Chai-2 reports 16% hit rate in zero-shot de novo antibody design
Source check: Needs source check. Not independent scientific confirmation.
Finding: Designing at most 20 antibodies or nanobodies per target for 52 targets without prior PDB binders gave at least one hit for 50% of targets in a single round; 68% wet-lab success for miniproteins. Preprint; the abstract is the only material reviewed; independent replication and developability are not shown; some strengths come from the company's own assays.
Technology: Chai-2 multimodal generative model
Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- Generative model proposed antibody/nanobody sequences tested in wet-lab binding assays.
- Test and result
- Designing at most 20 antibodies or nanobodies per target for 52 targets without prior PDB binders gave at least one hit for 50% of targets in a single round; 68% wet-lab success for miniproteins.
- Limitation / still unknown
- Preprint; the abstract is the only material reviewed; independent replication and developability are not shown; some strengths come from the company's own assays.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:%2210.1101/2025.07.05.663018%22&resultType=core&format=json
Needs source check · editorial details
The source has not been fully checked or contains conflicting information. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 17 Nov 2026. Review scope: Abstract and metadata via Europe PMC; full text not read.
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.