Prompteina: First Text-Conditioned All-Atom Protein Structure Generation Model
PangWeiKoh · x · 2026-10-14
Prompteina is presented as the first text-conditioned all-atom protein structure generation model, producing both sequence and full all-atom 3D structure directly from natural-language prompts, replacing property-by-property engineered conditioning with a single language interface.
Key contributions:
- Prompteina-Data: 1.8M protein-chain structure entries (PDB, AlphaFold DB, synthetic dimers) paired with 52.4M LLM-written captions (29 per structure, up to 59 annotation types).
- Captions include fine-grained residue-linked constraints such as disulfide bonds, catalytic sites, and protein-protein contacts, with phrase-to-residue correspondences.
- Demo cases include generating small-molecule binders, up-down bundles, alpha-beta barrels from text, with experimental evidence like 68.8 nM binding affinity.
More from Research
- IBM ported Spyre's torch.compile backend to Inductor, cutting code 7x — lmoroney · 2026-10-14
- Neuro for AI & AI for Neuro workshop at AAAI 2027 opens call for papers in Montreal — naturecomputes · 2026-10-14
- BVB Benchmark Tests Agent Video Understanding by Rebuilding 288 Real Videos in Blender — SonglinYang4 · 2026-10-14
- NSF awards $20M to AI Institute in Dynamic Systems for robotic manufacturing — eigensteve · 2026-10-14
- Should ICLR slash its acceptance rate to ~10% as submissions surge? — boknilev · 2026-10-14
- Is 'Attention' the Essence of Intelligence? Quanta examines the idea behind Transformers — TMWNN · 2026-10-14