Effect of Selection of Molecular Descriptors on the Prediction of Blood−Brain Barrier Penetrating and Nonpenetrating Agents by Statistical Learning Methods

Prediction of blood-brain barrier permeability using machine learning approaches based on various molecular representation

The assessment of compound blood-brain barrier (BBB) permeability poses a significant challenge in the discovery of drugs targeting the central nervous system. Conventional experimental approaches to measure BBB permeability are labor-intensive, cost-ineffective, and time-consuming. In this study, we constructed six machine learning classification models by combining various machine learning algorithms and molecular representations. The model based on ExtraTree algorithm and random partitioning strategy obtains the best prediction result, with AUC value of 0.932±0.004 and balanced accuracy (BA) of 0.837±0.010 for the test set. We employed the SHAP method to identify important features associated with BBB permeability. In addition, matched molecular pair (MMP) analysis and representative substructure derivation method were utilized to uncover the transformation rules and distinctive structural features of BBB permeable compounds. The machine learning models proposed in this work can serve as an effective tool for assessing BBB permeability in the drug discovery for central nervous system disease.

Assessing the anticholinergic cognitive burden classification of putative anticholinergic drugs using drug properties

AIMS

This study evaluated the use of machine learning to leverage drug absorption, distribution, metabolism and excretion (ADME) data together with physicochemical and pharmacological data to develop a novel anticholinergic burden scale and compare its performance to previously published scales.

METHODS

Experimental and in silico ADME, physicochemical and pharmacological data were collected for antimuscarinic activity, blood-brain barrier penetration, bioavailability, chemical structure and P-glycoprotein (P-gp) substrate profile. These five drug properties were used to train an unsupervised model to assign anticholinergic burden scores to drugs. The model performance was evaluated through 10-fold cross-validation and compared with the clinical Anticholinergic Cognitive Burden (ACB) scale and nonclinical Anticholinergic Toxicity Scores (ATS) scale, which is based primarily on muscarinic binding affinity.

RESULTS

In silico software (ADMET Predictor) used for screening drugs for their blood-brain barrier (BBB) penetration correctly identified some drugs that do not cross the BBB. The mean area under the curve for the unsupervised and ACB scale based on the five selected variables was 0.76 and 0.64, respectively. The unsupervised model agreed with the ACB scale on the classification of more than half of the drugs (49 of 88) agreed on the classification of less than half the drugs in the ATS scale (12 of 25).

CONCLUSIONS

Our findings suggest that the commonly used ACB scale may misclassify certain drugs due to their inability to cross the BBB. By contrast, the ATS scale would misclassify drugs solely depending on muscarinic binding affinity without considering other drug properties. Machine learning models can be trained on these features to build classification models that are easy to update and have greater generalizability.

Identifying Substructures That Facilitate Compounds to Penetrate the Blood-Brain Barrier via Passive Transport Using Machine Learning Explainer Models

The local interpretable model-agnostic explanation (LIME) method was used to interpret two machine learning models of compounds penetrating the blood-brain barrier. The classification models, Random Forest, ExtraTrees, and Deep Residual Network, were trained and validated using the blood-brain barrier penetration dataset, which shows the penetrability of compounds in the blood-brain barrier. LIME was able to create explanations for such penetrability, highlighting the most important substructures of molecules that affect drug penetration in the barrier. The simple and intuitive outputs prove the applicability of this explainable model to interpreting the permeability of compounds across the blood-brain barrier in terms of molecular features. LIME explanations were filtered with a weight equal to or greater than 0.1 to obtain only the most relevant explanations. The results showed several structures that are important for blood-brain barrier penetration. In general, it was found that some compounds with nitrogenous substructures are more likely to permeate the blood-brain barrier. The application of these structural explanations may help the pharmaceutical industry and potential drug synthesis research groups to synthesize active molecules more rationally.

Pharmacokinetics Profiler (PhaKinPro): Model Development, Validation, and Implementation as a Web Tool for Triaging Compounds with Undesired Pharmacokinetics Profiles

Computational models that predict pharmacokinetic properties are critical to deprioritize drug candidates that emerge as hits in high-throughput screening campaigns. We collected, curated, and integrated a database of compounds tested in 12 major end points comprising over 10,000 unique molecules. We then employed these data to build and validate binary quantitative structure-activity relationship (QSAR) models. All trained models achieved a correct classification rate above 0.60 and a positive predictive value above 0.50. To illustrate their utility in drug discovery, we used these models to predict the pharmacokinetic properties for drugs in the NCATS Inxight Drugs database. In addition, we employed the developed models to predict the pharmacokinetic properties of all compounds in the DrugBank. All models described in this paper have been integrated and made publicly available via the PhaKinPro Web-portal that can be accessed at https://phakinpro.mml.unc.edu/.

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.

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.

Predictive Models Based on Molecular Images and Molecular Descriptors for Drug Screening

Various toxicity and pharmacokinetic evaluations as screening experiments are needed at the drug discovery stage. Currently, to reduce the use of animal experiments and developmental expenses, the development of high-performance predictive models based on quantitative structure-activity relationship analysis is desired. From these evaluation targets, we selected 50% lethal dose (LD50), blood-brain barrier penetration (BBBP), and the clearance (CL) pathway for this investigation and constructed predictive models for each target using 636-11,886 compounds. First, we constructed predictive models using the DeepSnap-deep learning (DL) method and images of compounds as features. The calculated area under the curve (AUC) and balanced accuracy (BAC) were, respectively, 0.887 and 0.818 for LD50, 0.893 and 0.824 for BBBP, and 0.883 and 0.763 for the CL pathway. Next, molecular descriptors (MDs) of compounds were calculated using Molecular Operating Environment, alvaDesc, and ADMET Predictor to construct predictive models using the MD-based method. Using these MDs, we constructed predictive models using DataRobot. The calculated AUC and BAC were, respectively, 0.931 and 0.805 for LD50, 0.919 and 0.849 for BBBP, and 0.900 and 0.807 for the CL pathway. In this investigation, we constructed predictive models combining the DeepSnap-DL and MD-based methods. In ensemble models using the mean predictive probability of the DeepSnap-DL and MD-based methods, the calculated AUC and BAC were, respectively, 0.942 and 0.842 for LD50, 0.936 and 0.853 for BBBP, and 0.908 and 0.832 for the CL pathway, with improved predictive performance observed for all variables compared with either single method alone. Moreover, in consensus models that adopted only compounds for which the results of the two methods agreed, the calculated BAC for LD50, BBBP, and the CL pathway were 0.916, 0.918, and 0.847, respectively, indicating higher predictive performance than the ensemble models for all three variables. The predictive models combining the DeepSnap-DL and MD-based methods displayed high predictive performance for LD50, BBBP, and the CL pathway. Therefore, the application of this approach to prediction targets in various drug discovery screenings is expected to accelerate drug discovery.

Identification of in vitro metabolites of an Allium organosulfur compound and environmental toxicity prediction as part of its risk assessment

Propyl-propane-thiosulfonate (PTSO) is an organosulfur compound found inAllium spp. Due to its antioxidant and antimicrobial activities, PTSO has been proposed for applications in the agri-food sector, such as feed additive. However, its use with commercial purposes depends on its toxicity evaluation. The present work aimed to perform a pilot-study of toxicokinetic profile of PTSO combining in silico and in vitro techniques, important steps in the risk assessment process. In silico ecotoxicity studies were also performed considering the importance of the environmental impact of the compound before its commercial use. First, an analytical method has been developed and validated to determine the original compound and its metabolites by ultra-performance liquid chromatography-tandem mass spectrometry. The phase I and II metabolism of PTSO was predicted using Meta-Pred Web Server. For the phase I metabolism, rat (male and female) and human liver microsomes were incubated with PTSO and NADPH regeneration system. Furthermore, in the phase II, microsomes were incubated with PTSO and glutathione or uridine 5'- diphosphoglucuronic acid. The analysis revealed the presence of propylpropane thiosulfinate (PTS) originated by redox reaction in phase I, and two conjugates from the phase II: S-propylmercaptoglutathione (GSSP) and S-propylmercaptocysteine (CSSP). Additionally, considering the environmental fate of PTSO and its metabolites, the ADME parameters and the potential ecotoxicity were also predicted using in silico softwares. The results of the ecotoxicity in silico study evidenced that the metabolism induced the formation of detoxified metabolites from the parent compound, except for dimercaprol and 3-mercaptopropane1,2-diol. Further in vivo assays are needed to confirm this prediction.

Discovery of 3CLpro inhibitor of SARS-CoV-2 main protease

Coronavirus main protease (3CLpro), a special cysteine protease in coronavirus family, is highly desirable in the life cycle of coronavirus. Here, molecular docking, ADMET pharmacokinetic profiles and molecular dynamics (MD) simulation were performed to develop specific 3CLpro inhibitor. The results showed that the 137 compounds originated from Chinese herbal have good binding affinity to 3CLpro. Among these, Cleomiscosin C, (+)-Norchelidonine, Protopine, Turkiyenine, Isochelidonine and Mallotucin A possessed prominent drug-likeness properties. Cleomiscosin C and Turkiyenine exhibited excellent pharmacokinetic profiles. Furthermore, the complex of Cleomiscosin C with SARS-CoV-2 main protease presented high stability. The findings in this work indicated that Cleomiscosin C is highly promising as a potential 3CLpro inhibitor, thus facilitating the development of effective drugs for COVID-19.

Computational Approach to Drug Penetration across the Blood-Brain and Blood-Milk Barrier Using Chromatographic Descriptors

Drug penetration through biological barriers is an important aspect of pharmacokinetics. Although the structure of the blood-brain and blood-milk barriers is different, a connection can be found in the literature between drugs entering the central nervous system (CNS) and breast milk. This study was created to reveal such a relationship with the use of statistical modelling. The basic physicochemical properties of 37 active pharmaceutical compounds (APIs) and their chromatographic retention data (TLC and HPLC) were incorporated into calculations as molecular descriptors (MDs). Chromatography was performed in a thin layer format (TLC), where the plates were impregnated with bovine serum albumin to mimic plasma protein binding. Two columns were used in high performance liquid chromatography (HPLC): one with immobilized human serum albumin (HSA), and the other containing an immobilized artificial membrane (IAM). Statistical methods including multiple linear regression (MLR), cluster analysis (CA) and random forest regression (RF) were performed with satisfactory results: the MLR model explains 83% of the independent variable variability related to CNS bioavailability; while the RF model explains up to 87%. In both cases, the parameter related to breast milk penetration was included in the created models. A significant share of reversed-phase TLC retention values was also noticed in the RF model.

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.

Pharmacophore Modeling Using Machine Learning for Screening the Blood-Brain Barrier Permeation of Xenobiotics

Daily exposure to xenobiotics affects human health, especially the nervous system, causing neurodegenerative diseases. The nervous system is protected by tight junctions present at the blood-brain barrier (BBB), but only molecules with desirable physicochemical properties can permeate it. This is why permeation is a decisive step in avoiding unwanted brain toxicity and also in developing neuronal drugs. In silico methods are being implemented as an initial step to reduce animal testing and the time complexity of the in vitro screening process. However, most in silico methods are ligand based, and consider only the physiochemical properties of ligands. However, these ligand-based methods have their own limitations and sometimes fail to predict the BBB permeation of xenobiotics. The objective of this work was to investigate the influence of the pharmacophoric features of protein-ligand interactions on BBB permeation. For these purposes, receptor-based pharmacophore and ligand-based pharmacophore fingerprints were developed using docking and Rdkit, respectively. Then, these fingerprints were trained on classical machine-learning models and compared with classical fingerprints. Among the tested footprints, the ligand-based pharmacophore fingerprint achieved slightly better (77% accuracy) performance compared to the classical fingerprint method. In contrast, receptor-based pharmacophores did not lead to much improvement compared to classical descriptors. The performance can be further improved by considering efflux proteins such as BCRP (breast cancer resistance protein), as well as P-gp (P-glycoprotein). However, the limited data availability for other proteins regarding their pharmacophoric interactions is a bottleneck to its improvement. Nonetheless, the developed models and exploratory analysis provide a path to extend the same framework for environmental chemicals, which, like drugs, are also xenobiotics. This research can help in human health risk assessment by a priori screening for neurotoxicity-causing agents.

A merged molecular representation deep learning method for blood-brain barrier permeability prediction

The ability of a compound to permeate across the blood-brain barrier (BBB) is a significant factor for central nervous system drug development. Thus, for speeding up the drug discovery process, it is crucial to perform high-throughput screenings to predict the BBB permeability of the candidate compounds. Although experimental methods are capable of determining BBB permeability, they are still cost-ineffective and time-consuming. To complement the shortcomings of existing methods, we present a deep learning-based multi-model framework model, called Deep-B3, to predict the BBB permeability of candidate compounds. In Deep-B3, the samples are encoded in three kinds of features, namely molecular descriptors and fingerprints, molecular graph and simplified molecular input line entry system (SMILES) text notation. The pre-trained models were built to extract latent features from the molecular graph and SMILES. These features depicted the compounds in terms of tabular data, image and text, respectively. The validation results yielded from the independent dataset demonstrated that the performance of Deep-B3 is superior to that of the state-of-the-art models. Hence, Deep-B3 holds the potential to become a useful tool for drug development. A freely available online web-server for Deep-B3 was established at http://cbcb.cdutcm.edu.cn/deepb3/, and the source code and dataset of Deep-B3 are available at https://github.com/GreatChenLab/Deep-B3.

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.

HPE-GCN: predicting efficacy of tonic formulae via graph convolutional networks integrating traditionally defined herbal properties

Chinese herbal formulae are the heritage of traditional Chinese medicine (TCM) in treating diseases through thousands of years. The formula function is not just a simple herbal efficacy addition, but produces complex and nonlinear relationships between different herbs and their overall efficacy, which brings challenges to the formula efficacy analysis. In our study, we proposed a model called HPE-GCN that combines graph convolutional networks (GCN) with TCM-defined herbal properties (TCM-HPs) to predict formulae efficacy. In addition, to process the unstructured natural language in the formula text, we proposed a weighting calculation method related to herb frequency and the number of herbs in a formula called Formula-Herb dependence degree (FHDD), to assess the dependency degree of a formula with its herbs. In our research, 214 classic tonic formulae from ancient TCM books such as Synopsis of the Golden Chamber, Jingyue's Complete Works and the Golden Mirror of Medicin were collected as datasets. The performance of HPE-GCN on multi-classification of tonic formulae reached the best result compared with classic machine learning models, such as support vector machine, naive Bayes, logistic regression, gradient boosting decision tree, and K-nearest neighbors. The evaluated index Macro-Precision, Macro-Recall, Macro-F1 of HPE-GCN on the test set were 87.70%, 84.08% and 83.51% respectively, increased by 7.27%, 7.41% and 7.30% respectively from second best compared models. GCN has the advantage of low-dimensional feature expression for herbs and formulae, and is an effective analysis tool for TCM research. HPE-GCN integrates TCM-HPs and fits the complex nonlinear mapping relationship between TCM-HPs and formulae efficacy, which provides new ideas for related research.

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.

Large-Scale Evaluation of Collision Cross Sections to Investigate Blood-Brain Barrier Permeation of Drugs

Successful drug administration to the central nervous system requires accurate adjustment of the drugs’ molecular properties. Therefore, structure-derived descriptors of potential brain therapeutic agents are essential for an early evaluation of pharmacokinetics during drug development. The collision cross section (CCS) of molecules was recently introduced as a novel measurable parameter to describe blood-brain barrier (BBB) permeation. This descriptor combines molecular information about mass, structure, volume, branching and flexibility. As these chemical properties are known to influence cerebral pharmacokinetics, CCS determination of new drug candidates may provide important additional spatial information to support existing models of BBB penetration of drugs. Besides measuring CCS, calculation is also possible; but however, the reliability of computed CCS values for an evaluation of BBB permeation has not yet been fully investigated. In this work, prediction tools based on machine learning were used to compute CCS values of a large number of compounds listed in drug libraries as negative or positive with respect to brain penetration (BBB⁺ and BBB⁻ compounds). Statistical evaluation of computed CCS and several other descriptors could prove the high value of CCS. Further, CCS-deduced maximum molecular size of BBB⁺ drugs matched the dimensions of BBB pores. A threshold for transcellular penetration and possible permeation through pore-like openings of cellular tight-junctions is suggested. In sum, CCS evaluation with modern in silico tools shows high potential for its use in the drug development process.

A curated diverse molecular database of blood-brain barrier permeability with chemical descriptors

The highly-selective blood-brain barrier (BBB) prevents neurotoxic substances in blood from crossing into the extracellular fluid of the central nervous system (CNS). As such, the BBB has a close relationship with CNS disease development and treatment, so predicting whether a substance crosses the BBB is a key task in lead discovery for CNS drugs. Machine learning (ML) is a promising strategy for predicting the BBB permeability, but existing studies have been limited by small datasets with limited chemical diversity. To mitigate this issue, we present a large benchmark dataset, B3DB, complied from 50 published resources and categorized based on experimental uncertainty. A subset of the molecules in B3DB has numerical log BB values (1058 compounds), while the whole dataset has categorical (BBB+ or BBB-) BBB permeability labels (7807). The dataset is freely available at https://github.com/theochem/B3DB and https://doi.org/10.6084/m9.figshare.15634230.v3 (version 3). We also provide some physicochemical properties of the molecules. By analyzing these properties, we can demonstrate some physiochemical similarities and differences between BBB+ and BBB- compounds.

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.

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.

Computer Assisted Models for Blood Brain Barrier Permeation of 1, 5-Benzodiazepines

AIM

To generate and validate predictive models for blood-brain permeation (BBB) of CNS molecules using the QSPR approach.

BACKGROUND

Prediction of molecules crossing BBB remains a challenge in drug delivery. Predictive models are designed for the evaluation of a set of preclinical drugs which may serve as alternatives for determining BBB permeation by experimentation.

OBJECTIVE

The objective of the present study was to generate QSPR models for the permeation of CNS molecules across BBB and its validation using existing in-house leads.

METHODS

The present study envisaged the determination of the set of molecular descriptors which are considered significant correlative factors for BBB permeation property. Quantitative Structure- Property Relationship (QSPR) approach was followed to describe the correlation between identified descriptors for 45 molecules and highest, moderate and least BBB permeation data. The molecular descriptors were selected based on drug-likeness, hydrophilicity, hydrophobicity, polar surface area, etc. of molecules that served the highest correlation with BBB permeation. The experimental data in terms of log BB were collected from available literature, subjected to 2D-QSPR model generation using a regression analysis method like Multiple Linear Regression (MLR).

RESULTS

The best QSPR model was Model 3, which exhibited regression coefficient as R²= 0.89, F = 36; Q²= 0.7805 and properties such as polar surface area, hydrophobic hydrophilic distance, electronegativity, etc., which were considered key parameters in the determination of the BBB permeability. The developed QSPR models were validated with in-house 1,5-benzodiazepines molecules and correlation studies were conducted between experimental and predicted BBB permeability.

CONCLUSION

The QSPR model 3 showed predictive results that were in good agreements with experimental results for blood-brain permeation. Thus, this model was found to be satisfactory in achieving a good correlation between selected descriptors and BBB permeation for benzodiazepines and tricyclic compounds.

Unravelling the potency of triazole analogues for inhibiting α-synuclein fibrillogenesis and in vitro disaggregation

A series of triazole-based compounds was synthesized using a click chemistry approach and evaluated for the inhibition of α-synuclein (α-syn) fibrillogenesis and its disaggregation. Compounds Tr3, Tr7, Tr12, Tr15, and Tr16 exhibited good effect in inhibiting α-syn fibrillogenesis confirmed by Thioflavin-T assay and fluorescence microscopy and α-syn disaggregation confirmed by fluorescence microscopy. Molecular docking was used to understand the plausible mechanism of the test compounds for inhibiting the α-syn fibrillogenesis and to verify the in vitro results. Compounds Tr3, Tr7, Tr12, Tr15 and Tr16 showed good binding interactions with the essential amino acid residues of α-syn. The compounds which were found to be good inhibitors or disaggregators had no toxic effects on the SH-SY5Y cell line. These compounds have the potential to be developed as therapeutic interventions against synucleinopathies including Parkinson's disease and Lewy body dementia.

Molecular Scaffold Hopping via Holistic Molecular Representation

Molecular descriptors encode a variety of molecular representations for computer-assisted drug discovery. Here, we focus on the Weighted Holistic Atom Localization and Entity Shape (WHALES) descriptors, which were originally designed for scaffold hopping from natural products to synthetic molecules. WHALES descriptors capture molecular shape and partial charges simultaneously. We introduce the key aspects of the WHALES concept and provide a step-by-step guide on how to use these descriptors for virtual compound screening and scaffold hopping. The results presented can be reproduced by using the code freely available from URL: github.com/ETHmodlab/scaffold_hopping_whales .

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.

Tuning Properties for Blood-Brain Barrier Permeation: A Statistics-Based Analysis

In the effort to define a set of rules useful in tuning the properties for a successful blood-brain barrier (BBB) permeation, we statistically analyzed a set of 328 compounds and correlated their experimental in vivo logBB with a series of computed descriptors. Contingency tables were constructed, observed and expected distributions were calculated, and chi-square (χ²) distributions were evaluated. This allowed to point out a significant dependence of certain physicochemical properties in influencing the BBB permeation. Of over 15 computed descriptors, 9 resulted to be particularly important showing highly significant χ² distribution: polar surface area (χ² = 66.79; p = 1.08 × 10^-13), nitrogen and oxygen count (χ² = 51.17; p = 2.06 × 10^-10), logP (χ² = 47.38; p = 1.27 × 10^-9), nitrogen count (χ² = 38.29; p = 9.77 × 10^-8), logD (χ² = 36.80; p = 36.80), oxygen count (χ² = 35.83; p = 3.13 × 10^-7), ionization state (χ² = 33.02, p = 3.19 × 10^-7), hydrogen bond acceptors (χ² = 30.80; p = 3.36 × 10^-6), and hydrogen bond donors (χ² = 29.29; p = 6.81 × 10^-6). Other parameters describing the mass and size of the molecules (molecular weight: 11.18; p = 2.46 × 10^-2) resulted in being not significant since the population within the observed and expected distribution was similar. Depending on the combination of the significant descriptors, we set a three cases probabilistic scenario (BBB⁺, BBB^-, BBB⁺/BBB^-) that would prospectively be used to tune properties for BBB permeation.

Efficient identification of novel anti-glioma lead compounds by machine learning models

Glioblastoma multiforme (GBM) is the most devastating and widespread primary central nervous system tumor. Pharmacological treatment of this malignance is limited by the selective permeability of the blood-brain barrier (BBB) and relies on a single drug, temozolomide (TMZ), thus making the discovery of new compounds challenging and urgent. Therefore, aiming to discover new anti-glioma drugs, we developed robust machine learning models for predicting anti-glioma activity and BBB penetration ability of new compounds. Using these models, we prioritized 41 compounds from our in-house library of compounds, for further in vitro testing against three glioma cell lines and astrocytes. Subsequently, the most potent and selective compounds were resynthesized and tested in vivo using an orthotopic glioma model. This approach revealed two lead candidates, 4m and 4n, which efficiently decreased malignant glioma development in mice, probably by inhibiting thioredoxin reductase activity, as shown by our enzymological assays. Moreover, these two compounds did not promote body weight reduction, death of animals, or altered hematological and toxicological markers, making then good candidates for lead optimization as anti-glioma drug candidates.

Exploring the Pharmacological Mechanism of the Herb Pair "HuangLian-GanJiang" against Colorectal Cancer Based on Network Pharmacology

Since the herb pair Huang Lian-Gan Jiang (HL-GJ) was put forward as conventional compatibility for cold-heat regulation in the middle energizer in the theory of Traditional Chinese Medicine (TCM), their therapeutic effects were observed on the prevention and treatment of intestinal inflammation and tumors including colorectal cancer (CRC). However, the active compounds, crucial targets, and related pathways of HL-GJ against CRC remained unclear. The purpose of this research was to establish a comprehensive and systemic approach that could identify the active compounds, excavate crucial targets, and reveal anti-CRC mechanisms of HL-GJ against CRC based on network pharmacology. We used methods including chemical compound screening based on absorption, distribution, metabolism, and excretion (ADME), compound target prediction, CRC target collection, network construction and analysis, Gene Ontology (GO), and pathway analysis. In this study, eight main active compounds of HL-GJ were identified, including Gingerenone C, Isogingerenone B, 5,8-dihydroxy-2-(2-phenylethyl) Chromone, 2,3,4-trihydroxy-benzenepropanoic acid, 3,4-dihydroxyphenylethyl Alcohol Glucoside, 3-carboxy-4-hydroxy-phenoxy Glucoside, Moupinamide, and Obaculactone. HRAS, KRAS, PIK3CA, PDE5A, PPARG, TGFBR1, and TGFBR2 were identified as crucial targets of HL-GJ against CRC. There were mainly 500 biological processes and 70 molecular functions regulated during HL-GJ against CRC (P < 0.001). There were mainly 162 signaling pathways contributing to therapeutic effects (P < 0.001), the top 10 of which included DAP12 signaling, signaling by PDGF, signaling by EGFR, NGF signaling via TRKA from the plasma membrane, signaling by NGF, downstream signal transduction, DAP12 interactions, signaling by VEGF, signaling by FGFR3, and signaling by FGFR4. The study established a comprehensive and systematic paradigm to understand the pharmacological mechanisms of multiherb compatibility such as an herb pair, which might accelerate the development and modernization of TCM.

To Pass or Not To Pass: Predicting the Blood-Brain Barrier Permeability with the 3D-RISM-KH Molecular Solvation Theory

Predicting the ability of chemical species to cross the blood-brain barrier (BBB) is an active field of research for development and mechanistic understanding in the pharmaceutical industry. Here, we report the BBB permeability of a large data set of compounds by incorporating molecular solvation energy descriptors computed by the 3D-RISM-KH molecular solvation theory. We have been able to show, for the first time, that the computed excess chemical potential in different solvents can be successfully used to predict permeability of compounds in a binary manner (yes/no) via a minimum-descriptor-based model. Our findings successfully combine the molecular solvation theory with the machine learning approach to address one of the most daunting challenges in predictive structure-activity relationship modeling. The workflow presented in this work is simple enough to be used by nonexperts with ease.

Artificial Intelligence in Drug Treatment

The most common applications of artificial intelligence (AI) in drug treatment have to do with matching patients to their optimal drug or combination of drugs, predicting drug-target or drug-drug interactions, and optimizing treatment protocols. This review outlines some of the recently developed AI methods aiding the drug treatment and administration process. Selection of the best drug(s) for a patient typically requires the integration of patient data, such as genetics or proteomics, with drug data, like compound chemical descriptors, to score the therapeutic efficacy of drugs. The prediction of drug interactions often relies on similarity metrics, assuming that drugs with similar structures or targets will have comparable behavior or may interfere with each other. Optimizing the dosage schedule for administration of drugs is performed using mathematical models to interpret pharmacokinetic and pharmacodynamic data. The recently developed and powerful models for each of these tasks are addressed, explained, and analyzed here.

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

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.

Improved Classification of Blood-Brain-Barrier Drugs Using Deep Learning

Blood-Brain-Barrier (BBB) is a strict permeability barrier for maintaining the Central Nervous System (CNS) homeostasis. One of the most important conditions to judge a CNS drug is to figure out whether it has BBB permeability or not. In the past 20 years, the existing prediction approaches are usually based on the data of the physical characteristics and chemical structure of drugs. However, these methods are usually only applicable to small molecule compounds based on passive diffusion through BBB. To deal this problem, one of the most famous methods is multi-core SVM method, which is based on clinical phenotypes about Drug Side Effects and Drug Indications to predict drug penetration of BBB. This paper proposed a Deep Learning method to predict the Blood-Brain-Barrier permeability based on the clinical phenotypes data. The validation result on three datasets proved that Deep Learning method achieves better performance than the other existing methods. The average accuracy of our method reaches 0.97, AUC reaches 0.98, and the F1 score is 0.92. The results proved that Deep Learning methods can significantly improve the prediction accuracy of drug BBB permeability and it can help researchers to reduce clinical trials and find new CNS drugs.

RP-18 HPLC Analysis of Drugs’ Ability to Cross the Blood-Brain Barrier

One hundred ten compounds of diverse structures (actives and excipients used in pharmaceutical preparations) were studied by RP-18 HPLC with acetonitrile-pH 7.4 phosphate buffer 1 : 1 (v/v) as the mobile phase. The relationships between the BBB permeation coefficients and the chromatographic parameters log k and (log k)/PSA were compared to those between the blood-brain barrier (BBB) permeation parameters and the RP-18 TLC descriptors Rf and Rf/PSA known from our earlier studies. It was found that the correlations between the BBB permeability and the HPLC data are slightly worse than those achieved for the thin-layer chromatographic data. MLR analysis based upon the physicochemical data confirmed the value of the molecular descriptors, related to the CNS bioavailability. These variables, combined with the HPLC data, made it possible to generate computational models, explaining 70–96% of the total variance of the CNS bioavailability. Contrary to TLC Rf, the advantage of the modification of HPLC log k with PSA (polar surface area) has not been confirmed and the results obtained with log k are superior to those obtained after a novel (log k)/PSA parameter has been introduced. Establishing a firm threshold limit of (log k)/PSA, log k, or even k and k/PSA to distinguish between the CNS+ and CNS− compounds was impossible. On the other hand, discriminant function analyses involving log k and (log k)/PSA as discriminating variables separated the CNS+ and CNS− compounds with the success rate ca. 90%. On the basis of these results, it was concluded that the RP-18 HPLC analytical models are entirely successful in studies and predictions of the BBB permeability.

Predicting Blood⁻Brain Barrier Permeability of Marine-Derived Kinase Inhibitors Using Ensemble Classifiers Reveals Potential Hits for Neurodegenerative Disorders

The recent success of small-molecule kinase inhibitors as anticancer drugs has generated significant interest in their application to other clinical areas, such as disorders of the central nervous system (CNS). However, most kinase inhibitor drug candidates investigated to date have been ineffective at treating CNS disorders, mainly due to poor blood⁻brain barrier (BBB) permeability. It is, therefore, imperative to evaluate new chemical entities for both kinase inhibition and BBB permeability. Over the last 35 years, marine biodiscovery has yielded 471 natural products reported as kinase inhibitors, yet very few have been evaluated for BBB permeability. In this study, we revisited these marine natural products and predicted their ability to cross the BBB by applying freely available open-source chemoinformatics and machine learning algorithms to a training set of 332 previously reported CNS-penetrant small molecules. We evaluated several regression and classification models, and found that our optimised classifiers (random forest, gradient boosting, and logistic regression) outperformed other models, with overall cross-validated model accuracies of 80%⁻82% and 78%⁻80% on external testing. All 3 binary classifiers predicted 13 marine-derived kinase inhibitors with appropriate physicochemical characteristics for BBB permeability.

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

Blood-brain barrier (BBB) permeability of a compound determines whether the compound can effectively enter the brain. It is an essential property which must be accounted for in drug discovery with a target in the brain. Several computational methods have been used to predict the BBB permeability. In particular, support vector machine (SVM), which is a kernel-based machine learning method, has been used popularly in this field. For SVM training and prediction, the compounds are characterized by molecular descriptors. Some SVM models were based on the use of molecular property-based descriptors (including 1D, 2D, and 3D descriptors) or fragment-based descriptors (known as the fingerprints of a molecule). The selection of descriptors is critical for the performance of a SVM model. In this study, we aimed to develop a generally applicable new SVM model by combining all of the features of the molecular property-based descriptors and fingerprints to improve the accuracy for the BBB permeability prediction. The results indicate that our SVM model has improved accuracy compared to the currently available models of the BBB permeability prediction.

Machine Learning-Assisted Network Inference Approach to Identify a New Class of Genes that Coordinate the Functionality of Cancer Networks

Emerging evidence indicates the existence of a new class of cancer genes that act as "signal linkers" coordinating oncogenic signals between mutated and differentially expressed genes. While frequently mutated oncogenes and differentially expressed genes, which we term Class I cancer genes, are readily detected by most analytical tools, the new class of cancer-related genes, i.e., Class II, escape detection because they are neither mutated nor differentially expressed. Given this hypothesis, we developed a Machine Learning-Assisted Network Inference (MALANI) algorithm, which assesses all genes regardless of expression or mutational status in the context of cancer etiology. We used 8807 expression arrays, corresponding to 9 cancer types, to build more than 2 × 108 Support Vector Machine (SVM) models for reconstructing a cancer network. We found that ~3% of ~19,000 not differentially expressed genes are Class II cancer gene candidates. Some Class II genes that we found, such as SLC19A1 and ATAD3B, have been recently reported to associate with cancer outcomes. To our knowledge, this is the first study that utilizes both machine learning and network biology approaches to uncover Class II cancer genes in coordinating functionality in cancer networks and will illuminate our understanding of how genes are modulated in a tissue-specific network contribute to tumorigenesis and therapy development.

Predict drug permeability to blood-brain-barrier from clinical phenotypes: drug side effects and drug indications

Motivation

Blood-Brain-Barrier (BBB) is a rigorous permeability barrier for maintaining homeostasis of Central Nervous System (CNS). Determination of compound's permeability to BBB is prerequisite in CNS drug discovery. Existing computational methods usually predict drug BBB permeability from chemical structure and they generally apply to small compounds passing BBB through passive diffusion. As abundant information on drug side effects and indications has been recorded over time through extensive clinical usage, we aim to explore BBB permeability prediction from a new angle and introduce a novel approach to predict BBB permeability from drug clinical phenotypes (drug side effects and drug indications). This method can apply to both small compounds and macro-molecules penetrating BBB through various mechanisms besides passive diffusion.

Results

We composed a training dataset of 213 drugs with known brain and blood steady-state concentrations ratio and extracted their side effects and indications as features. Next, we trained SVM models with polynomial kernel and obtained accuracy of 76.0%, AUC 0.739, and F 1 score (macro weighted) 0.760 with Monte Carlo cross validation. The independent test accuracy was 68.3%, AUC 0.692, F 1 score 0.676. When both chemical features and clinical phenotypes were available, combining the two types of features achieved significantly better performance than chemical feature based approach (accuracy 85.5% versus 72.9%, AUC 0.854 versus 0.733, F 1 score 0.854 versus 0.725; P  < e -90 ). We also conducted de novo prediction and identified 110 drugs in SIDER database having the potential to penetrate BBB, which could serve as start point for CNS drug repositioning research.

Availability and Implementation

https://github.com/bioinformatics-gao/CASE-BBB-prediction-Data.

Contact

rxx@case.edu.

Supplementary information

Supplementary data are available at Bioinformatics online.

A novel descriptor based on atom-pair properties

BACKGROUND

Molecular descriptors have been widely used to predict biological activities and physicochemical properties or to analyze chemical libraries on the basis of similarity. Although fingerprints and properties are generally used as descriptors, neither is perfect for these purposes. A fingerprint can distinguish between molecules, whereas a property may not do the same in certain cases, and vice versa. When the number of the training set is especially small, the construction of good predictive models is difficult. Herein, a novel descriptor integrating mutually compensating fingerprint and property characteristics is described. The format of this descriptor is not conventional. It has two dimensions with variable length in one dimension to represent one molecule. This format is not acceptable for any machine learning methods. Therefore the distance between molecules has been newly defined for application to machine learning techniques. The evaluation of this descriptor, as applied to classification tasks, was performed using a support vector machine after the features of the descriptor had been optimized by a genetic algorithm.

RESULTS

Because the optimizing feature is time-intensive due to the complicated calculation of distances between molecules, the optimization was forced to stop before it was completed. As a result, no remarkable improvement was observed in the classification results for the new descriptor compared with those for other descriptors in any evaluation set used in this work. However, extremely low accuracies were also not found for any set.

CONCLUSIONS

The novel descriptor proposed in this work can potentially be used to make highly accurate predictive models. This new concept in descriptors is expected to be useful for developing novel predictive methods with quick training and high accuracy.

Systems pharmacology exploration of botanic drug pairs reveals the mechanism for treating different diseases

Multi-herb therapy has been widely used in Traditional Chinese medicine and tailored to meet the specific needs of each individual. However, the potential molecular or systems mechanisms of them to treat various diseases have not been fully elucidated. To address this question, a systems pharmacology approach, integrating pharmacokinetics, pharmacology and systems biology, is used to comprehensively identify the drug-target and drug-disease networks, exemplified by three representative Radix Salviae Miltiorrhizae herb pairs for treating various diseases (coronary heart disease, dysmenorrheal and nephrotic syndrome). First, the compounds evaluation and the multiple targeting technology screen the active ingredients and identify the specific targets for each herb of three pairs. Second, the herb feature mapping reveals the differences in chemistry and pharmacological synergy between pairs. Third, the constructed compound-target-disease network explains the mechanisms of treatment for various diseases from a systematic level. Finally, experimental verification is taken to confirm our strategy. Our work provides an integrated strategy for revealing the mechanism of synergistic herb pairs, and also a rational way for developing novel drug combinations for treatments of complex diseases.

Reliability of In Vitro and In Vivo Methods for Predicting the Effect of P-Glycoprotein on the Delivery of Antidepressants to the Brain

As the effect of P-glycoprotein (P-gp) transport on antidepressant delivery has been extensively evaluated using in vitro cellular and in vivo rodent models, an increasing number of publications have addressed the effect of P-gp in limiting brain penetration of antidepressants and causing treatment-resistant depression in current clinical therapies. However, contradictory results have been observed in different systems. It is of vital importance to understand the potential for drug interactions related to P-gp at the blood-brain barrier (BBB), and whether coadministration of a P-gp inhibitor together with an antidepressant is a good clinical strategy for dosing of patients with treatment-resistant depression. In this review, the complicated construction of the BBB, the transport mechanisms for compounds that cross the BBB, and the basic characteristics of antidepressants are illustrated. Further, the reliability of different systems related to antidepressant brain delivery, including in vitro bidirectional transport cell lines, in vivo Mdr1 knockout mice, and chemical inhibition studies in rodents are analyzed, supporting a low possibility that P-gp affects currently marketed antidepressants when these results are extrapolated to the human BBB. These findings can also be applied to other central nervous system drugs.

Molecular determinants of blood-brain barrier permeation

The blood-brain barrier (BBB) is a microvascular unit which selectively regulates the permeability of drugs to the brain. With the rise in CNS drug targets and diseases, there is a need to be able to accurately predict a priori which compounds in a company database should be pursued for favorable properties. In this review, we will explore the different computational tools available today, as well as underpin these to the experimental methods used to determine BBB permeability. These include in vitro models and the in vivo models that yield the dataset we use to generate predictive models. Understanding of how these models were experimentally derived determines our accurate and predicted use for determining a balance between activity and BBB distribution.

Recent progresses in the exploration of machine learning methods as in-silico ADME prediction tools

In-silico methods have been explored as potential tools for assessing ADME and ADME regulatory properties particularly in early drug discovery stages. Machine learning methods, with their ability in classifying diverse structures and complex mechanisms, are well suited for predicting ADME and ADME regulatory properties. Recent efforts have been directed at the broadening of application scopes and the improvement of predictive performance with particular focuses on the coverage of ADME properties, and exploration of more diversified training data, appropriate molecular features, and consensus modeling. Moreover, several online machine learning ADME prediction servers have emerged. Here we review these progresses and discuss the performances, application prospects and challenges of exploring machine learning methods as useful tools in predicting ADME and ADME regulatory properties.

Towards Better BBB Passage Prediction Using an Extensive and Curated Data Set

In the present report, the challenging task of drug delivery across the blood-brain barrier (BBB) is addressed via a computational approach. The BBB passage was modeled using classification and regression schemes on a novel extensive and curated data set (the largest to the best of our knowledge) in terms of log BB. Prior to the model development, steps of data analysis that comprise chemical data curation, structural, cutoff and cluster analysis (CA) were conducted. Linear Discriminant Analysis (LDA) and Multiple Linear Regression (MLR) were used to fit classification and correlation functions. The best LDA-based model showed overall accuracies over 85 % and 83 % for the training and test sets, respectively. Also a MLR-based model with acceptable explanation of more than 69 % of the variance in the experimental log BB was developed. A brief and general interpretation of proposed models allowed the estimation on how 'near' our computational approach is to the factors that determine the passage of molecules through the BBB. In a final effort some popular and powerful Machine Learning methods were considered. Comparable or similar performance was observed respect to the simpler linear techniques. Most of the compounds with anomalous behavior were put aside into a set denoted as controversial set and discussion regarding to these compounds is provided. Finally, our results were compared with methodologies previously reported in the literature showing comparable to better results. The results could represent useful tools available and reproducible by all scientific community in the early stages of neuropharmaceutical drug discovery/development projects.

Qualitative and quantitative structure-activity relationship modelling for predicting blood-brain barrier permeability of structurally diverse chemicals

In this study, structure-activity relationship (SAR) models have been established for qualitative and quantitative prediction of the blood-brain barrier (BBB) permeability of chemicals. The structural diversity of the chemicals and nonlinear structure in the data were tested. The predictive and generalization ability of the developed SAR models were tested through internal and external validation procedures. In complete data, the QSAR models rendered ternary classification accuracy of >98.15%, while the quantitative SAR models yielded correlation (r(2)) of >0.926 between the measured and the predicted BBB permeability values with the mean squared error (MSE) <0.045. The proposed models were also applied to an external new in vitro data and yielded classification accuracy of >82.7% and r(2) > 0.905 (MSE < 0.019). The sensitivity analysis revealed that topological polar surface area (TPSA) has the highest effect in qualitative and quantitative models for predicting the BBB permeability of chemicals. Moreover, these models showed predictive performance superior to those reported earlier in the literature. This demonstrates the appropriateness of the developed SAR models to reliably predict the BBB permeability of new chemicals, which can be used for initial screening of the molecules in the drug development process.

Drug/nondrug classification using Support Vector Machines with various feature selection strategies

In conjunction with the advance in computer technology, virtual screening of small molecules has been started to use in drug discovery. Since there are thousands of compounds in early-phase of drug discovery, a fast classification method, which can distinguish between active and inactive molecules, can be used for screening large compound collections. In this study, we used Support Vector Machines (SVM) for this type of classification task. SVM is a powerful classification tool that is becoming increasingly popular in various machine-learning applications. The data sets consist of 631 compounds for training set and 216 compounds for a separate test set. In data pre-processing step, the Pearson's correlation coefficient used as a filter to eliminate redundant features. After application of the correlation filter, a single SVM has been applied to this reduced data set. Moreover, we have investigated the performance of SVM with different feature selection strategies, including SVM-Recursive Feature Elimination, Wrapper Method and Subset Selection. All feature selection methods generally represent better performance than a single SVM while Subset Selection outperforms other feature selection methods. We have tested SVM as a classification tool in a real-life drug discovery problem and our results revealed that it could be a useful method for classification task in early-phase of drug discovery.

A method to predict blood-brain barrier permeability of drug-like compounds using molecular dynamics simulations

The blood-brain barrier (BBB) is formed by specialized tight junctions between endothelial cells that line brain capillaries to create a highly selective barrier between the brain and the rest of the body. A major problem to overcome in drug design is the ability of the compound in question to cross the BBB. Neuroactive drugs are required to cross the BBB to function. Conversely, drugs that target other parts of the body ideally should not cross the BBB to avoid possible psychotropic side effects. Thus, the task of predicting the BBB permeability of new compounds is of great importance. Two gold-standard experimental measures of BBB permeability are logBB (the concentration of drug in the brain divided by concentration in the blood) and logPS (permeability surface-area product). Both methods are time-consuming and expensive, and although logPS is considered the more informative measure, it is lower throughput and more resource intensive. With continual increases in computer power and improvements in molecular simulations, in silico methods may provide viable alternatives. Computational predictions of these two parameters for a sample of 12 small molecule compounds were performed. The potential of mean force for each compound through a 1,2-dioleoyl-sn-glycero-3-phosphocholine bilayer is determined by molecular dynamics simulations. This system setup is often used as a simple BBB mimetic. Additionally, one-dimensional position-dependent diffusion coefficients are calculated from the molecular dynamics trajectories. The diffusion coefficient is combined with the free energy landscape to calculate the effective permeability (Peff) for each sample compound. The relative values of these permeabilities are compared to experimentally determined logBB and logPS values. Our computational predictions correlate remarkably well with both logBB (R(2) = 0.94) and logPS (R(2) = 0.90). Thus, we have demonstrated that this approach may have the potential to provide reliable, quantitatively predictive BBB permeability, using a relatively quick, inexpensive method.

A prediction model of drug-induced ototoxicity developed by an optimal support vector machine (SVM) method

Drug-induced ototoxicity, as a toxic side effect, is an important issue needed to be considered in drug discovery. Nevertheless, current experimental methods used to evaluate drug-induced ototoxicity are often time-consuming and expensive, indicating that they are not suitable for a large-scale evaluation of drug-induced ototoxicity in the early stage of drug discovery. We thus, in this investigation, established an effective computational prediction model of drug-induced ototoxicity using an optimal support vector machine (SVM) method, GA-CG-SVM. Three GA-CG-SVM models were developed based on three training sets containing agents bearing different risk levels of drug-induced ototoxicity. For comparison, models based on naïve Bayesian (NB) and recursive partitioning (RP) methods were also used on the same training sets. Among all the prediction models, the GA-CG-SVM model II showed the best performance, which offered prediction accuracies of 85.33% and 83.05% for two independent test sets, respectively. Overall, the good performance of the GA-CG-SVM model II indicates that it could be used for the prediction of drug-induced ototoxicity in the early stage of drug discovery.