretty hard for asking for too little. Um, and honestly, it was like so like warranted, you know, like it it's kind of like very true that typically a project this ambitious would be looking for like at

least $5 million to operate. Um, but we really wanted to prove a point that um there are a lot of projects that could happen if we connected the dots. And so, yeah, in this case, we uh were able to find and piece together the things that were needed to follow this new approach. And uh these were different resources than you needed for the traditional approach. Uh we were able to work with engineers who were just excited to get a chance to contribute to something that had patient impact. And so um although in retrospect I I do think we should have asked for, you know, a little more because I'm I'm behind on sleep. Uh I I think we're going to have this successful way to tell a story of, you know, a new approach. And then you know

my hope is that when we take something like that to you know stakeholders when we have patients helping tell the story of like you know why aren't we getting these computers working on these kind of projects like you know very helpful uh that'll be what we need to win people over. Um but you know another thing that helps uh Narb is a chance to tell the story here you know to your audience to you and also just for myself you know it's it's like a a pretty challenging thing uh have have taken on um you know is it a time where uh you know there are a lot of different things you get can get involved in as a machine learning scientist. So, I think there's definitely people who think I'm a little stupid for for working on rare disease.

But, you know, even just a thing like connecting to uh someone who's a patient and, you know, if nothing else, hopefully expressing some empathy and just being part of, you know, your experience going through that as as like the supporter of a a patient of a loved one. You know, it sort of like as a again that patient myself, it really is a meaningful nar. So, seriously, bro, thank you so much for having me on. It was a lot of fun. My pleasure, man. And yeah, those people who are questioning your decision for sticking reges, um, yeah, they they they can go away for for for all I care because the work you're doing is wonderful, man. You're an amazing person. Uh, very brilliant, and I'm really looking forward to seeing um

how your research plays out here and and going forward. Oh, this is so kind of you, my friend. And uh I'm honestly just having um a lot of fun with this stuff, too. I I I described before that we're at this moment where we're just getting the first like grainy black and white images back of the inside of these incredible systems. And um I grew up uh in PaloAlto and I remember um uh when the camera was first invented uh someone at Stanford used it to or a certain type of camera was first invented you know take a photo of a running horse because I I think there had been a controversy about whether all of the hor's legs ever come

off the ground when they're when they're running full out. Um, and it's just sort of interesting like you know another thing like that is I think of the first microscopes right and the first time you know you got to see that that world down there and and yeah just you know uh there are many things our generation is having to deal with that I uh hope we can clean up before my kids are ready to take the wheel but um I I do feel like we're very privileged to be the first people to see that stuff. It's It's kind of an honor and uh yeah, so just uh you know, screw those people. Uh love my patients and my my my DI friends and uh anyway, Nar, you'll have to have me uh back on once we get the molecules back from the wet lab and maybe we can kind

of take a look at the, you know, 3D structures, tell you a little bit about how the proteins work. Yeah, that's amazing, man. Yeah. Yeah, for sure. I felt like we could probably keep going for another couple hours at this rate. Um but yeah, uh unfortunately, uh we're at time here. Um Stanley, thank you so much for taking the time out of your day to to come on the show and uh yeah, definitely um you're more than welcome to come back on and uh give us the full scoop on the research and results. Yay. Oh man. Well, so good to see you. And uh you know, Nar, I will as well, but you know, get a couple sets in on the bench for me, okay? And then uh next You got it. I'm telling you, bro, we're taking you to Muscle Beach. Okay. Hell yeah.

Yeah. We we'll go we'll go scout for Arnold. Hey, take care, sir. 100%. All right, all hope you enjoyed uh today's episode of Devantel. Um hope everybody has a very happy Friday, happy weekend, wherever you may be. And we'll catch you back here for another great episode next week. All right, all. Cheers.