Development of Natural Compound Molecular Fingerprint (NC-MFP) with the Dictionary of Natural Products (DNP) for natural product-based drug development

Artifical intelligence: a virtual chemist for natural product drug discovery

Nature is full of a bundle of medicinal substances and its product perceived as a prerogative structure to collaborate with protein drug targets. The natural product's (NPs) structure heterogeneity and eccentric characteristics inspired scientists to work on natural product-inspired medicine. To gear NP drug-finding artificial intelligence (AI) to confront and excavate unexplored opportunities. Natural product-inspired drug discoveries based on AI to act as an innovative tool for molecular design and lead discovery. Various models of machine learning produce quickly synthesizable mimetics of the natural products templates. The invention of novel natural products mimetics by computer-assisted technology provides a feasible strategy to get the natural product with defined bio-activities. AI's hit rate makes its high importance by improving trail patterns such as dose selection, trail life span, efficacy parameters, and biomarkers. Along these lines, AI methods can be a successful tool in a targeted way to formulate advanced medicinal applications for natural products. 'Prediction of future of natural product based drug discovery is not magic, actually its artificial intelligence'Communicated by Ramaswamy H. Sarma.

Effectiveness of molecular fingerprints for exploring the chemical space of natural products

Natural products are a diverse class of compounds with promising biological properties, such as high potency and excellent selectivity. However, they have different structural motifs than typical drug-like compounds, e.g., a wider range of molecular weight, multiple stereocenters and higher fraction of sp3-hybridized carbons. This makes the encoding of natural products via molecular fingerprints difficult, thus restricting their use in cheminformatics studies. To tackle this issue, we explored over 30 years of research to systematically evaluate which molecular fingerprint provides the best performance on the natural product chemical space. We considered 20 molecular fingerprints from four different sources, which we then benchmarked on over 100,000 unique natural products from the COCONUT (COlleCtion of Open Natural prodUcTs) and CMNPD (Comprehensive Marine Natural Products Database) databases. Our analysis focused on the correlation between different fingerprints and their classification performance on 12 bioactivity prediction datasets. Our results show that different encodings can provide fundamentally different views of the natural product chemical space, leading to substantial differences in pairwise similarity and performance. While Extended Connectivity Fingerprints are the de-facto option to encoding drug-like compounds, other fingerprints resulted to match or outperform them for bioactivity prediction of natural products. These results highlight the need to evaluate multiple fingerprinting algorithms for optimal performance and suggest new areas of research. Finally, we provide an open-source Python package for computing all molecular fingerprints considered in the study, as well as data and scripts necessary to reproduce the results, at https://github.com/dahvida/NP_Fingerprints .

Combined substituent number utilized machine learning for the development of antimicrobial agent

The utilization of machine learning has a potential to improve the environment of the development of antimicrobial agents. For practical use of machine learning, it is important that the conversion of molecules information to an appropriate descriptor because too informative descriptor requires enormous computation time and experiments for gathering data, whereas a less informative descriptor has problems in validity. In this study, we utilized a descriptor only focused on substituent. The type and the position of substituents on the molecules that have a 4-quinolone structure (11,879 compounds) were converted to the combined substituent number (CSN). While the CSN does not include information on the detailed structure, physical properties, and quantum chemistry of molecules, the prediction model constructed by machine learning of CSN indicated a sufficient coefficient of determination (0.719 for the training dataset and 0.519 for the validation dataset). In addition, this CSN can easily construct the unknown molecules library which has a relatively consistent structure by recombination of substituents (32,079,318 compounds) and screening of them. The validity of the prediction model was also confirmed by growth inhibition experiments for E. coli using the model-suggested molecules and commercially available antimicrobial agents.

From intuition to AI: evolution of small molecule representations in drug discovery

Within drug discovery, the goal of AI scientists and cheminformaticians is to help identify molecular starting points that will develop into safe and efficacious drugs while reducing costs, time and failure rates. To achieve this goal, it is crucial to represent molecules in a digital format that makes them machine-readable and facilitates the accurate prediction of properties that drive decision-making. Over the years, molecular representations have evolved from intuitive and human-readable formats to bespoke numerical descriptors and fingerprints, and now to learned representations that capture patterns and salient features across vast chemical spaces. Among these, sequence-based and graph-based representations of small molecules have become highly popular. However, each approach has strengths and weaknesses across dimensions such as generality, computational cost, inversibility for generative applications and interpretability, which can be critical in informing practitioners' decisions. As the drug discovery landscape evolves, opportunities for innovation continue to emerge. These include the creation of molecular representations for high-value, low-data regimes, the distillation of broader biological and chemical knowledge into novel learned representations and the modeling of up-and-coming therapeutic modalities.

Artificial intelligence for drug discovery: Resources, methods, and applications

Conventional wet laboratory testing, validations, and synthetic procedures are costly and time-consuming for drug discovery. Advancements in artificial intelligence (AI) techniques have revolutionized their applications to drug discovery. Combined with accessible data resources, AI techniques are changing the landscape of drug discovery. In the past decades, a series of AI-based models have been developed for various steps of drug discovery. These models have been used as complements of conventional experiments and have accelerated the drug discovery process. In this review, we first introduced the widely used data resources in drug discovery, such as ChEMBL and DrugBank, followed by the molecular representation schemes that convert data into computer-readable formats. Meanwhile, we summarized the algorithms used to develop AI-based models for drug discovery. Subsequently, we discussed the applications of AI techniques in pharmaceutical analysis including predicting drug toxicity, drug bioactivity, and drug physicochemical property. Furthermore, we introduced the AI-based models for de novo drug design, drug-target structure prediction, drug-target interaction, and binding affinity prediction. Moreover, we also highlighted the advanced applications of AI in drug synergism/antagonism prediction and nanomedicine design. Finally, we discussed the challenges and future perspectives on the applications of AI to drug discovery.

Identification of structural scaffold from interbioscreen (IBS) database to inhibit 3CLpro, PLpro, and RdRp of SARS-CoV-2 using molecular docking and dynamic simulation studies

A novel coronavirus SARS-CoV-2 has caused a worldwide pandemic and remained a severe threat to the entire human population. Researchers worldwide are struggling to find an effective drug treatment to combat this deadly disease. Many FDA-approved drugs from varying inhibitory classes and plant-derived compounds are screened to combat this virus. Still, due to the lack of structural information and several mutations of this virus, initial drug discovery efforts have limited success. A high-resolution crystal structure of important proteins like the main protease (3CLpro) that are required for SARS-CoV-2 viral replication and polymerase (RdRp) and papain-like protease (PLpro) as a vital target in other coronaviruses still presents important targets for the drug discovery. With this knowledge, scaffold library of Interbioscreen (IBS) database was explored through molecular docking, MD simulation and postdynamic binding free energy studies. The 3D docking structures and simulation data for the IBS compounds was studied and articulated. The compounds were further evaluated for ADMET studies using QikProp and SwissADME tools. The results revealed that the natural compounds STOCK2N-00385, STOCK2N-00244, and STOCK2N-00331 interacted strongly with 3CLpro, PLpro, and RdRp, respectively, and ADMET data was also observed in the range of limits for almost all the compounds with few exceptions. Thus, it suggests that these compounds may be potential inhibitors of selected target proteins, or their structural scaffolds can be further optimized to obtain effective drug candidates for SARS-CoV-2. The findings of in-silico data need to be supported by in-vivo studies which could shed light on understanding the exact mode of inhibitory action.Communicated by Ramaswamy H. Sarma.

Hyper-Mol: Molecular Representation Learning via Fingerprint-Based Hypergraph

With the development of artificial intelligence (AI) in the field of drug design and discovery, learning informative representations of molecules is becoming crucial for those AI-driven tasks. In recent years, the graph neural networks (GNNs) have emerged as a preferred choice of deep learning architecture and have been successfully applied to molecular representation learning (MRL). Up-to-date MRL methods directly apply the message passing mechanism on the atom-level attributes (i.e., atoms and bonds) of molecules. However, they neglect latent yet significant hyperstructured knowledge, such as the information of pharmacophore or functional class. Hence, in this paper, we propose Hyper-Mol, a new MRL framework that applies GNNs to encode hypergraph structures of molecules via fingerprint-based features. Hyper-Mol explores the hyperstructured knowledge and the latent relationships of the fingerprint substructures from a hypergraph perspective. The molecular hypergraph generation algorithm is designed to depict the hyperstructured information with the physical and chemical characteristics of molecules. Thus, the fingerprint-level message passing process can encode both the intra-structured and inter-structured information of fingerprint substructures according to the molecular hypergraphs. We evaluate Hyper-Mol on molecular property prediction tasks, and the experimental results on real-world benchmarks show that Hyper-Mol can learn comprehensive hyperstructured knowledge of molecules and is superior to the state-of-the-art baselines.

A Guide to In Silico Drug Design

The drug discovery process is a rocky path that is full of challenges, with the result that very few candidates progress from hit compound to a commercially available product, often due to factors, such as poor binding affinity, off-target effects, or physicochemical properties, such as solubility or stability. This process is further complicated by high research and development costs and time requirements. It is thus important to optimise every step of the process in order to maximise the chances of success. As a result of the recent advancements in computer power and technology, computer-aided drug design (CADD) has become an integral part of modern drug discovery to guide and accelerate the process. In this review, we present an overview of the important CADD methods and applications, such as in silico structure prediction, refinement, modelling and target validation, that are commonly used in this area.

Research Progress in the Pharmacological Activities, Toxicities, and Pharmacokinetics of Sophoridine and Its Derivatives

Sophoridine is a natural quinolizidine alkaloid and a bioactive ingredient that can be isolated and identified from certain herbs, including Sophora flavescens Alt, Sophora alopecuroides L, and Sophora viciifolia Hance. In recent years, this quinolizidine alkaloid has gained widespread attention because of its unique structure and minimal side effects. Modern pharmacological investigations have uncovered sophoridine's multiple wide range biological activities, such as anti-cancer, anti-inflammatory, anti-viral, anti-arrhythmia, and analgesic functions, among others. These pharmacological activities and beneficial effects point to sophoridine as a strong potential therapeutic candidate for the treatment of various diseases, including several cancer types, hepatitis B virus, enterovirus 71, coxsackievirus B3, cerebral edema, cancer pain, heart failure, acute myocardial ischemia, arrhythmia, inflammation, acute lung injury, and osteoporosis. The data showed that sophoridine had adverse reactions, including hepatotoxicity and neurotoxicity. Additionally, analyses of sophoridine's safety, bioavailability, and pharmacokinetic parameters in animal models of research have been limited, especially in the clinic, as have been investigations on its structure-activity relationship. In this article, we comprehensively summarize the biological activities, toxicity, and pharmacokinetic characteristics of sophoridine and its derivatives, as currently reported in publications, as we attempt to provide an overall perspective on sophoridine analogs and the prospects of its application clinically.

Natural product drug discovery in the artificial intelligence era

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

Topological Distance-Based Electron Interaction Tensor to Apply a Convolutional Neural Network on Drug-like Compounds

Deep learning (DL) models in quantitative structure-activity relationship fed the molecular structure directly to the network without using human-designed descriptors by representing molecule as a graph or string (e.g., SMILES code). However, these two representations were oversimplification of real molecules to reflect chemical properties of molecular structures. Given that the choice of molecular representation determines the architecture of the DL model to apply, a novel way of molecular representation can open a way to apply diverse DL networks developed and used in other fields. A topological distance-based electron interaction (TDEi) tensor has been developed in this study inspired by the quantum mechanical model of the molecule, which defines a molecule with electrons and protons. In the TDEi tensor, the atomic orbital (AO) of each atom is represented by an electron configuration (EC) vector, which is a bit string based on the presence and absence of electrons in each AO according to spin indicated by positive and negative signs. Interactions between EC vectors were calculated based on the topological distance between atoms in a molecule. As a molecular structure was translated into 3D array, CNN models (modified VGGNet) were applied using a TDEi tensor to predict four physicochemical properties of drug-like compound datasets: MP (275,131), Lipop (4193), Esol (1127), and Freesolv (639). Models achieved good prediction accuracy. PCA showed that a stronger correlation was observed between the extracted features and the target endpoint as features were extracted from the deeper layer.

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.

Antimicrobial Activity, in silico Molecular Docking, ADMET and DFT Analysis of Secondary Metabolites from Roots of Three Ethiopian Medicinal Plants

BACKGROUND

Uvaria scheffleri (Annonaceae), Clematis burgensis (Ranunculaceae), and Euphorbia schimperiana (Euphorbiaceae) are medicinal plants traditionally used to treat cough, tuberculosis, asthma, sore throat and skin infections.

METHODS

Silica gel column chromatographic separation was used to isolate compounds. Crude extract and isolated compounds were evaluated for antimicrobial activity against Staphylococcus aureus, Escherichia coli, and Candida albicans via the broth dilution method. Docking studies were performed with E. coli DNA-Gyrase B and human DNA topoisomerase IIα by using AutoDock Vina. ADMET were predicted by SwissADME, PreADMET, and OSIRIS Property predictions. The optimized structures and molecular electrostatic potential surface of the isolated compounds were predicted by DFT analysis using B3LYP/6-31G basis levels.

RESULTS

Silica gel column chromatographic separation afforded five compounds 1-5 of which N-methyl-2,3-bis(2-hydroxybenzyl)-1Н-indol (1) is reported herein for the first time, along with known C-benzylated dihydrochalcone uvaretin (2), bis(2-ethylheptyl) phthalate (3), lupeol (4) and suberosin derivative (5). Dichloromethane roots extract of U. scheffleri showed potent antibacterial activity against S. aureus (MIC = 6.25 µg/mL) compared to gentamicin (MIC=5 µg/mL). In silico, molecular docking analysis of compounds (1and 3-5) showed strong interaction with E. coli DNA gyrase B with a binding energy value ranging from -6.9 to -6.0 kcal/mol compared to ciprofloxacin -7.2 kcal/mol, whereas analysis against human topoisomerase IIα showed binding energy value ranging from -5.9 to -5.3 kcal/mol compared to vosaroxin (-6.2 kcal/mol).

CONCLUSION

The results obtained suggest that N-methyl-2,3-bis(2-hydroxybenzyl)-1Н-indol (1) and coumarin (5) are potential topoisomerase II α inhibitors and might be used as anticancer agents. The ADMET studies showed the highest drug-likeness properties for studied compounds other than bis(2-ethylheptyl) phthalate (3). DFT calculations suggested that studied compounds showed the lowest gap energy and were chemically reactive, and isolated compounds may serve as potential drug candidates that corroborate with the traditional uses of studied plants.

Natural product scores and fingerprints extracted from artificial neural networks

Due to their desirable properties, natural products are an important ligand class for medicinal chemists. However, due to their structural distinctiveness, traditional cheminformatic approaches, like ligand-based virtual screening, often perform worse for natural products. Based on our recent work, we evaluated the ability of neural networks to generate fingerprints more appropriate for use with natural products. A manually curated dataset of natural products and synthetic decoys was used to train a multi-layer perceptron network and an autoencoder-like network. In-depth analysis showed that the extracted natural product-specific neural fingerprint outperforms traditional as well as natural product-specific fingerprints on three datasets. Further, we explored how the activations from the output layer of a network can work as a novel natural product likeness score. Overall, two natural product-specific datasets were generated, which are publicly available together with the code to create the fingerprints and the novel natural product likeness score.

Synergizing the potential of bacterial genomics and metabolomics to find novel antibiotics

Antibiotic development based on natural products has faced a long lasting decline since the 1970s, while both the speed and the extent of antimicrobial resistance (AMR) development have been severely underestimated. The discovery of antimicrobial natural products of bacterial and fungal origin featuring new chemistry and previously unknown mode of actions is increasingly challenged by rediscovery issues. Natural products that are abundantly produced by the corresponding wild type organisms often featuring strong UV signals have been extensively characterized, especially the ones produced by extensively screened microbial genera such as streptomycetes. Purely synthetic chemistry approaches aiming to replace the declining supply from natural products as starting materials to develop novel antibiotics largely failed to provide significant numbers of antibiotic drug leads. To cope with this fundamental issue, microbial natural products science is being transformed from a 'grind-and-find' study to an integrated approach based on bacterial genomics and metabolomics. Novel technologies in instrumental analytics are increasingly employed to lower detection limits and expand the space of detectable substance classes, while broadening the scope of accessible and potentially bioactive natural products. Furthermore, the almost exponential increase in publicly available bacterial genome data has shown that the biosynthetic potential of the investigated strains by far exceeds the amount of detected metabolites. This can be judged by the discrepancy between the number of biosynthetic gene clusters (BGC) encoded in the genome of each microbial strain and the number of secondary metabolites actually detected, even when considering the increased sensitivity provided by novel analytical instrumentation. In silico annotation tools for biosynthetic gene cluster classification and analysis allow fast prioritization in BGC-to-compound workflows, which is highly important to be able to process the enormous underlying data volumes. BGC prioritization is currently accompanied by novel molecular biology-based approaches to access the so-called orphan BGCs not yet correlated with a secondary metabolite. Integration of metabolomics, in silico genomics and molecular biology approaches into the mainstream of natural product research will critically influence future success and impact the natural product field in pharmaceutical, nutritional and agrochemical applications and especially in anti-infective research.

Profiling and analysis of chemical compounds using pointwise mutual information

Pointwise mutual information (PMI) is a measure of association used in information theory. In this paper, PMI is used to characterize several publicly available databases (DrugBank, ChEMBL, PubChem and ZINC) in terms of association strength between compound structural features resulting in database PMI interrelation profiles. As structural features, substructure fragments obtained by coding individual compounds as MACCS, PubChemKey and ECFP fingerprints are used. The analysis of publicly available databases reveals, in accord with other studies, unusual properties of DrugBank compounds which further confirms the validity of PMI profiling approach. Z-standardized relative feature tightness (ZRFT), a PMI-derived measure that quantifies how well the given compound's feature combinations fit these in a particular compound set, is applied for the analysis of compound synthetic accessibility (SA), as well as for the classification of compounds as easy (ES) and hard (HS) to synthesize. ZRFT value distributions are compared with these of SYBA and SAScore. The analysis of ZRFT values of structurally complex compounds in the SAVI database reveals oligopeptide structures that are mispredicted by SAScore as HS, while correctly predicted by ZRFT and SYBA as ES. Compared to SAScore, SYBA and random forest, ZRFT predictions are less accurate, though by a narrow margin (AccZRFT = 94.5%, AccSYBA = 98.8%, AccSAScore = 99.0%, AccRF = 97.3%). However, ZRFT ability to distinguish between ES and HS compounds is surprisingly high considering that while SYBA, SAScore and random forest are dedicated SA models, ZRFT is a generic measurement that merely quantifies the strength of interrelations between structural feature pairs. The results presented in the current work indicate that structural feature co-occurrence, quantified by PMI or ZRFT, contains a significant amount of information relevant to physico-chemical properties of organic compounds.

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.

Use of size-dependent electron configuration fingerprint to develop general prediction models for nanomaterials

Due to the lack of nano descriptors that can appropriately represent the wide chemical space of engineered nanomaterials (ENMs), applicability domain of nano-quantitative structure-activity relationship models are limited to certain types of ENMs, such as metal oxides, metals, carbon-based nanomaterials, or quantum dots. In this study, a size-dependent electron configuration fingerprint (SDEC FP) was introduced to estimate the quantity of electrons based on the core, doping, and coating materials of ENMs in different sizes. SDEC FP was used in prediction model development and nanostructure similarity analysis on datasets including metal and carbon-based nanomaterials with and without surface modifications. Cytotoxicity and zeta potential prediction models developed with SDEC FP achieved good prediction accuracies on test set. Nanostructure similarity analysis was performed through principal component analysis which showed that structural similarity between ENMs measured by SDEC FP was highly correlated with their properties.

The year 2020 in natural product bioinformatics: an overview of the latest tools and databases

Covering: 2020 Bioinformatic approaches to document and analyse chemical structures, biosynthetic gene clusters and analytical data play an important role in the study of natural products. Every year, such a large number of new algorithms, tools and databases are released, that it is difficult to keep track of all the latest developments. The aim of this short article is to provide a concise overview of and reference to the major tools, methods and databases that have been released in the past year.

Cheminformatics in Natural Product-based Drug Discovery

This review seeks to provide a timely survey of the scope and limitations of cheminformatics methods in natural product-based drug discovery. Following an overview of data resources of chemical, biological and structural information on natural products, we discuss, among other aspects, in silico methods for (i) data curation and natural products dereplication, (ii) analysis, visualization, navigation and comparison of the chemical space, (iii) quantification of natural product-likeness, (iv) prediction of the bioactivities (virtual screening, target prediction), ADME and safety profiles (toxicity) of natural products, (v) natural products-inspired de novo design and (vi) prediction of natural products prone to cause interference with biological assays. Among the many methods discussed are rule-based, similarity-based, shape-based, pharmacophore-based and network-based approaches, docking and machine learning methods.