Deep-learning de novo GLP-1RAs show half-life about 3x semaglutide in mice
Source check: Needs source check. Not independent scientific confirmation.
Finding: 10,000 designed GLP-1RAs; 60 passed criteria; 62% in vitro success; two had half-lives about three times semaglutide and the best candidate outperformed semaglutide in diabetic and obesity mouse models. Preprint; mouse data only; head-to-head claims not independently checked; affiliations not read.
Technology: Deep-learning protein design plus functional screening
Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- Deep-learning design generated peptide candidates before wet-lab screening.
- Test and result
- 10,000 designed GLP-1RAs; 60 passed criteria; 62% in vitro success; two had half-lives about three times semaglutide and the best candidate outperformed semaglutide in diabetic and obesity mouse models.
- Limitation / still unknown
- Preprint; mouse data only; head-to-head claims not independently checked; affiliations not read.
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:%2210.1101/2025.03.26.645438%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 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.