Skip to main content
NVIDIA AI Podcast

Isomorphic Labs Discusses AI-Driven Drug Discovery and the Future of Medicine - Ep. 252

39 min episode · 2 min read
·
Isomorphic Labs

Episode

39 min

Read time

2 min

Topics

Fundraising & VC, Design & UX, Artificial Intelligence

AI-Generated Summary

Key Takeaways

  • General vs Local Models: Isomorphic builds AI models that work across the entire proteome and chemical space, allowing the same technology to design drugs for multiple diseases simultaneously, unlike traditional approaches where each target requires starting from scratch with no knowledge transfer.
  • In Silico Design Cycles: The company aims to complete entire drug design programs through computational modeling alone, validating only once at the end with physical experiments. This contrasts with conventional methods requiring continuous wet lab testing, enabling bolder molecular changes and faster iteration.
  • Chemical Space Exploration: Even with perfect predictive models, the drug design space contains 10 to the 60 possible molecules. Isomorphic uses generative AI and search agents to navigate this space, vastly exceeding traditional screening libraries of one million to one billion compounds.
  • AlphaFold 3 Capabilities: Released in 2024, AlphaFold 3 predicts structures of proteins interacting with DNA, RNA, and small molecules at experimental accuracy. Chemists can now see structural changes from molecular modifications in seconds rather than months, fundamentally changing the design workflow.

What It Covers

Isomorphic Labs' Chief AI Officer Max Jaderberg and CTO Sergei Yakhnin explain how their company uses general AI models like AlphaFold 3 to design drugs computationally, eliminating traditional design-make-test cycles and targeting previously intractable proteins.

Key Questions Answered

  • General vs Local Models: Isomorphic builds AI models that work across the entire proteome and chemical space, allowing the same technology to design drugs for multiple diseases simultaneously, unlike traditional approaches where each target requires starting from scratch with no knowledge transfer.
  • In Silico Design Cycles: The company aims to complete entire drug design programs through computational modeling alone, validating only once at the end with physical experiments. This contrasts with conventional methods requiring continuous wet lab testing, enabling bolder molecular changes and faster iteration.
  • Chemical Space Exploration: Even with perfect predictive models, the drug design space contains 10 to the 60 possible molecules. Isomorphic uses generative AI and search agents to navigate this space, vastly exceeding traditional screening libraries of one million to one billion compounds.
  • AlphaFold 3 Capabilities: Released in 2024, AlphaFold 3 predicts structures of proteins interacting with DNA, RNA, and small molecules at experimental accuracy. Chemists can now see structural changes from molecular modifications in seconds rather than months, fundamentally changing the design workflow.

Notable Moment

Novartis provided Isomorphic with targets chemists had worked on unsuccessfully for over ten years, calling them impossible. Within months, Isomorphic's AI generated novel chemical matter and modulation approaches that astonished experienced drug designers with their viability.

Know someone who'd find this useful?

Episode Transcript

Hello, and welcome to the NVIDIA AI podcast. I'm your host, Noah Kravitz. My guests today are Max Jotterberg and Sergei Yakhnin. Max is the chief AI officer at Isomorphic Labs, and Sergei is the chief technology officer. Isomorphic Labs is the company building a world leading AI drug design engine to transform drug discovery and usher in a new era of biomedical breakthroughs. I'm here with Max and Sergei live at GTC 25 in San Jose. Gentlemen, thanks for taking time out of the week to join the podcast. No. Thank you. It's great to be here. Yeah. It's a pleasure. So why don't we start with a little bit, if you would, about yourselves, your background, and how you wound up at Isomorphic Labs? Do you wanna go, Max? Yeah. Sure. So, I've actually been in in field of AI for, you know, about fifteen years now. This is, you know, long before it was cool. Right. Back then, you know, I was working a lot on computer vision, so applying, you know, early days of AlexNet, how do we use this for ImageNet, how do we scale up for, you know, object recognition, text recognition. During my PhD, we had, you know, we had the best image recognition models in the world. Actually, we had a company in this space that, ultimately got acquired by Google to join DeepMind, and that's how I ended up starting to work with Demis. Gotcha. Demis Desavez. Spent a long time at DeepMind working on, you know, early days of generative models and then caught the reinforcement learning bug. Right. Worked a lot on these challenge domains of, you know, AI for games, trying to beat the top professionals at StarCraft, Hugo, all this sort of stuff. But, really, at the core, you know, deep learning was the thing I loved. It's this amazing technology. Yeah. And I want to see it have real fundamental impact on the world and positive impacts on humanity. Right. And so as we started to see AlphaFold unfolding, there was this incredible opportunity to create this new company, Isomorphic Labs. And this was just such a brilliant opportunity to apply all of this amazing deep learning and machine learning toolbox that we've been developing over time to really try and transform the drug design space. And and that that's what brought me over to Right. Isomorphic to to really head up AI in this space. Right. So to hit that cross of the technology you love so much and continuing to push the frontiers, but applying it to something that's meaningful to you. Exactly. Exactly. And I I've always loved the application of AI as well as the fundamentals. And just to see it have that really positive impact, that's that's really key for me. Absolutely. That's great. Sergei? Yeah. I've, I've also been at this since way before it was cool. I want to say, to borrow from Max's words, I was living in …

Get the full transcript (7,124 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all NVIDIA AI Podcast transcripts →

You just read a 3-minute summary of a 36-minute episode.

Get NVIDIA AI Podcast summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links.

Tools

  • by DeepMind

    Released in 2024, AlphaFold 3 predicts structures of proteins interacting with DNA, RNA, and small molecules at experimental accuracy.

More from NVIDIA AI Podcast

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into NVIDIA AI Podcast.

Every Monday, we deliver AI summaries of the latest episodes from NVIDIA AI Podcast and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime