In Silico Prediction of Blood-Brain Barrier Permeability of Compounds by Machine Learning and Resampling 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.

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.

Expanding Predictive Capacities in Toxicology: Insights from Hackathon-Enhanced Data and Model Aggregation

In the realm of predictive toxicology for small molecules, the applicability domain of QSAR models is often limited by the coverage of the chemical space in the training set. Consequently, classical models fail to provide reliable predictions for wide classes of molecules. However, the emergence of innovative data collection methods such as intensive hackathons have promise to quickly expand the available chemical space for model construction. Combined with algorithmic refinement methods, these tools can address the challenges of toxicity prediction, enhancing both the robustness and applicability of the corresponding models. This study aimed to investigate the roles of gradient boosting and strategic data aggregation in enhancing the predictivity ability of models for the toxicity of small organic molecules. We focused on evaluating the impact of incorporating fragment features and expanding the chemical space, facilitated by a comprehensive dataset procured in an open hackathon. We used gradient boosting techniques, accounting for critical features such as the structural fragments or functional groups often associated with manifestations of toxicity.

Artificial intelligence for drug discovery and development in Alzheimer's disease

The complex molecular mechanism and pathophysiology of Alzheimer's disease (AD) limits the development of effective therapeutics or prevention strategies. Artificial Intelligence (AI)-guided drug discovery combined with genetics/multi-omics (genomics, epigenomics, transcriptomics, proteomics, and metabolomics) analysis contributes to the understanding of the pathophysiology and precision medicine of the disease, including AD and AD-related dementia. In this review, we summarize the AI-driven methodologies for AD-agnostic drug discovery and development, including de novo drug design, virtual screening, and prediction of drug-target interactions, all of which have shown potentials. In particular, AI-based drug repurposing emerges as a compelling strategy to identify new indications for existing drugs for AD. We provide several emerging AD targets from human genetics and multi-omics findings and highlight recent AI-based technologies and their applications in drug discovery using AD as a prototypical example. In closing, we discuss future challenges and directions in AI-based drug discovery for AD and other neurodegenerative diseases.

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.Communicated by Ramaswamy H. Sarma.

Microphysiological Blood-Brain Barrier Systems for Disease Modeling and Drug Development

The blood-brain barrier (BBB) is a highly controlled microenvironment that regulates the interactions between cerebral blood and brain tissue. Due to its selectivity, many therapeutics targeting various neurological disorders are not able to penetrate into brain tissue. Pre-clinical studies using animals and other in vitro platforms have not shown the ability to fully replicate the human BBB leading to the failure of a majority of therapeutics in clinical trials. However, recent innovations in vitro and ex vivo modeling called organs-on-chips have shown the potential to create more accurate disease models for improved drug development. These microfluidic platforms induce physiological stressors on cultured cells and are able to generate more physiologically accurate BBBs compared to previous in vitro models. In this review, different approaches to create BBBs-on-chips are explored alongside their application in modeling various neurological disorders and potential therapeutic efficacy. Additionally, organs-on-chips use in BBB drug delivery studies is discussed, and advances in linking brain organs-on-chips onto multiorgan platforms to mimic organ crosstalk are reviewed.

Neuronanomedicine for Alzheimer's and Parkinson's disease: Current progress and a guide to improve clinical translation

Neuronanomedicine is an emerging multidisciplinary field that aims to create innovative nanotechnologies to treat major neurodegenerative disorders, such as Alzheimer's (AD) and Parkinson's disease (PD). A key component of neuronanomedicine are nanoparticles, which can improve drug properties and demonstrate enhanced safety and delivery across the blood-brain barrier, a major improvement on existing therapeutic approaches. In this review, we critically analyze the latest nanoparticle-based strategies to modify underlying disease pathology to slow or halt AD/PD progression. We find that a major roadblock for neuronanomedicine translation to date is a poor understanding of how nanoparticles interact with biological systems (i.e., bio-nano interactions), which is partly due to inconsistent reporting in published works. Accordingly, this review makes a set of specific recommendations to help guide researchers to harness the unique properties of nanoparticles and thus realise breakthrough treatments for AD/PD.

A Comprehensive Study on Nanoparticle Drug Delivery to the Brain: Application of Machine Learning Techniques

The delivery of drugs to specific target tissues and cells in the brain poses a significant challenge in brain therapeutics, primarily due to limited understanding of how nanoparticle (NP) properties influence drug biodistribution and off-target organ accumulation. This study addresses the limitations of previous research by using various predictive models based on collection of large data sets of 403 data points incorporating both numerical and categorical features. Machine learning techniques and comprehensive literature data analysis were used to develop models for predicting NP delivery to the brain. Furthermore, the physicochemical properties of loaded drugs and NPs were analyzed through a systematic analysis of pharmacodynamic parameters such as plasma area under the curve. The analysis employed various linear models, with a particular emphasis on linear mixed-effect models (LMEMs) that demonstrated exceptional accuracy. The model was validated via the preparation and administration of two distinct NP formulations via the intranasal and intravenous routes. Among the various modeling approaches, LMEMs exhibited superior performance in capturing underlying patterns. Factors such as the release rate and molecular weight had a negative impact on brain targeting. The model also suggests a slightly positive impact on brain targeting when the drug is a P-glycoprotein substrate.

Synthesis, Antimalarial, Antileishmanial, and Cytotoxicity Activities and Preliminary In Silico ADMET Studies of 2-(7-Chloroquinolin-4-ylamino)ethyl Benzoate Derivatives

A series of heterocyclic chloroquine hybrids, containing a chain of two carbon atoms at position four of the quinolinic chain and acting as a link between quinoline and several benzoyl groups, is synthesized and screened in vitro as an inhibitor of β-hematin formation and in vivo for its antimalarial activity against chloroquine-sensitive strains of Plasmodium berghei ANKA in this study. The compounds significantly reduced haeme crystallization, with IC50 values < 10 µM. The values were comparable to chloroquine's, with an IC50 of 1.50 ± 0.01 µM. The compounds 4c and 4e prolonged the average survival time of the infected mice to 16.7 ± 2.16 and 14.4 ± 1.20 days, respectively. We also studied the effect of the compounds 4b, 4c, and 4e on another important human parasite, Leishmania mexicana, which is responsible for cutaneous leishmaniasis, demonstrating a potential leishmanicidal effect against promasigotes, with an IC50 < 10 µM. Concerning the possible mechanism of action of these compounds on Lesihmania mexicana, we performed experiments demonstrating that these three compounds could induce the collapse of the parasite mitochondrial electrochemical membrane potential (Δφ). The in vitro cytotoxicity assays against mammalian cancerous and noncancerous human cell lines showed that the studied compounds exhibit low cytotoxic effects. The ADME/Tox analysis predicted moderate lipophilicity values, low unbound fraction values, and a poor distribution for these compounds. Therefore, moderate bioavailability was expected. We calculated other molecular descriptors, such as the topological polar surface area, according to Veber's rules, and except for 2 and 4i, the rest of the compounds violated this descriptor, demonstrating the low antimalarial activity of our compounds in vivo.

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.

Therapeutic Potential of the Genus Zanthoxylum Phytochemicals: A Theoretical ADME/Tox Analysis

Natural products (NPs) are essential in the search for new drugs to treat a wide range of diseases, including infectious and malignant disorders. However, despite the discovery of many bioactive NPs, they often do not make it to market as drugs due to toxicity and other challenges. The development of NPs into drugs is a long and expensive process, and many promising compounds are abandoned along the way. These molecules require in silico ADMET profiling in order to speed up their development into drugs lower costs, and the high attrition rate. The objective of this work was to produce thorough ADMET profiles of secondary metabolites from several classes that were isolated from Zanthoxylum species. The genus has a long history of therapeutic use, including treating tumours, hypertension, gonorrhoea, coughs, bilharzia, chest pains, and toothaches. The study used a dataset of 406 compounds from the genus for theoretical ADMET analysis. The findings revealed that 81% of the compounds met Lipinski's rule of five, indicating good oral bioavailability. The drug-likeness criteria were taken into account, with percentages ranging from 66.2 to 88.1 percent. Additionally, 9.2% of the compounds were predicted to be lead-like, demonstrating their potential as promising drug development candidates. Interestingly, none of the compounds inhibited hERG I, while 33% inhibited hERG II, potentially having cardiac implications. Additionally, 30% of the compounds exhibited AMES toxicity inhibition, while 23.6% were identified as hepatotoxic and 22.2% would cause skin sensitivity. Moreover, 81.8% of the compounds demonstrated high intestinal absorption, making them desirable for oral drugs. In conclusion, these findings highlight the diverse properties of the investigated compounds and their potential for drug development.

Unraveling the Interaction Mechanism of the Compounds From Cladophora sp to Recognize Prospective Larvicidal and Bactericidal Activities: In vitro and In Silico Approaches

The present investigation aims to validate the larvicidal and antibacterial potential of Cladophora sp through in vitro and in silico approaches. The presence of phytoconstituents, functional groups and the compounds responsible for antibacterial and larvicidal activity were assessed through FT-IR and GC-MS analyses which unveiled the existence of active secondary metabolites, hydroxyl, alkane and carbonyl groups. The larvicidal and antibacterial activity of algal extract were examined and revealed complete mortality and substantial zone of inhibition was observed against Culex quinquefasciatus and E. coli. To support the in vitro investigation in silico studies were performed. Molecular docking investigations of the selected compounds from GC-MS which exhibited favorable agreement with drug likeness and ADMET properties indicated robust interactions with the larvicidal and bacterial proteins showcasing considerable binding affinities. Notably, 1,2,4-Oxadiazole, 3-(1,3-benzodioxol-5-yl)-5-[(4-iodo-1H-pyrazol-1-yl) methyl]- exhibited strong interactions with the target proteins. Density Functional Theory revealed that the energy gap of the lead compound was reduced and substantiates the occurrence of intermolecular charge transfer. Molecular Dynamic simulations confirms the stability and flexibility of the lead compound. Hence, this investigation offers computational perspectives on the molecular interactions of Cladophora sp, suggesting its suitability as a promising biocontrol agent.

A machine learning-based quantitative model (LogBB_Pred) to predict the blood-brain barrier permeability (logBB value) of drug compounds

MOTIVATION

Efficient assessment of the blood-brain barrier (BBB) penetration ability of a drug compound is one of the major hurdles in central nervous system drug discovery since experimental methods are costly and time-consuming. To advance and elevate the success rate of neurotherapeutic drug discovery, it is essential to develop an accurate computational quantitative model to determine the absolute logBB value (a logarithmic ratio of the concentration of a drug in the brain to its concentration in the blood) of a drug candidate.

RESULTS

Here, we developed a quantitative model (LogBB_Pred) capable of predicting a logBB value of a query compound. The model achieved an R2 of 0.61 on an independent test dataset and outperformed other publicly available quantitative models. When compared with the available qualitative (classification) models that only classified whether a compound is BBB-permeable or not, our model achieved the same accuracy (0.85) with the best qualitative model and far-outperformed other qualitative models (accuracies between 0.64 and 0.70). For further evaluation, our model, quantitative models, and the qualitative models were evaluated on a real-world central nervous system drug screening library. Our model showed an accuracy of 0.97 while the other models showed an accuracy in the range of 0.29-0.83. Consequently, our model can accurately classify BBB-permeable compounds as well as predict the absolute logBB values of drug candidates.

AVAILABILITY AND IMPLEMENTATION

Web server is freely available on the web at http://ssbio.cau.ac.kr/software/logbb_pred/. The data used in this study are available to download at http://ssbio.cau.ac.kr/software/logbb_pred/dataset.zip.

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.

DeepGRID: Deep Learning Using GRID Descriptors for BBB Prediction

Deep Learning approaches are able to automatically extract relevant features from the input data and capture nonlinear relationships between the input and output. In this work, we present the GRID-derived AI (GrAId) descriptors, a simple modification to GRID MIFs that facilitate their use in combination with Convolutional Neural Networks (CNNs) to build Deep Learning models in a rotationally, conformationally, and alignment-independent approach we are calling DeepGRID. To our knowledge, this is the first time that GRID MIFs have been combined with CNNs in a Deep Learning approach. We applied the approach to build regression and classification models for blood-brain barrier permeation, an important factor when designing CNS drugs and conversely when designing to avoid off-target effects for CNS-inactive drugs. The VolSurf approach was one of the first to successfully model this property from three-dimensional structures, using descriptors derived from their GRID Molecular Interaction Fields (MIFs) in combination with PLS. We compared the DeepGRID models with others built using the hand-crafted VolSurf descriptors in combination with both PLS and Random Forest (RF). Both the DeepGRID and RF regression models performed best according to the % of compounds with a Geometric Mean Fold Error (GMFE) within 2-fold of the experimental data. Applying these regression models as classifiers, for the smaller 332 and 416 compound data sets all models performed well with ROC AUC values of ∼0.9 on the external test set. For the larger 2105 compound data set, the DeepGRID classifier performed the best with an AUC of 0.87 on the external test set with the RF model having an AUC of 0.84 and the original VolSurf lgBB model having an AUC of 0.83.

How effective are ionization state-based QSPKR models at predicting pharmacokinetic parameters in humans?

Optimizing the pharmacokinetics (PK) of a drug candidate to support oral dosing is a key challenge in drug development. PK parameters are usually estimated from the concentration-time profile following intravenous administration; however, traditional methods are time-consuming and expensive. In recent years, quantitative structure-pharmacokinetic relationship (QSPKR), an in silico tool that aims to develop a mathematical relationship between the structure of a molecule and its PK properties, has emerged as a useful alternative to experimental testing. Due to the complex nature of the various processes involved in dictating the fate of a drug, the development of adequate QSPKR models that can be used in real-world pre-screening situations has proved challenging. Given the crucial role played by a molecule's ionization state in determining its PK properties, this work aims to build predictive QSPKR models for PK parameters in humans using an ionization state-based strategy. We divide a high-quality dataset into clusters based on ionization state at physiological pH and build global and ion subset-based 'local' models for three major PK parameters: plasma clearance (CL), steady-state volume of distribution (VDss), and half-life (t1/2). We use a robust methodology developed in our lab entitled 'EigenValue ANalySis' that accounts for the stereospecificity in drug disposition and use the support vector machine algorithm for model building. Our findings suggest that categorizing compounds in accordance with ionization state does not result in improved QSPKR models. The narrow ranges in the endpoints along with redundancies in the data adversely affect the ion subset-based QSPKR models. We suggest alternative approaches such as elimination route-based models that account for drug-transporter interactions for CL and chemotype-specific QSPKR for VDss.

Explaining Blood-Brain Barrier Permeability of Small Molecules by Integrated Analysis of Different Transport Mechanisms

The blood-brain barrier (BBB) represents a major obstacle to delivering drugs to the central nervous system (CNS), resulting in the lack of effective treatment for many CNS diseases including brain cancer. To accelerate CNS drug development, computational prediction models could save the time and effort needed for experimental evaluation. Here, we studied BBB permeability focusing on active transport (influx and efflux) as well as passive diffusion using previously published and self-curated data sets. We created prediction models based on physicochemical properties, molecular substructures, or their combination to understand which mechanisms contribute to BBB permeability. Our results show that features that predicted passive diffusion over membranes overlap with features that explain endothelial permeation of approved CNS-active drugs. We also identified physical properties and molecular substructures that positively or negatively predicted BBB transport. These findings provide guidance toward identifying BBB-permeable compounds by optimally matching physicochemical and molecular properties to BBB transport mechanisms.

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.

New Meloxicam Derivatives-Synthesis and Interaction with Phospholipid Bilayers Measured by Differential Scanning Calorimetry and Fluorescence Spectroscopy

The purpose of the present paper was to assess the ability of five newly designed and synthesized meloxicam analogues to interact with phospholipid bilayers. Calorimetric and fluorescence spectroscopic measurements revealed that, depending on the details of the chemical structure, the studied compounds penetrated bilayers and affected mainly their polar/apolar regions, closer to the surface of the model membrane. The influence of meloxicam analogues on the thermotropic properties of DPPC bilayers was clearly visible because these compounds reduced the temperature and cooperativity of the main phospholipid phase transition. Additionally, the studied compounds quenched the fluorescence of prodan to a higher extent than laurdan, what pointed to a more pronounced interaction with membrane segments close to its surface. We presume that a more pronounced intercalation of the studied compounds into the phospholipid bilayer may be related to the presence of the molecule of a two-carbon aliphatic linker with a carbonyl group and fluorine substituent/trifluoromethyl group (compounds PR25 and PR49) or the three-carbon linker together with the trifluoromethyl group (PR50). Moreover, computational investigations of the ADMET properties have shown that the new meloxicam analogues are characterized by beneficial expected physicochemical parameters, so we may presume that they will have a good bioavailability after an oral administration.

Development of sertraline analogues as potential anti-ischemic stroke agents

Ischemic stroke (IS) is harmful to human health and social development, and there is no medicine available at present. To find the hit compound for treating ischemic stroke, we screened 28 FDA approved nervous system drugs by using an in vitro OGD-induced stroke model. Notably, our in vitro and in vivo studies demonstrated that low-dose sertraline had good neuroprotective activities, while high-dose sertraline showed significant toxicity. Interestingly, the same high-dose sertraline in the control group did not exhibit any obvious toxic effect. Therefore, it is important to modify the structure of sertraline to improve the activity and reduce the toxicity. Stereoisomers of sertraline were first investigated to analyze the influence of stereochemistry on the neuroprotective activities, which showed no obvious difference. Then we evaluated the activity of our previously reported sertraline analogues and found that introducing amide or alkane groups to the amino moiety might be beneficial to enhance the activity and reduce the toxicity. Thus, 10 new analogues were designed, synthesized, and evaluated. Among them, compound OY-201 showed the best safety and neuroprotective activity in both in vitro and in vivo models. Moreover, it exhibited good blood-brain barrier (BBB) permeability, indicating its potential for the development of anti-ischemic stroke drugs.

Anticancer and antimicrobial activity of new copper (II) complexes

In this study, three new organic ligands N'-(benzylidene)-6-chloropyrazine-2-carbohydrazonamide (L₁), 6-chloro-N'-(4-nitrobenzylidene)picolinohydrazonamide(L₂), and N'-(benzylidene)-4-chloropicolinohydrazonamide (L₃) and three copper coordination compounds (Cu(L₁)Cl₂, Cu(L₂)Cl₂ and Cu(L₃)Cl₂) based on them were synthesized. All obtained compounds were characterized using appropriate analytical techniques: elemental analysis (EA), thermogravimetric analysis (TG-DTG), Fourier transform infrared spectroscopy (FTIR) and flame-atomic absorption spectrometry (F-AAS). These methods of physicochemical analyses helped to assume that the complexation in three cases proceeds in a bidentate manner. The X-ray investigation confirmed the synthesis pathway and molecular structures for L₁ and L₃ ligands. The antimicrobial activity of the obtained compounds was then comprehensively investigated, where Cu(L₃)Cl₂ showed the strongest antibacterial properties against all tested bacteria (Pseudomonas aeruginosa, Staphylococcus aureus, Escherichia coli). LN229 human glioma cells and BJ human normal fibroblasts cells were treated with tested compounds and their cytotoxicity was evaluated with MTT test. The effect of complexing on antitumor activity has been investigated. The ligand L₁ and its complex showed similar activity against normal cells while complexation increases toxicity against cancer cells in concentrations of 50 and 100 μM. For the one pair of ligand/complex compounds the apoptosis detection, cell cycle analysis and gene expression analysis (qRT-PCR) were performed. Cu(L₁)Cl₂ showed the stronger toxic effect in comparison with L₁ due to the population of early apoptotic cells which revealed metabolic activity in MTT assay.

Comparative Studies on Resampling Techniques in Machine Learning and Deep Learning Models for Drug-Target Interaction Prediction

The prediction of drug-target interactions (DTIs) is a vital step in drug discovery. The success of machine learning and deep learning methods in accurately predicting DTIs plays a huge role in drug discovery. However, when dealing with learning algorithms, the datasets used are usually highly dimensional and extremely imbalanced. To solve this issue, the dataset must be resampled accordingly. In this paper, we have compared several data resampling techniques to overcome class imbalance in machine learning methods as well as to study the effectiveness of deep learning methods in overcoming class imbalance in DTI prediction in terms of binary classification using ten (10) cancer-related activity classes from BindingDB. It is found that the use of Random Undersampling (RUS) in predicting DTIs severely affects the performance of a model, especially when the dataset is highly imbalanced, thus, rendering RUS unreliable. It is also found that SVM-SMOTE can be used as a go-to resampling method when paired with the Random Forest and Gaussian Naïve Bayes classifiers, whereby a high F1 score is recorded for all activity classes that are severely and moderately imbalanced. Additionally, the deep learning method called Multilayer Perceptron recorded high F1 scores for all activity classes even when no resampling method was applied.

Artificial Intelligence and Machine Learning for Lead-to-Candidate Decision-Making and Beyond

The use of artificial intelligence (AI) and machine learning (ML) in pharmaceutical research and development has to date focused on research: target identification; docking-, fragment-, and motif-based generation of compound libraries; modeling of synthesis feasibility; rank-ordering likely hits according to structural and chemometric similarity to compounds having known activity and affinity to the target(s); optimizing a smaller library for synthesis and high-throughput screening; and combining evidence from screening to support hit-to-lead decisions. Applying AI/ML methods to lead optimization and lead-to-candidate (L2C) decision-making has shown slower progress, especially regarding predicting absorption, distribution, metabolism, excretion, and toxicology properties. The present review surveys reasons why this is so, reports progress that has occurred in recent years, and summarizes some of the issues that remain. Effective AI/ML tools to derisk L2C and later phases of development are important to accelerate the pharmaceutical development process, ameliorate escalating development costs, and achieve greater success rates.

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.

Synthesis and Anticancer Activity of Indole-Functionalized Derivatives of Betulin

Pentacyclic triterpenes, including betulin, are widespread natural products with various pharmacological effects. These compounds are the starting material for the synthesis of substances with promising anticancer activity. The chemical modification of the betulin scaffold that was carried out as part of the research consisted of introducing the indole moiety at the C-28 position. The synthesized new 28-indole-betulin derivatives were evaluated for anticancer activity against seven human cancer lines (A549, MDA-MB-231, MCF-7, DLD-1, HT-29, A375, and C32). It was observed that MCF-7 breast cancer cells were most sensitive to the action of the 28-indole-betulin derivatives. The study shows that the lup-20(29)-ene-3-ol-28-yl 2-(1H-indol-3-yl)acetate caused the MCF-7 cells to arrest in the G1 phase, preventing the cells from entering the S phase. The performed cytometric analysis of DNA fragmentation indicates that the mechanism of EB355A action on the MCF-7 cell line is related to the induction of apoptosis. An in silico ADMET profile analysis of EB355A and EB365 showed that both compounds are bioactive molecules characterized by good intestinal absorption. In addition, the in silico studies indicate that the 28-indole-betulin derivatives are substances of relatively low toxicity.

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.

Effect of tricyclic 1,2-thiazine derivatives in neuroinflammation induced by preincubation with lipopolysaccharide or coculturing with microglia-like cells

Background

Alzheimer’s disease (AD) is considered the most common cause of dementia among the elderly. One of the modifiable causes of AD is neuroinflammation. The current study aimed to investigate the influence of new tricyclic 1,2-thiazine derivatives on in vitro model of neuroinflammation and their ability to cross the blood–brain barrier (BBB).

Methods

The potential anti-inflammatory effect of new tricyclic 1,2-thiazine derivatives (TP1, TP4, TP5, TP6, TP7, TP8, TP9, TP10) was assessed in SH-SY5Y cells differentiated to the neuron-like phenotype incubated with bacterial lipopolysaccharide (5 or 50 μg/ml) or THP-1 microglial cell culture supernatant using MTT, DCF-DA, Griess, and fast halo (FHA) assays. Additionally, for cultures preincubated with 50 µg/ml lipopolysaccharide (LPS), a cyclooxygenase (COX) activity assay was performed. Finally, the potential ability of tested compounds to cross the BBB was evaluated by computational studies. Molecular docking was performed with the TLR4/MD-2 complex to assess the possibility of binding the tested compounds in the LPS binding pocket. Prediction of ADMET parameters (absorption, distribution, metabolism, excretion and toxicity) was also conducted.

Results

The unfavorable effect of LPS and co-culture with THP-1 cells on neuronal cell viability was counteracted with TP1 and TP4 in all tested concentrations. Tested compounds reduced the oxidative and nitrosative stress induced by both LPS and microglia activation and also reduced DNA damage. Furthermore, new derivatives inhibited total COX activity. Additionally, new compounds would cross the BBB with high probability and reach concentrations in the brain not lower than in the serum. The binding affinity at the TLR4/MD-2 complex binding site of TP4 and TP8 compounds is similar to that of the drug donepezil used in Alzheimer's disease. The ADMET analysis showed that the tested compounds should not be toxic and should show high intestinal absorption.

Conclusions

New tricyclic 1,2-thiazine derivatives exert a neuroregenerative effect in the neuroinflammation model, presumably via their inhibitory influence on COX activity and reduction of oxidative and nitrosative stress.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43440-022-00414-8.

Application of machine learning to predict the inhibitory activity of organic chemicals on thyroid stimulating hormone receptor

With the promotion of carbon neutrality, it is also important to synchronously promote the assessment and sustainable management of chemicals so as to protect public health. Humans and animals are possibly exposed to endocrine disruptors that have inhibitory effects on thyroid stimulating hormone receptor (TSHR). As such, it is important to identify chemicals that inhibit TSHR and to develop models to predict their inhibitory activity. In this study, 5952 compounds derived from a cyclic adenosine monophosphate (cAMP) analysis, a key signaling pathway in thyrocytes, were used to establish a binary classification model comparing methods that included random forest (RF), extreme gradient boosting (XGB), and logistic regression (LR). The prediction model based on RF showed the highest identification accuracy for revealing chemicals that may inhibit TSHR. For the RF model, recall was calculated at 0.89, balance accuracy was 0.85, and its receiver operating characteristic (ROC) curve-area under (AUC) was 0.92, indicating that the model had very high predictive capacity. The lowest CDocker energy (CE) and CDocker interaction energy (CIE) for chemicals and TSHR were determined and were subsequently introduced into the predictive model as descriptors. A regression model, extreme gradient boosting-Regression (XGBR), was successfully established yielding an R² = 0.65 to predict inhibitory activity for active compounds. Parameters that included dissociation characteristics, molecular structure, and binding energy were all key factors in the predictive model. We demonstrate that QSAR models are useful approaches, not only for identifying chemicals that inhibit TSHR, but for predicting inhibitory activity of active compounds.

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.

Dysfunction of ABC Transporters at the Surface of BBB: Potential Implications in Intractable Epilepsy and Applications of Nanotechnology Enabled Drug Delivery

Epilepsy is a chronic neurological disorder affecting 70 million people globally. One of the fascinating attributes of brain microvasculature is the (BBB), which controls a chain of distinct features that securely regulate the molecules, ions, and cells movement between the blood and the parenchyma. The barrier's integrity is of paramount importance and essential for maintaining brain homeostasis, as it offers both physical and chemical barriers to counter pathogens and xenobiotics. Dysfunction of various transporters in the (BBB), mainly ATP binding cassette (ABC), is considered to play a vital role in hampering the availability of antiepileptic drugs into the brain. ABC (ATP-binding cassette) transporters constitute a most diverse protein superfamily, which plays an essential part in various biological processes, including cell homeostasis, cell signaling, uptake of nutrients, and drug metabolism. Moreover, it plays a crucial role in neuroprotection by out-flowing various internal and external toxic substances from the interior of a cell, thus decreasing their buildup inside the cell. In humans, forty-eight ABC transporters have been acknowledged and categorized into subfamilies A to G based on their phylogenetic analysis. ABC subfamilies B, C, and G, impart a vital role at the BBB in guarding the brain against the entrance of various xenobiotic and their buildup. The illnesses of the central nervous system have received a lot of attention lately Owing to the existence of the BBB, the penetration effectiveness of most CNS medicines into the brain parenchyma is very limited (BBB). In the development of neurological therapies, BBB crossing for medication delivery to the CNS continues to be a major barrier. Nanomaterials with BBB cross ability have indeed been extensively developed for the treatment of CNS diseases due to their advantageous properties. This review will focus on multiple possible factors like inflammation, oxidative stress, uncontrolled recurrent seizures, and genetic polymorphisms that result in the deregulation of ABC transporters in epilepsy and nanotechnology-enabled delivery across BBB in epilepsy.

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.

Microwave-assisted synthesis, spectroscopic characterization, and biological evaluation of fused thieno[2,3-d]pyrimidines as potential anti-cancer agents targeting EGFRWT and EGFRT790M

Epidermal growth factor receptor (EGFR) is a transmembrane protein tyrosine kinase that is usually overexpressed in many types of cancers. In the present study, an effort was done in synthesis of new 3,4-diaminothieno[2,3-b] thiophene-2,5-dicarbonitrile derivatives 2-8, assisted by a microwave device. Different spectroscopic instruments were used for their analysis and confirmed their chemical structures. The antimicrobial properties of the produced compounds were investigated and found to be promising. Next, they were tested for cytotoxicity against MCF-7, HepG-2, HCT-116, and A549 cell lines. Moreover, in vitro cytotoxicity evaluation against well-known standards, namely, gefitinib and erlotinib was achieved using MTT method. The obtained compounds (2-8) were found to be more effective against the two tested cancer cell lines than erlotinib. In MCF-7 and A549 cells, compound 3 was found to be 4.42 and 4.12 times more active than erlotinib, respectively. The activity of radical scavenging was inhibited by 78%. The most cytotoxic compounds were subsequently studied for their kinase inhibitory effect against EGFR^WT and EGFR^T790M using the HTRF assay. Compound 3 was shown to be the most powerful against both kinds of EGFR, with IC₅₀ values of 0.28 and 5.02. Furthermore, compound 2 demonstrated the highest antioxidant activity as it has a radical scavenging activity of 78%. Compounds 2,6,7 and 8 revealed to be the most safe compounds, none hepatotoxic, none carcinogenic, none immunotoxic, none mutagenic and none cytotoxic.

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.

Phenotypes based Classification of Blood-Brain-Barrier Drugs using Feature Selection Methods and Extreme Gradient Boosting

In this work, an attempt has been made to discriminate drug with blood brain barrier (BBB) permeability using clinical phenotypes and extreme gradient boosting (XGBoost) methods. For this, the drug name and their clinical phenotypes namely side effects and indications are obtained from public available database. Prominent clinical phenotypes are selected using genetic algorithm (GA) and binary particle swarm optimization (BPSO). Four machine algorithms namely k-Nearest Neighbours, support vector machines, rotation forest and XGBoost are used for classification of BBB drugs. The result show that the proposed clinical phenotypes based features are able to distinguish drugs with BBB permeability. The maximum number of clinical phenotypes (69%) is reduced by BPSO and GA for classification. The XGBoost method is found to be most accurate [Formula: see text] is discriminating drugs with BBB permeability. The proposed approach are found to be capable of handling multi-parametric characteristics of the drugs. Particularly, the combination of XGBoost with combination of side effects and indications could be used for precision medicine applications. Clinical relevance- This establishes XGBoost approach for improved BBB permeability based drug classification with F1 =98.7% using exclusively clinical phenotypes.

Predicting In Vivo Compound Brain Penetration Using Multi-task Graph Neural Networks

Assessing whether compounds penetrate the brain can become critical in drug discovery, either to prevent adverse events or to reach the biological target. Generally, pre-clinical in vivo studies measuring the ratio of brain and blood concentrations (K_p) are required to estimate the brain penetration potential of a new drug entity. In this work, we developed machine learning models to predict in vivo compound brain penetration (as LogK_p) from chemical structure. Our results show the benefit of including in vitro experimental data as auxiliary tasks in multi-task graph neural network (MT-GNN) models. MT-GNNs outperformed single-task (ST) models solely trained on in vivo brain penetration data. The best-performing MT-GNN regression model achieved a coefficient of determination of 0.42 and a mean absolute error of 0.39 (2.5-fold) on a prospective validation set and outperformed all tested ST models. To facilitate decision-making, compounds were classified into brain-penetrant or non-penetrant, achieving a Matthew's correlation coefficient of 0.66. Taken together, our findings indicate that the inclusion of in vitro assay data as MT-GNN auxiliary tasks improves in vivo brain penetration predictions and prospective compound prioritization.

In Silico Approaches for Addressing Challenges in CNS Radiopharmaceutical Design

Positron emission tomography (PET) is a highly sensitive and versatile molecular imaging modality that leverages radiolabeled molecules, known as radiotracers, to interrogate biochemical processes such as metabolism, enzymatic activity, and receptor expression. The ability to probe specific molecular and cellular events longitudinally in a noninvasive manner makes PET imaging a particularly powerful technique for studying the central nervous system (CNS) in both health and disease. Unfortunately, developing and translating a single CNS PET tracer for clinical use is typically an extremely resource-intensive endeavor, often requiring synthesis and evaluation of numerous candidate molecules. While existing in vitro methods are beginning to address the challenge of derisking molecules prior to costly in vivo PET studies, most require a significant investment of resources and possess substantial limitations. In the context of CNS drug development, significant time and resources have been invested into the development and optimization of computational methods, particularly involving machine learning, to streamline the design of better CNS therapeutics. However, analogous efforts developed and validated for CNS radiotracer design are conspicuously limited. In this Perspective, we overview the requirements and challenges of CNS PET tracer design, survey the most promising computational methods for in silico CNS drug design, and bridge these two areas by discussing the potential applications and impact of computational design tools in CNS radiotracer design.

MegaSyn: Integrating Generative Molecular Design, Automated Analog Designer, and Synthetic Viability Prediction

Generative machine learning models have become widely adopted in drug discovery and other fields to produce new molecules and explore molecular space, with the goal of discovering novel compounds with optimized properties. These generative models are frequently combined with transfer learning or scoring of the physicochemical properties to steer generative design, yet often, they are not capable of addressing a wide variety of potential problems, as well as converge into similar molecular space when combined with a scoring function for the desired properties. In addition, these generated compounds may not be synthetically feasible, reducing their capabilities and limiting their usefulness in real-world scenarios. Here, we introduce a suite of automated tools called MegaSyn representing three components: a new hill-climb algorithm, which makes use of SMILES-based recurrent neural network (RNN) generative models, analog generation software, and retrosynthetic analysis coupled with fragment analysis to score molecules for their synthetic feasibility. We show that by deconstructing the targeted molecules and focusing on substructures, combined with an ensemble of generative models, MegaSyn generally performs well for the specific tasks of generating new scaffolds as well as targeted analogs, which are likely synthesizable and druglike. We now describe the development, benchmarking, and testing of this suite of tools and propose how they might be used to optimize molecules or prioritize promising lead compounds using these RNN examples provided by multiple test case examples.

Prediction Models for Brain Distribution of Drugs Based on Biomimetic Chromatographic Data

The development of high-throughput approaches for the valid estimation of brain disposition is of great importance in the early drug screening of drug candidates. However, the complexity of brain tissue, which is protected by a unique vasculature formation called the blood−brain barrier (BBB), complicates the development of robust in silico models. In addition, most computational approaches focus only on brain permeability data without considering the crucial factors of plasma and tissue binding. In the present study, we combined experimental data obtained by HPLC using three biomimetic columns, i.e., immobilized artificial membranes, human serum albumin, and α1-acid glycoprotein, with molecular descriptors to model brain disposition of drugs. Kp,uu,brain, as the ratio between the unbound drug concentration in the brain interstitial fluid to the corresponding plasma concentration, brain permeability, the unbound fraction in the brain, and the brain unbound volume of distribution, was collected from literature. Given the complexity of the investigated biological processes, the extracted models displayed high statistical quality (R2 > 0.6), while in the case of the brain fraction unbound, the models showed excellent performance (R2 > 0.9). All models were thoroughly validated, and their applicability domain was estimated. Our approach highlighted the importance of phospholipid, as well as tissue and protein, binding in balance with BBB permeability in brain disposition and suggests biomimetic chromatography as a rapid and simple technique to construct models with experimental evidence for the early evaluation of CNS drug candidates.

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.

Drug-Induced Immune Thrombocytopenia Toxicity Prediction Based on Machine Learning

Drug-induced immune thrombocytopenia (DITP) often occurs in patients receiving many drug treatments simultaneously. However, clinicians usually fail to accurately distinguish which drugs can be plausible culprits. Despite significant advances in laboratory-based DITP testing, in vitro experimental assays have been expensive and, in certain cases, cannot provide a timely diagnosis to patients. To address these shortcomings, this paper proposes an efficient machine learning-based method for DITP toxicity prediction. A small dataset consisting of 225 molecules was constructed. The molecules were represented by six fingerprints, three descriptors, and their combinations. Seven classical machine learning-based models were examined to determine an optimal model. The results show that the RDMD + PubChem-k-NN model provides the best prediction performance among all the models, achieving an area under the curve of 76.9% and overall accuracy of 75.6% on the external validation set. The application domain (AD) analysis demonstrates the prediction reliability of the RDMD + PubChem-k-NN model. Five structural fragments related to the DITP toxicity are identified through information gain (IG) method along with fragment frequency analysis. Overall, as far as known, it is the first machine learning-based classification model for recognizing chemicals with DITP toxicity and can be used as an efficient tool in drug design and clinical therapy.

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.

BF3·OEt2 catalyzed decarbonylative arylation/C-H functionalization of diazoamides with arylaldehydes: synthesis of substituted 3-aryloxindoles

A metal-free BF₃·OEt₂ catalyzed direct decarbonylative arylation of diazoamides with readily accessible aryl aldehydes under an open-air atmosphere was developed to afford 3-aryloxindoles via 1,2-aryl migration with high selectivity. The reaction offers an efficient pathway for 3-arylation of diazoamides under relatively mild conditions, which shows a high level of functional group tolerance of both electron-donating and electron-withdrawing groups with a broad substrate scope. 3-Aryloxindoles were also obtained by a substituent-controlled chemo- and site-selective C-H bond functionalization of unprotected salicylaldehyde derivatives.

In silico screening of the effectiveness of natural compounds from algae as SARS-CoV-2 inhibitors: molecular docking, ADMT profile and molecular dynamic studies

Marine species are known as rich sources of metabolites largely involved in the pharmaceutical industry. This study aimed to evaluate in silico the effect of natural compounds identified in algae on the SARS-CoV-2 Main protease, RNA-dependent-RNA polymerase activity (RdRp), endoribonuclease (NSP15) as well as on their interaction with viral spike protein. A total of 45 natural compounds were screened for their possible interaction on SARS-CoV-2 target proteins using Maestro interface for molecular docking, molecular dynamic (MD) simulation to estimate compounds binding affinities. Among the algal compounds screened in this study, three (Laminarin, Astaxanthin and 4'-chlorostypotriol triacetate) exhibited the lowest docking energy and best interaction with SARS-CoV-2 viral proteins (Main protease, RdRp, Nsp15, and spike protein). The complex of the main protease with laminarin shows the most stable RMSD during a 150 ns MD simulation time. Which indicates their possible inhibitory activity on SARS-CoV-2.Communicated by Ramaswamy H. Sarma.

Applications of Phyto-Nanotechnology for the Treatment of Neurodegenerative Disorders

The strategies involved in the development of therapeutics for neurodegenerative disorders are very complex and challenging due to the existence of the blood-brain barrier (BBB), a closely spaced network of blood vessels and endothelial cells that functions to prevent the entry of unwanted substances in the brain. The emergence and advancement of nanotechnology shows favourable prospects to overcome this phenomenon. Engineered nanoparticles conjugated with drug moieties and imaging agents that have dimensions between 1 and 100 nm could potentially be used to ensure enhanced efficacy, cellular uptake, specific transport, and delivery of specific molecules to the brain, owing to their modified physico-chemical features. The conjugates of nanoparticles and medicinal plants, or their components known as nano phytomedicine, have been gaining significance lately in the development of novel neuro-therapeutics owing to their natural abundance, promising targeted delivery to the brain, and lesser potential to show adverse effects. In the present review, the promising application, and recent trends of combined nanotechnology and phytomedicine for the treatment of neurological disorders (ND) as compared to conventional therapies, have been addressed. Nanotechnology-based efforts performed in bioinformatics for early diagnosis as well as futuristic precision medicine in ND have also been discussed in the context of computational approach.

Synthesis of novel thiazolidinic-phthalimide derivatives evaluated as new multi-target antiepileptic agents

Epilepsy is a disease that affects millions of people around the globe and has a multifactorial cause. Inflammation is a process that can be involved in the development of seizures. Thus, the present study proposed the design and synthesis of new candidates for antiepileptic drugs that would also control the inflammatory process. Nine new derivatives of the substituted thiazophthalimide hybrid core were obtained with satisfactory purity ≥99% and yields between 27% and 87%. All compounds showed cell viability values greater than 90% in the culture of PBMC cells from healthy volunteers and, therefore, were not considered cytotoxic. These compounds modulated proinflammatory cytokines IFN-y and IL-17A and can mitigate inflammation. Acute toxicity studies of compound 7i in an animal model indicated that the compound has low toxicity and an LD50 greater than 2 g/kg in healthy adult rats. The same compound did not show positive results for anticonvulsant activity through the PTZ test. However, 7i demonstrates the interaction with the target GABA-A receptor in silico, indicating a possible activity as an agonist of that receptor. Thus, further studies are needed to investigate the anticonvulsant activity, in particular, using models in which the inflammatory process triggers epileptic seizures.

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

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