AI Designs Reprogramming Drugs, Boosting Efficiency 3x
jacobkimmel · x · 2026-07-11
This update discusses how advanced AI systems are being used for the virtual design of "cellular reprogramming drugs" prior to physical lab experiments.
The core breakthrough: models previously trained on only a single cell type or lineage achieved cross-lineage generalization this summer. Consequently, data learned from one project can directly benefit others, resulting in a >3x improvement in sample efficiency and reducing the number of real experiments needed to launch new projects.
They also shared two experimental updates:
- In a newly launched vascular endothelial repair project, the team quickly set up an assay for age-related functional damage and identified 5 payloads that make older endothelial cells genetically resemble younger cells while improving regenerative function.
- In a metabolic recovery project, candidate drugs accelerated recovery after alcohol consumption in aged animal models, with this enhanced resilience persisting beyond the initial dosage.
More from Companies & People
- Anthropic and Physical Intelligence held early M&A talks this spring — steph_palazzolo · 2026-07-21
- Google DeepMind’s Project Genie talk shows how creatives feed into model research — alexanderchen · 2026-07-21
- OpenAI’s London Codex event packed a room with teams shipping in one day — paw_lean · 2026-07-21
- Tesla’s FSD momentum fuels a new question: what happens to Uber in 10 years? — oilmutt · 2026-07-21
- Applied Intuition launches Dana for physical AI, alongside a16z interview on one billion machines — a16z · 2026-07-21
- By 2026, software teams may use AI for 80% of the work — but old metrics still miss the point — dfinke · 2026-07-21