Discovery of anticancer peptides from natural and generated sequences using deep learning
Source check: Needs source check. Not independent scientific confirmation.
Finding: Discovery of anticancer peptides from natural and generated sequences using deep learning. The predictor screened over 3.8 million UniProt sequences and 100,000 generated sequences for anticancer peptides. 37 of 41 candidate peptides inhibited tumor cells in vitro; in vitro and in vivo follow-up reported in the abstract. Evidence limits: Baseline benchmarks are the authors' own; in vivo scope not assessed beyond the abstract. Reviewed from Europe PMC abstract only.
Technology: CNBT-ACPred three-channel deep learning predictor plus a generative model
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- The predictor screened over 3.8 million UniProt sequences and 100,000 generated sequences for anticancer peptides.
- Test and result
- 37 of 41 candidate peptides inhibited tumor cells in vitro; in vitro and in vivo follow-up reported in the abstract.
- Limitation / still unknown
- Baseline benchmarks are the authors' own; in vivo scope not assessed beyond the abstract.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/article/MED/39706427
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: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
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.