Fingerprint-Based Machine Learning Approach to Identify Potent and Selective 5-HT2BR Ligands

The application of artificial intelligence to accelerate G protein-coupled receptor drug discovery

The application of artificial intelligence (AI) approaches to drug discovery for G protein-coupled receptors (GPCRs) is a rapidly expanding area. Artificial intelligence can be used at multiple stages during the drug discovery process, from aiding our understanding of the fundamental actions of GPCRs to the discovery of new ligand-GPCR interactions or the prediction of clinical responses. Here, we provide an overview of the concepts behind artificial intelligence, including the subfields of machine learning and deep learning. We summarise the published applications of artificial intelligence to different stages of the GPCR drug discovery process. Finally, we reflect on the benefits and limitations of artificial intelligence and share our vision for the exciting potential for further development of applications to aid GPCR drug discovery. In addition to making the drug discovery process "faster, smarter and cheaper," we anticipate that the application of artificial intelligence will create exciting new opportunities for GPCR drug discovery. LINKED ARTICLES: This article is part of a themed issue Therapeutic Targeting of G Protein-Coupled Receptors: hot topics from the Australasian Society of Clinical and Experimental Pharmacologists and Toxicologists 2021 Virtual Annual Scientific Meeting. To view the other articles in this section visit http://onlinelibrary.wiley.com/doi/10.1111/bph.v181.14/issuetoc.

Effect of Bulky N-Dibenzofuranylmethyl Substitution on the 5-HT2 Receptor Affinity and Efficacy of a Psychedelic Phenethylamine

The introduction of arylmethyl substituents on the amine nitrogen atom of phenethylamines and tryptamines often results in profound increases in their affinity and functional activity at 5-HT2 serotonin receptors. To probe the sensitivity of this effect to substantially larger N-substituents, ten derivatives of the well-characterized psychedelic phenethylamine 2C-B were prepared by appending different dibenzo[b,d]furylmethyl (DBFM) moieties to the basic nitrogen. The DBFM group attached to the amino group through its 1-, -2-, or 3-position decreased affinity and agonist activity at the 5-HT2A/2C receptors. Substitution through the 4-position usually favored affinity for all three 5-HT2 receptor subtypes with compound 5 exhibiting 10- and 40-fold higher affinities at the 5-HT2A and 5-HT2C receptors, respectively, but less than fourfold selectivity among the three receptor subtypes. Nevertheless, all were relatively weak partial 5-HT2AR agonists, mostly in the low micromolar range, but full or nearly full agonists at the 5-HT2C subtype as determined in a calcium mobilization assay. Molecular docking simulations suggested that the dibenzofuryl portion dives more deeply into the orthosteric binding site of the 5-HT2A than the 5-HT2C receptor, interacting with the Trp3366.48 toggle switch associated with its activation, while the phenylamine moiety lies close to the extracellular side of the receptor. In conclusion, a very bulky N-substituent on a phenethylamine 5-HT2 receptor agonist is tolerated and may increase affinity if its orientation is appropriate. However, the Gq protein-mediated potencies are generally low, with low efficacy (relative to 5-HT) at the 5-HT2A receptor, somewhat higher efficacy at the 5-HT2B subtype, and full or nearly full efficacy at the 5-HT2C subtype.

AI-driven GPCR analysis, engineering, and targeting

This article investigates the role of recent advances in Artificial Intelligence (AI) to revolutionise the study of G protein-coupled receptors (GPCRs). AI has been applied to many areas of GPCR research, including the application of machine learning (ML) in GPCR classification, prediction of GPCR activation levels, modelling GPCR 3D structures and interactions, understanding G-protein selectivity, aiding elucidation of GPCRs structures, and drug design. Despite progress, challenges in predicting GPCR structures and addressing the complex nature of GPCRs remain, providing avenues for future research and development.

Activity Models of Key GPCR Families in the Central Nervous System: A Tool for Many Purposes

G protein-coupled receptors (GPCRs) are targets of many drugs, of which ∼25% are indicated for central nervous system (CNS) disorders. Drug promiscuity affects their efficacy and safety profiles. Predicting the polypharmacology profile of compounds against GPCRs can thus provide a basis for producing more precise therapeutics by considering the targets and the anti-targets in that family of closely related proteins. We provide a tool for predicting the polypharmacology of compounds within prominent GPCR families in the CNS: serotonin, dopamine, histamine, muscarinic, opioid, and cannabinoid receptors. Our in-house algorithm, "iterative stochastic elimination" (ISE), produces high-quality ligand-based models for agonism and antagonism at 31 GPCRs. The ISE models correctly predict 68% of CNS drug-GPCR interactions, while the "similarity ensemble approach" predicts only 33%. The activity models correctly predict 56% of reported activities of DrugBank molecules for these CNS receptors. We conclude that the combination of interactions and activity profiles generated by screening through our models form the basis for subsequent designing and discovering novel therapeutics, either single, multitargeting, or repurposed.

Distinct activation mechanisms regulate subtype selectivity of Cannabinoid receptors

Design of cannabinergic subtype selective ligands is challenging because of high sequence and structural similarities of cannabinoid receptors (CB₁ and CB₂). We hypothesize that the subtype selectivity of designed selective ligands can be explained by the ligand binding to the conformationally distinct states between cannabinoid receptors. Analysis of ~ 700 μs of unbiased simulations using Markov state models and VAMPnets identifies the similarities and distinctions between the activation mechanism of both receptors. Structural and dynamic comparisons of metastable intermediate states allow us to observe the distinction in the binding pocket volume change during CB₁ and CB₂ activation. Docking analysis reveals that only a few of the intermediate metastable states of CB₁ show high affinity towards CB₂ selective agonists. In contrast, all the CB₂ metastable states show a similar affinity for these agonists. These results mechanistically explain the subtype selectivity of these agonists by deciphering the activation mechanism of cannabinoid receptors.

Positron Emission Tomography (PET) Imaging Tracers for Serotonin Receptors

Serotonin (5-hydroxytryptamine, 5-HT) and 5-HT receptors (5-HTRs) have crucial roles in various neuropsychiatric disorders and neurodegenerative diseases, making them attractive diagnostic and therapeutic targets. Positron emission tomography (PET) is a noninvasive nuclear molecular imaging technique and is an essential tool in clinical diagnosis and drug discovery. In this context, numerous PET ligands have been developed for "visualizing" 5-HTRs in the brain and translated into human use to study disease mechanisms and/or support drug development. Herein, we present a comprehensive repertoire of 5-HTR PET ligands by focusing on their chemotypes and performance in PET imaging studies. Furthermore, this Perspective summarizes recent 5-HTR-focused drug discovery, including biased agonists and allosteric modulators, which would stimulate the development of more potent and subtype-selective 5-HTR PET ligands and thus further our understanding of 5-HTR biology.

Structure-Based Virtual Screening for Ligands of G Protein-Coupled Receptors: What Can Molecular Docking Do for You?

G protein-coupled receptors (GPCRs) constitute the largest family of membrane proteins in the human genome and are important therapeutic targets. During the last decade, the number of atomic-resolution structures of GPCRs has increased rapidly, providing insights into drug binding at the molecular level. These breakthroughs have created excitement regarding the potential of using structural information in ligand design and initiated a new era of rational drug discovery for GPCRs. The molecular docking method is now widely applied to model the three-dimensional structures of GPCR-ligand complexes and screen for chemical probes in large compound libraries. In this review article, we first summarize the current structural coverage of the GPCR superfamily and the understanding of receptor-ligand interactions at atomic resolution. We then present the general workflow of structure-based virtual screening and strategies to discover GPCR ligands in chemical libraries. We assess the state of the art of this research field by summarizing prospective applications of virtual screening based on experimental structures. Strategies to identify compounds with specific efficacy and selectivity profiles are discussed, illustrating the opportunities and limitations of the molecular docking method. Our overview shows that structure-based virtual screening can discover novel leads and will be essential in pursuing the next generation of GPCR drugs. SIGNIFICANCE STATEMENT: Extraordinary advances in the structural biology of G protein-coupled receptors have revealed the molecular details of ligand recognition by this large family of therapeutic targets, providing novel avenues for rational drug design. Structure-based docking is an efficient computational approach to identify novel chemical probes from large compound libraries, which has the potential to accelerate the development of drug candidates.

pdCSM-GPCR: predicting potent GPCR ligands with graph-based signatures

MOTIVATION

G protein-coupled receptors (GPCRs) can selectively bind to many types of ligands, ranging from light-sensitive compounds, ions, hormones, pheromones and neurotransmitters, modulating cell physiology. Considering their role in many essential cellular processes, they are one of the most targeted protein families, with over a third of all approved drugs modulating GPCR signalling. Despite this, the large diversity of receptors and their multipass transmembrane architectures make the identification and development of novel specific, and safe GPCR ligands a challenge. While computational approaches have the potential to assist GPCR drug development, they have presented limited performance and generalization capabilities. Here, we explored the use of graph-based signatures to develop pdCSM-GPCR, a method capable of rapidly and accurately screening potential GPCR ligands.

RESULTS

Bioactivity data (IC50, EC50, Ki and Kd) for individual GPCRs were curated. After curation, we used the data for developing predictive models for 36 major GPCR targets, across 4 classes (A, B, C and F). Our models compose the most comprehensive computational resource for GPCR bioactivity prediction to date. Across stratified 10-fold cross-validation and blind tests, our approach achieved Pearson's correlations of up to 0.89, significantly outperforming previous methods. Interpreting our results, we identified common important features of potent GPCRs ligands, which tend to have bicyclic rings, leading to higher levels of aromaticity. We believe pdCSM-GPCR will be an invaluable tool to assist screening efforts, enriching compound libraries and ranking candidates for further experimental validation.

AVAILABILITY AND IMPLEMENTATION

pdCSM-GPCR predictive models and datasets used have been made available via a freely accessible and easy-to-use web server at http://biosig.unimelb.edu.au/pdcsm_gpcr/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics Advances online.

Artificial intelligence in drug design: algorithms, applications, challenges and ethics

The discovery paradigm of drugs is rapidly growing due to advances in machine learning (ML) and artificial intelligence (AI). This review covers myriad faces of AI and ML in drug design. There is a plethora of AI algorithms, the most common of which are summarized in this review. In addition, AI is fraught with challenges that are highlighted along with plausible solutions to them. Examples are provided to illustrate the use of AI and ML in drug discovery and in predicting drug properties such as binding affinities and interactions, solubility, toxicology, blood–brain barrier permeability and chemical properties. The review also includes examples depicting the implementation of AI and ML in tackling intractable diseases such as COVID-19, cancer and Alzheimer’s disease. Ethical considerations and future perspectives of AI are also covered in this review.

Trends in application of advancing computational approaches in GPCR ligand discovery

G protein-coupled receptors (GPCRs) comprise the most important superfamily of protein targets in current ligand discovery and drug development. GPCRs are integral membrane proteins that play key roles in various cellular signaling processes. Therefore, GPCR signaling pathways are closely associated with numerous diseases, including cancer and several neurological, immunological, and hematological disorders. Computer-aided drug design (CADD) can expedite the process of GPCR drug discovery and potentially reduce the actual cost of research and development. Increasing knowledge of biological structures, as well as improvements on computer power and algorithms, have led to unprecedented use of CADD for the discovery of novel GPCR modulators. Similarly, machine learning approaches are now widely applied in various fields of drug target research. This review briefly summarizes the application of rising CADD methodologies, as well as novel machine learning techniques, in GPCR structural studies and bioligand discovery in the past few years. Recent novel computational strategies and feasible workflows are updated, and representative cases addressing challenging issues on olfactory receptors, biased agonism, and drug-induced cardiotoxic effects are highlighted to provide insights into future GPCR drug discovery.

Structure, Function, and Pharmaceutical Ligands of 5-Hydroxytryptamine 2B Receptor

Since the first characterization of the 5-hydroxytryptamine 2B receptor (5-HT2BR) in 1992, significant progress has been made in 5-HT2BR research. Herein, we summarize the biological function, structure, and small-molecule pharmaceutical ligands of the 5-HT2BR. Emerging evidence has suggested that the 5-HT2BR is implicated in the regulation of the cardiovascular system, fibrosis disorders, cancer, the gastrointestinal (GI) tract, and the nervous system. Eight crystal complex structures of the 5-HT2BR bound with different ligands provided great insights into ligand recognition, activation mechanism, and biased signaling. Numerous 5-HT2BR antagonists have been discovered and developed, and several of them have advanced to clinical trials. It is expected that the novel 5-HT2BR antagonists with high potency and selectivity will lead to the development of first-in-class drugs in various therapeutic areas.

Biased Ligands Differentially Shape the Conformation of the Extracellular Loop Region in 5-HT2B Receptors

G protein-coupled receptors are linked to various intracellular transducers, each pathway associated with different physiological effects. Biased ligands, capable of activating one pathway over another, are gaining attention for their therapeutic potential, as they could selectively activate beneficial pathways whilst avoiding those responsible for adverse effects. We performed molecular dynamics simulations with known β-arrestin-biased ligands like lysergic acid diethylamide and ergotamine in complex with the 5-HT_2B receptor and discovered that the extent of ligand bias is directly connected with the degree of closure of the extracellular loop region. Given a loose allosteric coupling of extracellular and intracellular receptor regions, we delineate a concept for biased signaling at serotonin receptors, by which conformational interference with binding pocket closure restricts the signaling repertoire of the receptor. Molecular docking studies of biased ligands gathered from the BiasDB demonstrate that larger ligands only show plausible docking poses in the ergotamine-bound structure, highlighting the conformational constraints associated with bias. This emphasizes the importance of selecting the appropriate receptor conformation on which to base virtual screening workflows in structure-based drug design of biased ligands. As this mechanism of ligand bias has also been observed for muscarinic receptors, our studies provide a general mechanism of signaling bias transferable between aminergic receptors.

Illuminating the Path to Target GPCR Structures and Functions

G-Protein-coupled receptors (GPCRs) are ubiquitous within eukaryotes, responsible for a wide array of physiological and pathological processes. Indeed, the fact that they are the most drugged target in the human genome is indicative of their importance. Despite the clear interest in GPCRs, most information regarding their activity has been so far obtained by analyzing the response from a "bulk medium". As such, this Perspective summarizes some of the common methods for this indirect observation. Nonetheless, by inspecting approaches applying super-resolution imaging, we argue that imaging is perfectly situated to obtain more detailed structural and spatial information, assisting in the development of new GPCR-targeted drugs and clinical strategies. The benefits of direct optical visualization of GPCRs are analyzed in the context of potential future directions in the field.

Fragment-Based Computational Method for Designing GPCR Ligands

G protein-coupled receptors (GPCRs) are the largest family of cell surface receptors, which is arguably the most important family of drug target. With the technology breakthroughs in X-ray crystallography and cryo-electron microscopy, more than 300 GPCR-ligand complex structures have been publicly reported since 2007, covering about 60 unique GPCRs. Such abundant structural information certainly will facilitate the structure-based drug design by targeting GPCRs. In this study, we have developed a fragment-based computational method for designing novel GPCR ligands. We first extracted the characteristic interaction patterns (CIPs) on the binding interfaces between GPCRs and their ligands. The CIPs were used as queries to search the chemical fragments derived from GPCR ligands, which were required to form similar interaction patterns with GPCR. Then, the selected chemical fragments were assembled into complete molecules by using the AutoT&T2 software. In this work, we chose β-adrenergic receptor (β-AR) and muscarinic acetylcholine receptor (mAChR) as the targets to validate this method. Based on the designs suggested by our method, samples of 63 compounds were purchased and tested in a cell-based functional assay. A total of 15 and 22 compounds were identified as active antagonists for β₂-AR and mAChR M1, respectively. Molecular dynamics simulations and binding free energy analysis were performed to explore the key interactions (e.g., hydrogen bonds and π-π interactions) between those active compounds and their target GPCRs. In summary, our work presents a useful approach to the de novo design of GPCR ligands based on the relevant 3D structural information.

Applications of machine learning in GPCR bioactive ligand discovery

GPCRs constitute the largest druggable family having targets for 475 Food and Drug Administration (FDA) approved drugs. As GPCRs are of great interest to pharmaceutical industry, enormous efforts are being expended to find relevant and potent GPCR ligands as lead compounds. There are tens of millions of compounds present in different chemical databases. In order to scan this immense chemical space, computational methods, especially machine learning (ML) methods, are essential components of GPCR drug discovery pipelines. ML approaches have applications in both ligand-based and structure-based virtual screening. We present here a cheminformatics overview of ML applications to different stages of GPCR drug discovery. Focusing on olfactory receptors, which are the largest family of GPCRs, a case study for predicting agonists for an ectopic olfactory receptor, OR1G1, compares four classical ML methods.