Machine learning helps identify a Beclin 2-Ubiquilin 1 interaction in breast-cancer cells
Source check: Source checked. Not independent scientific confirmation.
Finding: Classical machine-learning classifiers predicted autophagy-related protein interactions, which researchers intersected with immunoprecipitation-mass-spectrometry results to select candidates in triple-negative breast-cancer cells. Co-immunoprecipitation supported the Beclin 2-Ubiquilin 1 interaction, and cell experiments linked Beclin 2 overexpression to increased Ubiquilin 1, autophagy and reduced proliferation and migration. Despite the title, the reported classifiers are Naive Bayes, decision trees and k-nearest neighbors; the results do not establish clinical benefit.
Technology: Naive Bayes; decision tree; k-nearest neighbors
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- Naive Bayes, decision-tree and k-nearest-neighbor classifiers predicted protein interactions; predictions were intersected with experimentally detected Beclin 2-associated proteins before targeted validation.
- Test and result
- Co-immunoprecipitation supported the predicted Beclin 2-Ubiquilin 1 interaction; subsequent MDA-MB-231 cell assays examined autophagy, proliferation and migration.
- Limitation / still unknown
- The represented result is from cell experiments, not clinical treatment. Predicted interaction counts are not experimentally confirmed interaction counts.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.32604/or.2024.055921 · https://pmc.ncbi.nlm.nih.gov/articles/PMC11671618/
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: 21 Nov 2026. Review scope: Primary full article Methods, result-specific experiments, discussion, affiliations and journal publication metadata; no independent replication performed..
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.