Blood–Brain Barrier Permeability Prediction by Integrating Deep Learning Representations with Chemical Compound Knowledge
- 1Rensselaer Polytechnic Institute , , , ,
- 2The University of Chicago , , , ,
Abstract
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.
Related
- Integrating classical similarity and multitask neural representations
- Gas-Conditioned Message Passing Graph Neural Network for Permeability Prediction in Polymeric Membranes
- Predicting Blood–Brain Barrier Permeability from Experimental Data: An Interpretable and Externally Validated Machine Learning Framework
- Integrating dft-based spectroscopic analysis, molecular docking, admet prediction, and natural biosorbent adsorption studies of flupyradifurone
- Hybrid-CatBoost: an empirical comparison of molecular representations for aqueous-solubility prediction on the TDC benchmark
BibTeX
@article{grant2026bloodbrain,
title = {{Blood–Brain Barrier Permeability Prediction by Integrating Deep Learning Representations with Chemical Compound Knowledge}},
author = {Nadine Grant and Diego Machado Reyes and Zefan Yang and Alec Wang and Leo Q. Wan and Chunyu Wang and Pingkun Yan},
journal = {ACS Omega},
year = {2026},
month = oct,
doi = {10.1021/acsomega.6c01181},
url = {https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c01181/5456826/Blood-Brain-Barrier-Permeability-Prediction-by},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Blood–Brain Barrier Permeability Prediction by Integrating Deep Learning Representations with Chemical Compound Knowledge
AU - Nadine Grant
AU - Diego Machado Reyes
AU - Zefan Yang
AU - Alec Wang
AU - Leo Q. Wan
AU - Chunyu Wang
AU - Pingkun Yan
PY - 2026
DA - 2026/10/23
JO - ACS Omega
DO - 10.1021/acsomega.6c01181
UR - https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c01181/5456826/Blood-Brain-Barrier-Permeability-Prediction-by
AB - 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.
SN - 2470-1343
ER -