212. One Cure For All Snake Venoms Via AI

The Next Byte Podcast · 25 Feb 2025 · 18m

AI in practice: 2 real uses of AI described

What this episode covers

Hosts discuss research by Dr. Timothy Patrick Jenkins of the Technical University of Denmark and Nobel laureate Dr. David Baker of the University of Washington, who used AI to design proteins that neutralize snake venom. The team focused on '3-finger toxins' found in cobra venom, using deep learning to generate candidate proteins that bind to and deactivate these toxins without relying on animal plasma. Lab tests on mice showed an 80-100% survival rate against lethal doses, highlighting the potential for cheaper, more accessible, and species-agnostic anti-venoms.

AI in practice

Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.

Designsignificantly reduced discovery phase

The team used a deep learning model to design proteins that bind to and neutralize snake venom toxins, which significantly reduced the number of molecules that needed to be tested in the discovery phase.

“the lab. The team explicitly calls that out saying, hey, this deep learning model that we're using, we only had to test a few molecules, which significantly reduced a discovery phase, and that significantly reduces the cost…”

Speaker 2 · Hear it at 9:28

Engineering & simulationcomputers using AI

Researchers used AI and computational protein design to generate specific proteins capable of binding to and deactivating the neurotoxins found in cobra venom.

“they're trying to see if they can generate any proteins using computers using AI, to bind to and deactivate these toxins, to make sure that, um, essentially, you're able to have an anti-venom treatment that's protein-based…”

Speaker 1 · Hear it at 7:59

Most relevant to

makers and hobbyists

Topics

Mentioned

Companies
Mouser Electronics, Technical University of Denmark, University of Washington
Also
Dr. Timothy Patrick Jenkins, Dr. David Baker

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by The Next Byte Podcast. The episode itself belongs to its publisher.