Machine learning estimates of natural product conformational energies

Recent advances in the development of P2Y14R inhibitors: a patent and literature review (2018-present)

INTRODUCTION

The P2Y14 receptor (P2Y14R), a member of the G protein-coupled receptor family, is activated by extracellular nucleotides. Due to its involvement in inflammatory, immunological and other associated processes, P2Y14R has emerged as a promising therapeutic target. Despite lacking a determined three-dimensional crystal structure, the homology modeling technique based on closely related P2Y receptors' crystallography has been extensively utilized for developing active compounds targeting P2Y14R. Recent discoveries have unveiled numerous highly effective and subtype-specific P2Y14R inhibitors. This study presents an overview of the latest advancements in P2Y14R inhibitors.

AREAS COVERED

This review presents an overview of the advancements in P2Y14R inhibitor research over the past five years, encompassing new patents, journal articles, and highlighting the therapeutic prospects inherent in these compounds.

EXPERT OPINION

The recent revelation of the vast potential of P2Y14R inhibitors has led to the development of novel compounds that exhibit promising capabilities for the treatment of sterile inflammation of the kidney, potentially diabetes, and asthma. Despite being a relatively nascent class of compounds, certain members have already exhibited their capacity to surmount specific challenges posed by conventional P2Y14R inhibitors. Targeting P2Y14R through small molecules may present a promising therapeutic strategy for effectively managing diverse inflammatory diseases.

Multifidelity Machine Learning for Molecular Excitation Energies

The accurate but fast calculation of molecular excited states is still a very challenging topic. For many applications, detailed knowledge of the energy funnel in larger molecular aggregates is of key importance, requiring highly accurate excitation energies. To this end, machine learning techniques can be a very useful tool, though the cost of generating highly accurate training data sets still remains a severe challenge. To overcome this hurdle, this work proposes the use of multifidelity machine learning where very little training data from high accuracies is combined with cheaper and less accurate data to achieve the accuracy of the costlier level. In the present study, the approach is employed to predict vertical excitation energies to the first excited state for three molecules of increasing size, namely, benzene, naphthalene, and anthracene. The energies are trained and tested for conformations stemming from classical molecular dynamics and density functional based tight-binding simulations. It can be shown that the multifidelity machine learning model can achieve the same accuracy as a machine learning model built only on high-cost training data while expending a much lower computational effort to generate the data. The numerical gain observed in these benchmark test calculations was over a factor of 30 but certainly can be much higher for high-accuracy data.

Active learning of reactive Bayesian force fields applied to heterogeneous catalysis dynamics of H/Pt

Atomistic modeling of chemically reactive systems has so far relied on either expensive ab initio methods or bond-order force fields requiring arduous parametrization. Here, we describe a Bayesian active learning framework for autonomous "on-the-fly" training of fast and accurate reactive many-body force fields during molecular dynamics simulations. At each time-step, predictive uncertainties of a sparse Gaussian process are evaluated to automatically determine whether additional ab initio training data are needed. We introduce a general method for mapping trained kernel models onto equivalent polynomial models whose prediction cost is much lower and independent of the training set size. As a demonstration, we perform direct two-phase simulations of heterogeneous H2 turnover on the Pt(111) catalyst surface at chemical accuracy. The model trains itself in three days and performs at twice the speed of a ReaxFF model, while maintaining much higher fidelity to DFT and excellent agreement with experiment.

Δ-Quantum machine-learning for medicinal chemistry

Many molecular design tasks benefit from fast and accurate calculations of quantum-mechanical (QM) properties. However, the computational cost of QM methods applied to drug-like molecules currently renders large-scale applications of quantum chemistry challenging. Aiming to mitigate this problem, we developed DelFTa, an open-source toolbox for the prediction of electronic properties of drug-like molecules at the density functional (DFT) level of theory, using Δ-machine-learning. Δ-Learning corrects the prediction error (Δ) of a fast but inaccurate property calculation. DelFTa employs state-of-the-art three-dimensional message-passing neural networks trained on a large dataset of QM properties. It provides access to a wide array of quantum observables on the molecular, atomic and bond levels by predicting approximations to DFT values from a low-cost semiempirical baseline. Δ-Learning outperformed its direct-learning counterpart for most of the considered QM endpoints. The results suggest that predictions for non-covalent intra- and intermolecular interactions can be extrapolated to larger biomolecular systems. The software is fully open-sourced and features documented command-line and Python APIs.

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.

Molecular Modeling Applied to the Discovery of New Lead Compounds for P2 Receptors Based on Natural Sources

P2 receptors are a family of transmembrane receptors activated by nucleotides and nucleosides. Two classes have been described in mammals, P2X and P2Y, which are implicated in various diseases. Currently, only P2Y12 has medicines approved for clinical use as antiplatelet agents and natural products have emerged as a source of new drugs with action on P2 receptors due to the diversity of chemical structures. In drug discovery, in silico virtual screening (VS) techniques have become popular because they have numerous advantages, which include the evaluation of thousands of molecules against a target, usually proteins, faster and cheaper than classical high throughput screening (HTS). The number of studies using VS techniques has been growing in recent years and has led to the discovery of new molecules of natural origin with action on different P2X and P2Y receptors. Using different algorithms it is possible to obtain information on absorption, distribution, metabolism, toxicity, as well as predictions on biological activity and the lead-likeness of the selected hits. Selected biomolecules may then be tested by molecular dynamics and, if necessary, rationally designed or modified to improve their interaction for the target. The algorithms of these in silico tools are being improved to permit the precision development of new drugs and, in the future, this process will take the front of drug development against some central nervous system (CNS) disorders. Therefore, this review discusses the methodologies of in silico tools concerning P2 receptors, as well as future perspectives and discoveries, such as the employment of artificial intelligence in drug discovery.

Assigning the Origin of Microbial Natural Products by Chemical Space Map and Machine Learning

Microbial natural products (NPs) are an important source of drugs, however, their structural diversity remains poorly understood. Here we used our recently reported MinHashed Atom Pair fingerprint with diameter of four bonds (MAP4), a fingerprint suitable for molecules across very different sizes, to analyze the Natural Products Atlas (NPAtlas), a database of 25,523 NPs of bacterial or fungal origin. To visualize NPAtlas by MAP4 similarity, we used the dimensionality reduction method tree map (TMAP). The resulting interactive map organizes molecules by physico-chemical properties and compound families such as peptides and glycosides. Remarkably, the map separates bacterial and fungal NPs from one another, revealing that these two compound families are intrinsically different despite their related biosynthetic pathways. We used these differences to train a machine learning model capable of distinguishing between NPs of bacterial or fungal origin.

Quantum Chemistry in the Age of Machine Learning

As the quantum chemistry (QC) community embraces machine learning (ML), the number of new methods and applications based on the combination of QC and ML is surging. In this Perspective, a view of the current state of affairs in this new and exciting research field is offered, challenges of using machine learning in quantum chemistry applications are described, and potential future developments are outlined. Specifically, examples of how machine learning is used to improve the accuracy and accelerate quantum chemical research are shown. Generalization and classification of existing techniques are provided to ease the navigation in the sea of literature and to guide researchers entering the field. The emphasis of this Perspective is on supervised machine learning.

NPASS: natural product activity and species source database for natural product research, discovery and tool development

There has been renewed interests in the exploration of natural products (NPs) for drug discovery, and continuous investigations of the therapeutic claims and mechanisms of traditional and herbal medicines. In-silico methods have been employed for facilitating these studies. These studies and the optimization of in-silico algorithms for NP applications can be facilitated by the quantitative activity and species source data of the NPs. A number of databases collectively provide the structural and other information of ∼470 000 NPs, including qualitative activity information for many NPs, but only ∼4000 NPs are with the experimental activity values. There is a need for the activity and species source data of more NPs. We therefore developed a new database, NPASS (Natural Product Activity and Species Source) to complement other databases by providing the experimental activity values and species sources of 35 032 NPs from 25 041 species targeting 5863 targets (2946 proteins, 1352 microbial species and 1227 cell-lines). NPASS contains 446 552 quantitative activity records (e.g. IC50, Ki, EC50, GI50 or MIC mainly in units of nM) of 222 092 NP-target pairs and 288 002 NP-species pairs. NPASS, http://bidd2.nus.edu.sg/NPASS/, is freely accessible with its contents searchable by keywords, physicochemical property range, structural similarity, species and target search facilities.

Drug target prediction using chem- and bioinformatics

The biological pre-validation of natural products (NPs) and their underlying frameworks ensures an unrivaled source of inspiration for chemical probe and drug design. However, the poor knowledge of their drug target counterparts critically hinders the broader exploration of NPs in chemical biology and molecular medicine. Cutting-edge algorithms now provide powerful means for the target deconvolution of phenotypic screen hits and generate motivated research hypotheses. Herein, we present recent progress in artificial intelligence applied to target identification that may accelerate future NP-inspired molecular medicine.

Cheminformatics-aided discovery of small-molecule Protein-Protein Interaction (PPI) dual inhibitors of Tumor Necrosis Factor (TNF) and Receptor Activator of NF-κB Ligand (RANKL)

We present an in silico drug discovery pipeline developed and applied for the identification and virtual screening of small-molecule Protein-Protein Interaction (PPI) compounds that act as dual inhibitors of TNF and RANKL through the trimerization interface. The cheminformatics part of the pipeline was developed by combining structure-based with ligand-based modeling using the largest available set of known TNF inhibitors in the literature (2481 small molecules). To facilitate virtual screening, the consensus predictive model was made freely available at: http://enalos.insilicotox.com/TNFPubChem/. We thus generated a priority list of nine small molecules as candidates for direct TNF function inhibition. In vitro evaluation of these compounds led to the selection of two small molecules that act as potent direct inhibitors of TNF function, with IC50 values comparable to those of a previously-described direct inhibitor (SPD304), but with significantly reduced toxicity. These molecules were also identified as RANKL inhibitors and validated in vitro with respect to this second functionality. Direct binding of the two compounds was confirmed both for TNF and RANKL, as well as their ability to inhibit the biologically-active trimer forms. Molecular dynamics calculations were also carried out for the two small molecules in each protein to offer additional insight into the interactions that govern TNF and RANKL complex formation. To our knowledge, these compounds, namely T8 and T23, constitute the second and third published examples of dual small-molecule direct function inhibitors of TNF and RANKL, and could serve as lead compounds for the development of novel treatments for inflammatory and autoimmune diseases.

Counting on natural products for drug design

Natural products and their molecular frameworks have a long tradition as valuable starting points for medicinal chemistry and drug discovery. Recently, there has been a revitalization of interest in the inclusion of these chemotypes in compound collections for screening and achieving selective target modulation. Here we discuss natural-product-inspired drug discovery with a focus on recent advances in the design of synthetically tractable small molecules that mimic nature's chemistry. We highlight the potential of innovative computational tools in processing structurally complex natural products to predict their macromolecular targets and attempt to forecast the role that natural-product-derived fragments and fragment-like natural products will play in next-generation drug discovery.

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.

Machine-learning scoring functions to improve structure-based binding affinity prediction and virtual screening

Docking tools to predict whether and how a small molecule binds to a target can be applied if a structural model of such target is available. The reliability of docking depends, however, on the accuracy of the adopted scoring function (SF). Despite intense research over the years, improving the accuracy of SFs for structure-based binding affinity prediction or virtual screening has proven to be a challenging task for any class of method. New SFs based on modern machine-learning regression models, which do not impose a predetermined functional form and thus are able to exploit effectively much larger amounts of experimental data, have recently been introduced. These machine-learning SFs have been shown to outperform a wide range of classical SFs at both binding affinity prediction and virtual screening. The emerging picture from these studies is that the classical approach of using linear regression with a small number of expert-selected structural features can be strongly improved by a machine-learning approach based on nonlinear regression allied with comprehensive data-driven feature selection. Furthermore, the performance of classical SFs does not grow with larger training datasets and hence this performance gap is expected to widen as more training data becomes available in the future. Other topics covered in this review include predicting the reliability of a SF on a particular target class, generating synthetic data to improve predictive performance and modeling guidelines for SF development. WIREs Comput Mol Sci 2015, 5:405-424. doi: 10.1002/wcms.1225 For further resources related to this article, please visit the WIREs website.

Assessing the suitability of the multilevel strategy for the conformational analysis of small ligands

Predicting the conformational preferences of flexible compounds is a challenging problem in drug design, where the recognition between ligand and receptor is affected by the ability of the interacting partners to adopt a favorable conformation for the binding. To explore the conformational space of flexible ligands and to obtain the relative free energy of the conformation wells, we have recently reported a multilevel computational strategy that relies on the predominant-state approximation-where the conformational space is partitioned into distinct conformational wells-and combines a low-level method for sampling the conformational minima and high-level ab initio calculations for estimating their relative stability. In this study, we assess the performance of the multilevel strategy for predicting the conformational preferences of a series of structurally related phenylethylamines and streptomycin in aqueous solution. The charged nature of these compounds and the chemical complexity of streptomycin make them a challenging test for the multilevel approach. Furthermore, we explore the suitability of using a molecular mechanics approach as a source of approximate ensembles in the first stage of the multilevel strategy. The results support the reliability of the multilevel approach for obtaining an accurate conformational ensemble of small (bio)organic molecules in aqueous solution.

Future De Novo Drug Design

The computer-assisted generation of new chemical entities (NCEs) has matured into solid technology supporting early drug discovery. Both ligand- and receptor-based methods are increasingly used for designing small lead- and druglike molecules with anticipated multi-target activities. Advanced "polypharmacology" prediction tools are essential pillars of these endeavors. In addition, it has been realized that iterative design-synthesis-test cycles facilitate the rapid identification of NCEs with the desired activity profile. Lab-on-a-chip platforms integrating synthesis, analytics and bioactivity determination and controlled by adaptive, chemistry-driven de novo design software will play an important role for future drug discovery.