EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing the Predictive Power of Macrocyclic Drug Permeability by Knowledge Distillation from Analogous Pretraining Data

Yu Zhang iD, Olli T Pentikäinen iD

Journal of Medicinal Chemistry · 2025

DOI: 10.1021/acs.jmedchem.5c02620 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medicinal Chemistry, 2025. Verfasst von Yu Zhang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Biomedicine, Integrative Physiology and Pharmacy, University of Turku, FI-20014 Turku, Finland. Hauptthemen laut MEDLINE: Macrocyclic Compounds, Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Novo Nordisk Fonden, Suomen Kulttuurirahasto.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Macrocyclic drugs offer powerful opportunities for modulating protein-protein interactions, yet their development is limited by poor and unpredictable membrane permeability. Experimental testing is slow, and 3D modeling of macrocycles is computationally demanding due to their large conformational space. To address this, we present Multi_DDPP, a deep learning (DL) model that predicts macrocycle permeability directly from 2D structures. Multi_DDPP employs knowledge distillation to leverage permeability data from multiple cell lines, improving generalizability, and uses a task-specific swing-range strategy to reduce label noise. By integrating diverse molecular representations, including physicochemical descriptors, fingerprints, molecular graphs, and hybrid features, the model outperforms existing ML and DL approaches. Node masking highlights the substructures that contribute most to permeability, and regression extensions incorporating physiological parameters further refine these predictions. Early 2D-based permeability prediction with Multi_DDPP avoids the costly generation of 3D conformers and enables the efficient prioritization of macrocycles with favorable pharmacokinetic potential.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Macrocyclic CompoundsDeep LearningHumansCell Membrane PermeabilityPermeabilityModels, Molecular

Substanzen

Macrocyclic Compounds

Autor:innen und Institutionen

  • Institute of Biomedicine, Integrative Physiology and Pharmacy, University of Turku, FI-20014 Turku, Finland.
  • InFLAMES Research Flagship Center, University of Turku, FI-20014 Turku, Finland.

ORCID-Profile: Yu Zhang, Olli T Pentikäinen

Förderung

  • Novo Nordisk Fonden
  • Suomen Kulttuurirahasto

Zitieren

APA

Zhang, Y., & Pentikäinen, O. T. (2025). Enhancing the Predictive Power of Macrocyclic Drug Permeability by Knowledge Distillation from Analogous Pretraining Data. Journal of Medicinal Chemistry. https://doi.org/10.1021/acs.jmedchem.5c02620

Vancouver

Zhang Y, Pentikäinen OT. Enhancing the Predictive Power of Macrocyclic Drug Permeability by Knowledge Distillation from Analogous Pretraining Data. Journal of Medicinal Chemistry. 2025. doi:10.1021/acs.jmedchem.5c02620

BibTeX
@article{Zhang2025,
  author = {Zhang, Yu and Pentikäinen, Olli T},
  title = {Enhancing the Predictive Power of Macrocyclic Drug Permeability by Knowledge Distillation from Analogous Pretraining Data},
  journal = {Journal of Medicinal Chemistry},
  year = {2025},
  doi = {10.1021/acs.jmedchem.5c02620}
}
Kostenlos starten →