Genentech and Google DeepMind unveil PerturbME for discovering unknown biology
AllThingsApx · x · 2026-08-22
Genentech, in collaboration with Google DeepMind, the Broad Institute, and Stanford, introduced PerturbME, a framework designed to scale the discovery of unknown biology and mechanisms. It combines GDM's Co-Scientist agent with a sample-efficient, genome-wide, multimodal perturbation framework. This technique allows selective sequencing of informative cancer cells while Co-Scientist generates mechanistic hypotheses. Insights from this work could advance next-generation cancer therapies, including protein binders, mRNA vaccines, and CAR-T cells. A preprint with data and code has been released.
More from Research
- Devin Oncall tops SREGym with 100% end-to-end success, auto-resolving production incidents — tianyin_xu · 2026-10-16
- SJTU AutoLab releases Drive3R, a streaming geometric foundation model for long-horizon driving 3D reconstruction — AutoLab-SJTU · 2026-10-16
- Cortex A/B-tests coding-agent skills and rules by replaying developer corrections before keeping them — Samuele Giampieri · 2026-10-16
- Zero-latency lab-in-the-loop tests whether drug-discovery agents cheat via memorization — niloofar_mire · 2026-10-16
- 260M-parameter looped diffusion transformer beats 6x larger baselines with 5x less compute — burkov · 2026-10-16
- Stanford's Next-Concept Modeling sketches text first, 21x faster generation on one H100 — lmoroney · 2026-10-16