David Baker Lab Uses AI to Design Precision Kinase Regulators
DaveJuergens · x · 2026-07-15
The David Baker Lab has successfully used AI to design genetically encoded small proteins that directly regulate kinase activity.
- Breakthrough: Kinase structures are highly similar, causing traditional inhibitors to easily miss targets. The designed proteins directly target the kinase catalytic domain rather than traditional allosteric sites.
- Experimental Data: 96 binding proteins were designed for FAK kinase, 33 of which showed regulatory activity. Among the top 4, 2 inhibited FAK at low nanomolar levels, and 2 increased activity by over 2-fold.
- Cellular Validation: Expressing these proteins in living cells successfully replicated in vitro kinase inhibition/activation effects and rewrote intracellular signaling.
- Expansion Potential: Leveraging structural similarities, the team adapted FAK inhibitors into Src kinase inhibitors, providing a universal design blueprint for kinase-targeted drugs.
More from Research
- HarnessMM cuts agent tokens per task by up to 88% while raising success rates — omarsar0 · 2026-10-26
- Ben Recht: The world needs a truly open language model, and it's easier to build than you think — beenwrekt · 2026-10-26
- New Blog Breaks Black-Box Distillation Into Five Practical Steps — chrisrohlf · 2026-10-26
- DetectorScope turns black-box AI text detectors into auditable ones with sparse autoencoders — _akhaliq · 2026-10-26
- OPST paper shows LLMs self-improve with zero human data, guided only by topic descriptions — _akhaliq · 2026-10-26
- Tencent's HiSTEVE 1.0: hierarchical VLA agent plays Minecraft with native keyboard and mouse, hits 85% SOTA — _akhaliq · 2026-10-26