Prediction of Blood-Brain Barrier Penetration (BBBP) Based on Molecular Descriptors of the Free-Form and In-Blood-Form Datasets

Abstract

The blood–brain barrier (BBB) controls the entry of chemicals from the blood to the brain. Since brain drugs need to penetrate the BBB, rapid and reliable prediction of BBB penetration (BBBP) is helpful for drug development. In this study, free-form and in-blood-form datasets were prepared by modifying the original BBBP dataset, and the effects of the data modification were investigated. For each dataset, molecular descriptors were generated and used for BBBP prediction by machine learning (ML). For ML, the dataset was split into training, validation, and test data by the scaffold split algorithm MoleculeNet used. This creates an unbalanced split and makes the prediction difficult; however, we decided to use that algorithm to evaluate the predictive performance for unknown compounds dissimilar to existing ones. The highest prediction score was obtained by the random forest model using 212 descriptors from the free-form dataset, and this score was higher than the existing best score using the same split algorithm without using any external database. Furthermore, using a deep neural network, a comparable result was obtained with only 11 descriptors from the free-form dataset, and the resulting descriptors suggested the importance of recognizing the glucose-like characteristics in BBBP prediction.

The in silico identification of novel broad-spectrum antidotes for poisoning by organophosphate anticholinesterases

“…The evaluation metrics for the BBB permeability model compared well with those of other published models [ 35 , 40 – 42 ]. The optimal RS included descriptors, TPSA, molecular weight, number of hydrogen bond donors, and logP, that are consistent with those found in other modeling studies[ 37 , 43 ], as well as with known characteristics of BBB penetrating chemicals [ 44 ].…”

“…Unlike for AChE reactivation, there are numerous ML-based models to predict the BBB permeability of chemicals[ 12 – 14 , 16 , 17 , 35 – 37 ]. Though these models generally show good predictive capabilities, we chose to independently develop a model for this study because it was important to keep the same set of starting features for both the AChE reactivation and BBB permeability models so that common influential descriptors could be identified and examined.…”

Breaking the Barriers: Machine-Learning-Based c-RASAR Approach for Accurate Blood–Brain Barrier Permeability Prediction

“…In this section, we conducted a comparative analysis between our optimal model and those of previous studies, employing various machine learning and deep learning models to predict BBB permeability. To facilitate this comparison, we specifically chose 13 prominent studies published between 2012 and 2023. − Table presents comprehensive details of diverse external validation metrics derived from our study and those acquired from preceding models.…”

“…They attained a maximum AUC of 0.85 and an accuracy of 0.784. Sakiyama et al 30 reported a random forest model employing RDKit MDs for 1957 compounds, achieving an AUC score of 0.77. Yu et al 31 utilized molecular and fingerprint descriptors for 940 molecules to develop an SVM model, reaching a maximum predictive accuracy of 0.96 and an AUC score of 0.98.…”

Experimental and Computational Methods to Assess Central Nervous System Penetration of Small Molecules

“…A deep learning (DL) method achieved better accuracy than the ML methods on three different datasets [ 41 ]. Recently, various DL methods such as artificial neural networks (ANN), deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), and graph convolutional neural networks (GCNN) have been used to predict BBB permeability with high accuracy [ 42 , 43 , 44 , 45 , 46 , 47 , 48 ]. Alsenan et al [ 49 ] published a highly accurate deep learning model based on a recurrent neural network.…”