Marc Tessier-Lavigne

speaker
407 appearances 1 recordings 1 series first heard Mar 2026 last heard 12 Mar

Marc Tessier-Lavigne’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months
1 · Mar OctJan 26AprJulnow

Recordings per month over the last 12 months — 1 in all, peaking in Mar 2026 with 1.

Appearances

newest first · ▶ plays the moment
Yeah.
Well, let me start by maybe just mentioning again, or building on what you just said about the Nobel Prize.
In the fall of 2024, the Nobel Prize was shared by two groups, Demis Hassabis and John Jumper at Google DeepMind.
And they got half the prize for alpha fold, for showing how you can use AI to predict how proteins fold.
Proteins are
As you know, made of strings of building blocks, amino acids.
It's been believed for close to 70 years that just the sequence of the proteins would determine how the proteins fold.
What matters for drug discovery is the shape of proteins because that's how they do their work.
That's also how we make drugs.
They attach to particular parts of a protein and the shape matters enormously for that.
So being able to predict shape from sequence was very important, and they showed how you could use AI leveraging a very large data set.
This is important, actually, to where the field is, called the Protein Data Bank.
It's
200,000 highly curated structures of proteins that had been assembled over a period of about 70 years, many by academics, some by industry, deposited in a public repository for everybody to use.
And AlphaFull trained on that data set and incredibly showed that you could use that information with AI to predict with high accuracy the structure of most proteins.
And for that, they received half of the Nobel Prize.
The other half went to David Baker, our co-founder.
He, building on that work and also on work that he himself had done previously, he showed how you could use generative AI to create entirely new proteins of desired functions.
So it's a synthetic biology, if you will.
to say, can we use AI to design a protein that has a particular shape and a particular function, for example, to attach itself to a drug target in order to switch it off or to switch it on?
Showing 41–60 of 407 · page 3 of 21 ← Previous Next →