4 million captions derived from database annotations, scientific literature and properties computed from structures.
Natural language can steer all-atom protein design across diverse objectives
Prompteina generated protein sequences and structures from textual specifications, outperforming specialized baselines and producing experimentally confirmed binders to GM2A.
Top University
Joseph Lee · Yanjing Li · Bo Qiang · Gregory Lau · Allyson Ettinger · Noah A. Smith · +4 more
University of Washington · National University of Singapore · Allen Institute for AI (Ai2) · Howard Hughes Medical Institute
Research Digest··3 min read
Lee and colleagues developed Prompteina, a model that jointly generates protein sequences and all-atom structures conditioned on natural-language descriptions of desired properties.
Why this paper
From Allen Institute for AI (Ai2) and 3 others
In one line
Prompteina generates all-atom protein structures from natural language descriptions, outperforming baselines and experimentally validating binders.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§