Improved Prediction of Blood-Brain Barrier Permeability Through Machine Learning with Combined Use of Molecular Property-Based Descriptors and Fingerprints

AI-driven innovations in smart multifunctional nanocarriers for drug and gene delivery: A mini-review

The convergence of artificial intelligence (AI) and nanomedicine has revolutionized the design of smart multifunctional nanocarriers (SMNs) for drug and gene delivery, offering unprecedented precision, efficiency, and personalization in therapeutic applications. AI-driven approaches enhance the development of these nanocarriers by accelerating their design, optimizing drug loading and release kinetics, improving biocompatibility, and predicting interactions with biological barriers. This review explores the transformative role of AI in the fabrication and functionalization of SMNs, emphasizing its impact on overcoming challenges in targeted drug delivery, controlled release, and theranostics. We discuss the integration of AI with advanced nanomaterials-such as polymeric, lipidic, and inorganic nanoparticles-highlighting their potential in oncology and hematology. Furthermore, we examine recent clinical and preclinical case studies demonstrating AI-assisted nanocarrier development for personalized medicine. The synergy between AI and nanotechnology paves the way for next-generation precision therapeutics, addressing critical limitations in traditional drug delivery systems. However, data standardization, regulatory compliance, and translational scalability challenges remain. This review underscores the need for interdisciplinary collaboration to unlock AI's potential in nanomedicine fully, ultimately advancing the clinical application of SMNs for more effective and safer patient care.

GCN-BBB: Deep Learning Blood-Brain Barrier (BBB) Permeability PharmacoAnalytics with Graph Convolutional Neural (GCN) Network

The Blood-Brain Barrier (BBB) is a selective barrier between the Central Nervous System (CNS) and the peripheral system, regulating the distribution of molecules. BBB permeability has been crucial in CNS-targeting drug development, such as glioblastoma-related drug discovery. In addition, more CNS diseases still present significant challenges, for instance, neurological disorders like Alzheimer's Disease (AD) and drug abuse. Conversely, cannabinoid drugs that do not cross the BBB are needed to avoid off-target CNS psychotropic effects. In vitro and in vivo experiments measuring BBB permeability are costly and low throughput. Computational pharmacoanalytics modeling, particularly using deep-learning Graph Neural Networks (GNNs), offers a promising alternative. GNNs excel at capturing intricate relationships in graph-based information, such as small molecular structures. In this study, we developed GNNs model for BBB permeability using the graph representation of drugs. The GNNs were compared with other algorithms using molecular fingerprints or physical-chemical descriptors. With a dataset of 1924 molecules, the best GNNs model, a convolutional graph neural network using a normalized Laplacian matrix (GCN_2), achieved a precision of 0.94, recall of 0.96, F1 score of 0.95, and MCC score of 0.77. This outperformed other machine learning algorithms with molecular fingerprints. The findings indicate that the graphic representation of small molecules combined with GNNs architecture is powerful in predicting BBB permeability with high accuracy and recall. The developed GNNs model can be utilized in the initial screening stage for new drug development.

Masked graph transformer for blood-brain barrier permeability prediction

The blood-brain barrier (BBB) is a highly protective structure that strictly regulates the passage of molecules, ensuring the central nervous system remains free from harmful chemicals and maintains brain homeostasis. Since most compounds cannot easily cross the BBB, assessing the blood-brain barrier permeability (BBBP) of drug candidates is critical in drug discovery. While several computational methods have been developed to screen BBBP with promising results, these approaches have limitations that affect their predictive power. In this study, we constructed classification models for screening the BBBP of molecules. Our models were trained with chemical data featurized by a Masked Graph Transformer-based Pretrained (MGTP) encoder. The molecular encoder was designed to generate molecular features for various downstream tasks. The training of the MGTP encoder was guided by masked attention-based learning, improving the model's generalization in encoding molecular structures. The results showed that classification models developed using MGTP features had outperformed those using other representations in 6 out of 8 cases, demonstrating the effectiveness of the proposed encoder. Also, chemical diversity analysis confirmed the encoder's ability to effectively distinguish between different classes of molecules.

Machine Learning in Drug Development for Neurological Diseases: A Review of Blood Brain Barrier Permeability Prediction Models

The blood brain barrier (BBB) is an endothelial-derived structure which restricts the movement of certain molecules between the general somatic circulatory system to the central nervous system (CNS). While the BBB maintains homeostasis by regulating the molecular environment induced by cerebrovascular perfusion, it also presents significant challenges in developing therapeutics intended to act on CNS targets. Many drug development practices rely partly on extensive cell and animal models to predict, to an extent, whether prospective therapeutic molecules can cross the BBB. In interest to reduce costs and improve prediction accuracy, many propose using advanced computational modeling of BBB permeability profiles leveraging empirical data. Given the scale of growth in machine learning and deep learning, we review the most recent machine learning approaches in predicting BBB permeability.

Decoding Drug Discovery: Exploring A-to-Z In Silico Methods for Beginners

The drug development process is a critical challenge in the pharmaceutical industry due to its time-consuming nature and the need to discover new drug potentials to address various ailments. The initial step in drug development, drug target identification, often consumes considerable time. While valid, traditional methods such as in vivo and in vitro approaches are limited in their ability to analyze vast amounts of data efficiently, leading to wasteful outcomes. To expedite and streamline drug development, an increasing reliance on computer-aided drug design (CADD) approaches has merged. These sophisticated in silico methods offer a promising avenue for efficiently identifying viable drug candidates, thus providing pharmaceutical firms with significant opportunities to uncover new prospective drug targets. The main goal of this work is to review in silico methods used in the drug development process with a focus on identifying therapeutic targets linked to specific diseases at the genetic or protein level. This article thoroughly discusses A-to-Z in silico techniques, which are essential for identifying the targets of bioactive compounds and their potential therapeutic effects. This review intends to improve drug discovery processes by illuminating the state of these cutting-edge approaches, thereby maximizing the effectiveness and duration of clinical trials for novel drug target investigation.

Computational Modeling of Pharmaceuticals with an Emphasis on Crossing the Blood-Brain Barrier

The discovery and development of new pharmaceutical drugs is a costly, time-consuming, and highly manual process, with significant challenges in ensuring drug bioavailability at target sites. Computational techniques are highly employed in drug design, particularly to predict the pharmacokinetic properties of molecules. One major kinetic challenge in central nervous system drug development is the permeation through the blood-brain barrier (BBB). Several different computational techniques are used to evaluate both BBB permeability and target delivery. Methods such as quantitative structure-activity relationships, machine learning models, molecular dynamics simulations, end-point free energy calculations, or transporter models have pros and cons for drug development, all contributing to a better understanding of a specific characteristic. Additionally, the design (assisted or not by computers) of prodrug and nanoparticle-based drug delivery systems can enhance BBB permeability by leveraging enzymatic activation and transporter-mediated uptake. Neuroactive peptide computational development is also a relevant field in drug design, since biopharmaceuticals are on the edge of drug discovery. By integrating these computational and formulation-based strategies, researchers can enhance the rational design of BBB-permeable drugs while minimizing off-target effects. This review is valuable for understanding BBB selectivity principles and the latest in silico and nanotechnological approaches for improving CNS drug delivery.

Synthesis, Characterization, and antiviral evaluation of New Chalcone-Based Imidazo[1,2-a]pyridine Derivatives: Insights from in vitro and in silico Anti-HIV studies

Given the ease of synthetic accessibility and the promising biological profile demonstrated by both imidazo[1,2-a]pyridine and Chalcone derivatives, a series of Chalcone-based imidazo[1,2-a]pyridine derivatives were synthesized and characterized using 1H NMR, 13C NMR, Mass Spectrometry and FTIR techniques. Density functional theory (DFT) was employed to investigate the structural and electronic properties, providing insights into potential reactive sites. The synthesized compounds were evaluated in vitro for their antiviral properties against human immunodeficiency virus type-1 (HIV-1) and human immunodeficiency virus type-2 (HIV-2) in MT-4 cells. Furthermore, Molecular docking studies show strong binding affinities with HIV-1 reverse transcriptase and HIV-2 protease. To further understand the dynamic behavior and stability of these interactions, molecular dynamics (MD) simulations were conducted. The MD results indicated stable binding conformations of the ligands within the active sites, with low RMSD and RMSF values throughout the simulation, confirming the robustness of these interactions. ADME predictions suggested acceptable pharmacokinetic profiles, though solubility remains a limitation for these compounds. Although the in vitro antiviral activity was limited, the combination of in vitro and in silico approaches provided valuable insights, guiding further structural optimization to improve bioavailability and enhance the therapeutic potential of these derivatives.

MolGraph: a Python package for the implementation of molecular graphs and graph neural networks with TensorFlow and Keras

Molecular machine learning (ML) has proven important for tackling various molecular problems, such as predicting molecular properties based on molecular descriptors or fingerprints. Since relatively recently, graph neural network (GNN) algorithms have been implemented for molecular ML, showing comparable or superior performance to descriptor or fingerprint-based approaches. Although various tools and packages exist to apply GNNs in molecular ML, a new GNN package, named MolGraph, was developed in this work with the motivation to create GNN model pipelines highly compatible with the TensorFlow and Keras application programming interface (API). MolGraph also implements a module to accommodate the generation of small molecular graphs, which can be passed to a GNN algorithm to solve a molecular ML problem. To validate the GNNs, benchmarking was conducted using the datasets from MoleculeNet, as well as three chromatographic retention time datasets. The benchmarking results demonstrate that the GNNs performed in line with expectations. Additionally, the GNNs proved useful for molecular identification and improved interpretability of chromatographic retention time data. MolGraph is available at https://github.com/akensert/molgraph . Installation, tutorials and implementation details can be found at  https://molgraph.readthedocs.io/en/latest/ .

Uncovering blood-brain barrier permeability: a comparative study of machine learning models using molecular fingerprints, and SHAP explainability

This study illustrates the use of chemical fingerprints with machine learning for blood-brain barrier (BBB) permeability prediction. Employing the Blood Brain Barrier Database (B3DB) dataset for BBB permeability prediction, we extracted nine different fingerprints. Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) algorithms were used to develop models for permeability prediction. Random Forest recursive Feature Selection (RF-RFS) method was used for extracting informative attributes. An additional database was employed for the validation phase. The results indicate that all nine datasets achieved good performance in training, test and validation stages. We further took MACC Keys fingerprints, one of the best performing models for explainability analysis. For this purpose, we used SHapley Additive exPlanations (SHAP) analysis on this dataset for the identification of key structural features influencing BBB permeability prediction. These features include aliphatic carbons, methyl groups and oxygen-containing groups. This study highlights the effectiveness of different fingerprint descriptors in predicting BBB permeability. SHAP analysis provides value additions to the simulations. These simulations will be of significant help in drug discovery processes, particularly in developing Central Nervous System (CNS) therapeutics.

Synthesis, crystal structure, and antiviral evaluation of new imidazopyridine-schiff base derivatives: in vitro and in silico anti-HIV studies

A series of Imidazo[1,2-a]pyridine-Schiff base derivatives were synthesized and characterized using 1H NMR, 13C NMR, Mass Spectrometry and FTIR techniques, and the structure of 4a was further confirmed through single-crystal X-ray diffraction analysis. Density Functional Theory (DFT) has been used to investigate the structural and electronic properties. The synthesized compounds were evaluated in vitro for their antiviral activity against human immunodeficiency virus type-1 (HIV-1) and human immunodeficiency virus type-2 (HIV-2) in MT-4 cells. Compound 4a displayed EC50 values of 82,02 and 47,72 μg ml-1 against HIV-1 and HIV-2, respectively. Molecular docking studies were conducted to gain insights into the interaction mechanism of the synthesized compounds with HIV-1 reverse transcriptase. ADME analysis suggested acceptable pharmacokinetic profiles, though solubility remains a limitation for these compounds, highlighting the need for further structural modifications to enhance bioavailability and therapeutic potential.

Unlocking Benzosampangine's Potential: A Computational Approach to Investigating, Its Role as a PD-L1 Inhibitor in Tumor Immune Evasion via Molecular Docking, Dynamic Simulation, and ADMET Profiling

The interaction between programmed cell death protein 1 (PD-1) and its ligand PD-L1 plays a crucial role in tumor immune evasion, presenting a critical target for cancer immunotherapy. Despite being effective, current monoclonal antibodies present some drawbacks such as high costs, toxicity, and resistance development. Therefore, the development of small-molecule inhibitors is necessary, especially those derived from natural sources. In this study, benzosampangine is predicted as a promising PD-L1 inhibitor, with potential applications in cancer immunotherapy. Utilizing the high-resolution crystal structure of human PD-L1 (PDB ID: 5O45), we screened 511 natural compounds, identifying benzosampangine as a top candidate with exceptional inhibitory properties. Molecular docking predicted that benzosampangine exhibits a strong binding affinity for PD-L1 (-9.4 kcal/mol) compared with established controls such as CA-170 (-6.5 kcal/mol), BMS-202 (-8.6 kcal/mol), and pyrvinium (-8.9 kcal/mol). The compound's predicted binding efficacy is highlighted by robust interactions with key amino acids (ILE54, TYR56, GLN66, MET115, ILE116, SER117, ALA121, ASP122) within the active site, notably forming 3 Pi-sulfur interactions with MET115-an interaction absents in control inhibitors. In addition, ADMET profiling suggests that over the control molecules, benzosampangine has several key advantages, including favorable solubility, permeability, metabolic stability, and low toxicity, while adhering to Lipinski's rule of five. Molecular dynamic simulations predict the stability of the benzosampangine-PD-L1 complex, reinforcing its potential to sustain inhibition of the PD-1/PD-L1 pathway. MMGBSA analysis calculated a binding free energy (ΔGbind) of -39.39 kcal/mol for the benzosampangine-PD-L1 complex, with significant contributions from Coulombic, lipophilic, and Van der Waals interactions, validating the predicted docking results. This study investigates in silico benzosampangine, predicting its better molecular interactions and pharmacokinetic profile compared with several already known PD-L1 inhibitors.

Combined machine learning models, docking analysis, ADMET studies and molecular dynamics simulations for the design of novel FAK inhibitors against glioblastoma

Gliomas, particularly glioblastoma (GBM), are highly aggressive brain tumors with poor prognosis and high recurrence rates. This underscores the urgent need for novel therapeutic approaches. One promising target is Focal adhesion kinase (FAK), a key regulator of tumor progression currently in clinical trials for glioma treatment. Drug development, however, is both challenging and costly, necessitating efficient strategies. Computer-Aided Drug Design (CADD), especially when combined with machine learning (ML), streamlines the processes of virtual screening and optimization, significantly enhancing the efficiency and accuracy of drug discovery. Our study integrates ML, docking analysis, ADMET (absorption, distribution, metabolism, elimination, and toxicity) studies to identify novel FAK inhibitors specific to GBM. Predictive models showed strong performance, with an R2 of 0.892, MAE of 0.331, and RMSE of 0.467 using protein-level IC50 data in combined CDK, CDK extended fingerprints, and substructure fingerprint counts derived from 1280 FAK inhibitors. Another model, based on IC50 data from 2608 compounds tested on U87-MG cells, achieved an R2 of 0.789, MAE of 0.395, and RMSE of 0.536. Using these models, we efficiently identified 275 potentially active compounds out of 5107 candidates. Subsequent ADMET analysis narrowed this down to 16 potential FAK inhibitors that meet the established drug-likeness criteria. Moreover, molecular dynamics (MD) simulations validated the stable binding interactions between the selected compounds and the FAK protein. This study highlights the effectiveness of combining ML, docking analysis, and ADMET studies to rapidly identify potential FAK inhibitors from large databases, providing valuable insights for the systematic design of FAK inhibitors.

Improving glioma drug delivery: A multifaceted approach for glioma drug development

Glioma is one of the most common central nervous system (CNS) cancers that can be found within the brain and the spinal cord. One of the pressing issues plaguing the development of therapeutics for glioma originates from the selective and semipermeable CNS membranes: the blood-brain barrier (BBB) and blood-spinal cord barrier (BSCB). It is difficult to bypass these membranes and target the desired cancerous tissue because the purpose of the BBB and BSCB is to filter toxins and foreign material from invading CNS spaces. There are currently four varieties of Food and Drug Administration (FDA)-approved drug treatment for glioma; yet these therapies have limitations including, but not limited to, relatively low transmission through the BBB/BSCB, despite pharmacokinetic characteristics that allow them to cross the barriers. Steps must be taken to improve the development of novel and repurposed glioma treatments through the consideration of pharmacological profiles and innovative drug delivery techniques. This review addresses current FDA-approved glioma treatments' gaps, shortcomings, and challenges. We then outline how incorporating computational BBB/BSCB models and innovative drug delivery mechanisms will help motivate clinical advancements in glioma drug delivery. Ultimately, considering these attributes will improve the process of novel and repurposed drug development in glioma and the efficacy of glioma treatment.

Construction of IRAK4 inhibitor activity prediction model based on machine learning

Interleukin-1 receptor-associated kinase 4 (IRAK4) is a crucial serine/threonine protein kinase that belongs to the IRAK family and plays a pivotal role in Toll-like receptor (TLR) and Interleukin-1 receptor (IL-1R) signaling pathways. Due to IRAK4's significant role in immunity, inflammation, and malignancies, it has become an intriguing target for discovering and developing potent small-molecule inhibitors. Consequently, there is a pressing need for rapid and accurate prediction of IRAK4 inhibitor activity. Leveraging a comprehensive dataset encompassing activity data for 1628 IRAK4 inhibitors, we constructed a prediction model using the LightGBM algorithm and molecular fingerprints. This model achieved an R2 of 0.829, an MAE of 0.317, and an RMSE of 0.460 in independent testing. To further validate the model's generalization ability, we tested it on 90 IRAK4 inhibitors collected in 2023. Subsequently, we applied the model to predict the activity of 13,268 compounds with docking scores less than - 9.503 kcal/mol. These compounds were initially screened from a pool of 1.6 million molecules in the chemdiv database through high-throughput molecular docking. Among these, 259 compounds with predicted pIC50 values greater than or equal to 8.00 were identified. We then performed ADMET predictions on these selected compounds. Finally, through a rigorous screening process, we identified 34 compounds that adhere to the four complementary drug-likeness rules, making them promising candidates for further investigation. Additionally, molecular dynamics simulations confirmed the stable binding of the screened compounds to the IRAK4 protein. Overall, this work presents a machine learning model for accurate prediction of IRAK4 inhibitor activity and offers new insights for subsequent structure-guided design of novel IRAK4 inhibitors.

Non-animal models for blood-brain barrier permeability evaluation of drug-like compounds

Diseases related to the central nervous system (CNS) are major health concerns and have serious social and economic impacts. Developing new drugs for CNS-related disorders presents a major challenge as it actively involves delivering drugs into the CNS. Therefore, it is imperative to develop in silico methodologies to reliably identify potential lead compounds that can penetrate the blood-brain barrier (BBB) and help to thoroughly understand the role of different physicochemical properties fundamental to the BBB permeation of molecules. In this study, we have analysed the chemical space of the CNS drugs and compared it to the non-CNS-approved drugs. Additionally, we have collected a feature selection dataset from Muehlbacher et al. (J Comput Aided Mol Des 25(12):1095-1106, 2011. 10.1007/s10822-011-9478-1) and an in-house dataset. This information was utilised to design a molecular fingerprint that was used to train machine learning (ML) models. The best-performing models reported in this study achieved accuracies of 0.997 and 0.98, sensitivities of 1.0 and 0.992, specificities of 0.971 and 0.962, MCCs of 0.984 and 0.958, and ROC-AUCs of 0.997 and 0.999 on an imbalanced and a balanced dataset, respectively. They demonstrated overall good accuracies and sensitivities in the blind validation dataset. The reported models can be applied for fast and early screening drug-like molecules with BBB potential. Furthermore, the bbbPythoN package can be used by the research community to both produce the BBB-specific molecular fingerprints and employ the models mentioned earlier for BBB-permeability prediction.

ANN multi-layer perceptron for prediction of blood-brain barrier permeable compounds for central nervous system therapeutics

Endothelial cells produce a semipermeable barrier known as the blood-brain barrier (BBB) to keep undesired chemicals out of the central nervous system (CNS). However, this barrier also restricts the exploration of potential new medications due to insufficient exposure. To address this challenge, machine learning (ML) algorithms can be useful to predict the BBB permeability of chemical compounds. Support vector machines, continuous neural networks, and deep learning approaches have been used to identify compounds that can penetrate the BBB. However, predicting BBB permeability based solely on chemical structure can be difficult. In the current research, we developed an ML model using a large dataset to predict BBB permeability, which could be used for early-stage drug screening of potential CNS medications. Our artificial neural network ANN algorithm exhibited an accuracy of 0.94, specificity of 0.83, sensitivity of 0.97, AUC of 0.96, and MCC of 0.83. These metrics suggest that our model has a high accuracy rate in predicting BBB permeability and therefore has the potential to advance drug discovery efforts in the CNS. This study's outcomes demonstrate the potential for ML models to predict BBB permeability accurately, aiding in the identification of new CNS therapeutic options.

Synthesis, Characterizations, and Quantum Chemical Investigations on Imidazo[1,2-a]pyrimidine-Schiff Base Derivative: (E)-2-Phenyl-N-(thiophen-2-ylmethylene)imidazo[1,2-a]pyrimidin-3-amine

In this study, (E)-2-phenyl-N-(thiophen-2-ylmethylene)imidazo[1,2-a]pyrimidin-3-amine (3) is synthesized, and detailed spectral characterizations using 1H NMR, 13C NMR, mass, and Fourier transform infrared (FT-IR) spectroscopy were performed. The optimized geometry was computed using the density functional theory method at the B3LYP/6-311++G(d,p) basis set. The theoretical FT-IR and NMR (1H and 13C) analysis are agreed to validate the structural assignment made for (3). Frontier molecular orbitals, molecular electrostatic potential, Mulliken atomic charge, electron localization function, localized orbital locator, natural bond orbital, nonlinear optical, Fukui functions, and quantum theory of atoms in molecules analyses are undertaken and meticulously interpreted, providing profound insights into the molecular nature and behaviors. In addition, ADMET and drug-likeness studies were carried out and investigated. Furthermore, molecular docking and molecular dynamics simulations have been studied, indicating that this is an ideal molecule to develop as a potential vascular endothelial growth factor receptor-2 inhibitor.

A new perspective on predicting the reaction rate constants of hydrated electrons for organic contaminants: Exploring molecular structure characterization methods and ambient conditions

Hydrated electrons (eaq-) exhibit rapid degradation of diverse persistent organic contaminants (OCs) and hold great promise as a formidable reducing agent in water treatment. However, the diverse structures of compounds exert different influences on the second-order rate constant of hydrated electron reactions (keaq-), while the same OCs demonstrate notable discrepancies in keaq- values across different pH levels. This study aims to develop machine learning (ML) models that can effectively simulate the intricate reaction kinetics between eaq- and OCs. Furthermore, the introduction of the pH variable enables a comprehensive investigation into the impact of ambient conditions on this process, thereby improving the practicality of the model. A dataset encompassing 701 keaq- values derived from 351 peer-reviewed publications was compiled. To comprehensively investigate compound properties, this study introduced molecular descriptor (MD), molecular fingerprint (MF), and the integration of both (MD + MF) as model variables. Furthermore, 60 sets of predictive models were established utilizing two variable screening methodologies (MLR and RF) and ten prominent algorithms. Through statistical parameter analysis, it was determined that descriptors combined with MD and MF, the RF screening method, and the symbolism algorithm exhibited the best predictive efficacy. Importantly, the combination of descriptor models exhibited significantly superior performance compared to individual MF and MD models. Notably, the optimal model, denoted as RF - (MF + MD) - LGB, exhibited highly satisfactory predictive results (R2tra = 0.967, Q2tra = 0.840, R2ext = 0.761). The mechanistic explanation study based on Shapley Additive Explanations (SHAP) values further elucidated the crucial influences of polarity, pH, molecular weight, electronegativity, carbon-carbon double bonds, and molecular topology on the degradation of OCs by eaq-. The proposed modeling approach, particularly the integration of MF and MD, alongside the introduction of pH, may furnish innovative ideas for advanced reduction or oxidation processes (ARPs/AOPs) and machine learning applications in other domains.

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

Owing to their potential to cause serious adverse health effects, significant efforts have been made to develop antidotes for organophosphate (OP) anticholinesterases, such as nerve agents. To be optimally effective, antidotes must not only reactivate inhibited target enzymes, but also have the ability to cross the blood-brain barrier (BBB). Progress has been made toward brain-penetrating acetylcholinesterase reactivators through the development of a new group of substituted phenoxyalkyl pyridinium oximes. To help in the selection and prioritization of compounds for future synthesis and testing within this class of chemicals, and to identify candidate broad-spectrum molecules, an in silico framework was developed to systematically generate structures and screen them for reactivation efficacy and BBB penetration potential.

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.

Advances in Computational Approaches for Estimating Passive Permeability in Drug Discovery

Passive permeation of cellular membranes is a key feature of many therapeutics. The relevance of passive permeability spans all biological systems as they all employ biomembranes for compartmentalization. A variety of computational techniques are currently utilized and under active development to facilitate the characterization of passive permeability. These methods include lipophilicity relations, molecular dynamics simulations, and machine learning, which vary in accuracy, complexity, and computational cost. This review briefly introduces the underlying theories, such as the prominent inhomogeneous solubility diffusion model, and covers a number of recent applications. Various machine-learning applications, which have demonstrated good potential for high-volume, data-driven permeability predictions, are also discussed. Due to the confluence of novel computational methods and next-generation exascale computers, we anticipate an exciting future for computationally driven permeability predictions.

Combining SILCS and Artificial Intelligence for High-Throughput Prediction of the Passive Permeability of Drug Molecules

Membrane permeability of drug molecules plays a significant role in the development of new therapeutic agents. Accordingly, methods to predict the passive permeability of drug candidates during a medicinal chemistry campaign offer the potential to accelerate the drug design process. In this work, we combine the physics-based site identification by ligand competitive saturation (SILCS) method and data-driven artificial intelligence (AI) to create a high-throughput predictive model for the passive permeability of druglike molecules. In this study, we present a comparative analysis of four regression models to predict membrane permeabilities of small druglike molecules; of the tested models, Random Forest was the most predictive yielding an R2 of 0.81 for the independent data set. The input feature vector used to train the developed prediction model includes absolute free energy profiles of ligands through a POPC-cholesterol bilayer based on ligand grid free energy (LGFE) profiles obtained from the SILCS approach. The use of the membrane free energy profiles from SILCS offers information on the physical forces contributing to ligand permeability, while the use of AI yields a more predictive model trained on experimental PAMPA permeability data for a collection of 229 molecules. This combination allows for rapid estimations of ligand permeability at a level of accuracy beyond currently available predictive models while offering insights into the contributions of the functional groups in the ligands to the permeability barrier, thereby offering quantitative information to facilitate rational ligand design.

Machine learning assisted-nanomedicine using magnetic nanoparticles for central nervous system diseases

Magnetic nanoparticles possess unique properties distinct from other types of nanoparticles developed for biomedical applications. Their unique magnetic properties and multifunctionalities are especially beneficial for central nervous system (CNS) disease therapy and diagnostics, as well as targeted and personalized applications using image-guided therapy and theranostics. This review discusses the recent development of magnetic nanoparticles for CNS applications, including Alzheimer's disease, Parkinson's disease, epilepsy, multiple sclerosis, and drug addiction. Machine learning (ML) methods are increasingly applied towards the processing, optimization and development of nanomaterials. By using data-driven approach, ML has the potential to bridge the gap between basic research and clinical research. We review ML approaches used within the various stages of nanomedicine development, from nanoparticle synthesis and characterization to performance prediction and disease diagnosis.

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

Because of their potential to cause serious adverse health effects, significant efforts have been made to develop antidotes for organophosphate (OP) anticholinesterases, such as nerve agents. To be optimally effective, antidotes must not only reactivate inhibited target enzymes, but also have the ability to cross the blood brain barrier (BBB). Progress has been made toward brain-penetrating acetylcholinesterase reactivators through the development of a new group of substituted phenoxyalkyl pyridinium oximes. To help in the selection and prioritization of compounds for future synthesis and testing within this class of chemicals, and to identify candidate broad-spectrum molecules, an in silico framework was developed to systematically generate structures and screen them for reactivation efficacy and BBB penetration potential.

Chromatographic Data in Statistical Analysis of BBB Permeability Indices

Blood-brain barrier (BBB) permeability is an essential phenomena when considering the treatment of neurological disorders as well as in the case of central nervous system (CNS) adverse effects caused by peripherally acting drugs. The presented work contains statistical analyses and the correlation assessment of the analyzed group of active pharmaceutical ingredients (APIs) with their BBB-permeability data collected from the literature (such as computational log BB; Kp,uu,brain, and CNS+/- groups). A number of regression models were constructed in order to observe the connections between the APIs' physicochemical properties in combination with their retention data from the chromatographic experiments (TLC and HPLC) and the indices of bioavailability in the CNS. Conducted analyses confirm that descriptors significant in BBB permeability modeling are hydrogen bond acceptors and donors, physiological charge, or energy of the lowest unoccupied molecular orbital. These molecular descriptors were the basis, along with the chromatographic data from the TLC in log BB regression analyses. Normal-phase TLC data showed a significant contribution to the creation of the log BB regression model using the multiple linear regression method. The model using them showed a good predictive value at the level of R² = 0.87. Models for Kp,uu,brain resulted in lower statistics: R² = 0.56 for the group of 23 APIs with the participation of k IAM.

Machine learning based dynamic consensus model for predicting blood-brain barrier permeability

The blood-brain barrier (BBB) is an important defence mechanism that restricts disease-causing pathogens and toxins to enter the brain from the bloodstream. In recent years, many in silico methods were proposed for predicting BBB permeability, however, the reliability of these models is questionable due to the smaller and class-imbalance dataset which subsequently leads to a very high false positive rate. In this study, machine learning and deep learning-based predictive models were built using XGboost, Random Forest, Extra-tree classifiers and deep neural network. A dataset of 8153 compounds comprising both the BBB permeable and BBB non-permeable was curated and subjected to calculations of molecular descriptors and fingerprints for generating the features for machine learning and deep learning models. Three balancing techniques were then applied to the dataset to address the class-imbalance issue. A comprehensive comparison among the models showed that the deep neural network model generated on the balanced MACCS fingerprint dataset outperformed with an accuracy of 97.8% and a ROC-AUC score of 0.98 among all the models. Additionally, a dynamic consensus model was prepared with the machine learning models and validated with a benchmark dataset for predicting BBB permeability with higher confidence scores.

Recent Studies of Artificial Intelligence on In Silico Drug Distribution Prediction

Drug distribution is an important process in pharmacokinetics because it has the potential to influence both the amount of medicine reaching the active sites and the effectiveness as well as safety of the drug. The main causes of 90% of drug failures in clinical development are lack of efficacy and uncontrolled toxicity. In recent years, several advances and promising developments in drug distribution property prediction have been achieved, especially in silico, which helped to drastically reduce the time and expense of screening undesired drug candidates. In this study, we provide comprehensive knowledge of drug distribution background, influencing factors, and artificial intelligence-based distribution property prediction models from 2019 to the present. Additionally, we gathered and analyzed public databases and datasets commonly utilized by the scientific community for distribution prediction. The distribution property prediction performance of five large ADMET prediction tools is mentioned as a benchmark for future research. On this basis, we also offer future challenges in drug distribution prediction and research directions. We hope that this review will provide researchers with helpful insight into distribution prediction, thus facilitating the development of innovative approaches for drug discovery.

Development of QSAR models to predict blood-brain barrier permeability

Assessing drug permeability across the blood-brain barrier (BBB) is important when evaluating the abuse potential of new pharmaceuticals as well as developing novel therapeutics that target central nervous system disorders. One of the gold-standard in vivo methods for determining BBB permeability is rodent log BB; however, like most in vivo methods, it is time-consuming and expensive. In the present study, two statistical-based quantitative structure-activity relationship (QSAR) models were developed to predict BBB permeability of drugs based on their chemical structure. The in vivo BBB permeability data were harvested for 921 compounds from publicly available literature, non-proprietary drug approval packages, and University of Washington's Drug Interaction Database. The cross-validation performance statistics for the BBB models ranged from 82 to 85% in sensitivity and 80-83% in negative predictivity. Additionally, the performance of newly developed models was assessed using an external validation set comprised of 83 chemicals. Overall, performance of individual models ranged from 70 to 75% in sensitivity, 70-72% in negative predictivity, and 78-86% in coverage. The predictive performance was further improved to 93% in coverage by combining predictions across the two software programs. These new models can be rapidly deployed to predict blood brain barrier permeability of pharmaceutical candidates and reduce the use of experimental animals.

Improving VAE based molecular representations for compound property prediction

Collecting labeled data for many important tasks in chemoinformatics is time consuming and requires expensive experiments. In recent years, machine learning has been used to learn rich representations of molecules using large scale unlabeled molecular datasets and transfer the knowledge to solve the more challenging tasks with limited datasets. Variational autoencoders are one of the tools that have been proposed to perform the transfer for both chemical property prediction and molecular generation tasks. In this work we propose a simple method to improve chemical property prediction performance of machine learning models by incorporating additional information on correlated molecular descriptors in the representations learned by variational autoencoders. We verify the method on three property prediction tasks. We explore the impact of the number of incorporated descriptors, correlation between the descriptors and the target properties, sizes of the datasets etc. Finally, we show the relation between the performance of property prediction models and the distance between property prediction dataset and the larger unlabeled dataset in the representation space.

Multi-Targeting Approach in Glioblastoma Using Computer-Assisted Drug Discovery Tools to Overcome the Blood–Brain Barrier and Target EGFR/PI3Kp110β Signaling

Simple Summary

Treatment of glioblastoma is hampered by the activation of compensatory survival mechanisms by malignant cells that lead to drug resistance. Moreover, the blood–brain barrier (BBB) precludes the brain entrance of most drugs. We hypothesized that computer-assisted drug discovery tools would reveal novel multi-targeting drug candidates with BBB-permeant and favorable ADMET properties. We aimed to discover molecules with predicted ability to inhibit the EGFR/PI3Kp110β pathway and to validate their efficacy and safety in biological assays. We used quantitative structure–activity relationship models and structure-based virtual screening, and assessed ADMET properties, to identify BBB-permeant drug candidates. Moreover, we tested their anti-tumor efficacy and BBB safety and permeation in cell models. We found two EGFR, two PI3Kp110β, and, mostly, two dual inhibitors with anti-tumor effects. Among them, one EGFR and two PI3Kp110β inhibitors were able to cross the BBB endothelium without compromising it. These studies revealed novel drug candidates for glioblastoma treatment.

Abstract

The epidermal growth factor receptor (EGFR) is upregulated in glioblastoma, becoming an attractive therapeutic target. However, activation of compensatory pathways generates inputs to downstream PI3Kp110β signaling, leading to anti-EGFR therapeutic resistance. Moreover, the blood–brain barrier (BBB) limits drugs’ brain penetration. We aimed to discover EGFR/PI3Kp110β pathway inhibitors for a multi-targeting approach, with favorable ADMET and BBB-permeant properties. We used quantitative structure–activity relationship models and structure-based virtual screening, and assessed ADMET properties, to identify BBB-permeant drug candidates. Predictions were validated in in vitro models of the human BBB and BBB-glioma co-cultures. The results disclosed 27 molecules (18 EGFR, 6 PI3Kp110β, and 3 dual inhibitors) for biological validation, performed in two glioblastoma cell lines (U87MG and U87MG overexpressing EGFR). Six molecules (two EGFR, two PI3Kp110β, and two dual inhibitors) decreased cell viability by 40–99%, with the greatest effect observed for the dual inhibitors. The glioma cytotoxicity was confirmed by analysis of targets’ downregulation and increased apoptosis (15–85%). Safety to BBB endothelial cells was confirmed for three of those molecules (one EGFR and two PI3Kp110β inhibitors). These molecules crossed the endothelial monolayer in the BBB in vitro model and in the BBB-glioblastoma co-culture system. These results revealed novel drug candidates for glioblastoma treatment.

Blood-brain barrier penetration prediction enhanced by uncertainty estimation

Blood–brain barrier is a pivotal factor to be considered in the process of central nervous system (CNS) drug development, and it is of great significance to rapidly explore the blood–brain barrier permeability (BBBp) of compounds in silico in early drug discovery process. Here, we focus on whether and how uncertainty estimation methods improve in silico BBBp models. We briefly surveyed the current state of in silico BBBp prediction and uncertainty estimation methods of deep learning models, and curated an independent dataset to determine the reliability of the state-of-the-art algorithms. The results exhibit that, despite the comparable performance on BBBp prediction between graph neural networks-based deep learning models and conventional physicochemical-based machine learning models, the GROVER-BBBp model shows greatly improvement when using uncertainty estimations. In particular, the strategy combined Entropy and MC-dropout can increase the accuracy of distinguishing BBB + from BBB − to above 99% by extracting predictions with high confidence level (uncertainty score < 0.1). Case studies on preclinical/clinical drugs for Alzheimer’ s disease and marketed antitumor drugs that verified by literature proved the application value of uncertainty estimation enhanced BBBp prediction model, that may facilitate the drug discovery in the field of CNS diseases and metastatic brain tumors.

Brain physiome: A concept bridging in vitro 3D brain models and in silico models for predicting drug toxicity in the brain

In the last few decades, adverse reactions to pharmaceuticals have been evaluated using 2D in vitro models and animal models. However, with increasing computational power, and as the key drivers of cellular behavior have been identified, in silico models have emerged. These models are time-efficient and cost-effective, but the prediction of adverse reactions to unknown drugs using these models requires relevant experimental input. Accordingly, the physiome concept has emerged to bridge experimental datasets with in silico models. The brain physiome describes the systemic interactions of its components, which are organized into a multilevel hierarchy. Because of the limitations in obtaining experimental data corresponding to each physiome component from 2D in vitro models and animal models, 3D in vitro brain models, including brain organoids and brain-on-a-chip, have been developed. In this review, we present the concept of the brain physiome and its hierarchical organization, including cell- and tissue-level organizations. We also summarize recently developed 3D in vitro brain models and link them with the elements of the brain physiome as a guideline for dataset collection. The connection between in vitro 3D brain models and in silico modeling will lead to the establishment of cost-effective and time-efficient in silico models for the prediction of the safety of unknown drugs.

Relational graph convolutional networks for predicting blood-brain barrier penetration of drug molecules

MOTIVATION

Evaluating the blood-brain barrier (BBB) permeability of drug molecules is a critical step in brain drug development. Traditional methods for the evaluation require complicated in vitro or in vivo testing. Alternatively, in silico predictions based on machine learning have proved to be a cost-efficient way to complement the in vitro and in vivo methods. However, the performance of the established models has been limited by their incapability of dealing with the interactions between drugs and proteins, which play an important role in the mechanism behind the BBB penetrating behaviors. To address this limitation, we employed the relational graph convolutional network (RGCN) to handle the drug-protein interactions as well as the properties of each individual drug.

RESULTS

The RGCN model achieved an overall accuracy of 0.872, an area under the receiver operating characteristic (AUROC) of 0.919 and an area under the precision-recall curve (AUPRC) of 0.838 for the testing dataset with the drug-protein interactions and the Mordred descriptors as the input. Introducing drug-drug similarity to connect structurally similar drugs in the data graph further improved the testing results, giving an overall accuracy of 0.876, an AUROC of 0.926 and an AUPRC of 0.865. In particular, the RGCN model was found to greatly outperform the LightGBM base model when evaluated with the drugs whose BBB penetration was dependent on drug-protein interactions. Our model is expected to provide high-confidence predictions of BBB permeability for drug prioritization in the experimental screening of BBB-penetrating drugs.

AVAILABILITY AND IMPLEMENTATION

The data and the codes are freely available at https://github.com/dingyan20/BBB-Penetration-Prediction.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

DeePred-BBB: A Blood Brain Barrier Permeability Prediction Model With Improved Accuracy

The blood-brain barrier (BBB) is a selective and semipermeable boundary that maintains homeostasis inside the central nervous system (CNS). The BBB permeability of compounds is an important consideration during CNS-acting drug development and is difficult to formulate in a succinct manner. Clinical experiments are the most accurate method of measuring BBB permeability. However, they are time taking and labor-intensive. Therefore, numerous efforts have been made to predict the BBB permeability of compounds using computational methods. However, the accuracy of BBB permeability prediction models has always been an issue. To improve the accuracy of the BBB permeability prediction, we applied deep learning and machine learning algorithms to a dataset of 3,605 diverse compounds. Each compound was encoded with 1,917 features containing 1,444 physicochemical (1D and 2D) properties, 166 molecular access system fingerprints (MACCS), and 307 substructure fingerprints. The prediction performance metrics of the developed models were compared and analyzed. The prediction accuracy of the deep neural network (DNN), one-dimensional convolutional neural network, and convolutional neural network by transfer learning was found to be 98.07, 97.44, and 97.61%, respectively. The best performing DNN-based model was selected for the development of the “DeePred-BBB” model, which can predict the BBB permeability of compounds using their simplified molecular input line entry system (SMILES) notations. It could be useful in the screening of compounds based on their BBB permeability at the preliminary stages of drug development. The DeePred-BBB is made available at https://github.com/12rajnish/DeePred-BBB.

Bioactivity assessment of natural compounds using machine learning models trained on target similarity between drugs

Natural compounds constitute a rich resource of potential small molecule therapeutics. While experimental access to this resource is limited due to its vast diversity and difficulties in systematic purification, computational assessment of structural similarity with known therapeutic molecules offers a scalable approach. Here, we assessed functional similarity between natural compounds and approved drugs by combining multiple chemical similarity metrics and physicochemical properties using a machine-learning approach. We computed pairwise similarities between 1410 drugs for training classification models and used the drugs shared protein targets as class labels. The best performing models were random forest which gave an average area under the ROC of 0.9, Matthews correlation coefficient of 0.35, and F1 score of 0.33, suggesting that it captured the structure-activity relation well. The models were then used to predict protein targets of circa 11k natural compounds by comparing them with the drugs. This revealed therapeutic potential of several natural compounds, including those with support from previously published sources as well as those hitherto unexplored. We experimentally validated one of the predicted pair’s activities, viz., Cox-1 inhibition by 5-methoxysalicylic acid, a molecule commonly found in tea, herbs and spices. In contrast, another natural compound, 4-isopropylbenzoic acid, with the highest similarity score when considering most weighted similarity metric but not picked by our models, did not inhibit Cox-1. Our results demonstrate the utility of a machine-learning approach combining multiple chemical features for uncovering protein binding potential of natural compounds.

DeepBBBP: High accuracy Blood-Brain-Barrier Permeability Prediction with a Mixed Deep Learning Model

Blood-brain-barrier permeability (BBBP) is an important property that is used to establish the drug-likeness of a molecule, as it establishes whether the molecule can cross the BBB when desired. It also eliminates those molecules which are not supposed to cross the barrier, as doing so would lead to toxicity. BBBP can be measured in vivo, in vitro or in silico. With the advent and subsequent rise of in silico methods for virtual drug screening, quite a bit of work has been done to predict this feature using statistical machine learning (ML) and deep learning (DL) based methods. In this work a mixed DL-based model, consisting of a Multi-layer Perceptron (MLP) and Convolutional Neural Network layers, has been paired with Mol2vec. Mol2vec is a convenient and unsupervised machine learning technique which produces high-dimensional vector representations of molecules and its molecular substructures. These succinct vector representations are utilized as inputs to the mixed DL model that is used for BBBP predictions. Several well-known benchmarks incorporating BBBP data have been used for supervised training and prediction by our mixed DL model which demonstrates superior results when compared to existing ML and DL techniques used for predicting BBBP.

Machine learning models for classification tasks related to drug safety

In this review, we outline the current trends in the field of machine learning-driven classification studies related to ADME (absorption, distribution, metabolism and excretion) and toxicity endpoints from the past six years (2015-2021). The study focuses only on classification models with large datasets (i.e. more than a thousand compounds). A comprehensive literature search and meta-analysis was carried out for nine different targets: hERG-mediated cardiotoxicity, blood-brain barrier penetration, permeability glycoprotein (P-gp) substrate/inhibitor, cytochrome P450 enzyme family, acute oral toxicity, mutagenicity, carcinogenicity, respiratory toxicity and irritation/corrosion. The comparison of the best classification models was targeted to reveal the differences between machine learning algorithms and modeling types, endpoint-specific performances, dataset sizes and the different validation protocols. Based on the evaluation of the data, we can say that tree-based algorithms are (still) dominating the field, with consensus modeling being an increasing trend in drug safety predictions. Although one can already find classification models with great performances to hERG-mediated cardiotoxicity and the isoenzymes of the cytochrome P450 enzyme family, these targets are still central to ADMET-related research efforts.

Comparing the Pfizer Central Nervous System Multiparameter Optimization Calculator and a BBB Machine Learning Model

The ability to calculate whether small molecules will cross the blood-brain barrier (BBB) is an important task for companies working in neuroscience drug discovery. For a decade, scientists have relied on relatively simplistic rules such as Pfizer's central nervous system multiparameter optimization models (CNS-MPO) for guidance during the drug selection process. In parallel, there has been a continued development of more sophisticated machine learning models that utilize different molecular descriptors and algorithms; however, these models represent a "black box" and are generally less interpretable. In both cases, these methods predict the ability of small molecules to cross the BBB using the molecular structure information on its own without in vitro or in vivo data. We describe here the implementation of two versions of Pfizer's algorithm (Pf-MPO.v1 and Pf-MPO.v2) and compare it with a Bayesian machine learning model of BBB penetration trained on a data set of 2296 active and inactive compounds using extended connectivity fingerprint descriptors. The predictive ability of these approaches was compared with 40 known CNS active drugs initially used by Pfizer as their positive set for validation of the Pf-MPO.v1 score. 37/40 (92.5%) compounds were predicted as active by the Bayesian model, while only 30/40 (75%) received a desirable Pf-MPO.v1 score ≥4 and 33/40 (82.5%) received a desirable Pf-MPO.v2 score ≥4, suggesting the Bayesian model is more accurate than MPO algorithms. This also indicates machine learning models are more flexible and have better predictive power for BBB penetration than simple rule sets that require multiple, accurate descriptor calculations. Our machine learning model statistics are comparable to recent published studies. We describe the implications of these findings and how machine learning may have a role alongside more interpretable methods.

A deep learning approach to predict blood-brain barrier permeability

The blood-brain barrier plays a crucial role in regulating the passage of 98% of the compounds that enter the central nervous system (CNS). Compounds with high permeability must be identified to enable the synthesis of brain medications for the treatment of various brain diseases, such as Parkinson's, Alzheimer's, and brain tumors. Throughout the years, several models have been developed to solve this problem and have achieved acceptable accuracy scores in predicting compounds that penetrate the blood-brain barrier. However, predicting compounds with "low" permeability has been a challenging task. In this study, we present a deep learning (DL) classification model to predict blood-brain barrier permeability. The proposed model addresses the fundamental issues presented in former models: high dimensionality, class imbalances, and low specificity scores. We address these issues to enhance the high-dimensional, imbalanced dataset before developing the classification model: the imbalanced dataset is addressed using oversampling techniques and the high dimensionality using a non-linear dimensionality reduction technique known as kernel principal component analysis (KPCA). This technique transforms the high-dimensional dataset into a low-dimensional Euclidean space while retaining invaluable information. For the classification task, we developed an enhanced feed-forward deep learning model and a convolutional neural network model. In terms of specificity scores (i.e., predicting compounds with low permeability), the results obtained by the enhanced feed-forward deep learning model outperformed those obtained by other models in the literature that were developed using the same technique. In addition, the proposed convolutional neural network model surpassed models used in other studies in multiple accuracy measures, including overall accuracy and specificity. The proposed approach solves the problem inevitably faced with obtaining low specificity resulting in high false positive rate.

LightBBB: computational prediction model of blood-brain-barrier penetration based on LightGBM

MOTIVATION

Identification of blood-brain barrier (BBB) permeability of a compound is a major challenge in neurotherapeutic drug discovery. Conventional approaches for BBB permeability measurement are expensive, time-consuming and labor-intensive. BBB permeability is associated with diverse chemical properties of compounds. However, BBB permeability prediction models have been developed using small datasets and limited features, which are usually not practical due to their low coverage of chemical diversity of compounds. Aim of this study is to develop a BBB permeability prediction model using a large dataset for practical applications. This model can be used for facilitated compound screening in the early stage of brain drug discovery.

RESULTS

A dataset of 7162 compounds with BBB permeability (5453 BBB+ and 1709 BBB-) was compiled from the literature, where BBB+ and BBB- denote BBB-permeable and non-permeable compounds, respectively. We trained a machine learning model based on Light Gradient Boosting Machine (LightGBM) algorithm and achieved an overall accuracy of 89%, an area under the curve (AUC) of 0.93, specificity of 0.77 and sensitivity of 0.93, when 10-fold cross-validation was performed. The model was further evaluated using 74 central nerve system compounds (39 BBB+ and 35 BBB-) obtained from the literature and showed an accuracy of 90%, sensitivity of 0.85 and specificity of 0.94. Our model outperforms over existing BBB permeability prediction models.

AVAILABILITYAND IMPLEMENTATION

The prediction server is available at http://ssbio.cau.ac.kr/software/bbb.

Prediction of the Blood-Brain Barrier (BBB) Permeability of Chemicals Based on Machine-Learning and Ensemble Methods

The ability of chemicals to enter the blood-brain barrier (BBB) is a key factor for central nervous system (CNS) drug development. Although many models for BBB permeability prediction have been developed, they have insufficient accuracy (ACC) and sensitivity (SEN). To improve performance, ensemble models were built to predict the BBB permeability of compounds. In this study, in silico ensemble-learning models were developed using 3 machine-learning algorithms and 9 molecular fingerprints from 1757 chemicals (integrated from 2 published data sets) to predict BBB permeability. The best prediction performance of the base classifier models was achieved by a prediction model based on an random forest (RF) and a MACCS molecular fingerprint with an ACC of 0.910, an area under the receiver-operating characteristic (ROC) curve (AUC) of 0.957, a SEN of 0.927, and a specificity of 0.867 in 5-fold cross-validation. The prediction performance of the ensemble models is better than that of most of the base classifiers. The final ensemble model has also demonstrated good accuracy for an external validation and can be used for the early screening of CNS drugs.

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

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Artificial Intelligence in Drug Discovery: A Comprehensive Review of Data-driven and Machine Learning Approaches

As expenditure on drug development increases exponentially, the overall drug discovery process requires a sustainable revolution. Since artificial intelligence (AI) is leading the fourth industrial revolution, AI can be considered as a viable solution for unstable drug research and development. Generally, AI is applied to fields with sufficient data such as computer vision and natural language processing, but there are many efforts to revolutionize the existing drug discovery process by applying AI. This review provides a comprehensive, organized summary of the recent research trends in AI-guided drug discovery process including target identification, hit identification, ADMET prediction, lead optimization, and drug repositioning. The main data sources in each field are also summarized in this review. In addition, an in-depth analysis of the remaining challenges and limitations will be provided, and proposals for promising future directions in each of the aforementioned areas.

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

Permeation through the blood–brain barrier (BBB) is among the most important processes controlling the pharmacokinetic properties of drugs and other bioactive compounds. Using the fragmental (substructural) descriptors representing the occurrence number of various substructures, as well as the artificial neural network approach and the double cross-validation procedure, we have developed a predictive in silico LogBB model based on an extensive and verified dataset (529 compounds), which is applicable to diverse drugs and drug-like compounds. The model has good predictivity parameters (Q2=0.815, RMSEcv=0.318) that are similar to or better than those of the most reliable models available in the literature. Larger datasets, and perhaps more sophisticated network architectures, are required to realize the full potential of deep neural networks. The analysis of fragment contributions reveals patterns of influence consistent with the known concepts of structural characteristics that affect the BBB permeability of organic compounds. The external validation of the model confirms good agreement between the predicted and experimental LogBB values for most of the compounds. The model enables the evaluation and optimization of the BBB permeability of potential neuroactive agents and other drug compounds.

Recent progress in translational engineered in vitro models of the central nervous system

The complexity of the human brain poses a substantial challenge for the development of models of the CNS. Current animal models lack many essential human characteristics (in addition to raising operational challenges and ethical concerns), and conventional in vitro models, in turn, are limited in their capacity to provide information regarding many functional and systemic responses. Indeed, these challenges may underlie the notoriously low success rates of CNS drug development efforts. During the past 5 years, there has been a leap in the complexity and functionality of in vitro systems of the CNS, which have the potential to overcome many of the limitations of traditional model systems. The availability of human-derived induced pluripotent stem cell technology has further increased the translational potential of these systems. Yet, the adoption of state-of-the-art in vitro platforms within the CNS research community is limited. This may be attributable to the high costs or the immaturity of the systems. Nevertheless, the costs of fabrication have decreased, and there are tremendous ongoing efforts to improve the quality of cell differentiation. Herein, we aim to raise awareness of the capabilities and accessibility of advanced in vitro CNS technologies. We provide an overview of some of the main recent developments (since 2015) in in vitro CNS models. In particular, we focus on engineered in vitro models based on cell culture systems combined with microfluidic platforms (e.g. 'organ-on-a-chip' systems). We delve into the fundamental principles underlying these systems and review several applications of these platforms for the study of the CNS in health and disease. Our discussion further addresses the challenges that hinder the implementation of advanced in vitro platforms in personalized medicine or in large-scale industrial settings, and outlines the existing differentiation protocols and industrial cell sources. We conclude by providing practical guidelines for laboratories that are considering adopting organ-on-a-chip technologies.

A Recurrent Neural Network model to predict blood-brain barrier permeability

The rapid development of computational methods and the increasing volume of chemical and biological data have contributed to an immense growth in chemical research. This field of study is known as "chemoinformatics," which is a discipline that uses machine-learning techniques to extract, process, and extrapolate data from chemical structures. One of the significant lines of research in chemoinformatics is the study of blood-brain barrier (BBB) permeability, which aims to identify drug penetration into the central nervous system (CNS). In this research, we attempt to solve the problem of BBB permeability by predicting compounds penetration to the CNS. To accomplish this goal: (i) First, an overview is provided to the field of chemoinformatics, its definition, applications, and challenges, (ii) Second, a broad view is taken to investigate previous machine-learning and deep-learning computational models to solve BBB permeability. Based on the analysis of previous models, three main challenges that collectively affect the classifier performance are identified, which we define as "the triple constraints"; subsequently, we map each constraint to a proposed solution, (iii) Finally, we conclude this endeavor by proposing a deep learning based Recurrent Neural Network model, to predict BBB permeability (RNN-BBB model). Our model outperformed other studies from the literature by scoring an overall accuracy of 96.53%, and a specificity score of 98.08%. The obtained results confirm that addressing the triple constraints substantially improves the classification model capability specifically when predicting compounds with low penetration.

In vivo characterization of toxicity of norcocaethylene and norcocaine identified as the most toxic cocaine metabolites in male mice

BACKGROUND

Majority of cocaine users also consume alcohol, and concurrent use of cocaine and alcohol produces cocaethylene, norcocaine, norcocaethylene, and other non-toxic metabolites. It is essential to know their relative toxicity for development of a truly effective therapeutics for cocaine toxicity treatment.

METHODS

Drug (norcocaethylene or norcocaine)-induced acute toxicity was characterized by the occurrence (and the timing) of prostration, seizure, and death after intraperitoneal administration of the drug (n = 15) using the same strain (Swiss Webster) of male mice reported in previous study by Hearn et al. to determine LD₅₀ of cocaine and cocaethylene. In addition, drug (cocaine, cocaethylene, norcocaine, or norcocaethylene)-induced hyperactivity was determined by locomotor activity testing (n = 8).

RESULTS

According to the animal data, norcocaethylene (LD₅₀=∼39.4 mg/kg) and norcocaine (LD₅₀=∼49.7 mg/kg) are the most toxic metabolites, but they do not induce significant hyperactivity. In addition, the relative toxicity of drugs correlates with the time to the occurrence of prostration/seizure/death after the drug administration.

CONCLUSIONS

The relative toxicity of these toxic drugs can be ranked in this order: norcocaethylene > norcocaine > cocaethylene > cocaine. The data suggest that norcocaethylene, norcocaine, and cocaethylene are all significant contributors to acute toxicity of cocaine in concurrent use of cocaine and alcohol. Hence, future therapeutic development for cocaine toxicity treatment must account for detoxification of these more toxic metabolites. In addition, the relative toxicity of different drugs correlates with the average time to the occurrence of death, seizure, or prostration after the drug administration with a same dose close to their LD₅₀ values.