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

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

Appearances

newest first · ▶ plays the moment

Vanguards of Healthcare by Bloomberg Intelligence · Xaira’s War on Trial-and-Error Drug Development · 12 Mar 2026 podcast

That's true of us.

It's true of them.

So currently we're not immediately overlapping, but I expect there's going to be a convergence.

And what you have is a number of companies trying to develop algorithms to do the best job possible of developing drugs in silico against molecular targets.

If I can suggest a few more words about what we're doing at Xera and sort of the business proposition, when it comes to using generative AI to make drugs, to make antibodies, it's

There are a few things you could do.

One is to use the model to try to make drugs faster against targets against which you could develop drugs by other means.

So there currently are some very good methods for making drugs, and they work very well against certain classes of proteins.

And again, if you'll indulge me, maybe I can explain to listeners, think of a protein that looks sort of like a stick that's sticking out of the cell.

And what you want to do is making a drug that will attach itself to that part of the protein that's sticking out of the cell.

It's relatively straightforward to make that portion of the protein and screen it in one of these high throughput screening approaches.

And you don't necessarily need AI to get a drug.

What we believe over time is that AI should enable us to get some of those drugs faster, but we're not there yet.

But what you can do with AI that you can't easily do with current methods is to go after proteins that are more difficult to study.

Think now of a cell membrane and think of a protein that snakes in and out of it, the membrane, where only the tip of the iceberg, the tip of the protein is sticking out of the cell membrane.

It's very difficult to screen for that kind of protein for drugs that will attach themselves in that way.

AI is not limited in that way because you ask the AI to make a drug against whatever part of the protein you want.

And so it's not limited by the difficulties of screening those proteins.

So there are entire classes of proteins that are well known to be good drug targets.

Some of them have names like GPCRs, G-protein coupled receptors.

Showing 141–160 of 407 · page 8 of 21