The Translation Gap
summary
Company builds a simulated cell technology that runs billions of in silico simulations to predict which patients respond to which drugs, producing terabytes of simulation outputs that biologists can “open up” for mechanistic explanations rather than black‑box scores. Product work includes a biology backlog template plus data‑scientist pairing and a three‑month AI training for biologists; the process reduces handoff conflict within about three to four months and yields benchmarkable predictive metrics aimed at improving clinical phase success.
AI-written summary · about
chapters (19)
- 0:00Turbine and translation gap
- 1:02Translation gap in drug discovery
- 4:40AI simulates cancer cells
- 8:39Cross-functional team challenges
- 12:30Trust and communication in teams
- 17:26Resolving biologist-engineer conflicts
- 21:23Aligning teams for drug discovery
- 22:27Q&A: Testing communication skills
- 24:14Q&A: Ethical vs fast development
- 24:57Q&A: Hiring skills for teams
- 26:41Q&A: Product vs scrum roles
- 27:45Q&A: COVID performance
- 28:29Q&A: Overcoming team dead ends
- 30:18Q&A: Hungary startup hub
- 31:21Q&A: COVID performance
- 32:45Q&A: Turbine’s first drug timeline
- 34:29Q&A: Product to sales transition
- 36:35Q&A: Last team conflict resolved
- 37:41Q&A: Measuring product impact
related talks
20mTranslating a Trillion Pointo Diseases of Data into Therapies
34mThe True Revolution Lies Ahead of Us
16mHow Biology Benefits from Technological Discoveries
23mAI in the Life Science Sector
16mBeyond Patterns: The Case for Physics-Grounded AI in Drug Discovery
08mEngineering the Future of Pharma: AI-Driven Drug Discovery
10mGenesis Final Round - Drylab AI
23mGenomics and AI on Cloud Foundry