Dr. David Fajgenbaum

And so, like, we at EveryCure feel that we got to make sure that up-to-date pages are up-to-date, and we also got to make sure that we get the word out to people that don't have access to it.

It would.

And that's what we're hoping to do with EveryCure.

And I'd love any ideas you have for how to get it out.

I mean, that's all we care about.

It's like the drugs we got should treat all the patients who could benefit from the drugs.

And it's like we got to just figure out how to make that match.

More podcasts.

I totally agree.

How does that not exist?

Yeah, it's sort of the kind of thing that we all think someone must have done or there must be something like that.

And then you sort of sit around and then all of a sudden you realize like,

If no one else is gonna do it, I guess we have to do it.

You know, it's like, I guess somehow these things just, everyone's got their lane, right?

And it's like sort of, oftentimes we lose track and there isn't someone who's taking that big picture look.

Sure.

So we use something called a biomedical knowledge graph, which is basically like if you took every drug, disease, gene, protein, everything you can imagine that's related to medicine and bioscience and just put it on the wall, like mapped it up, and then you put connections between every one of those things.

So we know that

interleukin 6 is elevated in castleman disease and you'd put that onto your map you'd map every single concept and then the relationship between everyone you'd create a map that basically represents what we know about all of medicine like every drug every disease every gene every relationship between all of them so now you've got sort of a map of what we know about all of medicine and then we train machine learning algorithms on treatments that we know work like we say siltuximab treats castleman disease

Sirolimus is effective for organ transplant rejection.