EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robustness of Protein–Ligand Binding Affinity Prediction Models to Docked and Predicted Structures

Joelle N Eaves iD, Daniel R Woldring iD

Journal of Chemical Information and Modeling · 13.07.2026 · 66 (13) · 7405-7413

DOI: 10.1021/acs.jcim.6c00592 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 23.06.2026. Verfasst von Joelle N Eaves und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering and Materials Science, Michigan State University, East Lansing, Michigan 48824, United States. Hauptthemen laut MEDLINE: Proteins, Molecular Docking Simulation. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, National Science Foundation Graduate Research Fellowship Program, National Institute of Food and Agriculture.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High Resolution Image Download MS PowerPoint Slide Structure-based deep learning models for protein–ligand binding affinity prediction (PLBAP) are commonly benchmarked using experimentally resolved co-crystal structures, but real use cases often rely on computed inputs (docked or predicted complexes). To quantify this benchmark-to-deployment mismatch, we compared the CASF-2016 performance of five reproducible PLBAP pipelines across crystal structures, GNINA docking into holo/apo/AlphaFold3-predicted receptors, and AlphaFold3 co-folding. Critically, access to an experimentally resolved apo receptor conformer provided only marginal benefit over AlphaFold3-predicted receptor structures. AlphaFold3 co-folding was competitive with, and for some models significantly better than, rigid-receptor docking into the apo conformer (Holm p ≤ 0.006). Multipose averaging showed source-dependent effects and did not recover near-crystal performance for any perturbed input. Interaction-level profiling revealed distinct shifts in protein–ligand interaction distributions that help explain the observed decrease in predictive performance. These findings provide practical guidance for two audiences: (1) model developers should consider reporting performance on benchmarks extending beyond crystal structures to more appropriately reflect deployment settings, and (2) end users should expect performance differences depending on structure generation method and pose selection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsMolecular Docking SimulationLigandsProtein BindingProtein Conformation

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Department of Chemical Engineering and Materials Science, Michigan State University, East Lansing, Michigan 48824, United States.
  • Institute for Quantitative Health Science and Engineering, Michigan State University, East Lansing, Michigan 48824, United States.

ORCID-Profile: Joelle N Eaves, Daniel R Woldring

Förderung

  • NIAID NIH HHS
  • National Science Foundation Graduate Research Fellowship Program
  • National Institute of Food and Agriculture
  • National Institute of Allergy and Infectious Diseases

Zitieren

APA

Eaves, J. N., & Woldring, D. R. (2026). Robustness of Protein–Ligand Binding Affinity Prediction Models to Docked and Predicted Structures. Journal of Chemical Information and Modeling, 66(13), 7405-7413. https://doi.org/10.1021/acs.jcim.6c00592

Vancouver

Eaves JN, Woldring DR. Robustness of Protein–Ligand Binding Affinity Prediction Models to Docked and Predicted Structures. Journal of Chemical Information and Modeling. 2026;66(13):7405-7413. doi:10.1021/acs.jcim.6c00592

BibTeX
@article{Eaves2026,
  author = {Eaves, Joelle N and Woldring, Daniel R},
  title = {Robustness of Protein–Ligand Binding Affinity Prediction Models to Docked and Predicted Structures},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {13},
  pages = {7405--7413},
  doi = {10.1021/acs.jcim.6c00592}
}
Kostenlos starten →