Designing protein domains with ESM3: function depends on the neighborhood, not isolation
bravo_abad · x · 2026-09-25
In his AI-for-Science newsletter, Jorge Bravo Abad highlights a protein design paper by Bülbül et al. that uses ESM3, ProteinMPNN and EvoDiff to generate new thiolation domains for non-ribosomal peptide synthetases. The key insight: instead of designing a domain in isolation, the authors keep its neighboring structure intact, since a domain's function can depend on what sits next to it — protein domains are not necessarily reusable Lego bricks. He collects such transferable ideas beyond the original papers.
Related event: 578 Variants Show Protein Domains Must Be Designed in Context(2 posts)→
More from Research
- Continuous diffusion LM RePlaid accepted at NeurIPS 2026, matches discrete diffusion scaling — ArashVahdat · 2026-09-25
- AAAI 2027 phase 1 reviews are out — CSProfKGD · 2026-09-25
- NeurIPS AC Posts Meta-Review Claiming No Rebuttal Submitted—Before the Rebuttal Period Even Started — BlackHC · 2026-09-25
- MUX latent reasoning method wins NeurIPS Spotlight, cuts CoT length 3-6x — mmbronstein · 2026-09-25
- Stanford's 37K AI agents analyzed 57K clinical trials as a 'virtual biotech' — james_y_zou · 2026-09-25
- CVP from UC San Diego and Lambda beats Video-3D-LLM on all five 3D spatial reasoning benchmarks — TheZachMueller · 2026-09-25