Engineering the Future of Pharma: AI-Driven Drug Discovery
summary
Traditional figures appear: $2.6B average cost and ~12 years to approval, and the talk gives concrete counters — platform engineering plus CI/CD and cloud infra automates pipelines and data‑oriented architectures so models run at scale, models claim >80% predicted success rates, AI-created molecule enters clinical trials in 8 months (vs 4–5 years typical) and a case screens over 6,000 compounds to find helan, an antibiotic effective against drug‑resistant bacteria; challenges remain: data quality, model interpretability, and experimental validation.
AI-written summary · about
chapters (9)
- 0:00intro
- 0:14agenda
- 0:44traditional drug discovery challenges
- 1:49role of ai in drug discovery
- 2:41ai methodologies in drug discovery
- 3:41case studies on ai in drug discovery
- 5:17benefits and challenges of ai in drug discovery
- 6:44future outlook of ai in drug discovery
- 7:31conclusion and closing remarks
related talks
30mAI in Drug Discovery
11mFaster to the Patient: How AI Is Revolutionizing the Pharmaceutical Industry
16mBeyond Patterns: The Case for Physics-Grounded AI in Drug Discovery
34mThe True Revolution Lies Ahead of Us
23mAI in the Life Science Sector
03mINTERVIEW
35mCan AI solve the biggest problem in drug discovery? Time!
21mShaping the future of health: Boehringer Ingelheim's Data & AI Journey