This is once you already have cancer detected in your body, it tracks to make sure that it is, you know, diminishing to a smaller amount.

Yeah, exactly.

This is for metastatic patients, uh, breast cancer patients.

It's, uh, but it's, it's, it's more than that because the sense that this is changing cancer from this sort of one step behind flying blind to this idea of being one step ahead with these blood tests.

And so it's really changing this idea from one and done testing to using our blood testing platform as a sort of cancer management platform.

And this is gonna spread not just to apply to breast cancer, but to almost every cancer type.

This is really the future of cancer care, the future paradigm of how physicians will manage their patients.

So on what timeline do you think it would migrate to other types of cancer? And what's the, what is the breakthrough that made this possible?

What do you-- Like, what's the most optimistic scenario here? What, what falls out of this?

Yeah, so I guess I can maybe sh-- like go backwards and show you kind of the evolution that's happened.

You know, a story I tell is, you know, this, like, tenth patient we sequenced, which we tested in twenty fourteen.

She was a, I think, Bay Area woman, forty-eight-year-old woman diagnosed with pancreatic cancer initially.

Uh, we ran a test Physician said, "You know, this doesn't look like pancreatic cancer.

Maybe it's ovarian cancer." Ran a few more tests, found out it was ovarian cancer, and then put her on like a drug that's been around for, you know, thirty years, and she had a complete response.

And our test was not designed to do that, you know, just gave a few clues that, you know, perhaps she was misdiagnosed.

What part of biology can be conquered and what answers can be answered using the abstractions afforded by the philosophy of computation, right? So there, uh, I-I'm curious from your vantage point, do you see that, you know, this compute maximalist or compute reductionist attitude can take us further? Because I'm trying to understand, like, if, uh, Isomorphic Labs, which c-- now claims that, you know, if bi-- if biology-enhanced disease is modelable and computable and you can hemp climb on GPUs, then where is the residue, uh, fr-from a company such as yours coming from? Uh, what is it that you can solve using your data assets and your compounding flywheels that a computation reductionist research lab like Isomorphic cannot?

So help us better understand how a simple blood draw can reveal changes happening inside a tumor.

Yeah, no, thank you for having me on, uh, Pamela.

It's, uh, really groundbreaking the, the way this study works.

Um, when you think about essentially, um, most, uh, treatments in cancer care, you're sort of waiting for the cancer to get visibly worse on a scan.

You're so- you're waiting for that three-alarm fire to essentially happen.

And then physicians decide, "Okay, let's switch therapy now.

Let's find something else." This trial was very different, where essentially we monitored those patients with a blood draw.

So how many blood draws would you need to get then to, to know if that tumor is changing?

So like, how did you sequence it? No pun intended.

Yeah, that's a great question.

Yeah.

It was sort of like, you know, I think, you know, the Tesla master plan in many ways, like, you know, maybe before that, where, you know, you look at some of the great companies out there, They figure out how to scale the price to performance sort of curve and sort of sequence those events.

What happens is most of healthcare has no leverage, which is why it grows.

It's why we spend $5 trillion now in healthcare in the US, $15,000 per capita.

Totally.

Tell folks