Real Alpha
Watch modeSubscribed

MTS · 2 min · Oct 21, 2026

Cancer AI tools could reach clinical trials within a year

TA

Tanishq Abraham

Co-founder & CEO, Sophont

  • Theo JaffeeHost · Co-founder & host, MTS

    One of the first members of a16z's new media team; earlier hosted the Emergent Ventures-backed Theo Jaffee Podcast.

  • Sophia DewHost · Host, MTS

About this segment

Abraham says some tools may reach retrospective trials, and potentially prospective ones, within a year. Those trials could provide evidence of clinical value.

From “Cancer AI Models Will Reach Clinical Trials Within a Year | Tanishq Abraham”, Oct 21, 2026. Watch the full episode

“some of these tools could potentially reach these clinical trials, at the very least, definitely like retrospective trials, potentially even prospective trials.”
TATanishq Abrahamat 21:50 · MTS21:50

Takeaways

  1. He expects evidence from trials before broad patient adoption.
  2. Retrospective trials are the nearer-term prospect.
  3. Prospective trials may also be possible with enough resources.
Watch 2:05 from 21:20

In this episode

Full episode
  1. 0:36Tumor slides can reveal biology that guides personalized care6:11
  2. 9:32Cancer AI could support research, drug development, and care2:51
  3. 12:33AI drug discovery needs evidence from human biology2:43

  4. 21:20Cancer AI tools could reach clinical trials within a year2:05

  5. 15:07Patient tests may matter before new drugs reach the clinic3:07Up next

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 21:25

    especially when it's open source it's such a collaborative open ecosystem yeah one last question i have for you before we go i know we talked about all the things that might happen in theory or might happen someday but i want to just get very concrete what do you think is something that could happen in a year from now that doesn't exist today that's a very good question um it's a year from now is a very tight timeline for sure in the space of biology. I mean, I think what we'll start to see is some of these tools could potentially reach these clinical trials, at the very least, definitely like retrospective trials, potentially even prospective trials. And so you will start to see evidence around the fact that these models can actually have useful impact. So yeah, I think that's kind of where it is. And then at that

  2. 22:15

    point, it will start to hopefully move on to actually having impacted patients. And, you know, people will start to adopt these sorts of tools. But I think like, yeah, a year is a bit of a tight timeline. But I think like, you know, the evidence will be around, there'll be a lot of evidence, a lot of kind of, you know, trials and things around this that could potentially happen, assuming, you know, people, you know, dedicate their resources to this, I think, you know, as a community, we need to be dedicating a lot more resources to medical AI and bio AI. So if we can do that, I think, you know, the progress that we can make can be very rapid, where we'll start to see the evidence. And then at that point, I think a year, maybe it might be possible that some of these things could start to reach sort of like, you know, just like very simple things of like,

  3. 22:58

    oh, maybe you can look at, you know, how, you know, again, patients are responding to different drugs, maybe not like a very comprehensive, like, you know, you know, like cure of cancer or anything all like this, obviously that's not going to be possible in a year, but there's some basic things that can still have huge impact on people's lives that I think, you know, within a couple of years, we can start to see this happen. So I'm very excited for the future for this reason.

  4. 23:18

    Very cool. Tanisha, I really wanted to thank you for joining us today on MTS. This is honestly one