In silico modeling on ADME properties of natural products: Classification models for blood-brain barrier permeability, its application to traditional Chinese medicine and in vitro experimental validation

Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules

INTRODUCTION

Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary.

AREAS COVERED

This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review.

EXPERT OPINION

ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.

Molecular Hybridization of Alkaloids Using 1,2,3-Triazole-Based Click Chemistry

Alkaloids found in multiple species, known as 'driver species', are more likely to be included in early-stage drug development due to their high biodiversity compared to rare alkaloids. Many synthetic approaches have been employed to hybridize the natural alkaloids in drug development. Click chemistry is a highly efficient and versatile reaction targeting specific areas, making it a valuable tool for creating complex natural products and diverse molecular structures. It has been used to create hybrid alkaloids that address their limitations and serve as potential drugs that mimic natural products. In this review, we highlight the recent advancements made in modifying alkaloids using click chemistry and their potential medicinal applications. We discuss the significance, current trends, and prospects of click chemistry in natural product-based medicine. Furthermore, we have employed computational methods to evaluate the ADMET properties and drug-like qualities of hybrid molecules.

A Fluorescent Probe for Investigating the Role of Biothiols in Signaling Pathways Associated with Cerebral Ischemia-Reperfusion Injury

Cerebral ischemia-reperfusion injury (CIRI) is intimately associated with the redox regulation of biothiol, a crucial antioxidant marker that precludes the onset of ROS. We designed a novel fluorescent probe, DCI-Ac-Py, showing various physicochemical properties, such as high selectivity, exceptional signal-to-noise ratio, near-infrared (NIR) optical window, and blood-brain barrier (BBB) penetrability, for detecting biothiols in the brain. The picolinate serves as a specific recognition group that is rapidly activated by biothiol and undergoes nucleophilic substitution with the adjacent acrylic ester to yield the desired NIR probe. Additionally, the probe's lipid solubility is improved through the inclusion of halogen atoms, which aids in penetrating the BBB. Using DCI-Ac-Py, we investigated changes of biothiols in vivo in the brains of mice during CIRI. We found that biothiol-mediated NF-kB classical (P65-related) and nonclassical (RelB-related) pathways contribute to abundant ROS production induced by CIRI and that biothiols are involved in redox regulation. These findings provide new insights into the study of CIRI and shed light on the physiological and pathological mechanisms of biothiols in the brain.

Synergistic Modulation by Halogens and Pyridine Crossing the Blood-Brain Barrier for In Situ Visualization of Thiol Flux in the Epileptic Brain

Epilepsy is a nervous system disease, and seizures are closely related to oxidative stress. Thiols, as the main antioxidant in an organism, play a key role in regulating the redox balance and defending from oxidative stress. As a result of the complexity of the brain structure, there is still a lack of suitable in situ detection methods of thiols to reveal the relationship between epilepsy and thiol level fluctuations. Therefore, by combining picolinate as the new recognition site for thiols, parallel synthesis, and the fluorescence rapid screening method, DCI-Br-3 was developed as a rapid, highly sensitive, and selective probe to monitor thiols in vitro and in vivo. It is worth noting that DCI-Br-3 effectively crossed the blood-brain barrier (BBB) to reveal the negative relationship between the level of thiols and the occurrence of epilepsy and may further provide important information for the prevention and treatment of thiol-related neurological diseases.

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.

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.

InflamNat: web-based database and predictor of anti-inflammatory natural products

Natural products (NPs) are a valuable source for anti-inflammatory drug discovery. However, they are limited by the unpredictability of the structures and functions. Therefore, computational and data-driven pre-evaluation could enable more efficient NP-inspired drug development. Since NPs possess structural features that differ from synthetic compounds, models trained with synthetic compounds may not perform well with NPs. There is also an urgent demand for well-curated databases and user-friendly predictive tools. We presented a comprehensive online web platform (InflamNat, http://www.inflamnat.com/ or http://39.104.56.4/) for anti-inflammatory natural product research. InflamNat is a database containing the physicochemical properties, cellular anti-inflammatory bioactivities, and molecular targets of 1351 NPs that tested on their anti-inflammatory activities. InflamNat provides two machine learning-based predictive tools specifically designed for NPs that (a) predict the anti-inflammatory activity of NPs, and (b) predict the compound-target relationship for compounds and targets collected in the database but lacking existing relationship data. A novel multi-tokenization transformer model (MTT) was proposed as the sequential encoder for both predictive tools to obtain a high-quality representation of sequential data. The experimental results showed that the proposed predictive tools achieved an AUC value of 0.842 and 0.872 in the prediction of anti-inflammatory activity and compound-target interactions, respectively.

Biological Membrane-Penetrating Peptides: Computational Prediction and Applications

Peptides comprise a versatile class of biomolecules that present a unique chemical space with diverse physicochemical and structural properties. Some classes of peptides are able to naturally cross the biological membranes, such as cell membrane and blood-brain barrier (BBB). Cell-penetrating peptides (CPPs) and blood-brain barrier-penetrating peptides (B3PPs) have been explored by the biotechnological and pharmaceutical industries to develop new therapeutic molecules and carrier systems. The computational prediction of peptides’ penetration into biological membranes has been emerged as an interesting strategy due to their high throughput and low-cost screening of large chemical libraries. Structure- and sequence-based information of peptides, as well as atomistic biophysical models, have been explored in computer-assisted discovery strategies to classify and identify new structures with pharmacokinetic properties related to the translocation through biomembranes. Computational strategies to predict the permeability into biomembranes include cheminformatic filters, molecular dynamics simulations, artificial intelligence algorithms, and statistical models, and the choice of the most adequate method depends on the purposes of the computational investigation. Here, we exhibit and discuss some principles and applications of these computational methods widely used to predict the permeability of peptides into biomembranes, exhibiting some of their pharmaceutical and biotechnological applications.

In Silico Investigation of Some Compounds from the N-Butanol Extract of Centaurea tougourensis Boiss. & Reut

Bioinformatics as a newly emerging discipline is considered nowadays a reference to characterize the physicochemical and pharmacological properties of the actual biocompounds contained in plants, which has helped the pharmaceutical industry a lot in the drug development process. In this study, a bioinformatics approach known as in silico was performed to predict, for the first time, the physicochemical properties, ADMET profile, pharmacological capacities, cytotoxicity, and nervous system macromolecular targets, as well as the gene expression profiles, of four compounds recently identified from Centaurea tougourensis via the gas chromatography–mass spectrometry (GC–MS) approach. Thus, four compounds were tested from the n-butanol (n-BuOH) extract of this plant, named, respectively, Acridin-9-amine, 1,2,3,4-tetrahydro-5,7-dimethyl- (compound 1), 3-[2,3-Dihydro-2,2-dimethylbenzofuran-7-yl]-5-methoxy-1,3,4-oxadiazol-2(3H)-one (compound 2), 9,9-Dimethoxybicyclo[3.3.1]nona-2,4-dione (compound 3), and 3-[3-Bromophenyl]-7-chloro-3,4-dihydro-10-hydroxy-1,9(2H,10H)-acridinedione (compound 4). The insilico investigation revealed that the four tested compounds could be a good candidate to regulate the expression of key genes and may also exert significant cytotoxic effects against several tumor celllines. In addition, these compounds could also be effective in the treatment of some diseases related to diabetes, skin pathologies, cardiovascular, and central nervous system disorders. The bioactive compounds of plant remain the best alternative in the context of the drug discovery and development process.

Natural product drug discovery in the artificial intelligence era

Natural products (NPs) are primarily recognized as privileged structures to interact with protein drug targets. Their unique characteristics and structural diversity continue to marvel scientists for developing NP-inspired medicines, even though the pharmaceutical industry has largely given up. High-performance computer hardware, extensive storage, accessible software and affordable online education have democratized the use of artificial intelligence (AI) in many sectors and research areas. The last decades have introduced natural language processing and machine learning algorithms, two subfields of AI, to tackle NP drug discovery challenges and open up opportunities. In this article, we review and discuss the rational applications of AI approaches developed to assist in discovering bioactive NPs and capturing the molecular "patterns" of these privileged structures for combinatorial design or target selectivity.

Dynamic 3D On-Chip BBB Model Design, Development, and Applications in Neurological Diseases

The blood-brain barrier (BBB) is a vital structure for maintaining homeostasis between the blood and the brain in the central nervous system (CNS). Biomolecule exchange, ion balance, nutrition delivery, and toxic molecule prevention rely on the normal function of the BBB. The dysfunction and the dysregulation of the BBB leads to the progression of neurological disorders and neurodegeneration. Therefore, in vitro BBB models can facilitate the investigation for proper therapies. As the demand increases, it is urgent to develop a more efficient and more physiologically relevant BBB model. In this review, the development of the microfluidics platform for the applications in neuroscience is summarized. This article focuses on the characterizations of in vitro BBB models derived from human stem cells and discusses the development of various types of in vitro models. The microfluidics-based system and BBB-on-chip models should provide a better platform for high-throughput drug-screening and targeted delivery.

Identification of Terpenoids From Abrus precatorius Against Parkinson's Disease Proteins Using In Silico Approach

Parkinson’s disease (PD) is the second major neuro-degenrative disorder that causes morbidity and mortality among older populations. Terpenoids were reported as potential neuro-protective agents. Therefore, this study seeks to unlock the inhibitory potential of terpenoids from Abrus precatorius seeds against proteins involve in PD pathogenesis. In this study, in silico molecular docking of 5 terpenoids derived from high-performance liquid chromatography (HPLC) analysis of A. precatorius seeds against α-synuclein, catechol-o-methyltransferase, and monoamine oxidase B which are markers of PD was performed using Autodock vina. The absorption, distribution, metabolism, excretion, and toxicity (ADME/Tox) of the hits were done using Swiss ADME predictor and molecular dynamic (MD) simulation of the hit-protein complex was performed using Desmond Schrodinger software. Five out of 6 compounds satisfied the ADME/Tox parameters and showed varying degrees of binding affinities with selected proteins. Drimenin-α-synuclein complex showed the lowest binding energy of −9.1 kcal/mol followed by interaction with key amino acid residues necessary for α-synuclein inhibition. The selection of this complex was justified by its stability in MD simulation conducted for 10 ns and exhibited stable interaction in terms of root mean square deviation (RMSD) and root mean square deviation error fluctuation (RMSF) values.

Ficus deltoidea: Potential inhibitor of pro-inflammatory mediators in lipopolysaccharide-induced activation of microglial cells

ETHNOPHARMACOLOGICAL RELEVANCE

Ficus deltoidea Jack (FD) is widely consumed in traditional medicine as a treatment for various diseases in Malaysia. Each part of the plant such as its leave, stem, fruit and root are used traditionally to treat different types of diseases. Vitexin and isovitexin are bioactive compounds abundantly found in the leaves of FD that possessed many pharmacological properties including neuroprotection. Nonetheless, its effects on key events in neuroinflammation are unknown.

AIM OF THE STUDY

To determine the inhibitory properties of FD aqueous extract on pro-inflammatory mediators involved in lipopolysaccharide (LPS)-induced microglial cells.

METHODS

Vitexin and isovitexin in the extract were quantified via high performance liquid chromatography (HPLC). The extract was evaluated for its cytotoxicity activity via 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay. Pre-treatment with the extract on LPS-induced microglial cells was done to determine its antioxidant and anti-neuroinflammatory properties by measuring the level of reactive oxygen species (ROS), nitric oxide (NO), tumour necrosis factor alpha (TNF-α), interleukin-1β (IL-1β) and interleukin-6 (IL-6) via 2'-7'-dichlorofluorescin diacetate (DCFDA) assay, Griess assay and Western blot respectively.

RESULTS

The extract at all tested concentrations (0.1 μg/mL, 1 μg/mL, 10 μg/mL, 100 μg/mL) were not cytotoxic as the percentage viability of microglial cells were all above ~80%. At the highest concentration (100 μg/mL), the extract significantly reduced the formation of ROS, NO, TNF-α, IL-1β and IL-6 in microglial cells induced by LPS.

CONCLUSION

The extract showed neuroprotective effects by attenuating the levels of pro-inflammatory and cytotoxic factors in LPS-induced microglial cells, possibly by mediating the nuclear factor-kappa B (NF-κB) signalling pathway.

Machine learning models for classification tasks related to drug safety

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

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

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

Applications of Virtual Screening in Bioprospecting: Facts, Shifts, and Perspectives to Explore the Chemo-Structural Diversity of Natural Products

Natural products are continually explored in the development of new bioactive compounds with industrial applications, attracting the attention of scientific research efforts due to their pharmacophore-like structures, pharmacokinetic properties, and unique chemical space. The systematic search for natural sources to obtain valuable molecules to develop products with commercial value and industrial purposes remains the most challenging task in bioprospecting. Virtual screening strategies have innovated the discovery of novel bioactive molecules assessing in silico large compound libraries, favoring the analysis of their chemical space, pharmacodynamics, and their pharmacokinetic properties, thus leading to the reduction of financial efforts, infrastructure, and time involved in the process of discovering new chemical entities. Herein, we discuss the computational approaches and methods developed to explore the chemo-structural diversity of natural products, focusing on the main paradigms involved in the discovery and screening of bioactive compounds from natural sources, placing particular emphasis on artificial intelligence, cheminformatics methods, and big data analyses.

Machine learning in pharmacometrics: Opportunities and challenges

The explosive growth in medical devices, imaging and diagnostics, computing, and communication and information technologies in drug development and healthcare has created an ever-expanding data landscape that the pharmacometrics (PMX) research community must now traverse. The tools of machine learning (ML) have emerged as a powerful computational approach in other data-rich disciplines but its effective utilization in the pharmaceutical sciences and PMX modelling is in its infancy. ML-based methods can complement PMX modelling by enabling the information in diverse sources of big data, e.g. population-based public databases and disease-specific clinical registries, to be harnessed because they are capable of efficiently identifying salient variables associated with outcomes and delineating their interdependencies. ML algorithms are computationally efficient, have strong predictive capabilities and can enable learning in the big data setting. ML algorithms can be viewed as providing a computational bridge from big data to complement PMX modelling. This review provides an overview of the strengths and weaknesses of ML approaches vis-à-vis population methods, assesses current research into ML applications in the pharmaceutical sciences and provides perspective for potential opportunities and strategies for the successful integration and utilization of ML in PMX.

Machine learning approaches for elucidating the biological effects of natural products

Covering: 2000 to 2020 Machine learning (ML) is an efficient tool for the prediction of bioactivity and the study of structure-activity relationships. Over the past decade, an emerging trend for combining these approaches with the study of natural products (NPs) has developed in order to manage the challenge of the discovery of bioactive NPs. In the present review, we will introduce the basic principles and protocols for using the ML approach to investigate the bioactivity of NPs, citing a series of practical examples regarding the study of anti-microbial, anti-cancer, and anti-inflammatory NPs, etc. ML algorithms manage a variety of classification and regression problems associated with bioactive NPs, from those that are linear to non-linear and from pure compounds to plant extracts. Inspired by cases reported in the literature and our own experience, a number of key points have been emphasized for reducing modeling errors, including dataset preparation and applicability domain analysis.