Cancer AI Models Will Reach Clinical Trials Within a Year | Tanishq Abraham

SPEAKER_1 (0:00)

Today, we are live in the studio with Tanishq Abraham, who is the co-founder and CEO of Cirquant, the Frontier Mental AI Lab.

SPEAKER_2 (0:08)

And just today, earlier, today on, this is literally a few hours ago, you guys officially announced the Holon S1 model. This is an AI model for cancer biology. Lots of great stuff. I'm super excited to just get in the weeds, talk all about what you guys are building, Sophont, Holon S1, so welcome to MTS.

Tanishq Abraham (0:26)

Yeah, thank you so much for having me. This is a lot of fun, yeah.

SPEAKER_2 (0:28)

Yeah, it's lots of fun. You live in Sacramento, so you're just here for the day, and so you happen to actually get to join us live on MTS. So let's just jump into it. So you guys announced Holon S1 earlier today. What was that big announcement?

Tanishq Abraham (0:42)

Yeah, so Holon S1 is a new cancer biology AI model that we've trained on pathology tissue slides. So the idea here is that the challenge with cancer specifically, obviously, is that why is it so hard to cure cancer? The reason it's so hard to cure cancer is because of the fact that cancer is a very diverse disease, right?

Every person has a slightly different kind of disease in terms of, even though they may have the same exact diagnosis, a person may have triple negative breast cancer, but the underlying biology can be quite different. The genes that are being expressed, the interactions of the cells with each other, all of that can be quite different.

So the question is, how can we actually map that and measure that? That can enable us to then more personalize the treatments for these patients. There are various different tools for doing these molecular tests and so on, but a lot of these tools can be quite expensive and also quite time-consuming. So the idea that we want to explore here is, can we extract a lot of those similar insights directly from a tissue slide? So a tissue slide, what we mean by this is that, basically whenever a cancer patient has a solid tumor, the typical standard of care or the typical goal standard for getting that cancer diagnosed in the first place is you take a biopsy, right? You take a sample of the tissue and then you put it under the microscope, you put it on a slide and you put it on the microscope and a doctor is analyzing that. And so in this case, what we're saying is, we can actually take that same exact slide and actually with the power of AI, we can extract a lot more information about what's happening at the molecular and biological level and what sorts of pathways are being expressed, what sorts of genes are being expressed, and what makes that tumor unique for that patient.

SPEAKER_2 (2:25)

Wow, that is so fascinating. I realize as we're saying this, I actually don't totally know how complex of a problem it is. You hear often, all right, AI is actually going to solve cancer, but we don't talk about how it's going to solve cancer. I know part of your solution, of course, with Holon S1 is having a specific AI model designed for cancer biology. What does that word designed mean?

Tanishq Abraham (2:48)

Yeah, I mean, I think the idea is like, we want to be able to train this model on, yeah, like the sort of pan-cancer understanding all these different cancer types.

I think like, the thing is these sorts of, in my opinion, a lot of these sorts of classifications of cancer types are a bit arbitrary too. Again, what really matters is what's happening at the molecular and biological level. So we want to train this model on a variety of different cancer types to understand exactly what's going on at this level and being able to connect this across different modalities, including modalities that are more easily accessible. And so that's the real power of these models, is to extract information with modalities that a regular patient may be able to have access to.

SPEAKER_2 (3:35)

So specifically, does this mean now that we'll learn more about rare cancers that we've never been able to learn before?

Tanishq Abraham (3:41)

Yeah, potentially.

I think a lot of this, of course, needs to further be validated. Of course, this is still a model that there's a lot more validation that needs to be done with this model. But yeah, I mean, we've seen some really interesting results with the model that we currently have. For example, we actually looked at a patient with a rare type of bone cancer called osteosarcoma. And our model wasn't actually trained on osteosarcoma, but it was able to extract a lot of biological insights that this patient's medical team had also observed. But that medical team had utilized very expensive molecular tests. And so we were able to identify, for example, this one gene which was actually then targeted by the medical team for treatment for this patient and led to a successful treatment for that patient. But we were able to do this directly from the pathology slide image. And so I think there is definitely potential for a lot of this stuff to be able to explore rare cancers. But again, it needs to be further validated, but we're really excited by the potential of this model for sure.