EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DockBind: A Quality-Controlled Data Set of Modeled Protein–Ligand Complexes Associated with Affinity Data

Alberto Rovetta, Alberto Memè, Hanne S Antila, Ruth Brenk iD

Journal of Chemical Information and Modeling · 09.11.2026 · 66 (21) · 13938-13955

DOI: 10.1021/acs.jcim.6c02093 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 26.10.2026. Verfasst von Alberto Rovetta und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedicine, University of Bergen, Jonas Lies vei 91, 5020Bergen, Norway. Hauptthemen laut MEDLINE: Proteins, Molecular Docking Simulation. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Norges Forskningsr?d.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ligand–protein interaction prediction is essential for structure-based drug discovery, but further development of machine-learning scoring functions is limited by a lack of high-quality training data sets. Here, we present DockBind, a curated data set of modeled protein–ligand complexes paired with experimental binding affinity data, generated through a quality-controlled docking workflow. This workflow was developed based on an expanded docking benchmark, where we systematically evaluated free and template-based docking methods as well as ligand similarity and maximum common substructure (MCS)-based pose filtering to generate and identify the most realistic poses. The resulting workflow was then incorporated into a pipeline integrating structural and binding affinity data from Binding MOAD, the Protein Data Bank, ChEMBL, and BindingDB, which resulted in 18,332 complexes across 612 protein targets, with high structural reliability and chemical diversity─the DockBind data set─providing a valuable resource for training and benchmarking machine-learning scoring functions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsMolecular Docking SimulationLigandsProtein BindingDatabases, ProteinQuality ControlProtein Conformation

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Department of Biomedicine, University of Bergen, Jonas Lies vei 91, 5020Bergen, Norway.
  • Computational Biology Unit, University of Bergen, Thormøhlensgate 55, 5008Bergen, Norway.
  • Fachbereich Physik, Freie Universität Berlin, Arnimallee 14, 14195Berlin, Germany.

ORCID-Profile: Ruth Brenk

Förderung

  • Norges Forskningsr?d

Zitieren

APA

Rovetta, A., Memè, A., Antila, H. S., & Brenk, R. (2026). DockBind: A Quality-Controlled Data Set of Modeled Protein–Ligand Complexes Associated with Affinity Data. Journal of Chemical Information and Modeling, 66(21), 13938-13955. https://doi.org/10.1021/acs.jcim.6c02093

Vancouver

Rovetta A, Memè A, Antila HS, Brenk R. DockBind: A Quality-Controlled Data Set of Modeled Protein–Ligand Complexes Associated with Affinity Data. Journal of Chemical Information and Modeling. 2026;66(21):13938-13955. doi:10.1021/acs.jcim.6c02093

BibTeX
@article{Rovetta2026,
  author = {Rovetta, Alberto and Memè, Alberto and Antila, Hanne S and Brenk, Ruth},
  title = {DockBind: A Quality-Controlled Data Set of Modeled Protein–Ligand Complexes Associated with Affinity Data},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {21},
  pages = {13938--13955},
  doi = {10.1021/acs.jcim.6c02093}
}
Kostenlos starten →