Multidimensional de novo design reveals 5-HT2B receptor-selective ligands

Chemoinformatic approaches for navigating large chemical spaces

INTRODUCTION

Large chemical spaces (CSs) include traditional large compound collections, combinatorial libraries covering billions to trillions of molecules, DNA-encoded chemical libraries comprising complete combinatorial CSs in a single mixture, and virtual CSs explored by generative models. The diverse nature of these types of CSs require different chemoinformatic approaches for navigation.

AREAS COVERED

An overview of different types of large CSs is provided. Molecular representations and similarity metrics suitable for large CS exploration are discussed. A summary of navigation of CSs in generative models is provided. Methods for characterizing and comparing CSs are discussed.

EXPERT OPINION

The size of large CSs might restrict navigation to specialized algorithms and limit it to considering neighborhoods of structurally similar molecules. Efficient navigation of large CSs not only requires methods that scale with size but also requires smart approaches that focus on better but not necessarily larger molecule selections. Deep generative models aim to provide such approaches by implicitly learning features relevant for targeted biological properties. It is unclear whether these models can fulfill this ideal as validation is difficult as long as the covered CSs remain mainly virtual without experimental verification.

Using deep neural networks to explore chemical space

INTRODUCTION

The popularity and success of advanced AI methods like deep neural networks has led to novel ways for exploring chemical space. Their opaque nature poses challenges for model evaluation regarding novelty, uniqueness, and distribution of the chemical space covered. However, these methods also promise to be able to explore uncharted chemical space in novel ways that do not rely directly on structural similarity.

AREAS COVERED

This review provides an overview of popular deep learning methods for chemical space exploration. Crucial aspects like choice of molecular representation, training for focused chemical space exploration, and criteria for assessing and validating chemical space coverage are discussed.

EXPERT OPINION

Deep learning offers great potential for chemical space exploration beyond conventional fragment-based methods. Given the rarity of prospective applications and considering the difficulty in assessing representativeness and comprehensiveness of chemical space covered, developing criteria for assessing and validating generative models is of great significance. Latent space models like variational autoencoders are conceptually appealing for inverse QSAR/QSPR approaches as neighborhood relationships in latent space can be trained to reflect property similarities. Future research in understanding and interpreting generative models might lead to a better understanding of biologically relevant properties of molecules.

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.

The Advent of Generative Chemistry

Generative adversarial networks (GANs), first published in 2014, are among the most important concepts in modern artificial intelligence (AI). Bridging deep learning and game theory, GANs are used to generate or "imagine" new objects with desired properties. Since 2016, multiple GANs with reinforcement learning (RL) have been successfully applied in pharmacology for de novo molecular design. Those techniques aim at a more efficient use of the data and a better exploration of the chemical space. We review recent advances for the generation of novel molecules with desired properties with a focus on the applications of GANs, RL, and related techniques. We also discuss the current limitations and challenges in the new growing field of generative chemistry.

Multi-objective de novo molecular design of organic structure-directing agents for zeolites using nature-inspired ant colony optimization

Organic structure-directing agents (OSDAs) are often employed for synthesis of zeolites with desired frameworks. A priori prediction of such OSDAs has mainly relied on the interaction energies between OSDAs and zeolite frameworks, without cost considerations. For practical purposes, the cost of OSDAs becomes a critical issue. Therefore, the development of a computational de novo prediction methodology that can speed up the trial-and-error cycle in the search for less expensive OSDAs is desired. This study utilized a nature-inspired ant colony optimization method to predict physicochemically and/or economically preferable OSDAs, while also taking molecular similarity and heuristics of zeolite synthesis into consideration. The prediction results included experimentally known OSDAs, candidates having structures closely related to known OSDAs, and novel ones, suggesting the applicability of this approach.

Inspired by the exploratory methods of ant colonies, adaptive optimization was employed to explore the chemical space for organic molecules that guide zeolite crystallization, giving both physicochemically and economically promising molecules.

Machine learning for target discovery in drug development

The discovery of macromolecular targets for bioactive agents is currently a bottleneck for the informed design of chemical probes and drug leads. Typically, activity profiling against genetically manipulated cell lines or chemical proteomics is pursued to shed light on their biology and deconvolute drug-target networks. By taking advantage of the ever-growing wealth of publicly available bioactivity data, learning algorithms now provide an attractive means to generate statistically motivated research hypotheses and thereby prioritize biochemical screens. Here, we highlight recent successes in machine intelligence for target identification and discuss challenges and opportunities for drug discovery.

Computational advances in combating colloidal aggregation in drug discovery

Small molecule effectors are essential for drug discovery. Specific molecular recognition, reversible binding and dose-dependency are usually key requirements to ensure utility of a novel chemical entity. However, artefactual frequent-hitter and assay interference compounds may divert lead optimization and screening programmes towards attrition-prone chemical matter. Colloidal aggregates are the prime source of false positive readouts, either through protein sequestration or protein-scaffold mimicry. Nevertheless, assessment of colloidal aggregation remains somewhat overlooked and under-appreciated. In this Review, we discuss the impact of aggregation in drug discovery by analysing select examples from the literature and publicly-available datasets. We also examine and comment on technologies used to experimentally identify these potentially problematic entities. We focus on evidence-based computational filters and machine learning algorithms that may be swiftly deployed to flag chemical matter and mitigate the impact of aggregates in discovery programmes. We highlight the tools that can be used to scrutinize libraries, and identify and eliminate these problematic compounds.

Harnessing the potential of natural products in drug discovery from a cheminformatics vantage point

Natural products (NPs) present a privileged source of inspiration for chemical probe and drug design. Despite the biological pre-validation of the underlying molecular architectures and their relevance in drug discovery, the poor accessibility to NPs, complexity of the synthetic routes and scarce knowledge of their macromolecular counterparts in phenotypic screens still hinder their broader exploration. Cheminformatics algorithms now provide a powerful means of circumventing the abovementioned challenges and unlocking the full potential of NPs in a drug discovery context. Herein, I discuss recent advances in the computer-assisted design of NP mimics and how artificial intelligence may accelerate future NP-inspired molecular medicine.

Exploring G Protein-Coupled Receptors (GPCRs) Ligand Space via Cheminformatics Approaches: Impact on Rational Drug Design

The primary goal of rational drug discovery is the identification of selective ligands which act on single or multiple drug targets to achieve the desired clinical outcome through the exploration of total chemical space. To identify such desired compounds, computational approaches are necessary in predicting their drug-like properties. G Protein-Coupled Receptors (GPCRs) represent one of the largest and most important integral membrane protein families. These receptors serve as increasingly attractive drug targets due to their relevance in the treatment of various diseases, such as inflammatory disorders, metabolic imbalances, cardiac disorders, cancer, monogenic disorders, etc. In the last decade, multitudes of three-dimensional (3D) structures were solved for diverse GPCRs, thus referring to this period as the "golden age for GPCR structural biology." Moreover, accumulation of data about the chemical properties of GPCR ligands has garnered much interest toward the exploration of GPCR chemical space. Due to the steady increase in the structural, ligand, and functional data of GPCRs, several cheminformatics approaches have been implemented in its drug discovery pipeline. In this review, we mainly focus on the cheminformatics-based paradigms in GPCR drug discovery. We provide a comprehensive view on the ligand- and structure-based cheminformatics approaches which are best illustrated via GPCR case studies. Furthermore, an appropriate combination of ligand-based knowledge with structure-based ones, i.e., integrated approach, which is emerging as a promising strategy for cheminformatics-based GPCR drug design is also discussed.

Challenges and Opportunities in Drug Discovery of Biased Ligands

The observation of biased agonism in G protein-coupled receptors (GPCRs) has provided new approaches for the development of more efficacious and safer drugs. However, in order to rationally design biased drugs, one must understand the molecular basis of this phenomenon. Computational approaches can help in exploring the conformational universe of GPCRs and detecting conformational states with relevance for distinct functional outcomes. This information is extremely valuable for the development of new therapeutic agents that promote desired conformational receptor states and responses while avoiding the ones leading to undesired side-effects.This book chapter intends to introduce the reader to powerful computational approaches for sampling the conformational space of these receptors, focusing first on molecular dynamics and the analysis of the produced data through methods such as dimensionality reduction, Markov State Models and adaptive sampling. Then, we show how to seek for compounds that target distinct conformational states via docking and virtual screening. In addition, we describe how to detect receptor-ligand interactions that drive signaling bias and comment current challenges and opportunities of presented methods.

Automating drug discovery

Small-molecule drug discovery can be viewed as a challenging multidimensional problem in which various characteristics of compounds - including efficacy, pharmacokinetics and safety - need to be optimized in parallel to provide drug candidates. Recent advances in areas such as microfluidics-assisted chemical synthesis and biological testing, as well as artificial intelligence systems that improve a design hypothesis through feedback analysis, are now providing a basis for the introduction of greater automation into aspects of this process. This could potentially accelerate time frames for compound discovery and optimization and enable more effective searches of chemical space. However, such approaches also raise considerable conceptual, technical and organizational challenges, as well as scepticism about the current hype around them. This article aims to identify the approaches and technologies that could be implemented robustly by medicinal chemists in the near future and to critically analyse the opportunities and challenges for their more widespread application.

Computational Multitarget Drug Design

Designing drugs that can simultaneously interact with multiple targets is a promising approach for treating complicated diseases. Compared to using combinations of single target drugs, multitarget drugs have advantages of higher efficacy, improved safety profile, and simpler administration. Many in silico methods have been developed to approach different aspects of this polypharmacology-guided drug design, particularly for drug repurposing and multitarget drug design. In this review, we summarize recent progress in computational multitarget drug design and discuss their advantages and limitations. Perspectives for future drug development will also be discussed.

A segmented flow platform for on-demand medicinal chemistry and compound synthesis in oscillating droplets

An automated flow chemistry platform performs single/multi-phase and single/multi-step chemistries in 14 μL droplets with online analysis and product collection.

Structure-Based Scaffold Repurposing for G Protein-Coupled Receptors: Transformation of Adenosine Derivatives into 5HT2B/5HT2C Serotonin Receptor Antagonists

Adenosine derivatives developed to activate adenosine receptors (ARs) revealed micromolar activity at serotonin 5HT_2B and 5HT_2C receptors (5HTRs). We explored the structure-activity relationship at 5HT₂Rs and modeled receptor interactions in order to optimize affinity and simultaneously reduce AR affinity. Depending on N⁶ substitution, small 5'-alkylamide modification maintained 5HT_2BR affinity, which was enhanced upon ribose substitution with rigid bicyclo[3.1.0]hexane (North (N)-methanocarba), e.g., N⁶-dicyclopropylmethyl 4'-CH₂OH derivative 14 (K_i 11 nM). 5'-Methylamide 23 was 170-fold selective as antagonist for 5HT_2BR vs 5HT_2CR. 5'-Methyl 25 and ethyl 26 esters potently antagonized 5HT₂Rs with moderate selectivity in comparison to ARs; related 6-N,N-dimethylamino analogue 30 was 5HT₂R-selective. 5' position flexibility of substitution was indicated in 5HT_2BR docking. Both 5'-ester and 5'-amide derivatives displayed in vivo t_1/2 of 3-4 h. Thus, we used G protein-coupled receptor modeling to repurpose nucleoside scaffolds in favor of binding at nonpurine receptors as novel 5HT₂R antagonists, with potential for cardioprotection, liver protection, or central nervous system activity.

Scoring of de novo Designed Chemical Entities by Macromolecular Target Prediction

Computational de novo molecular design and macromolecular target prediction have become routine in applied cheminformatics. In this study, we have generated populations of drug template-derived designs using ligand-based building block assembly, and predicted their potential targets. The results of our analysis show that the reaction-based de novo design generated new chemical entities with similar properties and pharmacophores as that of the template drugs as well as up to 44 % of the de novo compounds receiving the correct target predictions. Keeping in mind the probabilistic nature of the methods, such a combination of fast and meaningful computational structure generation by reaction-based design and product scoring by target class prediction may be appropriate for prospective application in medicinal chemistry.

Multi-objective active machine learning rapidly improves structure-activity models and reveals new protein-protein interaction inhibitors

Active machine learning puts artificial intelligence in charge of a sequential, feedback-driven discovery process. We present the application of a multi-objective active learning scheme for identifying small molecules that inhibit the protein-protein interaction between the anti-cancer target CXC chemokine receptor 4 (CXCR4) and its endogenous ligand CXCL-12 (SDF-1). Experimental design by active learning was used to retrieve informative active compounds that continuously improved the adaptive structure-activity model. The balanced character of the compound selection function rapidly delivered new molecular structures with the desired inhibitory activity and at the same time allowed us to focus on informative compounds for model adjustment. The results of our study validate active learning for prospective ligand finding by adaptive, focused screening of large compound repositories and virtual compound libraries.

Drug combination therapy increases successful drug repositioning

Repositioning of approved drugs has recently gained new momentum for rapid identification and development of new therapeutics for diseases that lack effective drug treatment. Reported repurposing screens have increased dramatically in number in the past five years. However, many newly identified compounds have low potency; this limits their immediate clinical applications because the known, tolerated plasma drug concentrations are lower than the required therapeutic drug concentrations. Drug combinations of two or more compounds with different mechanisms of action are an alternative approach to increase the success rate of drug repositioning.

In silico Exploration of the Conformational Universe of GPCRs

The structural plasticity of G protein coupled receptors (GPCRs) leads to a conformational universe going from inactive to active receptor states with several intermediate states. Many of them have not been captured yet and their role for GPCR activation is not well understood. The study of this conformational space and the transition dynamics between different receptor populations is a major challenge in molecular biophysics. The rational design of effector molecules that target such receptor populations allows fine-tuning receptor signalling with higher specificity to produce drugs with safer therapeutic profiles. In this minireview, we outline highly conserved receptor regions which are considered determinant for the establishment of distinct receptor states. We then discuss in-silico approaches such as dimensionality reduction methods and Markov State Models to explore the GPCR conformational universe and exploit the obtained conformations through structure-based drug design.

Web-based 3D-visualization of the DrugBank chemical space

Background

Similarly to the periodic table for elements, chemical space offers an organizing principle for representing the diversity of organic molecules, usually in the form of multi-dimensional property spaces that are subjected to dimensionality reduction methods to obtain 3D-spaces or 2D-maps suitable for visual inspection. Unfortunately, tools to look at chemical space on the internet are currently very limited.

Results

Herein we present webDrugCS, a web application freely available at www.gdb.unibe.ch to visualize DrugBank (www.drugbank.ca, containing over 6000 investigational and approved drugs) in five different property spaces. WebDrugCS displays 3D-clouds of color-coded grid points representing molecules, whose structural formula is displayed on mouse over with an option to link to the corresponding molecule page at the DrugBank website. The 3D-clouds are obtained by principal component analysis of high dimensional property spaces describing constitution and topology (42D molecular quantum numbers MQN), structural features (34D SMILES fingerprint SMIfp), molecular shape (20D atom pair fingerprint APfp), pharmacophores (55D atom category extended atom pair fingerprint Xfp) and substructures (1024D binary substructure fingerprint Sfp). User defined molecules can be uploaded as SMILES lists and displayed together with DrugBank. In contrast to 2D-maps where many compounds fold onto each other, these 3D-spaces have a comparable resolution to their parent high-dimensional chemical space.

Conclusion

To the best of our knowledge webDrugCS is the first publicly available web tool for interactive visualization and exploration of the DrugBank chemical space in 3D. WebDrugCS works on computers, tablets and phones, and facilitates the visual exploration of DrugBank to rapidly learn about the structural diversity of small molecule drugs.Graphical abstract

De Novo Design at the Edge of Chaos

Computational medicinal chemistry offers viable strategies for finding, characterizing, and optimizing innovative pharmacologically active compounds. Technological advances in both computer hardware and software as well as biological chemistry have enabled a renaissance of computer-assisted "de novo" design of molecules with desired pharmacological properties. Here, we present our current perspective on the concept of automated molecule generation by highlighting chemocentric methods that may capture druglike chemical space, consider ligand promiscuity for hit and lead finding, and provide fresh ideas for the rational design of customized screening of compound libraries.

Similarity Mapplet: Interactive Visualization of the Directory of Useful Decoys and ChEMBL in High Dimensional Chemical Spaces

An Internet portal accessible at www.gdb.unibe.ch has been set up to automatically generate color-coded similarity maps of the ChEMBL database in relation to up to two sets of active compounds taken from the enhanced Directory of Useful Decoys (eDUD), a random set of molecules, or up to two sets of user-defined reference molecules. These maps visualize the relationships between the selected compounds and ChEMBL in six different high dimensional chemical spaces, namely MQN (42-D molecular quantum numbers), SMIfp (34-D SMILES fingerprint), APfp (20-D shape fingerprint), Xfp (55-D pharmacophore fingerprint), Sfp (1024-bit substructure fingerprint), and ECfp4 (1024-bit extended connectivity fingerprint). The maps are supplied in form of Java based desktop applications called "similarity mapplets" allowing interactive content browsing and linked to a "Multifingerprint Browser for ChEMBL" (also accessible directly at www.gdb.unibe.ch ) to perform nearest neighbor searches. One can obtain six similarity mapplets of ChEMBL relative to random reference compounds, 606 similarity mapplets relative to single eDUD active sets, 30,300 similarity mapplets relative to pairs of eDUD active sets, and any number of similarity mapplets relative to user-defined reference sets to help visualize the structural diversity of compound series in drug optimization projects and their relationship to other known bioactive compounds.

Fragment-Based De Novo Design Reveals a Small-Molecule Inhibitor of Helicobacter Pylori HtrA

Sustained identification of innovative chemical entities is key for the success of chemical biology and drug discovery. We report the fragment-based, computer-assisted de novo design of a small molecule inhibiting Helicobacter pylori HtrA protease. Molecular binding of the designed compound to HtrA was confirmed through biophysical methods, supporting its functional activity in vitro. Hit expansion led to the identification of the currently best-in-class HtrA inhibitor. The results obtained reinforce the validity of ligand-based de novo design and binding-kinetics-guided optimization for the efficient discovery of pioneering lead structures and prototyping drug-like chemical probes with tailored bioactivity.

Repurposing de novo designed entities reveals phosphodiesterase 3B and cathepsin L modulators

Scaffold hopping: a computational algorithm correctly predicted the macromolecular target ofde novogenerated small molecular entities.