Skip to main content
GEN Podcasts

Reducing Drug Discovery and Development Risk with Mechanistic Modeling

40 min episode · 2 min read
·
Mechanistic Modeling

Episode

40 min

Read time

2 min

Topics

Startups, Fundraising & VC, Leadership

AI-Generated Summary

Key Takeaways

  • Early-stage candidate triage: Apply mechanistic modeling at project inception to rank-order drug concepts before committing resources. When evaluating 10 candidates with funding for only 2–3, modeling can identify which require the fewest experiments, have the most developable biophysical properties, and carry the lowest uncertainty in human dose predictions — potentially freeing budget for an additional program.
  • Sensitivity analysis as experiment prioritization: Mechanistic models use nonlinear differential equations where some parameters, when varied across thousands of simulations, produce negligible output changes, while others cause drastic shifts. Identifying these high-sensitivity parameters — such as protein synthesis rate constants — directs teams toward the specific experiments that resolve go/no-go decisions rather than generating broad datasets.
  • Justified higher starting doses for Phase 1: Traditional allometric scaling applies conservative safety factors that often produce homeopathic starting doses. Mechanistic models incorporating target expression levels, cell numbers, and binding kinetics can demonstrate to the FDA a more precise safety window, supporting a higher, pharmacologically relevant starting dose and compressing dose-escalation timelines.
  • Translational fidelity through layered model building: Build mechanistic models sequentially — in vitro, then mouse, then nonhuman primate — recapitulating each dataset using zero, first, and second-order reactions with minimal parameter fitting to avoid overfitting. This single connected model carries mechanistic assumptions across species, reducing translational uncertainty more reliably than dotted-line allometric extrapolation between species body weights.
  • Post-IND mechanistic PopPK for Phase 1b/2 design: After first-in-human data is available, integrate real clinical measurements back into the mechanistic model rather than switching immediately to standard population PK. This hybrid approach characterizes parameter distributions based on mechanism before patient numbers are large enough for purely statistical PopPK, enabling more precise recommended Phase 2 dose selection and trial design.

What It Covers

John Burke, cofounder and CEO of Applied BioMath, explains how mechanistic modeling replaces traditional allometric scaling in drug development. Using differential equations to simulate biological systems from in vitro through human dose prediction, the approach reduces late-stage attrition, accelerates IND submissions, and helps companies prioritize which drug candidates to advance.

Key Questions Answered

  • Early-stage candidate triage: Apply mechanistic modeling at project inception to rank-order drug concepts before committing resources. When evaluating 10 candidates with funding for only 2–3, modeling can identify which require the fewest experiments, have the most developable biophysical properties, and carry the lowest uncertainty in human dose predictions — potentially freeing budget for an additional program.
  • Sensitivity analysis as experiment prioritization: Mechanistic models use nonlinear differential equations where some parameters, when varied across thousands of simulations, produce negligible output changes, while others cause drastic shifts. Identifying these high-sensitivity parameters — such as protein synthesis rate constants — directs teams toward the specific experiments that resolve go/no-go decisions rather than generating broad datasets.
  • Justified higher starting doses for Phase 1: Traditional allometric scaling applies conservative safety factors that often produce homeopathic starting doses. Mechanistic models incorporating target expression levels, cell numbers, and binding kinetics can demonstrate to the FDA a more precise safety window, supporting a higher, pharmacologically relevant starting dose and compressing dose-escalation timelines.
  • Translational fidelity through layered model building: Build mechanistic models sequentially — in vitro, then mouse, then nonhuman primate — recapitulating each dataset using zero, first, and second-order reactions with minimal parameter fitting to avoid overfitting. This single connected model carries mechanistic assumptions across species, reducing translational uncertainty more reliably than dotted-line allometric extrapolation between species body weights.
  • Post-IND mechanistic PopPK for Phase 1b/2 design: After first-in-human data is available, integrate real clinical measurements back into the mechanistic model rather than switching immediately to standard population PK. This hybrid approach characterizes parameter distributions based on mechanism before patient numbers are large enough for purely statistical PopPK, enabling more precise recommended Phase 2 dose selection and trial design.

Notable Moment

Burke argues that if a drug fails a mechanistically designed trial, teams can be confident the target itself lacks efficacy — not that dosing, patient selection, or trial design was flawed. This distinction eliminates costly repeat Phase 2 or Phase 3 attempts chasing correctable variables.

Know someone who'd find this useful?

Episode Transcript

Welcome to Gencast, a sponsored podcast series brought to you by Genetic Engineering and Biotechnology News. I'm your host, Jeff Pageliscos. The drug discovery and development process can be an arduous endeavor to say the least. Manufacturers spend considerable resources and money chasing down potential candidate molecules in the process of creating a potential new therapeutic, often resulting in abandoning the candidate in the very later stages of development due to minor factors that might have been overlooked at the onset of the discovery process. Thankfully, there have always been those investigators who sought to merge the fields of mathematics and biology while taking advantage of advanced computing algorithms to help inform and derisk drug discovery decisions and streamline the development pipeline. This mechanistic modeling approach is helping to transform drug r and d projects by giving pharma and biotech companies the vital information they need to make the important decisions in a drug's path towards clinical success. In this Gencast, I sat down with an expert in mechanistic modeling to discuss the specifics of this approach and how companies are employing the technology successfully. Let's jump into the discussion. Welcome everyone to this latest Gencast episode. I'd like to welcome our special guest today, doctor John Burke, who is the cofounder, president, and CEO of Applied Biomath, a New England based services and software solutions company that is using mechanistic modeling to guide their pharma and biotech partners in accelerating and derisking the drug discovery and development process. Welcome, John. Good morning, Jeff. How are you doing today? I'm doing great. Thanks for joining us. We really appreciate it. John, maybe you could start off by telling us a little bit more about your background and how you came about to start a company like Applied Biomass. I'm assuming you want the short version. I was always interested in how patterns occurred in nature. If you look out in a lot of ways, trees look like bushes, look like rivers, look like, capillaries, look like your veins. And I was just always fascinated how how that happened. And, clearly, I'm not the first or the last person to be interested in that, but I wanted to go into mathematical biology to help understand that. I loved it. I loved working on dynamical systems, trying to understand how cells and tissues make decisions. After that, I was very fortunate to get a a to be accepted in into MIT for my postdoctoral research with Doug Lauffenburger in the biological engineering department. And what I was even more fortunate about is, during the interview process, I asked him if I could consult on the side. And Doug was more than positive about it, and he stated, and I'm paraphrasing, there's just a lot of trained PhDs out there, and there aren't enough professorships. It's a engineering department, and he encourages people to think about, industry. And at the time, I was consulting for a lot of large companies and small companies, …

Get the full transcript (6,820 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 GEN Podcasts transcripts →

You just read a 3-minute summary of a 37-minute episode.

Get GEN Podcasts summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from GEN Podcasts

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best Biotech Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Startups & Product Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into GEN Podcasts.

Every Monday, we deliver AI summaries of the latest episodes from GEN Podcasts and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime