iBBBP-EDL: An efficient ensemble deep Learning framework for blood-brain barrier permeability prediction
T. Vinh, Q. H. Trinh, L. Nguyen, P-U. Nguyen-Hoang, T-H Nguyen-Vo, and B. P. Nguyen∗
Motivation
As a highly protective biological structure, the blood-brain barrier prevents the uncontrolled passage of molecules to keep the central nervous system free from chemical toxification and maintain brain homeostasis. Since most substances are not allowed to freely penetrate the blood-brain barrier, examination of the bloodbrain barrier permeability (BBBP) of drug candidates is highly essential in drug discovery. To screen the BBBP of molecules, several computational methods were developed with satisfactory outcomes. These methods, however, have shortcomings that need to be addressed to improve prediction efficiency. In our study, we propose iBBBP-EDL, an ensemble deep learning model that combines two types of neural networks: a convolutional neural network and multilayer perceptrons, and three types of molecular representation schemes: the Extended-Connectivity Fingerprint, RDKit molecular descriptors, and Mol2vec-embedded features.
Results
Experimental results confirmed the robustness and stability of our proposed model. Also, the benchmarking analysis indicated that iBBBP-EDL outperformed all machine learning and deep learning baseline models with a lower computational cost.
Availability and implementation
Source code and data are available upon request.