Short answer: Dov Gertz says customers use three systems that plug into existing workflows: antibody engineering, protein yield optimization, and a virtual cell for target discovery and clinical trial patient stratification, making work faster, cheaper and better.
Watch this answer from Episode 32 (starts at 7:40) · Episode 32 notes and transcript
From Episode 32: From DNA to Drugs: How AI Is Rewriting Human Biology, starting at 7:40.
Jordan Metzner [7:39]: Awesome. Hey, Dov. So tell us a little bit, like, who your customers are. Tell us how they use your software. Tell us, like, what they're excited about. You know? Are these pharmaceuticals? Are these bio labs? Are these universities looking for research? Kind of who's using it? How are they using it? And, obviously, as you mentioned, this is kind of, the early innings. So, obviously, I think everyone's excited about its potential, but tell us a little bit about how your customers see that.
Dov Gertz [8:02]: Yeah. So biotech and pharma companies are our customers, and we're now opening up to academic labs as well. The way they're using it, we have three systems. You could see here on our website. You could see our solutions. So three different discrete solutions. Were always meant to really plug into, existing workflows. So here's the first solution for engineering antibodies, which is, now, in the past few years, become, the most prevalent therapeutic modality to pursue. So that's one workflow that's already existing through our system. The next one is for optimizing protein yield. So one of the biggest barriers is in manufacturing and scaling up the protein yield, and you could see it here. And the third solution that is already available to our customers is our virtual cell for discovering novel targets and optimizing clinical trials through biomarker discovery and patient stratification. That's choosing patients that are correct for a clinical trial. For and in essence, our customers use these as workflows that are very similar to what they're used to doing experimentally. Just they convert that same kind of workflow to a AI driven computational workflow, and we're showing state of the art results across every single one of these modalities that are starting to replace existing experimental workflows.
Jordan Metzner [9:21]: Yeah. And so are this obviously, it's, I presume, it's saving a lot of cost, but is it also saving a lot of time in being able to run more iterations faster? Obviously, there's the offset of, paying for your cost of the services and whatnot. But I just I guess if they're, they're trying to look for physical patients, then able to virtualize the patient, then obviously, like, that cuts down the time. But is it really just about more iterations, or is it about lower cost of testing or kind of the combination of the two?
Dov Gertz [9:47]: Yes. That's a great question. I think we're we're very privileged that if you think of the three, like, core pillar pillars of value that you could provide to a customer, I like to think about it as faster, cheaper, better. And we are very fortunate that our value proposition answers all three. So it is faster, better, and cheaper. I think a lot Of products are either one of these or two of these. We are fortunate to be in a world where AI has completely changed the game, and we're we're adding value in all three fronts.
