Skip to main content
StarTalk Radio

Curing All Disease with AI with Max Jaderberg

49 min episode · 2 min read
·
Ai With Max Jaderberg

Episode

49 min

Read time

2 min

Topics

Fundraising & VC, Design & UX, Artificial Intelligence

AI-Generated Summary

Key Takeaways

  • AlphaFold Accuracy: AlphaFold three achieves experimental-level accuracy predicting three-dimensional protein structures from amino acid sequences, completing in minutes what previously required months of crystallization and X-ray scattering analysis by biochemists in laboratory settings.
  • Drug Development Economics: Traditional drug development costs three billion dollars per molecule using random screening of millions of compounds. AI-driven rational design narrows search space from ten to the sixtieth power possible molecules, dramatically reducing costs and development timelines.
  • Protein Folding Foundation: Proteins fold spontaneously into three-dimensional shapes that function as molecular machines. Their interactions depend on shape-fitting dynamics at microsecond timescales. Misfolding causes diseases, while correct folding enables cellular function through thousands of interacting atoms.
  • Clinical Translation Path: AlphaFold enables bespoke drug design targeting individual patient mutations, particularly for cancer treatment. Drugs must achieve multiple properties simultaneously: target specificity, solubility, cell permeability, and non-toxicity while reaching correct tissue locations through bloodstream delivery.

What It Covers

Max Jaderberg from Isomorphic Labs explains how AlphaFold AI predicts protein folding structures with experimental-level accuracy, revolutionizing drug discovery by reducing development costs from three billion dollars per drug while targeting cancer and immunology.

Key Questions Answered

  • AlphaFold Accuracy: AlphaFold three achieves experimental-level accuracy predicting three-dimensional protein structures from amino acid sequences, completing in minutes what previously required months of crystallization and X-ray scattering analysis by biochemists in laboratory settings.
  • Drug Development Economics: Traditional drug development costs three billion dollars per molecule using random screening of millions of compounds. AI-driven rational design narrows search space from ten to the sixtieth power possible molecules, dramatically reducing costs and development timelines.
  • Protein Folding Foundation: Proteins fold spontaneously into three-dimensional shapes that function as molecular machines. Their interactions depend on shape-fitting dynamics at microsecond timescales. Misfolding causes diseases, while correct folding enables cellular function through thousands of interacting atoms.
  • Clinical Translation Path: AlphaFold enables bespoke drug design targeting individual patient mutations, particularly for cancer treatment. Drugs must achieve multiple properties simultaneously: target specificity, solubility, cell permeability, and non-toxicity while reaching correct tissue locations through bloodstream delivery.

Notable Moment

Jaderberg reveals his team discovered novel chemical compounds against decade-old unsolved drug targets by training neural networks on fifty years of crystallography data, then applying predictions to previously intractable protein structures without requiring laboratory synthesis first.

Know someone who'd find this useful?

Episode Transcript

So AI was not satisfied just whooping our ass in chess and in Jeopardy and everything else where it looks like brains mattered. It's now taken over our physiology. Well, no. You pointed it in a good direction. Aimed it at a good place, and we're getting somewhere. To solve our diseases. Yeah. So now it's going to cure us of all disease before it makes us its slaves. Because we need a healthy slave. All that and more coming up on StarTalk. Welcome to StarTalk, your place in the universe where science and pop culture collide. StarTalk begins right now. This is StarTalk special edition. Neil deGrasse Tyson, your personal astrophysicist. Special edition means we've got Gary O'Reilly in the house. Gary. Hi, Neil. Former soccer pro. Apparently. Yeah. And soccer announcer? Yes. Definitely. And you still do that, don't you? I do. Chuck, nice, baby. Hey. Announcing that I know nothing about soccer. You're in my club then. Announcing that you are American. American. You're doing good. Real football. Violence. So what we're talking about AI today. Yeah. That's a favorite topic. We we revisit that often. Only only the future of the entire world. At AI as it matters in biology. Oh, wow. Now that's a big deal. I know. Uh-huh. I know. Yeah. Because people thinking about, you know, composing your term paper Right. Or or winning a chess or Right. But it's got a whole frontier ready to be explored. Yeah. And so tell me what you and your producers cooked up today. Okay. So we've been on the case to get these guys involved for some time, but they are so busy. So here we go. I'll say it. I'm made of proteins. Yes. You're made of proteins from strings of amino acids that fold into shapes that put all together form us. But there's a fundamental problem in biology Mhmm. That has implications for all of medicine. How do these proteins fold up? Oh. For this solution, we look to AI and a Google DeepMind tool called AlphaFold. The second iteration of AlphaFold two won the Nobel Prize in chemistry last year for answering this very question. Who knew AI was smart? Now Christian AI win all the Nobel prizes. Yeah. Let's get into it now. Just park them all up. Pack them up. Now the isomorphic labs together with Google DeepMind developed and released AlphaFold three. Yes. We're on the third iteration. And that was last year and applied these new AI models for drug discovery. Oh, that's great. Alright. So think this through. Could our next generations of treatments be computer generated? Oh, yeah. Oh, by the way, Neil, let's introduce our guest. I will. We've got Max Joderberg. Did I pronounce that correctly? Yeah. You got it you got it right. Tweren't you say? Yeah. Let's see what you say. Me say it. Yeah. Max Sjoderberg. Oh, exactly what I said. He was practicing, he was practicing. So you studied …

Get the full transcript (9,149 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 StarTalk Radio transcripts →

You just read a 3-minute summary of a 46-minute episode.

Get StarTalk Radio 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

    Max Jaderberg from Isomorphic Labs explains how AlphaFold AI predicts protein folding structures with experimental-level accuracy, revolutionizing drug discovery.
  • by DeepMind

    AlphaFold three achieves experimental-level accuracy predicting three-dimensional protein structures from amino acid sequences, completing in minutes what previously required months of crystallization and X-ray scattering analysis.

company

  • Max Jaderberg from Isomorphic Labs explains how AlphaFold AI predicts protein folding structures.

More from StarTalk Radio

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 Science 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 StarTalk Radio.

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

Start My Monday Digest

No credit card · Unsubscribe anytime