Discovery of two novel small-molecule series with potent SARS-CoV-2 inhibition via putative nsp13 open-state trapping
Source check: Source checked. Not independent scientific confirmation.
Finding: A trained message-passing neural network prioritized compounds for experimental testing, leading to a reported new scaffold and two antiviral series. Cell-based assays found antiviral activity among tested compounds; the paper states that direct target engagement is unvalidated, so the proposed mechanism remains provisional.
Technology: A trained message-passing neural network prioritizes candidate compounds for experimental evaluation.
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- The learned model prioritized candidates that led to measured cell-based antiviral activity.
- Test and result
- The computational-to-experimental screen reports 31 compounds meeting its cell-based antiviral-potency criterion among 60 with complete measurements.
- Limitation / still unknown
- Cell-based activity is reported, but direct engagement of the proposed viral target is not experimentally established; no operational compound details are included here.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13523015/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary source full-text Methods and Results; version date and reported validation scope checked..
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.