muni AI Agent Discovers Three Sub-Nanomolar Protein Binders
AllThingsApx · x · 2026-08-19
Using NVIDIA's Proteina-Complexa model, muni.bio's autoresearch agent explored nearly 14,000 protein designs. Validated by Adaptyv's wet lab, nine designs showed strong binding signals, with three achieving sub-nanomolar affinity. This demonstrates agents' ability to close the loop between computational design and lab feedback to improve discovery.
More from Embodied
- UMA Robots assembles world-model team led by VL-JEPA co-author — RemiCadene · 2026-08-19
- OSRA Publishes Roadmap for Physical AI and ROS — kscottz · 2026-08-19
- Wayve hires Alex Toshev to lead new general robotics team at Wayve Labs — Jamie_Shotton · 2026-08-19
- microagi launches in London to put AI robots on British factory floors — chris_j_paxton · 2026-08-19
- VLA Model Paper Wins Outstanding Award at RLC — RobobertoMM · 2026-08-19
- CoRL 2026 Workshop: Continually Self-Improving Robots — chris_j_paxton · 2026-08-19