EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Discriminating High from Low Energy Conformers of Druglike Molecules: An Assessment of Machine Learning Potentials and Quantum Chemical Methods

Linghan Kong, Richard A Bryce iD

ChemPhysChem · 2025

DOI: 10.1002/cphc.202400992 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ChemPhysChem, 2025. Verfasst von Linghan Kong und 1 weiteren Autor:innen. Beteiligte Einrichtung: Division of Pharmacy and Optometry, School of Health Sciences, Manchester Academic Health Sciences Centre, University of Manchester, Oxford Road, Man…. Hauptthemen laut MEDLINE: Machine Learning, Quantum Theory. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research IT, Computational Shared Facility at the University of Manchester, EPSRC.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and efficient prediction of high energy ligand conformations is important in structure‐based drug discovery for the exclusion of unrealistic structures in docking‐based virtual screening and de novo design approaches. In this work, we constructed a database of 140 solution conformers from 20 druglike molecules of varying size and chemical complexity, with energetics evaluated at the DLPNO‐CCSD(T)/complete basis set (CBS) level. We then assessed a selection of machine learning potentials and semiempirical quantum mechanical models for their ability to predict conformational energetics. The GFN2‐xTB tight binding density functional method correlates with reference conformer energies, yielding a Kendall's τ of 0.63 and mean absolute error of 2.2 kcal/mol. As putative internal energy filters for screening, we find that the GFN2‐xTB, ANI‐2x and MACE‐OFF23(L) models perform well in identifying low energy conformer geometries, with sensitivities of 95 %, 89 % and 95 % respectively, but display a reduced ability to exclude high energy conformers, with respective specificities of 80 %, 61 % and 63 %. The GFN2‐xTB method therefore exhibited the best overall performance and appears currently the most suitable of the three methods to act as an internal energy filter for integration into drug discovery workflows. Enrichment of high energy conformers in the training of machine learning potentials could improve their performance as conformational filters.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningQuantum TheoryMolecular ConformationThermodynamicsPharmaceutical PreparationsLigandsDensity Functional Theory

Stichwörter der Autor:innen

Ligandhigh energy conformationsmachine learning potentialsquantum chemistry

Substanzen

Pharmaceutical PreparationsLigands

Autor:innen und Institutionen

  • Division of Pharmacy and Optometry, School of Health Sciences, Manchester Academic Health Sciences Centre, University of Manchester, Oxford Road, Manchester, M13 9PT, UK.

ORCID-Profile: Richard A Bryce

Förderung

  • Research IT
  • Computational Shared Facility at the University of Manchester
  • EPSRC
  • Engineering and Physical Sciences Research Council

Zitieren

APA

Kong, L., & Bryce, R. A. (2025). Discriminating High from Low Energy Conformers of Druglike Molecules: An Assessment of Machine Learning Potentials and Quantum Chemical Methods. ChemPhysChem. https://doi.org/10.1002/cphc.202400992

Vancouver

Kong L, Bryce RA. Discriminating High from Low Energy Conformers of Druglike Molecules: An Assessment of Machine Learning Potentials and Quantum Chemical Methods. ChemPhysChem. 2025. doi:10.1002/cphc.202400992

BibTeX
@article{Kong2025,
  author = {Kong, Linghan and Bryce, Richard A},
  title = {Discriminating High from Low Energy Conformers of Druglike Molecules: An Assessment of Machine Learning Potentials and Quantum Chemical Methods},
  journal = {ChemPhysChem},
  year = {2025},
  doi = {10.1002/cphc.202400992}
}
Kostenlos starten →