Scaffold hopping from natural products to synthetic mimetics by holistic molecular similarity

Targeting cancer using scaffold-hopping approaches: illuminating SAR to improve drug design

Scaffold hopping is a design approach involving alterations to the core structure of an already bioactive scaffold to generate novel molecules to discover bioactive hit compounds with innovative core structures. Scaffold hopping enhances selectivity and potency while maintaining physicochemical, pharmacodynamic (PD), and pharmacokinetic (PK) properties, including toxicity parameters. Numerous molecules have been designed based on a scaffold-hopping strategy that showed potent inhibition activity against multiple targets for the diverse types of malignancy. In this review, we critically discuss recent applications of scaffold hopping along with essential components of medicinal chemistry, such as structure-activity relationship (SAR) profiles. Moreover, we shed light on the limitations and challenges associated with scaffold hopping-based anticancer drug discovery.

Scaffold-Hopped Compound Identification by Ligand-Based Approaches with a Prospective Affinity Test

Scaffold-hopped (SH) compounds are bioactive compounds structurally different from known active compounds. Identifying SH compounds in the ligand-based approaches has been a central issue in medicinal chemistry, and various molecular representations of scaffold hopping have been proposed. However, appropriate representations for SH compound identification remain unclear. Herein, the ability of SH compound identification among several representations was fairly evaluated based on retrospective validation and prospective demonstration. In the retrospective validation, the combinations of two screening algorithms and four two- and three-dimensional molecular representations were compared using controlled data sets for the early identification of SH compounds. We found that the combination of the support vector machine and extended connectivity fingerprint with bond diameter 4 (SVM-ECFP4) and SVM and the rapid overlay of chemical structures (SVM-ROCS) showed a relatively high performance. The compounds that were highly ranked by SVM-ROCS did not share substructures with the active training compounds, while those ranked by SVM-ECFP4 were mostly recombinant. In the prospective demonstration, 93 SH compounds were prepared by screening the Namiki database using SVM-ROCS, targeting ABL1 inhibitors. The primary screening using surface plasmon resonance suggested five active compounds; however, in the competitive binding assays with adenosine triphosphate, no hits were found.

Molecular medicinal insights into scaffold hopping-based drug discovery success

In both academia and the pharmaceutical industry, innovative hypotheses, methodologies and technologies that can shorten the drug research and development, leading to higher success rates, are vital. In this review, we demonstrate how innovative variations of the scaffold-hopping strategy have been used to create new druggable molecular spaces, drugs, clinical candidates, preclinical candidates, and bioactive agents. We also analyze molecular modulations that enabled improvements of the pharmacodynamic (PD), physiochemical, and pharmacokinetic (PK) properties (P3 properties) of the drugs resulting from these scaffold-hopping strategies.

Artificial intelligence for natural product drug discovery

Developments in computational omics technologies have provided new means to access the hidden diversity of natural products, unearthing new potential for drug discovery. In parallel, artificial intelligence approaches such as machine learning have led to exciting developments in the computational drug design field, facilitating biological activity prediction and de novo drug design for molecular targets of interest. Here, we describe current and future synergies between these developments to effectively identify drug candidates from the plethora of molecules produced by nature. We also discuss how to address key challenges in realizing the potential of these synergies, such as the need for high-quality datasets to train deep learning algorithms and appropriate strategies for algorithm validation.

Recent Advances in Machine-Learning-Based Chemoinformatics: A Comprehensive Review

In modern drug discovery, the combination of chemoinformatics and quantitative structure-activity relationship (QSAR) modeling has emerged as a formidable alliance, enabling researchers to harness the vast potential of machine learning (ML) techniques for predictive molecular design and analysis. This review delves into the fundamental aspects of chemoinformatics, elucidating the intricate nature of chemical data and the crucial role of molecular descriptors in unveiling the underlying molecular properties. Molecular descriptors, including 2D fingerprints and topological indices, in conjunction with the structure-activity relationships (SARs), are pivotal in unlocking the pathway to small-molecule drug discovery. Technical intricacies of developing robust ML-QSAR models, including feature selection, model validation, and performance evaluation, are discussed herewith. Various ML algorithms, such as regression analysis and support vector machines, are showcased in the text for their ability to predict and comprehend the relationships between molecular structures and biological activities. This review serves as a comprehensive guide for researchers, providing an understanding of the synergy between chemoinformatics, QSAR, and ML. Due to embracing these cutting-edge technologies, predictive molecular analysis holds promise for expediting the discovery of novel therapeutic agents in the pharmaceutical sciences.

De Novo Design of Nurr1 Agonists via Fragment-Augmented Generative Deep Learning in Low-Data Regime

Generative neural networks trained on SMILES can design innovative bioactive molecules de novo. These so-called chemical language models (CLMs) have typically been trained on tens of template molecules for fine-tuning. However, it is challenging to apply CLM to orphan targets with few known ligands. We have fine-tuned a CLM with a single potent Nurr1 agonist as template in a fragment-augmented fashion and obtained novel Nurr1 agonists using sampling frequency for design prioritization. Nanomolar potency and binding affinity of the top-ranking design and its structural novelty compared to available Nurr1 ligands highlight its value as an early chemical tool and as a lead for Nurr1 agonist development, as well as the applicability of CLM in very low-data scenarios.

Multi-model in silico characterization of 3-benzamidobenzoic acid derivatives as partial agonists of Farnesoid X receptor in the management of NAFLD

Non-alcoholic fatty liver disease (NAFLD) is a pathological condition which is strongly correlated with fat accumulation in the liver that has become a major health hazard globally. So far, limited treatment options are available for the management of NAFLD and partial agonism of Farnesoid X receptor (FXR) has proven to be one of the most promising strategies for treatment of NAFLD. In present work, a range of validated predictive cheminformatics and molecular modeling studies were performed with a series of 3-benzamidobenzoic acid derivatives in order to recognize their structural requirements for possessing higher potency towards FXR. 2D-QSAR models were able to extract the most significant structural attributes determining the higher activity towards the receptor. Ligand-based pharmacophore model was created with a novel and less-explored open access tool named QPhAR to acquire information regarding important 3D-pharmacophoric features that lead to higher agonistic potential towards the FXR. The alignment of the dataset compounds based on pharmacophore mapping led to 3D-QSAR models that pointed out the most crucial steric and electrostatic influence. Molecular dynamics (MD) simulation performed with the most potent and the least potent derivatives of the current dataset helped us to understand how to link the structural interpretations obtained from 2D-QSAR, 3D-QSAR and pharmacophore models with the involvement of specific amino acid residues in the FXR protein. The current study revealed that hydrogen bond interactions with carboxylate group of the ligands play an important role in the ligand receptor binding but higher stabilization of different helices close to the binding site of FXR (e.g., H5, H6 and H8) through aromatic scaffolds of the ligands should lead to higher activity for these ligands. The present work affords important guidelines towards designing novel FXR partial agonists for new therapeutic options in the management of NAFLD. Moreover, we relied mainly on open-access tools to develop the in-silico models in order to ensure their reproducibility as well as utilization.

Machine Learning and Computational Chemistry for the Endocannabinoid System

Computational methods in medicinal chemistry facilitate drug discovery and design. In particular, machine learning methodologies have recently gained increasing attention. This chapter provides a structured overview of the current state of computational chemistry and its applications for the interrogation of the endocannabinoid system (ECS), highlighting methods in structure-based drug design, virtual screening, ligand-based quantitative structure-activity relationship (QSAR) modeling, and de novo molecular design. We emphasize emerging methods in machine learning and anticipate a forecast of future opportunities of computational medicinal chemistry for the ECS.

Recent Scaffold Hopping Applications in Central Nervous System Drug Discovery

The concept of bioisosterism and the implementation of bioisosteric replacement is fundamental to medicinal chemistry. The exploration of bioisosteres is often used to probe key structural features of candidate pharmacophores and enhance pharmacokinetic properties. As the understanding of bioisosterism has evolved, capabilities to undertake more ambitious bioisosteric replacements have emerged. Scaffold hopping is a broadly used term in the literature referring to a variety of different bioisosteric replacement strategies, ranging from simple heterocyclic replacements to topological structural overhauls. In this work, we have highlighted recent applications of scaffold hopping in the central nervous system drug discovery space. While we have highlighted the benefits of using scaffold hopping approaches in central nervous system drug discovery, these are also widely applicable to other medicinal chemistry fields. We also recommend a shift toward the use of more refined and meaningful terminology within the realm of scaffold hopping.

Phloroglucinol and Its Derivatives: Antimicrobial Properties toward Microbial Pathogens

Phloroglucinol (PG) is a natural product isolated from plants, algae, and microorganisms. Aside from that, the number of PG derivatives has expanded due to the discovery of their potential biological roles. Aside from its diverse biological activities, PG and its derivatives have been widely utilized to treat microbial infections caused by bacteria, fungus, and viruses. The rapid emergence of antimicrobial-resistant microbial infections necessitates the chemical synthesis of numerous PG derivatives in order to meet the growing demand for drugs. This review focuses on the use of PG and its derivatives to control microbial infection and the underlying mechanism of action. Furthermore, as future perspectives, some of the various alternative strategies, such as the use of PG and its derivatives in conjugation, nanoformulation, antibiotic combination, and encapsulation, have been thoroughly discussed. This review will enable the researcher to investigate the possible antibacterial properties of PG and its derivatives, either free or in the form of various formulations.

Visualization of Topological Pharmacophore Space with Graph Edit Distance

A topological pharmacophore (TP) is a chemical graph-based pharmacophore representation, where nodes are pharmacophoric features (PF) and edges are topological distances between PFs. Previously proposed sparse pharmacophore graphs (SPhGs) for TPs were shown to be effective in identifying structurally different active compounds while maintaining the interpretability of the graphs. However, one limitation of using SPhGs as queries is that many structurally similar SPhGs can be identified from a set of active compounds, requiring the classification and visualization of SPhGs, followed by an understanding of the pharmacophore hypotheses. In this study, we propose a scheme for SPhG analysis based on dimensionality reduction techniques with the graph edit distance (GED) metric. This metric enables measuring similarities among SPhGs in a quantitative manner. The visualization of SPhGs, which themselves are the graphs shared by active compounds, can help us understand the pharmacophore hypotheses as well as the data set. As a proof-of-concept study, we generated two-dimensional SPhG-maps using three dimensionality reduction techniques for six biological targets. A comparison with other pharmacophore representations was also conducted. We demonstrated knowledge extraction (interpretation of the data set) from the generated maps. Our findings include a suitable mapping algorithm as well as a pharmacophore hypothesis analysis procedure using an SPhG-map.

A Brief Review of Machine Learning-Based Bioactive Compound Research

Bioactive compounds are often used as initial substances for many therapeutic agents. In recent years, both theoretical and practical innovations in hardware-assisted and fast-evolving machine learning (ML) have made it possible to identify desired bioactive compounds in chemical spaces, such as those in natural products (NPs). This review introduces how machine learning approaches can be used for the identification and evaluation of bioactive compounds. It also provides an overview of recent research trends in machine learning-based prediction and the evaluation of bioactive compounds by listing real-world examples along with various input data. In addition, several ML-based approaches to identify specific bioactive compounds for cardiovascular and metabolic diseases are described. Overall, these approaches are important for the discovery of novel bioactive compounds and provide new insights into the machine learning basis for various traditional applications of bioactive compound-related research.

Structural derivatization strategies of natural phenols by semi-synthesis and total-synthesis

Structural derivatization of natural products has been a continuing and irreplaceable source of novel drug leads. Natural phenols are a broad category of natural products with wide pharmacological activity and have offered plenty of clinical drugs. However, the structural complexity and wide variety of natural phenols leads to the difficulty of structural derivatization. Skeleton analysis indicated most types of natural phenols can be structured by the combination and extension of three common fragments containing phenol, phenylpropanoid and benzoyl. Based on these fragments, the derivatization strategies of natural phenols were unified and comprehensively analyzed in this review. In addition to classical methods, advanced strategies with high selectivity, efficiency and practicality were emphasized. Total synthesis strategies of typical fragments such as stilbenes, chalcones and flavonoids were also covered and analyzed as the supplementary for supporting the diversity-oriented derivatization of natural phenols.

A straightforward access to trifluoromethylated natural products through late-stage functionalization

This review summarizes the applications of late-stage strategies in the direct trifluoromethylation of natural products in the past ten years, with particular emphasis on the reaction model of each method.

NPClassifier: A Deep Neural Network-Based Structural Classification Tool for Natural Products

Computational approaches such as genome and metabolome mining are becoming essential to natural products (NPs) research. Consequently, a need exists for an automated structure-type classification system to handle the massive amounts of data appearing for NP structures. An ideal semantic ontology for the classification of NPs should go beyond the simple presence/absence of chemical substructures, but also include the taxonomy of the producing organism, the nature of the biosynthetic pathway, and/or their biological properties. Thus, a holistic and automatic NP classification framework could have considerable value to comprehensively navigate the relatedness of NPs, and especially so when analyzing large numbers of NPs. Here, we introduce NPClassifier, a deep-learning tool for the automated structural classification of NPs from their counted Morgan fingerprints. NPClassifier is expected to accelerate and enhance NP discovery by linking NP structures to their underlying properties.

Chemoinformatics View on Bitter Taste Receptor Agonists in Food

Food compounds with a bitter taste have a role in human health, both for their capability to influence food choice and preferences and for their possible systemic effect due to the modulation of extra-oral bitter taste receptors (TAS2Rs). Investigating the interaction of bitter food compounds with TAS2Rs is a key step to unravel their complex effects on health and to pave the way to rationally design new additives for food formulation or drugs. Here, we propose a collection of food bitter compounds, for which in vitro activity data against TAS2Rs are available. The patterns of TAS2R subtype-specific agonists were analyzed using scaffold decomposition and chemical space analysis, providing a detailed characterization of the associations between food bitter tastants and TAS2Rs.

Unnatural Hygroscopic Property of Nicotinic Acid by Restructuring Molecular Density: Self-Healing Halide Perovskites

An unnatural hygroscopic property of nonhygroscopic nicotinic acid (NA) is demonstrated by tuning the intermolecular distance. After addition of NA into methylammonium lead iodide, (MAPbI₃) NA molecules are preferentially aligned on the interface of the three-dimensional (3D) MAPbI₃ crystal structure by a hydrogen bond. This unique behavior allows NA to be used as a versatile additive to improve the water durability of MAPbI₃. After exposure under a high humidity atmosphere (RH 100%, 35 °C), MAPbI₃ films with NA exhibited self-healing phenomena against moisture while bare MAPbI₃ rapidly lost its own intrinsic property. Density functional theory (DFT) calculations were conducted to reveal how H₂O molecules can effectively be absorbed by NA according to its planar molecular density. Also, further optimization of photovoltaic device performances was carried out by investigating the relationship between NA concentration and additive alignment.

Beam Search for Automated Design and Scoring of Novel ROR Ligands with Machine Intelligence*

Chemical language models enable de novo drug design without the requirement for explicit molecular construction rules. While such models have been applied to generate novel compounds with desired bioactivity, the actual prioritization and selection of the most promising computational designs remains challenging. Herein, we leveraged the probabilities learnt by chemical language models with the beam search algorithm as a model-intrinsic technique for automated molecule design and scoring. Prospective application of this method yielded novel inverse agonists of retinoic acid receptor-related orphan receptors (RORs). Each design was synthesizable in three reaction steps and presented low-micromolar to nanomolar potency towards RORγ. This model-intrinsic sampling technique eliminates the strict need for external compound scoring functions, thereby further extending the applicability of generative artificial intelligence to data-driven drug discovery.

Sparse Topological Pharmacophore Graphs for Interpretable Scaffold Hopping

The aim of scaffold hopping (SH) is to find compounds consisting of different scaffolds from those in already known active compounds, giving an opportunity for unexplored regions of chemical space. We previously demonstrated the usefulness of pharmacophore graphs (PhGs) for this purpose through proof-of-concept virtual screening experiments. PhGs consist of nodes and edges corresponding to pharmacophoric features (PFs) and their topological distances. Although PhGs were effective in SH, they are hard to interpret as they are complete graphs. Herein, we introduce an intuitive representation of a molecule, termed as sparse pharmacophore graphs (SPhG) by keeping the topological distances among PFs as much as possible while reducing the number of edges in the graphs. Several benchmark calculations quantitatively confirmed the sparseness of the graphs and the preservation of topological distances among pharmacophoric points. As proof-of-concept applications, virtual screening (VS) trials for SH were conducted using active and inactive compounds from ChEMBL and PubChem databases for three biological targets: thrombin, tyrosine kinase ABL1, and κ-opioid receptor. The performances of VS were comparable with using fully connected PhGs. Furthermore, highly ranked SPhGs were interpretable for the three biological targets, in particular for thrombin, for which selected SPhGs were in agreement with the structure-based interpretation.

A chemoinformatic analysis of atoms, scaffolds and functional groups in natural products

In the quest to know why natural products (NPs) have often been considered as privileged scaffolds for drug discovery purposes, many investigations into the differences between NPs and synthetic compounds have been carried out. Several attempts to answer this question have led to the investigation of the atomic composition, scaffolds and functional groups (FGs) of NPs, in comparison with synthetic drugs analysis. This chapter briefly describes an atomic enumeration method for chemical libraries that has been applied for the analysis of NP libraries, followed by a description of the main differences between NPs of marine and terrestrial origin in terms of their general physicochemical properties, most common scaffolds and “drug-likeness” properties. The last parts of the work describe an analysis of scaffolds and FGs common in NP libraries, focusing on huge NP databases, e.g. those in the Dictionary of Natural Products (DNP), NPs from cyanobacteria and the largest chemical class of NP – terpenoids.

Molecular Scaffold Hopping via Holistic Molecular Representation

Molecular descriptors encode a variety of molecular representations for computer-assisted drug discovery. Here, we focus on the Weighted Holistic Atom Localization and Entity Shape (WHALES) descriptors, which were originally designed for scaffold hopping from natural products to synthetic molecules. WHALES descriptors capture molecular shape and partial charges simultaneously. We introduce the key aspects of the WHALES concept and provide a step-by-step guide on how to use these descriptors for virtual compound screening and scaffold hopping. The results presented can be reproduced by using the code freely available from URL: github.com/ETHmodlab/scaffold_hopping_whales .

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.

Identifying new topoisomerase II poison scaffolds by combining publicly available toxicity data and 2D/3D-based virtual screening

Molecular descriptor (2D) and three dimensional (3D) shape based similarity methods are widely used in ligand based virtual drug design. In the present study pairwise structure comparisons among a set of 4858 DTP compounds tested in the NCI60 tumor cell line anticancer drug screen were computed using chemical hashed fingerprints and 3D molecule shapes to calculate 2D and 3D similarities, respectively. Additionally, pairwise biological activity similarities were calculated by correlating the 60 element vectors of pGI50 values corresponding to the cytotoxicity of the compounds across the NCI60 panel. Subsequently, we compared the power of 2D and 3D structural similarity metrics to predict the toxicity pattern of compounds. We found that while the positive predictive value and sensitivity of 3D and molecular descriptor based approaches to predict biological activity are similar, a subset of molecule pairs yielded contradictory results. By simultaneously requiring similarity of biological activities and 3D shapes, and dissimilarity of molecular descriptor based comparisons, we identify pairs of scaffold hopping candidates displaying characteristic core structural changes such as heteroatom/heterocycle change and ring closure. Attempts to discover scaffold hopping candidates of mitoxantrone recovered known Topoisomerase II (Top2) inhibitors, and also predicted new, previously unknown chemotypes possessing in vitro Top2 inhibitory activity.

The Symbiotic Relationship Between Drug Discovery and Organic Chemistry

All pharmaceutical products contain organic molecules; the source may be a natural product or a fully synthetic molecule, or a combination of both. Thus, it follows that organic chemistry underpins both existing and upcoming pharmaceutical products. The reverse relationship has also affected organic synthesis, changing its landscape towards increasingly complex targets. This Review article sets out to give a concise appraisal of this symbiotic relationship between organic chemistry and drug discovery, along with a discussion of the design concepts and highlighting key milestones along the journey. In particular, criteria for a high-quality compound library design enabling efficient virtual navigation of chemical space, as well as rise and fall of concepts for its synthetic exploration (such as combinatorial chemistry; diversity-, biology-, lead-, or fragment-oriented syntheses; and DNA-encoded libraries) are critically surveyed.

Improved Prediction of Drug-Target Interactions Using Self-Paced Learning with Collaborative Matrix Factorization

Identifying drug-target interactions (DTIs) plays an important role in the field of drug discovery, drug side-effects, and drug repositioning. However, in vivo or biochemical experimental methods for identifying new DTIs are extremely expensive and time-consuming. Recently, in silico or various computational methods have been developed for DTI prediction, such as ligand-based approaches and docking approaches, but these traditional computational methods have several limitations. This work utilizes the chemogenomic-based approaches for efficiently identifying potential DTI candidates, namely, self-paced learning with collaborative matrix factorization based on weighted low-rank approximation (SPLCMF) for DTI prediction, which integrates multiple networks related to drugs and targets into regularized least-squares and focuses on learning a low-dimensional vector representation of features. The SPLCMF framework can select samples from easy to complex into training by using soft weighting, which is inclined to more faithfully reflect the latent importance of samples in training. Experimental results on synthetic data and five benchmark data sets show that our proposed SPLCMF outperforms other existing state-of-the-art approaches. These results indicate that our proposed SPLCMF can provide a useful tool to predict unknown DTIs, which may provide new insights into drug discovery, drug side-effect prediction, and repositioning existing drug.

Phenylpropanoid Glycerol Glucosides Attenuate Glucose Production in Hepatocytes

An activity-guided fractionation approach revealed several phenylpropanoid glycerol glucosides isolated from the bulbs of Lilium longiflorum Thunb. (Easter lily) with gluconeogenesis inhibitory activities. The strongest activity was observed for (2S)-1-O-p-coumaroyl-2-O-β-d-glucopyranosylglycerol (3), (2S)-1-O-caffeoyl-2-O-β-d-glucopyranosylglycerol (1), and (2R)-1-O-β-d-glucopyranosyl-2-O-p-coumaroylglycerol (2) with inhibitions of 51.2, 39.2, and 36.8%, respectively. The p-coumaroyl-based (3) and its acetylated derivative (5) exhibited differential inhibition activity (51.2% as compared to 3.6%), suggesting that natural acetylation decreases the hypoglycemic activity of these compounds. Direct structure-activity analysis of phenylpropanoid glycerol glucosides indicated that the hydroxylation pattern of the hydroxy cinnamic acid moiety and acetylation were responsible for the differences in activity. This is the first report of phenylpropanoid glycerol glucosides as a phytochemical class of hepatic glucose production inhibitors.

Design of Natural-Product-Inspired Multitarget Ligands by Machine Learning

A virtual screening protocol based on machine learning models was used to identify mimetics of the natural product (-)-galantamine. This fully automated approach identified eight compounds with bioactivities on at least one of the macromolecular targets of (-)-galantamine, with different polypharmacological profiles. Two of the computer-generated hits possess an expanded spectrum of bioactivity on targets relevant to the treatment of Alzheimer's disease and are suitable for hit-to-lead expansion. These results advocate multitarget drug design by advanced virtual screening protocols based on chemically informed machine learning models.

NP-Scout: Machine Learning Approach for the Quantification and Visualization of the Natural Product-Likeness of Small Molecules

Natural products (NPs) remain the most prolific resource for the development of small-molecule drugs. Here we report a new machine learning approach that allows the identification of natural products with high accuracy. The method also generates similarity maps, which highlight atoms that contribute significantly to the classification of small molecules as a natural product or synthetic molecule. The method can hence be utilized to (i) identify natural products in large molecular libraries, (ii) quantify the natural product-likeness of small molecules, and (iii) visualize atoms in small molecules that are characteristic of natural products or synthetic molecules. The models are based on random forest classifiers trained on data sets consisting of more than 265,000 to 322,000 natural products and synthetic molecules. Two-dimensional molecular descriptors, MACCS keys and Morgan2 fingerprints were explored. On an independent test set the models reached areas under the receiver operating characteristic curve (AUC) of 0.997 and Matthews correlation coefficients (MCCs) of 0.954 and higher. The method was further tested on data from the Dictionary of Natural Products, ChEMBL and other resources. The best-performing models are accessible as a free web service at http://npscout.zbh.uni-hamburg.de/npscout.

A Strength-Weaknesses-Opportunities-Threats (SWOT) Analysis of Cheminformatics in Natural Product Research

Cheminformatics-based techniques, such as molecular modeling, docking, virtual screening, and machine learning, are well accepted for their usefulness in drug discovery and development of therapeutically relevant small molecules. Although delayed by several decades, their application in natural product research has led to outstanding findings. Combining information obtained from different sources, i.e., virtual predictions, traditional medicine, structural, biochemical, and biological data, and handling big data effectively will open up new possibilities, but also challenges in the future. Strategies and examples will be presented on how to integrate cheminformatics in pharmacognostic workflows to benefit from these two highly complementary disciplines toward streamlining experimental efforts. While considering their limits and pitfalls and by exploiting their potential, computer-aided strategies should successfully guide future studies and thereby augment our knowledge of bioactive natural lead structures.

Discovery of Novel Molecular Frameworks of Farnesoid X Receptor Modulators by Ensemble Machine Learning

The bile acid activated transcription factor farnesoid X receptor (FXR) has revealed therapeutic potential as a molecular drug target for the treatment of hepatic and metabolic disorders. Despite strong efforts in FXR ligand development, the structural diversity among the known FXR modulators is limited. Only four molecular frameworks account for more than 50 % of the FXR modulators annotated in ChEMBL. Here, we leverage machine learning methods to expand the chemical space of FXR-targeting small molecules by employing an ensemble of three complementary machine learning approaches. A counter-propagation artificial neural network, a k-nearest neighbor learner, and a three-dimensional pharmacophore descriptor were combined to retrieve novel FXR ligands from a collection of more than 3 million compounds. The ensemble machine learning model identified six new FXR modulators among ten top-ranked candidates. These active hits comprise both FXR activators and antagonists with micromolar potencies. With four novel FXR ligand scaffolds, these computationally identified bioactive compounds appreciably expand the chemical space of known FXR modulators and may serve as starting points for hit-to-lead expansion.