The application potential of machine learning and genomics for understanding natural product diversity, chemistry, and therapeutic translatability

Precision enzyme discovery through targeted mining of metagenomic data

Metagenomics has opened new avenues for exploring the genetic potential of uncultured microorganisms, which may serve as promising sources of enzymes and natural products for industrial applications. Identifying enzymes with improved catalytic properties from the vast amount of available metagenomic data poses a significant challenge that demands the development of novel computational and functional screening tools. The catalytic properties of all enzymes are primarily dictated by their structures, which are predominantly determined by their amino acid sequences. However, this aspect has not been fully considered in the enzyme bioprospecting processes. With the accumulating number of available enzyme sequences and the increasing demand for discovering novel biocatalysts, structural and functional modeling can be employed to identify potential enzymes with novel catalytic properties. Recent efforts to discover new polysaccharide-degrading enzymes from rumen metagenome data using homology-based searches and machine learning-based models have shown significant promise. Here, we will explore various computational approaches that can be employed to screen and shortlist metagenome-derived enzymes as potential biocatalyst candidates, in conjunction with the wet lab analytical methods traditionally used for enzyme characterization.

C-C Motif Chemokine Ligand 5 (CCL5): A Potential Biomarker and Immunotherapy Target for Osteosarcoma

BACKGROUND

Osteosarcoma (OS) is the most common primary malignant tumor of bone tissue, which has an insidious onset and is difficult to detect early, and few early diagnostic markers with high specificity and sensitivity. Therefore, this study aims to identify potential biomarkers that can help diagnose OS in its early stages and improve the prognosis of patients.

METHODS

The data sets of GSE12789, GSE28424, GSE33382 and GSE36001 were combined and normalized to identify Differentially Expressed Genes (DEGs). The data were analyzed by Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genome (KEGG) and Disease Ontology (DO). The hub gene was selected based on the common DEG that was obtained by applying two regression methods: the Least Absolute Shrinkage and Selection Operator (LASSO) and Support vVector Machine (SVM). Then the diagnostic value of the hub gene was evaluated in the GSE42572 data set. Finally, the correlation between immunocyte infiltration and key genes was analyzed by CIBERSORT.

RESULTS

The regression analysis results of LASSO and SVM are the following three DEGs: FK501 binding protein 51 (FKBP5), C-C motif chemokine ligand 5 (CCL5), complement component 1 Q subcomponent B chain (C1QB). We evaluated the diagnostic performance of three biomarkers (FKBP5, CCL5 and C1QB) for osteosarcoma using receiver operating characteristic (ROC) analysis. In the training group, the area under the curve (AUC) of FKBP5, CCL5 and C1QB was 0.907, 0.874 and 0.676, respectively. In the validation group, the AUC of FKBP5, CCL5 and C1QB was 0.618, 0.932 and 0.895, respectively. It is noteworthy that these genes were more expressed in tumor tissues than in normal tissues by various immune cell types, such as plasma cells, CD8+ T cells, T regulatory cells (Tregs), activated NK cells, activated dendritic cells and activated mast cells. These immune cell types are also associated with the expression levels of the three diagnostic genes that we identified.

CONCLUSION

We found that CCL5 can be considered an early diagnostic gene of osteosarcoma, and CCL5 interacts with immune cells to influence tumor occurrence and development. These findings have important implications for the early detection of osteosarcoma and the identification of novel therapeutic targets.

Navigating the Expansive Landscapes of Soft Materials: A User Guide for High-Throughput Workflows

Synthetic polymers are highly customizable with tailored structures and functionality, yet this versatility generates challenges in the design of advanced materials due to the size and complexity of the design space. Thus, exploration and optimization of polymer properties using combinatorial libraries has become increasingly common, which requires careful selection of synthetic strategies, characterization techniques, and rapid processing workflows to obtain fundamental principles from these large data sets. Herein, we provide guidelines for strategic design of macromolecule libraries and workflows to efficiently navigate these high-dimensional design spaces. We describe synthetic methods for multiple library sizes and structures as well as characterization methods to rapidly generate data sets, including tools that can be adapted from biological workflows. We further highlight relevant insights from statistics and machine learning to aid in data featurization, representation, and analysis. This Perspective acts as a "user guide" for researchers interested in leveraging high-throughput screening toward the design of multifunctional polymers and predictive modeling of structure-property relationships in soft materials.

Challenges in natural product-based drug discovery assisted with in silico-based methods

The application of traditional medicine by humans for the treatment of ailments as well as improving the quality of life far outdates recorded history. To date, a significant percentage of humans, especially those living in developing/underprivileged communities still rely on traditional medicine for primary healthcare needs. In silico-based methods have been shown to play a pivotal role in modern pharmaceutical drug discovery processes. The application of these methods in identifying natural product (NP)-based hits has been successful. This is very much observed in many research set-ups that use rationally in silico-based methods in combination with experimental validation techniques. The combination has rendered the use of in silico-based approaches even more popular and successful in the investigation of NPs. However, identifying and proposing novel NP-based hits for experimental validation comes with several challenges such as the availability of compounds by suppliers, the huge task of separating pure compounds from complex mixtures, the quantity of samples available from the natural source to be tested, not to mention the potential ecological impact if the natural source is exhausted. Because most peer-reviewed publications are biased towards "positive results", these challenges are generally not discussed in publications. In this review, we highlight and discuss these challenges. The idea is to give interested scientists in this field of research an idea of what they can come across or should be expecting as well as prompting them on how to avoid or fix these issues.

A critical review of machine-learning for "multi-omics" marine metabolite datasets

During the last decade, genomic, transcriptomic, proteomic, metabolomic, and other omics datasets have been generated for a wide range of marine organisms, and even more are still on the way. Marine organisms possess unique and diverse biosynthetic pathways contributing to the synthesis of novel secondary metabolites with significant bioactivities. As marine organisms have a greater tendency to adapt to stressed environmental conditions, the chance to identify novel bioactive metabolites with potential biotechnological application is very high. This review presents a comprehensive overview of the available "-omics" and "multi-omics" approaches employed for characterizing marine metabolites along with novel data integration tools. The need for the development of machine-learning algorithms for "multi-omics" approaches is briefly discussed. In addition, the challenges involved in the analysis of "multi-omics" data and recommendations for conducting "multi-omics" study were discussed.

Machine Learning-Enabled Genome Mining and Bioactivity Prediction of Natural Products

Natural products (NPs) produced by microorganisms and plants are a major source of drugs, herbicides, and fungicides. Thanks to recent advances in DNA sequencing, bioinformatics, and genome mining tools, a vast amount of data on NP biosynthesis has been generated over the years, which has been increasingly exploited to develop machine learning (ML) tools for NP discovery. In this review, we discuss the latest advances in developing and applying ML tools for exploring the potential NPs that can be encoded by genomic language and predicting the types of bioactivities of NPs. We also examine the technical challenges associated with the development and application of ML tools for NP research.

Advanced Methods for Natural Products Discovery: Bioactivity Screening, Dereplication, Metabolomics Profiling, Genomic Sequencing, Databases and Informatic Tools, and Structure Elucidation

Natural Products (NP) are essential for the discovery of novel drugs and products for numerous biotechnological applications. The NP discovery process is expensive and time-consuming, having as major hurdles dereplication (early identification of known compounds) and structure elucidation, particularly the determination of the absolute configuration of metabolites with stereogenic centers. This review comprehensively focuses on recent technological and instrumental advances, highlighting the development of methods that alleviate these obstacles, paving the way for accelerating NP discovery towards biotechnological applications. Herein, we emphasize the most innovative high-throughput tools and methods for advancing bioactivity screening, NP chemical analysis, dereplication, metabolite profiling, metabolomics, genome sequencing and/or genomics approaches, databases, bioinformatics, chemoinformatics, and three-dimensional NP structure elucidation.

In-Silico Approaches for the Screening and Discovery of Broad-Spectrum Marine Natural Product Antiviral Agents Against Coronaviruses

The urgent need for SARS-CoV-2 controls has led to a reassessment of approaches to identify and develop natural product inhibitors of zoonotic, highly virulent, and rapidly emerging viruses. There are yet no clinically approved broad-spectrum antivirals available for beta-coronaviruses. Discovery pipelines for pan-virus medications against a broad range of betacoronaviruses are therefore a priority. A variety of marine natural product (MNP) small molecules have shown inhibitory activity against viral species. Access to large data caches of small molecule structural information is vital to finding new pharmaceuticals. Increasingly, molecular docking simulations are being used to narrow the space of possibilities and generate drug leads. Combining in-silico methods, augmented by metaheuristic optimization and machine learning (ML) allows the generation of hits from within a virtual MNP library to narrow screens for novel targets against coronaviruses. In this review article, we explore current insights and techniques that can be leveraged to generate broad-spectrum antivirals against betacoronaviruses using in-silico optimization and ML. ML approaches are capable of simultaneously evaluating different features for predicting inhibitory activity. Many also provide a semi-quantitative measure of feature relevance and can guide in selecting a subset of features relevant for inhibition of SARS-CoV-2.

Novel chemical-structure TPOR agonist, TMEA, promotes megakaryocytes differentiation and thrombopoiesis via mTOR and ERK signalings

BACKGROUND

Non-peptide thrombopoietin receptor (TPOR) agonists are promising therapies for the mitigation and treatment of thrombocytopenia. However, only few agents are available as safe and effective for stimulating platelet production for thrombocytopenic patients in the clinic.

PURPOSE

This study aimed to develop a novel small molecule TPOR agonist and investigate its underlying regulation of function in megakaryocytes (MKs) differentiation and thrombopoiesis.

METHODS

A potential active compound that promotes MKs differentiation and thrombopoiesis was obtained by machine learning (ML). Meanwhile, the effect was verified in zebrafish model, HEL and Meg-01 cells. Next, the key regulatory target was identified by Drug Affinity Responsive Target Stabilization Assay (DARTS), Cellular Thermal Shift Assay (CETSA), and molecular simulation experiments. After that, RNA-sequencing (RNA-seq) was used to further confirm the associated pathways and evaluate the gene expression induced during MK differentiation. In vivo, irradiation (IR) mice, C57BL/6N-TPOR^em1cyagen (Tpor^-/-) mice were constructed by CRISPR/Cas9 technology to examine the therapeutic effect of TMEA on thrombocytopenia.

RESULTS

A natural chemical-structure small molecule TMEA was predicted to be a potential active compound based on ML. Obvious phenotypes of MKs differentiation were observed by TMEA induction in zebrafish model and TMEA could increase co-expression of CD41/CD42b, DNA content, and promote polyploidization and maturation of MKs in HEL and Meg-01 cells. Mechanically, TMEA could bind with TPOR protein and further regulate the PI3K/AKT/mTOR/P70S6K and MEK/ERK signal pathways. In vivo, TMEA evidently promoted platelet regeneration in mice with radiation-induced thrombocytopenia but had no effect on Tpor^-/- and C57BL/6 (WT) mice.

CONCLUSION

TMEA could serve as a novel TPOR agonist to promote MKs differentiation and thrombopoiesis via mTOR and ERK signaling and could potentially be created as a promising new drug to treat thrombocytopenia.

Antibiotic discovery in the artificial intelligence era

As the global burden of antibiotic resistance continues to grow, creative approaches to antibiotic discovery are needed to accelerate the development of novel medicines. A rapidly progressing computational revolution-artificial intelligence-offers an optimistic path forward due to its ability to alleviate bottlenecks in the antibiotic discovery pipeline. In this review, we discuss how advancements in artificial intelligence are reinvigorating the adoption of past antibiotic discovery models-namely natural product exploration and small molecule screening. We then explore the application of contemporary machine learning approaches to emerging areas of antibiotic discovery, including antibacterial systems biology, drug combination development, antimicrobial peptide discovery, and mechanism of action prediction. Lastly, we propose a call to action for open access of high-quality screening datasets and interdisciplinary collaboration to accelerate the rate at which machine learning models can be trained and new antibiotic drugs can be developed.

A brief guide to machine learning for antibiotic discovery

Rising antibiotic resistance and an alarmingly lean antibiotic pipeline require the adoption of novel approaches to rapidly discover new structural and functional classes of antibiotics. Excitingly, algorithmic approaches to antibiotic discovery are sufficiently advanced to meaningfully influence the antibiotic discovery process. Indeed, once trained on high-quality datasets, contemporary machine-learning and deep-learning models can be used to perform predictions for new antibiotics across vast chemical spaces, orders of magnitude more rapidly than compounds can be screened in the laboratory. This increases the probability of discovering new antibiotics with desirable properties. In this short review, we briefly describe the utility of contemporary machine-learning and deep-learning approaches to guide the discovery of new small-molecule antibiotics and unidentified natural products. We then propose a call to action for more open sharing of high-quality screening datasets to accelerate the rate at which forthcoming antibiotic-prediction models can be trained. Together, we aim to introduce antibiotic discoverers to a sample of recent applications of contemporary algorithmic methods to facilitate the wider adoption of these powerful computational approaches.

Targeted Large-Scale Genome Mining and Candidate Prioritization for Natural Product Discovery

Large-scale genome-mining analyses have identified an enormous number of cryptic biosynthetic gene clusters (BGCs) as a great source of novel bioactive natural products. Given the sheer number of natural product (NP) candidates, effective strategies and computational methods are keys to choosing appropriate BGCs for further NP characterization and production. This review discusses genomics-based approaches for prioritizing candidate BGCs extracted from large-scale genomic data, by highlighting studies that have successfully produced compounds with high chemical novelty, novel biosynthesis pathway, and potent bioactivities. We group these studies based on their BGC-prioritization logics: detecting presence of resistance genes, use of phylogenomics analysis as a guide, and targeting for specific chemical structures. We also briefly comment on the different bioinformatics tools used in the field and examine practical considerations when employing a large-scale genome mining study.

Characterization of siderophores from Escherichia coli strains through genome mining tools: an antiSMASH study

Although urinary tract infections (UTIs) affect many people, they are usually a disease observed in women. UTIs happen when exogenous and endogenous bacteria enter the urinary tract and colonize there. Cystitis and pyelonephritis occur when bacteria infect the bladder and the kidneys, respectively. UTIs become much serious if the bacteria causing the infection are antibiotic resistant. Since the pathogenic microorganisms have been adopted to current antibiotics via genetic variations, UTIs have become an even more severe health problem. Therefore, there is a great need for the discovery of novel antibiotics. Genome mining of nonpathogenic and pathogenic Escherichia coli strains for investigating secondary metabolites were conducted by the antiSMASH analysis. When the resulting secondary metabolites were examined, it was found that some of the siderophores are effective in UTIs. In conclusion, since the siderophore production in E. coli is directly related to UTIs, these molecules can be a good target for development of future pharmaceutical approaches and compounds. Siderophores can also be used in industrial studies due to their higher chelating affinity for iron.

Genome mining on nonpathogenic and pathogenic E. coli was studied.

Comprehensive and comparative analysis of siderophores were investigated.

The results may open a new gate on the development of new drugs on pathogenic E. coli-based diseases.

Exploring Newer Biosynthetic Gene Clusters in Marine Microbial Prospecting

Marine microbes genetically evolved to survive varying salinity, temperature, pH, and other stress factors by producing different bioactive metabolites. These microbial secondary metabolites (SMs) are novel, have high potential, and could be used as lead molecule. Genome sequencing of microbes revealed that they have the capability to produce numerous novel bioactive metabolites than observed under standard in vitro culture conditions. Microbial genome has specific regions responsible for SM assembly, termed biosynthetic gene clusters (BGCs), possessing all the necessary genes to encode different enzymes required to generate SM. In order to augment the microbial chemo diversity and to activate these gene clusters, various tools and techniques are developed. Metagenomics with functional gene expression studies aids in classifying novel peptides and enzymes and also in understanding the biosynthetic pathways. Genome shuffling is a high-throughput screening approach to improve the development of SMs by incorporating genomic recombination. Transcriptionally silent or lower level BGCs can be triggered by artificially knocking promoter of target BGC. Additionally, bioinformatic tools like antiSMASH, ClustScan, NAPDOS, and ClusterFinder are effective in identifying BGCs of existing class for annotation in genomes. This review summarizes the significance of BGCs and the different approaches for detecting and elucidating BGCs from marine microbes.

Strategies to access biosynthetic novelty in bacterial genomes for drug discovery

Bacteria provide a rich source of natural products with potential therapeutic applications, such as novel antibiotic classes or anticancer drugs. Bioactivity-guided screening of bacterial extracts and characterization of biosynthetic pathways for drug discovery is now complemented by the availability of large (meta)genomic collections, placing researchers into the postgenomic, big-data era. The progress in next-generation sequencing and the rise of powerful computational tools provide unprecedented insights into unexplored taxa, ecological niches and 'biosynthetic dark matter', revealing diverse and chemically distinct natural products in previously unstudied bacteria. In this Review, we discuss such sources of new chemical entities and the implications for drug discovery with a particular focus on the strategies that have emerged in recent years to identify and access novelty.

Complex peptide natural products: Biosynthetic principles, challenges and opportunities for pathway engineering

Complex peptide natural products exhibit diverse biological functions and a wide range of physico-chemical properties. As a result, many peptides have entered the clinics for various applications. Two main routes for the biosynthesis of complex peptides have evolved in nature: ribosomally synthesized and post-translationally modified peptide (RiPP) biosynthetic pathways and non-ribosomal peptide synthetases (NRPSs). Insights into both bioorthogonal peptide biosynthetic strategies led to the establishment of universal principles for each of the two routes. These universal rules can be leveraged for the targeted identification of novel peptide biosynthetic blueprints in genome sequences and used for the rational engineering of biosynthetic pathways to produce non-natural peptides. In this review, we contrast the key principles of both biosynthetic routes and compare the different biochemical strategies to install the most frequently encountered peptide modifications. In addition, the influence of the fundamentally different biosynthetic principles on past, current and future engineering approaches is illustrated. Despite the different biosynthetic principles of both peptide biosynthetic routes, the arsenal of characterized peptide modifications encountered in RiPP and NRPS systems is largely overlapping. The continuous expansion of the biocatalytic toolbox of peptide modifying enzymes for both routes paves the way towards the production of complex tailor-made peptides and opens up the possibility to produce NRPS-derived peptides using the ribosomal route and vice versa.

Small investments with big returns: environmental genomic bioprospecting of microbial life

Microorganisms and their natural products are major drivers of ecological processes and industrial applications. Microbial bioprospecting has been critical for the advancement in various fields such as pharmaceuticals, sustainable industries, food security and bioremediation. Next generation sequencing has been paramount in the exploration of diverse environmental microbiomes. It presents a culture-independent approach to investigating hitherto uncultured taxa, resulting in the creation of massive sequence databases, which are available in the public domain. Genome mining searches available (meta)genomic data for target biosynthetic genes, and combined with the large-scale public data, this in-silico bioprospecting method presents an efficient and extensive way to uncover microbial bioproducts. Bioinformatic tools have progressed to a stage where we can recover genomes from the environment; these metagenome-assembled genomes present a way to understand the metabolic capacity of microorganisms in a physiological and ecological context. Environmental sampling been extensive across various ecological settings, including microbiomes with unique physicochemical properties that could influence the discovery of novel functions and metabolic pathways. Although in-silico methods cannot completely substitute in-vitro studies, the contextual information it provides is invaluable for understanding the ecological and taxonomic distribution of microbial genotypes and to form effective strategies for future microbial bioprospecting efforts.

Discovery of a novel megakaryopoiesis enhancer, ingenol, promoting thrombopoiesis through PI3K-Akt signaling independent of thrombopoietin

Thrombocytopenia, a most common complication of radiotherapy and chemotherapy, is an important cause of morbidity and mortality in cancer patients. However, there are still no approved agents for the treatment of radiation- and chemotherapy-induced thrombocytopenia (RIT and CIT, respectively). In this study, a drug screening model for predicting compounds with activity in promoting megakaryocyte (MK) differentiation and platelet production was established based on machine learning (ML), and a natural product ingenol was predicted as a potential active compound. Then, in vitro experiments showed that ingenol significantly promoted MK differentiation in K562 and HEL cells. Furthermore, a RIT mice model and c-MPL knock-out (c-MPL^-/-) mice constructed by CRISPR/Cas9 technology were used to assess the therapeutic action of ingenol on thrombocytopenia. The results showed that ingenol accelerated megakaryopoiesis and thrombopoiesis both in RIT mice and c-MPL^-/- mice. Next, RNA-sequencing (RNA-seq) was carried out to analyze the gene expression profile induced by ingenol during MK differentiation. Finally, through experimental verifications, we demonstrated that the activation of PI3K/Akt signaling pathway was involved in ingenol-induced MK differentiation. Blocking PI3K/Akt signaling pathway abolished the promotion of ingenol on MK differentiation. Nevertheless, inhibition of TPO/c-MPL signaling pathway could not suppress ingenol-induced MK differentiation. In conclusion, our study builds a drug screening model to discover active compounds against thrombocytopenia, reveals the critical roles of ingenol in promoting MK differentiation and platelet production, and provides a promising avenue for the treatment of RIT.

Marine drugs: Biology, pipelines, current and future prospects for production

The marine environment is a huge reservoir of biodiversity and represents an excellent source of chemical compounds, some of which have large economical values. In the urgent quest for new pharmaceuticals, marine-based drug discovery has progressed significantly over the past several decades and we now benefit from a series of approved marine natural products (MNPs) to treat cancer and pain while an additional collection of promising leads are in clinical trials. However, the discovery and supply of MNPs has always been challenging given their low bioavailability and structural complexity. Their manufacture for pre-clinical and clinical development but also commercialization mainly relies upon marine source extraction and chemical synthesis, which are associated with high costs, unsustainability and severe environmental problems. In this review, we discuss how metabolic engineering now raises reasonable expectations for the implementation of microbial cell factories, which may provide a sustainable approach for MNP-based drug supply in the near future.

A roadmap for metagenomic enzyme discovery

Covering: up to 2021Metagenomics has yielded massive amounts of sequencing data offering a glimpse into the biosynthetic potential of the uncultivated microbial majority. While genome-resolved information about microbial communities from nearly every environment on earth is now available, the ability to accurately predict biocatalytic functions directly from sequencing data remains challenging. Compared to primary metabolic pathways, enzymes involved in secondary metabolism often catalyze specialized reactions with diverse substrates, making these pathways rich resources for the discovery of new enzymology. To date, functional insights gained from studies on environmental DNA (eDNA) have largely relied on PCR- or activity-based screening of eDNA fragments cloned in fosmid or cosmid libraries. As an alternative, shotgun metagenomics holds underexplored potential for the discovery of new enzymes directly from eDNA by avoiding common biases introduced through PCR- or activity-guided functional metagenomics workflows. However, inferring new enzyme functions directly from eDNA is similar to searching for a 'needle in a haystack' without direct links between genotype and phenotype. The goal of this review is to provide a roadmap to navigate shotgun metagenomic sequencing data and identify new candidate biosynthetic enzymes. We cover both computational and experimental strategies to mine metagenomes and explore protein sequence space with a spotlight on natural product biosynthesis. Specifically, we compare in silico methods for enzyme discovery including phylogenetics, sequence similarity networks, genomic context, 3D structure-based approaches, and machine learning techniques. We also discuss various experimental strategies to test computational predictions including heterologous expression and screening. Finally, we provide an outlook for future directions in the field with an emphasis on meta-omics, single-cell genomics, cell-free expression systems, and sequence-independent methods.

Artificial intelligence-guided discovery of anticancer lead compounds from plants and associated microorganisms

Plants and associated microorganisms are essential sources of natural products against human cancer diseases, partly exemplified by plant-derived anticancer drugs such as Taxol (paclitaxel). Natural products provide diverse mechanisms of action and can be used directly or as prodrugs for further anticancer optimization. Despite the success, major bottlenecks can delay anticancer lead discovery and implementation. Recent advances in sequencing and omics-related technology have provided a mine of information for developing new therapeutics from natural products. Artificial intelligence (AI), including machine learning (ML), has offered powerful techniques for extensive data analysis and prediction-making in anticancer leads discovery. This review presents an overview of current AI-guided solutions to discover anticancer lead compounds, focusing on natural products from plants and associated microorganisms.

Alkaloids in Contemporary Drug Discovery to Meet Global Disease Needs

An overview is presented of the well-established role of alkaloids in drug discovery, the application of more sustainable chemicals, and biological approaches, and the implementation of information systems to address the current challenges faced in meeting global disease needs. The necessity for a new international paradigm for natural product discovery and development for the treatment of multidrug resistant organisms, and rare and neglected tropical diseases in the era of the Fourth Industrial Revolution and the Quintuple Helix is discussed.

Predicting biochemical and physiological effects of natural products from molecular structures using machine learning

Covering: 2016 to 2021Discovery of novel natural products has been greatly facilitated by advances in genome sequencing, genome mining and analytical techniques. As a result, the volume of data for natural products has increased over the years, which started to serve as ingredients for developing machine learning models. In the past few years, a number of machine learning models have been developed to examine various aspects of a molecule by effectively processing its molecular structure. Understanding of the biological effects of natural products can benefit from such machine learning approaches. In this context, this Highlight reviews recent studies on machine learning models developed to infer various biological effects of molecules. A particular attention is paid to molecular featurization, or computational representation of a molecular structure, which is an essential process during the development of a machine learning model. Technical challenges associated with the use of machine learning for natural products are further discussed.

An Analysis of Biosynthesis Gene Clusters and Bioactivity of Marine Bacterial Symbionts

Symbiotic marine bacteria have a pivotal role in drug discovery due to the synthesis of diverse biologically potential compounds. The marine bacterial phyla proteobacteria, actinobacteria and firmicutes are commonly associated with marine macro organisms and frequently reported as dominant bioactive compound producers. They can produce biologically active compounds that possess antimicrobial, antiviral, antitumor, antibiofilm and antifouling properties. Synthesis of these bioactive compounds is controlled by a set of genes of their genomes that is known as biosynthesis gene clusters (BGCs). The development in the field of biotechnology and bioinformatics has uncovered the potential BGCs of the bacterial genome and its functions. Now-a-days researchers have focused their attention on the identification of potential BGCs for the discovery of novel bioactive compounds using advanced technology. This review highlights the marine bacterial symbionts and their BGCs which are responsible for the synthesis of bioactive compounds.