Machine Learning Assisted Approach for Finding Novel High Activity Agonists of Human Ectopic Olfactory Receptors.
Source check: Needs source check. Not independent scientific confirmation.
Finding: Random-forest screening and docking prioritized candidates from five databases; luciferase assays identified two OR1A1 agonists and one OR2W1 agonist. These receptor-activation assays do not establish a therapeutic effect.
Technology: Random forest classifier
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- Random-forest classifiers trained on molecular descriptors ranked database compounds within training-like chemical space; docking helped select candidates for receptor luciferase assays.
- Test and result
- Luciferase dose-response assays identified two OR1A1 agonists with EC50 95% confidence intervals of 11.5–24.4 and 12.2–25.0 μM, and 2-ethoxynaphthalene as an OR2W1 agonist with interval 3.05–6.59 μM. Benzophenone was the positive activation control. Other selected compounds were inactive or weak activators.
- Limitation / still unknown
- Only selected candidates were experimentally tested; classifier sensitivity and F1 scores were below 0.80. Receptor activation in this assay does not establish physiological or therapeutic effects.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.3390/ijms222111546
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: PMC primary abstract and indexed primary screening/luciferase Results including control and 95% EC50 confidence intervals; 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.