Democratizing AI for Biology | Discovery Engines
Get every episode summarized
Each time Discovery Engines – with Nabil publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
About this episode
Gabriele Corso, CEO and co-founder of Boltz, believes the most powerful AI models for drug discovery should be accessible to all, starting with the open models his team has put in the hands of over 100,000 scientists. In this episode, I sit down with Gabriele to explore the leap from predicting protein structures to designing new molecules with Boltz-1, Boltz-2, and BoltzGen, why he champions open access, their multi-year partnership with Pfizer, and the vision of "zero-shot" drug design.
Hosted by Nabil Laoudji. See below for episode links, chapters, and our socials. 🙏🙌
Episode Links:
- Boltz
- Boltz Repository
- Gabriele's LinkedIn
- Worldwide Protein Data Bank
- Ginkgo Lab Tour
- Pfizer Partnership Announcement
Chapters:
- (00:00) - Preview
- (00:56) - Intro
- (02:15) - Why Proteins Matter and Rational Drug Design
- (05:51) - Target Identification, the Toughest Problem in Drug Discovery
- (07:55) - Small Molecules and Biologics
- (12:57) - Does a Disease Have One Target or Many?
- (15:36) - The Billion Dollar Molecule and How Boltz's Models Work
- (22:05) - The Protein Data Bank (PDB) and the Role of Sequencing Data
- (25:55) - What New Data Could Improve AI Bio Models?
- (29:02) - Where Boltz's Training Data Comes From
- (31:46) - Unlocking Private Bio Data
- (35:34) - Boltz's Open Approach vs. DeepMind's Isomorphic Labs
- (39:18) - What Boltz's 100,000 Users Get Access To
- (41:32) - Inside the Pfizer Partnership
- (43:55) - Why Biotech Business Models Are So Hard (Microsoft, Apple, Red Hat)
- (49:17) - How Boltz Differs from Schrödinger, Recursion and Others
- (52:31) - Regulation, the FDA, and Trust in Computational Data
- (56:42) - Autonomous Labs and the Data Feedback Loop
- (1:00:25) - Faster Trials, Virtual Cells, and Other Speedups
- (1:03:34) - When Will a Boltz-Designed Drug Reach a Patient?
- (1:04:55) - How Listeners Can Help (Hiring, Partnerships, Investing)
- (1:06:27) - Closing Reflections on Access
Connect With Us:
Platforms:
Get every episode summarized
Each time Discovery Engines – with Nabil publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Discovery Engines – with Nabil
Building an AI-Driven Autonomous Lab for Life Science R&D | Discovery Engines
Discovery Engines – with Nabil
Building Safe AI - MIT AI Alignment's Riya Tyagi and Gatlen Culp
Discovery Engines – with Nabil
AI for Physics Discovery - Jesse Thaler of NSF's IAIFI, MIT's Center for Theoret...
Discovery Engines – with Nabil
Universal Lab Automation - Rick Wierenga of PyLabRobot
Discovery Engines – with Nabil