A Computational Physics-based Approach to Predict Unbound Brain-to-Plasma Partition Coefficient, Kp,uu

CNSMolGen: A Bidirectional Recurrent Neural Network-Based Generative Model for De Novo Central Nervous System Drug Design

Central nervous system (CNS) drugs have had a significant impact on treating a wide range of neurodegenerative and psychiatric disorders. In recent years, deep learning-based generative models have shown great potential for accelerating drug discovery and improving efficacy. However, specific applications of these techniques in CNS drug discovery have not been widely reported. In this study, we developed the CNSMolGen model, which uses a framework of bidirectional recurrent neural networks (Bi-RNNs) for de novo molecular design of CNS drugs. Results showed that the pretrained model was able to generate more than 90% of completely new molecular structures, which possessed the properties of CNS drug molecules and were synthesizable. In addition, transfer learning was performed on small data sets with specific biological activities to evaluate the potential application of the model for CNS drug optimization. Here, we used drugs against the classical CNS disease target serotonin transporter (SERT) as a fine-tuned data set and generated a focused database against the target protein. The potential biological activities of the generated molecules were verified by using the physics-based induced-fit docking study. The success of this model demonstrates its potential in CNS drug design and optimization, which provides a new impetus for future CNS drug development.

Accurate prediction of Kp,uu,brain based on experimental measurement of Kp,brain and computed physicochemical properties of candidate compounds in CNS drug discovery

A mathematical equation model was developed by building the relationship between the fu,b/fu,p ratio and the computed physicochemical properties of candidate compounds, thereby predicting Kp,uu,brain based on a single experimentally measured Kp,brain value. A total of 256 compounds and 36 marketed published drugs including acidic, basic, neutral, zwitterionic, CNS-penetrant, and non-CNS penetrant compounds with diverse structures and physicochemical properties were involved in this study. A strong correlation was demonstrated between the fu,b/fu,p ratio and physicochemical parameters (CLogP and ionized fraction). The model showed good performance in both internal and external validations. The percentages of compounds with Kp,uu,brain predictions within 2-fold variability were 80.0 %-83.3 %, and more than 90 % were within a 3-fold variability. Meanwhile, "black box" QSAR models constructed by machine learning approaches for predicting fu,b/fu,p ratio based on the chemical descriptors are also presented, and the ANN model displayed the highest accuracy with an RMSE value of 0.27 and 86.7 % of the test set drugs fell within a 2-fold window of linear regression. These models demonstrated strong predictive power and could be helpful tools for evaluating the Kp,uu,brain by a single measurement parameter of Kp,brain during lead optimization for CNS penetration evaluation and ranking CNS drug candidate molecules in the early stages of CNS drug discovery.

The Trends and Future Prospective of In Silico Models from the Viewpoint of ADME Evaluation in Drug Discovery

Drug discovery and development are aimed at identifying new chemical molecular entities (NCEs) with desirable pharmacokinetic profiles for high therapeutic efficacy. The plasma concentrations of NCEs are a biomarker of their efficacy and are governed by pharmacokinetic processes such as absorption, distribution, metabolism, and excretion (ADME). Poor ADME properties of NCEs are a major cause of attrition in drug development. ADME screening is used to identify and optimize lead compounds in the drug discovery process. Computational models predicting ADME properties have been developed with evolving model-building technologies from a simplified relationship between ADME endpoints and physicochemical properties to machine learning, including support vector machines, random forests, and convolution neural networks. Recently, in the field of in silico ADME research, there has been a shift toward evaluating the in vivo parameters or plasma concentrations of NCEs instead of using predictive results to guide chemical structure design. Another research hotspot is the establishment of a computational prediction platform to strengthen academic drug discovery. Bioinformatics projects have produced a series of in silico ADME models using free software and open-access databases. In this review, we introduce prediction models for various ADME parameters and discuss the currently available academic drug discovery platforms.