Machine learning discovery of missing links that mediate alternative branches to plant alkaloids

Molecular insights fast-tracked: AI in biosynthetic pathway research

Covering: 2000 to 2025This review explores the potential of artificial intelligence (AI) in addressing challenges and accelerating molecular insights in biosynthetic pathway research, which is crucial for developing bioactive natural products with applications in pharmacology, agriculture, and biotechnology. It provides an overview of various AI techniques relevant to this research field, including machine learning (ML), deep learning (DL), natural language processing, network analysis, and data mining. AI-powered applications across three main areas, namely, pathway discovery and mining, pathway design, and pathway optimization, are discussed, and the benefits and challenges of integrating omics data and AI for enhanced pathway research are also elucidated. This review also addresses the current limitations, future directions, and the importance of synergy between AI and experimental approaches in unlocking rapid advancements in biosynthetic pathway research. The review concludes with an evaluation of AI's current capabilities and future outlook, emphasizing the transformative impact of AI on biosynthetic pathway research and the potential for new opportunities in the discovery and optimization of bioactive natural products.

3,4-Dihydroxyphenylacetaldehyde synthase evolved an ordered structure to deliver oxygen to pyridoxal 5'-phosphate for cuticle assembly in the mosquito Aedes aegypti

3,4-Dihydroxyphenylacetaldehyde synthase (DHPAAS) catalyzes oxygen-dependent conversion of 3,4-dihydroxyphenylalanine (dopa) to 3,4-dihydroxyphenylacetaldehyde (DHPAA), a likely cross-linking agent precursor of the insect cuticle. In the current study, extensive in vivo experiments in Aedes aegypti show that DHPAAS is essential for abdominal integrity, egg development and cuticle structure formation. Solid-state 13C nuclear magnetic resonance analysis of the Ae. aegypti cuticle molecular structure shows chemical shifts of 115 to 145 ppm, suggesting the presence of catechols derived from DHPAA. The crystal structure of insect DHPAAS was then solved, revealing an active site that is divergent from that of the homologous enzyme dopa decarboxylase. In the DHPAAS crystal structure, stabilization of the flexible 320-350 region accompanies the positioning of the 350-360 loop relatively close to the catalytic Asn192 residue while the conserved active site residue Phe103 adopts an open conformation away from the active center; these distinct features participate in the formation of a specific hydrophobic tunnel which potentially facilitates delivery of oxygen to pyridoxal 5'-phosphate in the conversion of dopa to DHPAA.

Microbial Technologies Enhanced by Artificial Intelligence for Healthcare Applications

The combination of artificial intelligence (AI) with microbial technology marks the start of a major transformation, improving applications throughout biotechnology, especially in healthcare. With the capability of AI to process vast amounts of biological big data, advanced microbial technology allows for a comprehensive understanding of complex biological systems, advancing disease diagnosis, treatment and the development of microbial therapeutics. This mini review explores the impact of AI-integrated microbial technologies in healthcare, highlighting advancements in microbial biomarker-based diagnosis, the development of microbial therapeutics and the microbial production of therapeutic compounds. This exploration promises significant improvements in the design and implementation of health-related solutions, steering a new era in biotechnological applications.

De Novo Synthesis of Reticuline and Taxifolin Using Re-engineered Homologous Recombination in Yarrowia lipolytica

Yarrowia lipolytica has been widely engineered as a eukaryotic cell factory to produce various important compounds. However, the difficulty of gene editing and the lack of efficient neutral sites make rewiring of Y. lipolytica metabolism challenging. Herein, a Cas9 system was established to redesign the Y. lipolytica homologous recombination system, which caused a more than 56-fold increase in the HR efficiency. The fusion expression of the hBrex27 sequence in the C-terminus of Cas9 recruited more Rad51 protein, and the engineered Cas9 decreased NHEJ, achieving 85% single-gene positive efficiency and 25% multigene editing efficiency. With this system, neutral sites on different chromosomes were characterized, and a deep learning model was developed for gRNA activity prediction, thus providing the corresponding integration efficiency and expression intensity. Subsequently, the tool and platform strains were validated by applying them for the de novo synthesis of (S)-reticuline and (2S)-taxifolin. The developed platform strains and tools helped transform Y. lipolytica into an easy-to-operate model cell factory, similar to Saccharomyces cerevisiae.

A Guide to Metabolic Network Modeling for Plant Biology

Plants produce a diverse array of compounds that play crucial roles in growth, in development, and in responses to abiotic and biotic stresses. Understanding the fluxes within metabolic pathways is essential for guiding strategies aimed at directing metabolism for crop improvement and the plant natural product industry. Over the past decade, metabolic network modeling has emerged as a predominant tool for the integration, quantification, and prediction of the spatial and temporal distribution of metabolic flows. In this review, we present the primary methods for constructing mathematical models of metabolic systems and highlight recent achievements in plant metabolism using metabolic modeling. Furthermore, we discuss current challenges in applying network flux analysis in plants and explore the potential use of machine learning technologies in plant metabolic modeling. The practical application of mathematical modeling is expected to provide significant insights into the structure and regulation of plant metabolic networks.

Advancements in Microbial Cell Engineering for Benzylisoquinoline Alkaloid Production

Benzylisoquinoline alkaloids (BIAs) are a class of natural compounds found in plants of the Ranunculaceae family, known for their diverse pharmacological activities. However, the extraction yields of BIAs from plants are limited, and the cost of chemical synthesis is prohibitively high. Recent advancements in systems metabolic engineering and genomics have made it feasible to use microbes as bioreactors for BIAs production. This review explores recent progress in enhancing the production and yields of BIAs in two microbial systems: Escherichia coli and Saccharomyces cerevisiae. It covers various BIAs, including (S)-reticuline, morphinane, protoberberine, and aporphine alkaloids. The review provides strategies and technologies for BIAs synthesis, analyzes current challenges in BIAs research, and offers recommendations for future research directions.

Integrated metabolomic and transcriptomic analyses of Dendrobium chrysotoxum and D. thyrsiflorum reveal the biosynthetic pathway from gigantol to erianin

Erianin is one of the most representative bibenzyls with significant inhibitory activity against a wide range of tumor cells. However, the low erianin level in natural materials has severely inhibited its further development in health care. Our aim was to uncover the erianin biosynthetic pathway to lay the foundation for promoting its production. Firstly, we screened and obtained two Dendrobium species (Dendrobium thyrsiflorum stems with lower erianin content and D. chrysotoxum stems with higher erianin content), belonging to the same Dendrobium section (Chrysotoxae). A systematic analysis of bibenzyl structure and content in two stems revealed that gigantol might be an erianin biosynthetic intermediate, which was verified by introducing deuterium-labeled gigantol. Chemical structure analyses indicated that gigantol was modified by two kinds of enzymes (hydroxylases and O-methyltransferases), leading to erianin synthesis. Up-regulated hydroxylases and O-methyltransferases (OMTs) were screened out and were performed by molecular docking simulation experiments. We propose a rational biosynthetic pathway from gigantol to erianin, as well as relevant enzymes involved in the process. Our findings should significantly contribute to comprehensive resolution of the erianin biosynthetic pathway, promote its large-scale industrial production as well as contribute to biosynthesis studies of other bibenzyls.

Beyond co-expression: pathway discovery for plant pharmaceuticals

Plant natural products have been an important source of medicinal molecules since ancient times. To gain access to the whole diversity of these molecules for pharmaceutical applications, it is important to understand their biosynthetic origins. Whilst co-expression is a reliable tool for identifying gene candidates, a variety of complementary methods can aid in screening or refining candidate selection. Here, we review recently employed plant biosynthetic pathway discovery approaches, and highlight future directions in the field.

Unlocking plant bioactive pathways: omics data harnessing and machine learning assisting

Plant bioactives hold immense potential in the medicine and food industry. The recent advancements in omics applied in deciphering specialized metabolic pathways underscore the importance of high-quality genome releases and the wealth of data in metabolomics and transcriptomics. While harnessing data, whether integrated or standalone, has proven successful in unveiling plant natural product (PNP) biosynthetic pathways, the democratization of machine learning in biology opens exciting new opportunities for enhancing the exploration of these pathways. This review highlights the recent breakthroughs in disrupting plant-specialized biosynthetic pathways through the utilization of omics data harnessing and machine learning techniques.

Functional annotation of enzyme-encoding genes using deep learning with transformer layers

Functional annotation of open reading frames in microbial genomes remains substantially incomplete. Enzymes constitute the most prevalent functional gene class in microbial genomes and can be described by their specific catalytic functions using the Enzyme Commission (EC) number. Consequently, the ability to predict EC numbers could substantially reduce the number of un-annotated genes. Here we present a deep learning model, DeepECtransformer, which utilizes transformer layers as a neural network architecture to predict EC numbers. Using the extensively studied Escherichia coli K-12 MG1655 genome, DeepECtransformer predicted EC numbers for 464 un-annotated genes. We experimentally validated the enzymatic activities predicted for three proteins (YgfF, YciO, and YjdM). Further examination of the neural network's reasoning process revealed that the trained neural network relies on functional motifs of enzymes to predict EC numbers. Thus, DeepECtransformer is a method that facilitates the functional annotation of uncharacterized genes.

Deep learning for metabolic pathway design

The establishment of a bio-based circular economy is imperative in tackling the climate crisis and advancing sustainable development. In this realm, the creation of microbial cell factories is central to generating a variety of chemicals and materials. The design of metabolic pathways is crucial in shaping these microbial cell factories, especially when it comes to producing chemicals with yet-to-be-discovered biosynthetic routes. To aid in navigating the complexities of chemical and metabolic domains, computer-supported tools for metabolic pathway design have emerged. In this paper, we evaluate how digital strategies can be employed for pathway prediction and enzyme discovery. Additionally, we touch upon the recent strides made in using deep learning techniques for metabolic pathway prediction. These computational tools and strategies streamline the design of metabolic pathways, facilitating the development of microbial cell factories. Leveraging the capabilities of deep learning in metabolic pathway design is profoundly promising, potentially hastening the advent of a bio-based circular economy.

Integration of discovery and engineering in plant alkaloid research: Recent developments in elucidation, reconstruction, and repurposing biosynthetic pathways

Plants synthesize tens of thousands of bioactive nitrogen-containing compounds called alkaloids, including some clinically important drugs in modern medicine. The discovery of new alkaloid structures and their metabolism in plants have provided ways to access these rich sources of bioactivities including new-to-nature compounds relevant to therapeutic and industrial applications. This review discusses recent advances in alkaloid biosynthesis discovery, including complete pathway elucidations. Additionally, the latest developments in the production of new and established plant alkaloids based on either biosynthesis or semisynthesis are discussed.

Recent advances in machine learning applications in metabolic engineering

Metabolic engineering encompasses several widely-used strategies, which currently hold a high seat in the field of biotechnology when its potential is manifesting through a plethora of research and commercial products with a strong societal impact. The genomic revolution that occurred almost three decades ago has initiated the generation of large omics-datasets which has helped in gaining a better understanding of cellular behavior. The itinerary of metabolic engineering that has occurred based on these large datasets has allowed researchers to gain detailed insights and a reasonable understanding of the intricacies of biosystems. However, the existing trail-and-error approaches for metabolic engineering are laborious and time-intensive when it comes to the production of target compounds with high yields through genetic manipulations in host organisms. Machine learning (ML) coupled with the available metabolic engineering test instances and omics data brings a comprehensive and multidisciplinary approach that enables scientists to evaluate various parameters for effective strain design. This vast amount of biological data should be standardized through knowledge engineering to train different ML models for providing accurate predictions in gene circuits designing, modification of proteins, optimization of bioprocess parameters for scaling up, and screening of hyper-producing robust cell factories. This review briefs on the premise of ML, followed by mentioning various ML methods and algorithms alongside the numerous omics datasets available to train ML models for predicting metabolic outcomes with high-accuracy. The combinative interplay between the ML algorithms and biological datasets through knowledge engineering have guided the recent advancements in applications such as CRISPR/Cas systems, gene circuits, protein engineering, metabolic pathway reconstruction, and bioprocess engineering. Finally, this review addresses the probable challenges of applying ML in metabolic engineering which will guide the researchers toward novel techniques to overcome the limitations.

Metabolic and cellular engineering for the production of natural products

Increased awareness of the environmental and health concerns of consuming chemically synthesized products has led to a rising demand for natural products that are greener and more sustainable. Despite their importance, however, industrial-scale production of natural products has been challenging due to the low yield and high cost of the bioprocesses. To cope with this problem, systems metabolic engineering has been employed to efficiently produce natural products from renewable biomass. Here, we review the recent systems metabolic engineering strategies employed for enhanced production of value-added natural products, together with accompanying examples. Particular focus is set on systems-level engineering and cell physiology engineering strategies. Future perspectives are also discussed.