Synergistic drug combinations and machine learning for drug repurposing in chordoma.
Source check: Needs source check. Not independent scientific confirmation.
Finding: Bayesian models trained on prior chordoma-cell screening data ranked compounds for in-vitro testing; AZD2014 inhibited U-CH1 and U-CH2 cells (IC50 0.35 and 0.61 μM), though maximal U-CH2 inhibition was limited. Separately tested drug-pair synergy is not attributed to AI. No animal or clinical efficacy is shown.
Technology: Bayesian machine-learning inhibition models
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- Bayesian machine-learning inhibition models trained on prior chordoma-cell screening data ranked compounds from an NIH NCATS asset set for in-vitro testing; the drug-combination experiments were a separate study strategy.
- Test and result
- Indexed primary Results report AZD2014 IC50 of 0.35 μM in U-CH1 and 0.61 μM in U-CH2, with limited maximal U-CH2 inhibition. Afatinib/palbociclib were known-inhibitor comparators; drug combinations were a separate study strategy. Replicate details were not independently assessed.
- Limitation / still unknown
- Cell-line activity does not establish animal or clinical efficacy. Complete model-validation and replicate methods were not independently reviewed.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.1038/s41598-020-70026-w
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 date: 18 Nov 2026. Review scope: Indexed Nature primary abstract and Results passages on Bayesian selection, single-agent activity, and separately tested combinations; complete Methods not independently reviewed..
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 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.