EUVIMEDEUVIMED entdecken
Crossref

Manifold Embedding of Quantum Information as Molecule Representation to Predict Blood-Brain Barrier Permeability by Deep Learning

Jiaqing Li, Koushiki Basu, Xiaoqing Chen, Tonglei Li iD

Molecular Pharmaceutics · 2025

DOI: 10.1021/acs.molpharmaceut.5c01196 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Pharmaceutics, 2025. Verfasst von Jiaqing Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Industrial and Molecular Pharmaceutics, Purdue University, West Lafayette, Indiana 47907-2091, United States. Hauptthemen laut MEDLINE: Blood-Brain Barrier, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: Purdue Institute for Drug Discovery, Allen Chao Endowment.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neurological disorders continue to be a leading global health challenge, with the blood-brain barrier (BBB) presenting considerable obstacles to effective drug delivery for central nervous system (CNS) therapies. Accurately predicting BBB permeability is essential for the early stages of CNS drug design. This study utilizes Manifold Embedding of Molecular Surface (MEMS) as a quantum-informed molecule representation to improve log BB prediction using deep learning models. Employing the B3DB data set, our approach achieved competitive performance, with an average RMSE of 0.49 ± 0.06, MAE of 0.38 ± 0.05, and R2 of 0.55. The ability of MEMS to authentically encode molecular interactions facilitates a more direct modeling of log BB compared to traditional descriptors. Still, as expected, model performance is influenced by the size and quality of the data, exhibiting notable variability across different B3DB groups and imbalances in the distribution of the log BB values. Additionally, although chirality significantly influences BBB permeability, the limited stereochemical data in the data set constrain its impact. Future efforts should focus on curating high-quality, stereochemically rich measurements and addressing data imbalances to train predictive models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Blood-Brain BarrierDeep LearningPermeabilityHumansDrug Delivery SystemsDrug Design

Stichwörter der Autor:innen

artificial intelligenceblood-brain barrierdeep learningmanifold embeddingpermeabilityquantum information

Autor:innen und Institutionen

  • Industrial and Molecular Pharmaceutics, Purdue University, West Lafayette, Indiana 47907-2091, United States.

ORCID-Profile: Tonglei Li

Förderung

  • Purdue Institute for Drug Discovery
  • Allen Chao Endowment

Zitieren

APA

Li, J., Basu, K., Chen, X., & Li, T. (2025). Manifold Embedding of Quantum Information as Molecule Representation to Predict Blood-Brain Barrier Permeability by Deep Learning. Molecular Pharmaceutics. https://doi.org/10.1021/acs.molpharmaceut.5c01196

Vancouver

Li J, Basu K, Chen X, Li T. Manifold Embedding of Quantum Information as Molecule Representation to Predict Blood-Brain Barrier Permeability by Deep Learning. Molecular Pharmaceutics. 2025. doi:10.1021/acs.molpharmaceut.5c01196

BibTeX
@article{Li2025,
  author = {Li, Jiaqing and Basu, Koushiki and Chen, Xiaoqing and Li, Tonglei},
  title = {Manifold Embedding of Quantum Information as Molecule Representation to Predict Blood-Brain Barrier Permeability by Deep Learning},
  journal = {Molecular Pharmaceutics},
  year = {2025},
  doi = {10.1021/acs.molpharmaceut.5c01196}
}
Kostenlos starten →