Jacob Kimmel

The notion is that there's a lot of mutual information in biology, so if I measure something like most commonly, all the genes the cell is using at a given moment, which you can get by RNA sequencing,

that I get a decent enough picture of most of the other complexity going on.

And so that I can, for instance, take a bunch of healthy cells and a bunch of cells that are in a diseased or aged state, and I'm able then to compare those profiles and say, okay, my diseased cells use these genes, my healthy cells use these.

Are there any interventions I can find that I'm able to do experimentally in the lab that shift one toward the other?

And then the hope would be because you're never going to be able to scan combinatorially all the possible groups of genes just to make that concrete.

They're just going to be round with it.

But there's something like 20,000 genes in the genome.

You can then choose, you know, however many genes in your combination you want.

It's not crazy to think of hundreds at a time.

That's what transcription factors control.

That's how development works.

So the number of possible combinations is truly astronomical.

You just can't test it all.

So the hope would be that by doing some sparse sampling of those pairs, your inputs are here's what the cell looked like beforehand.

Here's the particular genes I perturbed.

You have some measurement then of the state that the cell resulted in.

So here's which genes went up.

Here's which went down.

And then you can start to ask, once I've trained a model to predict from the perturbations to the output on the cell state, what would happen for some arbitrary combinations of genes?

And now in silico, I can search all possible things that one might do and potentially discover targets that take my disease cells back to something like healthy cells.