What are the key takeaways from this Beyond Biotech episode?

Key insights include: **Human data gap in liver disease:** Only 40,000 liver transplants are performed globally each year against 1.5 million annual deaths from liver disease. Drug discovery fails here across three compounding problems: insufficient causal human biology knowledge, animal models that cannot predict fibrosis regression, and clinical trials that lack reliable human endpoint data — all requiring a human-first data strategy to address.; **AI requires causal data, not just correlational data:** AI models detect correlations that human brains cannot see, but correlation alone cannot resolve biological complexity or causality. To build genuinely predictive models, teams must generate perturbation data — knocking out every expressed gene across multiple human donors and disease states — then RNA sequence the results to construct a functional gene regulatory network.; **Designing data for AI at scale:** Ochre Bio and Lexogen generated a foundational perturbation dataset covering all expressed genes across multiple human liver donors and disease states. Lexogen's TAW technology, which eliminates the RNA extraction step, reduced variation and increased sensitivity, enabling detection of low-level gene expression. The project achieved a 95% success rate and was completed within five months.

What did Quinn Wills and Stefan Baj discuss on Beyond Biotech?

Ochre Bio CEO Quinn Wills and Lexogen CEO Stefan Baj examine why drug discovery fails due to non-human biology models, how they built one of the world's largest human liver functional genomics datasets, and how purpose-designed RNA sequencing data enables AI-driven target discovery for liver disease affecting 1.5 million deaths annually. Key topics include: **Human data gap in liver disease:** Only 40,000 liver transplants are performed globally each year against 1.5 million annual deaths from liver disease. Drug discovery fails here across three compounding problems: insufficient causal human biology knowledge, animal models that cannot predict fibrosis regression, and clinical trials that lack reliable human endpoint data — all requiring a human-first data strategy to address.; **AI requires causal data, not just correlational data:** AI models detect correlations that human brains cannot see, but correlation alone cannot resolve biological complexity or causality. To build genuinely predictive models, teams must generate perturbation data — knocking out every expressed gene across multiple human donors and disease states — then RNA sequence the results to construct a functional gene regulatory network..

How long is this episode of Beyond Biotech?

This episode is 38 minutes long. SignalCast provides an AI-generated summary so you can get the key insights in about 3 minutes.

Beyond Biotech

The problem at the heart of drug discovery: Lexogen & Ochre Bio on the power of AI on human data

May 22, 2026

38 min episode · 2 min read

Quinn Wills,Stefan Baj

Episode

38 min

Read time

2 min

Topics

Startups, Leadership, Design & UX

AI-Generated Summary

Published May 22, 2026

Key Takeaways

✓Human data gap in liver disease: Only 40,000 liver transplants are performed globally each year against 1.5 million annual deaths from liver disease. Drug discovery fails here across three compounding problems: insufficient causal human biology knowledge, animal models that cannot predict fibrosis regression, and clinical trials that lack reliable human endpoint data — all requiring a human-first data strategy to address.
✓AI requires causal data, not just correlational data: AI models detect correlations that human brains cannot see, but correlation alone cannot resolve biological complexity or causality. To build genuinely predictive models, teams must generate perturbation data — knocking out every expressed gene across multiple human donors and disease states — then RNA sequence the results to construct a functional gene regulatory network.
✓Designing data for AI at scale: Ochre Bio and Lexogen generated a foundational perturbation dataset covering all expressed genes across multiple human liver donors and disease states. Lexogen's TAW technology, which eliminates the RNA extraction step, reduced variation and increased sensitivity, enabling detection of low-level gene expression. The project achieved a 95% success rate and was completed within five months.
✓Lab-in-the-loop scaling strategy: Ochre Bio perturbs approximately 2,000 genes directly in complex human liver tissue models, then trains AI on that causal data to predict outcomes for all remaining untested genes in silico. This approach avoids reverting to simple cell lines while scaling predictions beyond what physical experimentation alone can achieve, using complex human tissue as the AI training ground.
✓Regulatory environment shifting toward human models: The FDA no longer requires animal studies before first-in-human trials, and recently indicated that liver disease clinical trials can move away from biopsy-dependent endpoints toward biomarker-driven measures. Bayesian clinical trial designs now allow data borrowing across prior studies and indications, enabling more sophisticated and ethically grounded use of human data in drug development.

What It Covers

Ochre Bio CEO Quinn Wills and Lexogen CEO Stefan Baj examine why drug discovery fails due to non-human biology models, how they built one of the world's largest human liver functional genomics datasets, and how purpose-designed RNA sequencing data enables AI-driven target discovery for liver disease affecting 1.5 million deaths annually.

Key Questions Answered

•Human data gap in liver disease: Only 40,000 liver transplants are performed globally each year against 1.5 million annual deaths from liver disease. Drug discovery fails here across three compounding problems: insufficient causal human biology knowledge, animal models that cannot predict fibrosis regression, and clinical trials that lack reliable human endpoint data — all requiring a human-first data strategy to address.
•AI requires causal data, not just correlational data: AI models detect correlations that human brains cannot see, but correlation alone cannot resolve biological complexity or causality. To build genuinely predictive models, teams must generate perturbation data — knocking out every expressed gene across multiple human donors and disease states — then RNA sequence the results to construct a functional gene regulatory network.
•Designing data for AI at scale: Ochre Bio and Lexogen generated a foundational perturbation dataset covering all expressed genes across multiple human liver donors and disease states. Lexogen's TAW technology, which eliminates the RNA extraction step, reduced variation and increased sensitivity, enabling detection of low-level gene expression. The project achieved a 95% success rate and was completed within five months.
•Lab-in-the-loop scaling strategy: Ochre Bio perturbs approximately 2,000 genes directly in complex human liver tissue models, then trains AI on that causal data to predict outcomes for all remaining untested genes in silico. This approach avoids reverting to simple cell lines while scaling predictions beyond what physical experimentation alone can achieve, using complex human tissue as the AI training ground.
•Regulatory environment shifting toward human models: The FDA no longer requires animal studies before first-in-human trials, and recently indicated that liver disease clinical trials can move away from biopsy-dependent endpoints toward biomarker-driven measures. Bayesian clinical trial designs now allow data borrowing across prior studies and indications, enabling more sophisticated and ethically grounded use of human data in drug development.

Notable Moment

Quinn Wills reveals that Ochre Bio's foundational genomics dataset is already generating drug target hypotheses — including identifying genes within hepatocytes that could upregulate FGF21 from within the cell itself, potentially replacing the current therapeutic approach of simply administering the protein externally as a treatment for liver fibrosis.

Know someone who'd find this useful?

Episode Transcript

Hello, and welcome to Beyond Biotech, the weekly podcast from Labiatek. I'm Dylan Khesain, and this is episode 198 for the podcast. Today, I'm welcoming two guests, Quinn Wills, CEO of OkaBio, a biotech developing RNA therapies for chronic liver disease using AI models, and Stefan Baj, CEO of Lexigen, an RNA transcriptomics company and NGS service provider. It's a deep dive into cutting edge transcriptomics, human first data, and artificial intelligence. I hope you enjoy our discussion. Quinn Wills, welcome to Beyond Biotech. Thank you very much. It's actually a pleasure to be here. Stefan, welcome to Beyond Biotech as well. Hi. Thank you very much. Look. I I wanna start somewhere a little bit bigger than just either of your companies because I think that's really the right place to begin. Let me set the scene for you here. Drug discovery, it's had a productivity problem for decades. Costs keep going up. Failure rates in the late stage trials are just really stubbornly high. And a significant part of that failure comes down to the fact that the biology being studied in the lab isn't human. Quinn, let me start with you. You built OkaBio on a conviction that this really has to change. Tell me about the problem you set out to solve and why you think this different approach is possible now when it hasn't been before. Mhmm. Absolutely. Happy to. So perhaps the a little bit of a back story on on why liver disease I'm I'm originally a clinician before I turn into an AI type. And way back when, we're talking about twenty five years ago, I really got to think about liver disease when I was studying alcoholism back in South Africa. You know, we have I I might have mentioned this before in in other pieces, but in South Africa, under apartheid, we had the dork system where you could pay people in alcohol, and it created a very sad situation, where alcoholic liver disease is a massive problem in certain parts of South Africa. And that's sort of how I got into thinking a lot about liver. And fast forward twenty five years, really, we still it still is such a big passion of mine. It is you know, for me, the two key numbers to know here are one and a half million people globally a year die of liver disease. And really, for the vast majority of those folks, the only real curative option is a liver transplant. And if you think that only forty about forty thousand liver transplants get done globally a year, it's a health lottery. It's not even health care. We're not even close to health care with liver disease. So it's a huge issue, and it's a issue that, disproportionately affects disadvantaged communities as we've seen in South Africa. So that that's really been the mission. It's been a big mission in my life, but there's a problem beyond just the patient problem. …

Get the full transcript (6,304 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all Beyond Biotech transcripts →