Comparative analysis of chemical similarity methods for modular natural products with a hypothetical structure enumeration algorithm

CatNet: Sequence-based deep learning with cross-attention mechanism for identifying endocrine-disrupting chemicals

Endocrine-disrupting chemicals (EDCs) pose significant environmental and health risks due to their potential to interfere with nuclear receptors (NRs), key regulators of physiological processes. Despite the evident risks, the majority of existing research narrows its focus on the interaction between compounds and the individual NR target, neglecting a comprehensive assessment across the entire NR family. In response, this study assembled a comprehensive human NR dataset, capturing 49,244 interactions between 35,467 unique compounds and 42 NRs. We introduced a cross-attention network framework, "CatNet", innovatively integrating compound and protein representations through cross-attention mechanisms. The results showed that CatNet model achieved excellent performance with an area under the receiver operating characteristic curve (AUCROC) = 0.916 on the test set, and exhibited reliable generalization on unseen compound-NR pairs. A distinguishing feature of our research is its capacity to expand to novel targets. Beyond its predictive accuracy, CatNet offers a valuable mechanistic perspective on compound-NR interactions through feature visualization. Augmenting the utility of our research, we have also developed a graphical user interface, empowering researchers to predict chemical binding to diverse NRs. Our model enables the prediction of human NR-related EDCs and shows the potential to identify EDCs related to other targets.

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.

TCMSID: a simplified integrated database for drug discovery from traditional chinese medicine

Traditional Chinese Medicine (TCM) has been widely used in the treatment of various diseases for millennia. In the modernization process of TCM, TCM ingredient databases are playing more and more important roles. However, most of the existing TCM ingredient databases do not provide simplification function for extracting key ingredients in each herb or formula, which hinders the research on the mechanism of actions of the ingredients in TCM databases. The lack of quality control and standardization of the data in most of these existing databases is also a prominent disadvantage. Therefore, we developed a Traditional Chinese Medicine Simplified Integrated Database (TCMSID) with high storage, high quality and standardization. The database includes 499 herbs registered in the Chinese pharmacopeia with 20,015 ingredients, 3270 targets as well as corresponding detailed information. TCMSID is not only a database of herbal ingredients, but also a TCM simplification platform. Key ingredients from TCM herbs are available to be screened out and regarded as representatives to explore the mechanism of TCM herbs by implementing multi-tool target prediction and multilevel network construction. TCMSID provides abundant data sources and analysis platforms for TCM simplification and drug discovery, which is expected to promote modernization and internationalization of TCM and enhance its international status in the future. TCMSID is freely available at https://tcm.scbdd.com .

Virtual screening of Indonesian herbal compounds as COVID-19 supportive therapy: machine learning and pharmacophore modeling approaches

Background

The number of COVID-19 cases continues to grow in Indonesia. This phenomenon motivates researchers to find alternative drugs that function for prevention or treatment. Due to the rich biodiversity of Indonesian medicinal plants, one alternative is to examine the potential of herbal medicines to support COVID therapy. This study aims to identify potential compound candidates in Indonesian herbal using a machine learning and pharmacophore modeling approaches.

Methods

We used three classification methods that had different decision-making processes: support vector machine (SVM), multilayer perceptron (MLP), and random forest (RF). For the pharmacophore modeling approach, we performed a structure-based analysis on the 3D structure of the main protease SARS-CoV-2 (3CLPro) and repurposed SARS, MERS, and SARS-CoV-2 drugs identified from the literature as datasets in the ligand-based method. Lastly, we used molecular docking to analyze the interactions between the 3CLpro and 14 hit compounds from the Indonesian Herbal Database (HerbalDB), with lopinavir as a positive control.

Results

From the molecular docking analysis, we found six potential compounds that may act as the main proteases of the SARS-CoV-2 inhibitor: hesperidin, kaempferol-3,4'-di-O-methyl ether (Ermanin); myricetin-3-glucoside, peonidin 3-(4’-arabinosylglucoside); quercetin 3-(2G-rhamnosylrutinoside); and rhamnetin 3-mannosyl-(1-2)-alloside.

Conclusions

Our layered virtual screening with machine learning and pharmacophore modeling approaches provided a more objective and optimal virtual screening and avoided subjective decision making of the results. Herbal compounds from the screening, i.e. hesperidin, kaempferol-3,4'-di-O-methyl ether (Ermanin); myricetin-3-glucoside, peonidin 3-(4’-arabinosylglucoside); quercetin 3-(2G-rhamnosylrutinoside); and rhamnetin 3-mannosyl-(1-2)-alloside are potential antiviral candidates for SARS-CoV-2. Moringa oleifera and Psidium guajava that consist of those compounds, could be an alternative option as COVID-19 herbal preventions.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12906-022-03686-y.

Three New Stigmatellin Derivatives Reveal Biosynthetic Insights of Its Side Chain Decoration

Myxobacteria generate natural products with unique chemical structures, which not only feature remarkable biological functions, but also demonstrate unprecedented biosynthetic assembly strategies. The stigmatellins have been previously described as potent inhibitors of the mitochondrial and photosynthetic respiratory chain and originate from an unusual polyketide synthase assembly line. While previous biosynthetic investigations were focused on the formation of the 5,7-dimethoxy-8-hydroxychromone ring, side chain decoration of the hydrophobic alkenyl chain in position 2 was investigated less thoroughly. We report here the full structure elucidation, as well as cytotoxic and antimicrobial activities of three new stigmatellins isolated from the myxobacterium Vitiosangium cumulatum MCy10943^T with side chain decorations distinct from previously characterized members of this compound family. The hydrophobic alkenyl chain in position 2 of the herein described stigmatellins feature a terminal carboxylic acid group (1), a methoxy group at C-12′ (2) or a vicinal diol (3). These findings provide further implications considering the side chain decoration of these aromatic myxobacterial polyketides and their underlying biosynthesis.

An atlas of fragrance chemicals in children's products

Exposure to environmental chemicals during early childhood is a potential health concern. At a tender age, children are exposed to fragrance chemicals used in toys and child care products. Although there are few initiatives in Europe and United States towards monitoring and regulation of fragrance chemicals in children's products, such efforts are still lacking elsewhere. Besides there has been no systematic effort to create a database compiling the surrounding knowledge on fragrance chemicals used in children's products from published literature. Here, we built a database of Fragrance Chemicals in Children's Products (FCCP) that compiles information on 153 fragrance chemicals from published literature. The fragrance chemicals in FCCP have been classified based on their chemical structure, children's product source, chemical origin and odor profile. Moreover, we have also compiled the physicochemical properties, predicted Absorption, Distribution, Metabolism, Excretion and Toxicity (ADMET) properties, molecular descriptors and human target genes for the fragrance chemicals in FCCP. After building FCCP, we performed multiple analyses of the associated fragrance chemical space. Firstly, we assessed the regulatory status of the fragrance chemicals in FCCP through a comparative analysis with 21 chemical lists reflecting current guidelines or regulations. We find that several fragrance chemicals in children's products are potential carcinogens, endocrine disruptors, neurotoxicants, phytotoxins and skin sensitizers. Secondly, we performed a similarity network based analysis of the fragrance chemicals in children's products to reveal the high structural diversity of the associated chemical space. Lastly, we identified skin sensitizing fragrance chemicals in children's products using ToxCast assays. In a nutshell, we present a comprehensive resource and detailed analysis of fragrance chemicals in children's products highlighting the need for their better risk assessment and regulation to deliver safer products for children. FCCP is accessible at: https://cb.imsc.res.in/fccp.

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.

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.

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.

Chemical similarity methods for analyzing secondary metabolite structures

The relation that exists between the structure of a compound and its function is an integral part of chemoinformatics. The similarity principle states that “structurally similar molecules tend to have similar properties and similar molecules exert similar biological activities”. The similarity of the molecules can either be studied at the structure level or at the descriptor level (properties level). Generally, the objective of chemical similarity measures is to enhance prediction of the biological activities of molecules. In this article, an overview of various methods used to compare the similarity between metabolite structures has been provided, including two-dimensional (2D) and three-dimensional (3D) approaches. The focus has been on methods description; e.g. fingerprint-based similarity in which the molecules under study are first fragmented and their fingerprints are computed, 2D structural similarity by comparing the Tanimoto coefficients and Euclidean distances, as well as the use of physiochemical properties descriptor-based similarity methods. The similarity between molecules could also be measured by using data mining (clustering) techniques, e.g. by using virtual screening (VS)-based similarity methods. In this approach, the molecules with the desired descriptors or /and structures are screened from large databases. Lastly, SMILES-based chemical similarity search is an important method for studying the exact structure search, substructure search and also descriptor similarity. The use of a particular method depends upon the requirements of the researcher.

Deep Learning Insights into Lanthanides Complexation Chemistry

Modern structure-property models are widely used in chemistry; however, in many cases, they are still a kind of a "black box" where there is no clear path from molecule structure to target property. Here we present an example of deep learning usage not only to build a model but also to determine key structural fragments of ligands influencing metal complexation. We have a series of chemically similar lanthanide ions, and we have collected data on complexes' stability, built models, predicting stability constants and decoded the models to obtain key fragments responsible for complexation efficiency. The results are in good correlation with the experimental ones, as well as modern theories of complexation. It was shown that the main influence on the constants had a mutual location of the binding centers.

Supervised topic modeling for predicting molecular substructure from mass spectrometry

Small-molecule metabolites are principal actors in myriad phenomena across biochemistry and serve as an important source of biomarkers and drug candidates. Given a sample of unknown composition, identifying the metabolites present is difficult given the large number of small molecules both known and yet to be discovered. Even for biofluids such as human blood, building reliable ways of identifying biomarkers is challenging. A workhorse method for characterizing individual molecules in such untargeted metabolomics studies is tandem mass spectrometry (MS/MS). MS/MS spectra provide rich information about chemical composition. However, structural characterization from spectra corresponding to unknown molecules remains a bottleneck in metabolomics. Current methods often rely on matching to pre-existing databases in one form or another.  Here we develop a preprocessing scheme and supervised topic modeling approach to identify modular groups of spectrum fragments and neutral losses corresponding to chemical substructures using labeled latent Dirichlet allocation (LLDA) to map spectrum features to known chemical structures. These structures appear in new unknown spectra and can be predicted. We find that LLDA is an interpretable and reliable method for structure prediction from MS/MS spectra. Specifically, the LLDA approach has the following advantages: (a) molecular topics are interpretable; (b) A practitioner can select any set of chemical structure labels relevant to their problem; (c ) LLDA performs well and can exceed the performance of other methods in predicting substructures in novel contexts.

Applications of Virtual Screening in Bioprospecting: Facts, Shifts, and Perspectives to Explore the Chemo-Structural Diversity of Natural Products

Natural products are continually explored in the development of new bioactive compounds with industrial applications, attracting the attention of scientific research efforts due to their pharmacophore-like structures, pharmacokinetic properties, and unique chemical space. The systematic search for natural sources to obtain valuable molecules to develop products with commercial value and industrial purposes remains the most challenging task in bioprospecting. Virtual screening strategies have innovated the discovery of novel bioactive molecules assessing in silico large compound libraries, favoring the analysis of their chemical space, pharmacodynamics, and their pharmacokinetic properties, thus leading to the reduction of financial efforts, infrastructure, and time involved in the process of discovering new chemical entities. Herein, we discuss the computational approaches and methods developed to explore the chemo-structural diversity of natural products, focusing on the main paradigms involved in the discovery and screening of bioactive compounds from natural sources, placing particular emphasis on artificial intelligence, cheminformatics methods, and big data analyses.

Comprehensive prediction of secondary metabolite structure and biological activity from microbial genome sequences

Novel antibiotics are urgently needed to address the looming global crisis of antibiotic resistance. Historically, the primary source of clinically used antibiotics has been microbial secondary metabolism. Microbial genome sequencing has revealed a plethora of uncharacterized natural antibiotics that remain to be discovered. However, the isolation of these molecules is hindered by the challenge of linking sequence information to the chemical structures of the encoded molecules. Here, we present PRISM 4, a comprehensive platform for prediction of the chemical structures of genomically encoded antibiotics, including all classes of bacterial antibiotics currently in clinical use. The accuracy of chemical structure prediction enables the development of machine-learning methods to predict the likely biological activity of encoded molecules. We apply PRISM 4 to chart secondary metabolite biosynthesis in a collection of over 10,000 bacterial genomes from both cultured isolates and metagenomic datasets, revealing thousands of encoded antibiotics. PRISM 4 is freely available as an interactive web application at http://prism.adapsyn.com.

Large-scale sequencing efforts have uncovered a large number of secondary metabolic pathways, but the chemicals they synthesise remain unknown. Here the authors present PRISM 4, which predicts the chemical structures encoded by microbial genome sequences, including all classes of bacterial antibiotics in clinical use.

Drug-drug similarity measure and its applications

Drug similarities play an important role in modern biology and medicine, as they help scientists gain deep insights into drugs' therapeutic mechanisms and conduct wet labs that may significantly improve the efficiency of drug research and development. Nowadays, a number of drug-related databases have been constructed, with which many methods have been developed for computing similarities between drugs for studying associations between drugs, human diseases, proteins (drug targets) and more. In this review, firstly, we briefly introduce the publicly available drug-related databases. Secondly, based on different drug features, interaction relationships and multimodal data, we summarize similarity calculation methods in details. Then, we discuss the applications of drug similarities in various biological and medical areas. Finally, we evaluate drug similarity calculation methods with common evaluation metrics to illustrate the important roles of drug similarity measures on different applications.

Biosynthesis of depsipeptides, or Depsi: The peptides with varied generations

Depsipeptides are compounds that contain both ester bonds and amide bonds. Important natural product depsipeptides include the piscicide antimycin, the K⁺ ionophores cereulide and valinomycin, the anticancer agent cryptophycin, and the antimicrobial kutzneride. Furthermore, database searches return hundreds of uncharacterized systems likely to produce novel depsipeptides. These compounds are made by specialized nonribosomal peptide synthetases (NRPSs). NRPSs are biosynthetic megaenzymes that use a module architecture and multi-step catalytic cycle to assemble monomer substrates into peptides, or in the case of specialized depsipeptide synthetases, depsipeptides. Two NRPS domains, the condensation domain and the thioesterase domain, catalyze ester bond formation, and ester bonds are introduced into depsipeptides in several different ways. The two most common occur during cyclization, in a reaction between a hydroxy-containing side chain and the C-terminal amino acid residue in a peptide intermediate, and during incorporation into the growing peptide chain of an α-hydroxy acyl moiety, recruited either by direct selection of an α-hydroxy acid substrate or by selection of an α-keto acid substrate that is reduced in situ. In this article, we discuss how and when these esters are introduced during depsipeptide synthesis, survey notable depsipeptide synthetases, and review insight into bacterial depsipeptide synthetases recently gained from structural studies.

A novel drug repurposing approach for non-small cell lung cancer using deep learning

Drug repurposing is an attractive and pragmatic way offering reduced risks and development time in the complicated process of drug discovery. In the past, drug repurposing has been largely accidental and serendipitous. The most successful examples so far have not involved a systematic approach. Nowadays, remarkable advances in drugs, diseases and bioinformatic knowledge are offering great opportunities for designing novel drug repurposing approach through comprehensive understanding of drug information. In this study, we introduced a novel drug repurposing approach based on transcriptomic data and chemical structures using deep learning. One strong candidate for repurposing has been identified. Pimozide is an anti-dyskinesia agent that is used for the suppression of motor and phonic tics in patients with Tourette's Disorder. However, our pipeline proposed it as a strong candidate for treating non-small cell lung cancer. The cytotoxicity of pimozide against A549 cell lines has been validated.

Unraveling Plant Natural Chemical Diversity for Drug Discovery Purposes

The screening and testing of extracts against a variety of pharmacological targets in order to benefit from the immense natural chemical diversity is a concern in many laboratories worldwide. And several successes have been recorded in finding new actives in natural products, some of which have become new drugs or new sources of inspiration for drugs. But in view of the vast amount of research on the subject, it is surprising that not more drug candidates were found. In our view, it is fundamental to reflect upon the approaches of such drug discovery programs and the technical processes that are used, along with their inherent difficulties and biases. Based on an extensive survey of recent publications, we discuss the origin and the variety of natural chemical diversity as well as the strategies to having the potential to embrace this diversity. It seemed to us that some of the difficulties of the area could be related with the technical approaches that are used, so the present review begins with synthetizing some of the more used discovery strategies, exemplifying some key points, in order to address some of their limitations. It appears that one of the challenges of natural product-based drug discovery programs should be an easier access to renewable sources of plant-derived products. Maximizing the use of the data together with the exploration of chemical diversity while working on reasonable supply of natural product-based entities could be a way to answer this challenge. We suggested alternative ways to access and explore part of this chemical diversity with in vitro cultures. We also reinforced how important it was organizing and making available this worldwide knowledge in an "inventory" of natural products and their sources. And finally, we focused on strategies based on synthetic biology and syntheses that allow reaching industrial scale supply. Approaches based on the opportunities lying in untapped natural plant chemical diversity are also considered.

DeepRiPP integrates multiomics data to automate discovery of novel ribosomally synthesized natural products

Microbial natural products represent a rich resource of evolved chemistry that forms the basis for the majority of pharmacotherapeutics. Ribosomally synthesized and posttranslationally modified peptides (RiPPs) are a particularly interesting class of natural products noted for their unique mode of biosynthesis and biological activities. Analyses of sequenced microbial genomes have revealed an enormous number of biosynthetic loci encoding RiPPs but whose products remain cryptic. In parallel, analyses of bacterial metabolomes typically assign chemical structures to only a minority of detected metabolites. Aligning these 2 disparate sources of data could provide a comprehensive strategy for natural product discovery. Here we present DeepRiPP, an integrated genomic and metabolomic platform that employs machine learning to automate the selective discovery and isolation of novel RiPPs. DeepRiPP includes 3 modules. The first, NLPPrecursor, identifies RiPPs independent of genomic context and neighboring biosynthetic genes. The second module, BARLEY, prioritizes loci that encode novel compounds, while the third, CLAMS, automates the isolation of their corresponding products from complex bacterial extracts. DeepRiPP pinpoints target metabolites using large-scale comparative metabolomics analysis across a database of 10,498 extracts generated from 463 strains. We apply the DeepRiPP platform to expand the landscape of novel RiPPs encoded within sequenced genomes and to discover 3 novel RiPPs, whose structures are exactly as predicted by our platform. By building on advances in machine learning technologies, DeepRiPP integrates genomic and metabolomic data to guide the isolation of novel RiPPs in an automated manner.

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.

Cheminformatics techniques in antimalarial drug discovery and development from natural products 1: basic concepts

A large number of natural products, especially those used in ethnomedicine of malaria, have shown varying in vitro antiplasmodial activities. Facilitating antimalarial drug development from this wealth of natural products is an imperative and laudable mission to pursue. However, limited manpower, high research cost coupled with high failure rate during preclinical and clinical studies might militate against the pursuit of this mission. These limitations may be overcome with cheminformatic techniques. Cheminformatics involves the organization, integration, curation, standardization, simulation, mining and transformation of pharmacology data (compounds and bioactivity) into knowledge that can drive rational and viable drug development decisions. This chapter will review the application of cheminformatics techniques (including molecular diversity analysis, quantitative-structure activity/property relationships and Machine learning) to natural products with in vitro and in vivo antiplasmodial activities in order to facilitate their development into antimalarial drug candidates and design of new potential antimalarial compounds.

A Computational Bipartite Graph-Based Drug Repurposing Method

We present a bipartite graph-based approach to calculate drug pairwise similarity for identifying potential new indications of approved drugs. Both chemical and molecular features were used in drug similarity calculation. In this paper, we first extracted drug chemical structures and drug-target interactions. Second, we computed chemical structure similarity and drug- target profile similarity. Further, we constructed a bipartite graph model with known relationships between drugs and their target proteins. Finally, we weighted summing drug structure similarity with target profile similarity to derive drug pairwise similarity, so that we can predict potential indication of a drug from its similar drugs. In addition, we summarized some alternative strategies and variations follow-up to each section in the overall analysis.