Episode

Beyond Language: Why Drug Discovery Needs Physical AI, Not Just Large Language Models

Podcast
Data in Biotech
Published
Jul 20, 2026
Duration seconds
3487
Processing state
not_requested
Canonical source
https://pod.co/data-in-biotech/beyond-language-why-drug-discovery-needs-physical-ai-not-just-large-language-models
Audio
https://downloads.pod.co/5fac40cd-043b-485f-838d-c63fa01ae1b2/5eff22ea-5ddf-4816-8605-d41b7b180fd7.mp3
JSON
/v1/public/podcasts/data-in-biotech-6628050/episodes/beyond-language-why-drug-discovery-needs-physical-ai-not-just-large-language-models
Markdown
/podcast/data-in-biotech-6628050/beyond-language-why-drug-discovery-needs-physical-ai-not-just-large-language-models.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/data-in-biotech-6628050/episodes/beyond-language-why-drug-discovery-needs-physical-ai-not-just-large-language-models/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/data-in-biotech-6628050/beyond-language-why-drug-discovery-needs-physical-ai-not-just-large-language-models.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

In this episode of Data in Biotech, host Ross Katz sits down with Woody Sherman, Founder and Chief Innovation Officer at PsiThera, for a conversation on why AI can transform drug discovery's paperwork and code while barely touching the hardest part of the problem: the molecules themselves. Woody's career runs through physical chemistry at MIT; over a decade at Schrödinger building tools the industry still relies on; founding Silicon Therapeutics (where his team took a small molecule STING agonist from concept to clinic in roughly three years); scaling that platform after Roivant's acquisition; and now leading PsiThera's effort to build oral small molecules for immunology targets that today are only reachable with injectable biologics. The conversation digs into why large language models excel at automation, coding, and regulatory writing but hit a wall when the task is predicting how a molecule behaves, what "physical AI" actually means as a category distinct from both LLMs and traditional physics-based simulation, and why representing molecules as quantum mechanical objects rather than text strings or 2D graphs changes what's predictable. Woody also walks through the STING program in detail, why the field's excitement over fast co-folding models like Boltz needs a strong dose of skepticism, and what it takes to build a database and team culture where chemists, biologists, and data scientists can actually understand each other. What you'll learn in this episode: >> Why the contradiction of "AI is transforming drug discovery" and "drugs still take a decade and billions of dollars" can both be true at once. >> How Silicon Therapeutics engineered a small molecule STING agonist to dimerize itself through a quantum mechanical interaction that had never been desi…