Real Alpha
Watch modeSubscribed

Moonshots · 3 min · Oct 24, 2024

AI-designed proteins could help target cancer cells

Ray Kurzweil describes protein-design systems and a proposed cell-level cancer detector. The example shows how AI-generated proteins could move from prediction toward treatment.

RK

Ray Kurzweil

Ray Kurzweil is an inventor, AI researcher and futurist.

  • Peter Diamandis, Host · Founder & executive chairman, XPRIZE Foundation

    Co-founded Singularity University and founded Zero-G; co-wrote the books Abundance and Bold.

About this segment

Ray Kurzweil describes protein-design systems and a proposed cell-level cancer detector. The example shows how AI-generated proteins could move from prediction toward treatment.

From “The Man Who Predicted AGI Decades Ago w/ Ray Kurzweil | EP #125”, Oct 24, 2024. Watch the full episode

“we can actually design new proteins that bind to a given target protein, and we can actually create something”
RKRay Kurzweilat 42:05 · Moonshots42:05

Takeaways

  1. AlphaFold predicted protein structures at a scale prior methods could not.
  2. AlphaProteo can design proteins that bind to chosen targets.
  3. A proposed protein flags cancerous division and destroys the cell.

In this episode

Full episode
  1. 20:00Computing power keeps accelerating across hardware and software4:32
  2. 27:02Automation will displace jobs before creating new kinds of work4:18
  3. 42:50Kurzweil expects longevity escape velocity around 20325:41
  4. 52:18Simulations could compress early drug discovery to days2:51
  5. 36:25Brain-to-cloud links may not need molecular nanomachines3:34

  6. 40:21AI-designed proteins could help target cancer cells2:36

  7. 4:05Larry Page offered to buy Kurzweil's startup outright2:24Up next
  8. 12:44Kurzweil has held to his 2029 AGI forecast since 19992:37

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 40:26

    Yeah, we just saw two Nobel Prizes, obviously, the prize that Jeffrey Hinton received, and then the prize that Demis and John Gemper received, both at DeepMind, related to AI and directly in AI, you know, in AlphaFold. Yes, it was very much for AI. Yes, it was a great year. And here's the question. It seems to me like I would imagine in the next two to 10 years and then beyond, almost every Nobel Prize in chemistry, math and physics will be enabled by or directly discovered by AI. Do you agree with that?

  2. 41:15

    yes i mean right now 95 of the nobel prizes in medicine go to people with mds i think they should get rid of that requirement uh because computer scientists they may not have studied anything but they know computer science and they can develop alpha fold for example which should stymie human beings 50 years get alpha fold yeah i remember when i was a medical school the the huge grand challenge was can you predict the folding of a protein yeah it was the unknown super some people could do that but they didn't do it very accurately and we only did a few hundred thousand then one year we did you know 200 million proteins and when one year and then alpha proteo we can actually design new proteins that bind to a given target protein, and we can actually create something, for example, that goes into a cell, determine

  3. 42:19

    whether or not it can divide cancerously, and if it divides cancerously, it will set a flag, and if that flag is set, it will destroy. that cell. So basically, there would be a cure for cancer. And we can actually do that with alpha proteo. We have to actually design the protein. So there's a few steps left. But that's actually done a very large fraction of curing cancer, for example. Let's switch on that note to the subject