AI Science Tracker
EN

Fitting quantum machine learning potentials to experimental free energy data: Predicting tautomer ratios in solution

Not stated in the abstract reviewed · 25 Oct 2020 · chemistry

Discovery

Fitting quantum machine learning potentials to experimental free energy data: Predicting tautomer ratios in solution

Source check: Source checked. Not independent scientific confirmation.

Finding / tested result: Quantum machine-learning potentials fitted to experimental free-energy data support alchemical calculations of tautomer ratios; on an independent 71-pair test set the optimized QML RMSE fell from 6.6 to 3.1 kcal/mol. This is a bounded computational chemistry result, not an experimentally discovered drug effect.

Technology: QML potentials provide learned quantum-chemical energies for alchemical free-energy estimation.

Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
QML potentials provide learned quantum-chemical energies for alchemical free-energy estimation.
Limitation / still unknown
BioRxiv v1 full text; Methods describes training/validation and Results reports independent test-set error on 71 tautomer pairs.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.biorxiv.org/content/10.1101/2020.10.24.353318v1.full

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: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

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 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse chemistry discoveries.