Blood–Brain Barrier Permeability Prediction by Integrating Deep Learning Representations with Chemical Compound Knowledge
ACS Omega · 03.11.2026 · 11 (43) · 66109-66119
DOI: 10.1021/acsomega.6c01181 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACS Omega, online erschienen am 22.10.2026. Verfasst von Nadine Grant und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, New York 12180, United States. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIA NIH HHS, U.S. Department of Health and Human Services.
Abstract (Originalsprache)
Predicting blood–brain barrier (BBB) permeability is essential for central nervous system drug discovery, but traditional descriptor-based methods of predicting BBB permeability lack structural context, and deep learning-based methods struggle with overfitting. We introduce a multimodel framework that integrates both transformer-derived molecular embeddings with physicochemical descriptors using a late-stage ensemble fusion strategy. Trained on both the B3DB and NeuTox data sets and evaluated on the benchmark BBBP, our model showed strong predictive performance, with data set-dependent performance. Feature fusion improved performance relative to embedding-only models in several settings, whereas descriptor-based models achieved comparable or higher performance in some settings. These results suggest that combining learned structural embeddings with chemical descriptors provides complementary predictive information, while the benefit of their integration may depend on the data distribution or classifier used.
Autor:innen und Institutionen
- Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, New York 12180, United States.
- Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, New York 12180, United States.
- Department of Computer Science, The University of Chicago, Chicago, Illinois 60637, United States.
- Department of Biological Sciences, Rensselaer Polytechnic Institute, Troy, New York 12180, United States.
ORCID-Profile: Diego Machado Reyes, Pingkun Yan
Förderung
- NIA NIH HHS
- U.S. Department of Health and Human Services
Zitieren
APA
Grant, N., Machado Reyes, D., Yang, Z., Wang, A., Wan, L. Q., Wang, C., & Yan, P. (2026). Blood–Brain Barrier Permeability Prediction by Integrating Deep Learning Representations with Chemical Compound Knowledge. ACS Omega, 11(43), 66109-66119. https://doi.org/10.1021/acsomega.6c01181
Vancouver
Grant N, Machado Reyes D, Yang Z, Wang A, Wan LQ, Wang C, et al. Blood–Brain Barrier Permeability Prediction by Integrating Deep Learning Representations with Chemical Compound Knowledge. ACS Omega. 2026;11(43):66109-66119. doi:10.1021/acsomega.6c01181
BibTeX
@article{Grant2026,
author = {Grant, Nadine and Machado Reyes, Diego and Yang, Zefan and Wang, Alec and Wan, Leo Q and Wang, Chunyu and Yan, Pingkun},
title = {Blood–Brain Barrier Permeability Prediction by Integrating Deep Learning Representations with Chemical Compound Knowledge},
journal = {ACS Omega},
year = {2026},
volume = {11},
number = {43},
pages = {66109--66119},
doi = {10.1021/acsomega.6c01181}
}
EUVIMED