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

They snake across the membrane multiple times.

They've been a great set of proteins to go after for drug development.

but many of them are difficult to screen and certainly difficult to screen for antibody therapeutics.

We're focusing on those kinds of targets that have some or a lot of validation where we believe we could make a real difference to patients if only we could make a drug against it, but that are difficult to screen with existing methods.

So if you will, we're not trying to go for the low-hanging fruit faster.

We're trying to go for the high-hanging fruit that's difficult to access with current methods.

So AI, we believe, will enable us to do two things.

One is to go after difficult-to-drug targets, the so-called undruggable targets.

That's where we're focused.

But also over time, as our models get better and better, to just make drugs faster than you can by conventional methods.

So both of those are the promise for AI.

I think you've framed it perfectly, Sam, that what we need to do is have a model of the cell that is sufficiently rich that you can actually get meaningful and useful answers, but it doesn't necessarily have to capture every single detail of the cell, at least at this point in time.

And I know as scientists, our ambition will be ultimately to do that, but we don't have to reach that ultimate goal to be able to make meaningful progress in developing models that can be useful for drug discovery.

So what do you need to make a model of cells that is useful for drug discovery?

So let me tell you the approach that we're taking.

Currently, there are a lot of data in the public domain generated by academics, generated by industry, that are descriptive data of cells.

People have taken cells of a particular kind.

They might be liver cells.

They might be muscle cells or nerve cells of interest.

And they've identified within those cells every single one of the genes that is turned on.

Showing 161–180 of 407 · page 9 of 21