Accelerated Discovery of Novel Ponatinib Analogs with Improved Properties for the Treatment of Parkinson's Disease.
Source check: Source checked. Not independent scientific confirmation.
Finding: Paired Naive Bayes models prospectively prioritized ponatinib analogs for c-Abl potency and reduced hERG liability. Of six new compounds tested, two combined sub-10 nM c-Abl activity with improved hERG assay profiles; this is biochemical optimization, not evidence of Parkinson’s efficacy or cardiac safety.
Technology: Paired Naïve Bayes networks
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- A single Naive Bayes network predicted c-Abl potency; two networks in concert prioritized c-Abl potency and predicted hERG IC50 greater than 1 μM, and the workflows were prospectively tested.
- Test and result
- Six novel compounds were tested. Table 1 reports compounds 4 and 5 with c-Abl IC50 below 10 nM and hERG IC50 5.02 and 12.1 μM; nilotinib/ponatinib hERG values are 0.45/0.77 μM. The correction swaps compounds 4/5 in the separate kinase-panel Table 2, not these Table 1 values.
- Limitation / still unknown
- The enzyme/channel and cell-toxicity assays do not establish Parkinson’s efficacy, in-vivo exposure, or clinical cardiac safety. The June 24 correction swaps compounds 4 and 5 in kinase-panel Table 2.
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/PMC7153011/ · https://doi.org/10.1021/acsmedchemlett.9b00612
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 18 Nov 2026. Review scope: PMC Results and Table 1; indexed primary correction Table 2; ACS online/issue publication metadata..
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.