Finding Needles in a Haystack: Determining Key Molecular Descriptors Associated with the Blood‐brain Barrier Entry of Chemical Compounds Using Machine Learning

Abstract

In this paper we used two sets of calculated molecular descriptors to predict blood-brain barrier (BBB) entry of a collection of 415 chemicals. The set of 579 descriptors were calculated by Schrodinger and TopoCluj software. Polly and Triplet software were used to calculate the second set of 198 descriptors. Following this, modelling and a two-deep, repeated external validation method was used for QSAR formulation. Results show that both sets of descriptors individually and their combination give models of reasonable prediction accuracy. We also uncover the effectiveness of a variable selection approach, by showing that for one of our descriptor sets, the top 5 % predictors in terms of random forest variable importance are able to provide a better performing model than the model with all predictors. The top influential descriptors indicate important aspects of molecular structural features that govern BBB entry of chemicals.Keywords: blood-brain barrier · molecular descriptors · variable selection · machine learning · random forest · two-deep cross validation · quantitative structure-activity relationship (QSAR)[a] S. Majumdar

Towards Deep Neural Network Models for the Prediction of the Blood–Brain Barrier Permeability for Diverse Organic Compounds

“…External estimates of probability that a compound will undergo active efflux mediated by P-glycoprotein (P-gp) can also be included [21,24,37]. In other approaches, large pools of various 1D, 2D (including molecular fingerprints), and 3D molecular descriptors calculated by different methods [26,[38][39][40][41][42][43][44][45][46][47][48][49][50][51][52] are analyzed by various statistical learning techniques, e.g., multiple linear regression, linear discriminant analysis, partial least squares regression, support vector machines, artificial neural networks, random forests, etc., often in combination with some descriptor selection protocols [23,24,26,[43][44][45][46][47][48][49][50][51][52]. However, the limited size of the training sets, use of unverified data, and too-small modeling errors for such an inherently noisy endpoint often give rise to the concerns of possible model overfitting [16].…”

Anticancer Activity of Natural and Synthetic Chalcones

“…Condensation is performed at 50°C, reaction time being 12–15 h or one week at room temperature [ 155 ]. Disadvantages of this method are inability to recover catalyst, formation of secondary compounds, lack of selectivity, long reaction time, extreme reaction conditions, and difficulty of isolating products [ 156 ]. New types of heterogeneous catalysts (Lewis acids, Bronsted acids, solid acids, and solid bases) have been identified for synthesis of chalcones with high selectivity.…”

Artificial intelligence and machine learning‐aided drug discovery in central nervous system diseases: State‐of‐the‐arts and future directions

“…In recent years, AI‐based predictive models have been proposed to minimize the number of laborious, expensive, time‐consuming BBB permeability experiments that need be carried out in CNS drug discovery. For the construction of BBB permeability predictive models, researchers have employed various supervised learning approaches, such as SVM, 222,329–333 recursive partitioning (RP), 334,335 Gaussian process, 336 DT, 337 KNN, 338 linear discriminant analysis, 339 consensus classifier, 340 and ANN 341–343 . All of these methods were developed to process physical and chemical features, which mainly include molecular weight, hydrophilicity (ClogP), lipophilicity (ClogD), topological polar surface area, acidic and basic atoms numbers, hydrogen bond donors and acceptors, water‐accessible volume, flexibility (rotatable bonds), van der Waals volume, and ionization potential.…”