Deep-Learning Resources for Studying Glycan-Mediated Host-Microbe Interactions

MHIPM: Accurate Prediction of Microbe-Host Interactions Using Multiview Features from a Heterogeneous Microbial Network

Current studies have demonstrated that microbe-host interactions (MHIs) play important roles in human public health. Therefore, identifying the interactions between microbes and hosts is beneficial to understanding the role of the microbiome and their underlying mechanisms. However, traditional wet-lab experimental approaches are insufficient for large-scale exploration of candidate microbes, as they are costly, laborious, and time-consuming. Thus, it is critical to prioritize microbe-interacting hosts by computational approaches for further biological experimental validation. In this work, we proposed a novel deep learning-based method called MHIPM, to predict MHIs by utilizing multisource biological information. Specifically, we first constructed a heterogeneous microbial network that consisted of human proteins, viruses, bacteriophages (phages), and pathogenic bacteria. Next, we used one of the largest protein language models, ESM-2, and a document embedding model, doc2vec, combined with a self-attention mechanism to extract the interview features from protein sequences. Then, an inductive learning-based model, GraphSAGE, was used to capture the intraview features from the heterogeneous network. Experimental results on three prediction tasks indicated that the MHIPM model consistently achieved better performance than seven baseline algorithms and its four variants. In addition, case studies and molecular docking experiments for two human proteins further confirmed the effectiveness of our model. In conclusion, MHIPM is an efficient and robust method in predicting MHIs and provides plausible candidate microbes for biological experiments. MHIPM is available at https://github.com/JIENWU/MHIPM.

Emerging and reemerging infectious diseases: global trends and new strategies for their prevention and control

To adequately prepare for potential hazards caused by emerging and reemerging infectious diseases, the WHO has issued a list of high-priority pathogens that are likely to cause future outbreaks and for which research and development (R&D) efforts are dedicated, known as paramount R&D blueprints. Within R&D efforts, the goal is to obtain effective prophylactic and therapeutic approaches, which depends on a comprehensive knowledge of the etiology, epidemiology, and pathogenesis of these diseases. In this process, the accessibility of animal models is a priority bottleneck because it plays a key role in bridging the gap between in-depth understanding and control efforts for infectious diseases. Here, we reviewed preclinical animal models for high priority disease in terms of their ability to simulate human infections, including both natural susceptibility models, artificially engineered models, and surrogate models. In addition, we have thoroughly reviewed the current landscape of vaccines, antibodies, and small molecule drugs, particularly hopeful candidates in the advanced stages of these infectious diseases. More importantly, focusing on global trends and novel technologies, several aspects of the prevention and control of infectious disease were discussed in detail, including but not limited to gaps in currently available animal models and medical responses, better immune correlates of protection established in animal models and humans, further understanding of disease mechanisms, and the role of artificial intelligence in guiding or supplementing the development of animal models, vaccines, and drugs. Overall, this review described pioneering approaches and sophisticated techniques involved in the study of the epidemiology, pathogenesis, prevention, and clinical theatment of WHO high-priority pathogens and proposed potential directions. Technological advances in these aspects would consolidate the line of defense, thus ensuring a timely response to WHO high priority pathogens.

Microbiome and infectious disease: diagnostics to therapeutics

Over 300 years of research on the microbial world has revealed their importance in human health and disease. This review explores the impact and potential of microbial-based detection methods and therapeutic interventions, integrating research of early microbiologists, current findings, and future perspectives.

Deep structure-level N-glycan identification using feature-induced structure diagnosis integrated with a deep learning model

Being a widely occurring protein post-translational modification, N-glycosylation features unique multi-dimensional structures including sequence and linkage isomers. There have been successful bioinformatics efforts in N-glycan structure identification using N-glycoproteomics data; however, symmetric "mirror" branch isomers and linkage isomers are largely unresolved. Here, we report deep structure-level N-glycan identification using feature-induced structure diagnosis (FISD) integrated with a deep learning model. A neural network model is integrated to conduct the identification of featured N-glycan motifs and boosts the process of structure diagnosis and distinction for linkage isomers. By adopting publicly available N-glycoproteomics datasets of five mouse tissues (17,136 intact N-glycopeptide spectrum matches) and a consideration of 23 motif features, a deep learning model integrated with a convolutional autoencoder and a multilayer perceptron was trained to be capable of predicting N-glycan featured motifs in the MS/MS spectra with previously identified compositions. In the test of the trained model, a prediction accuracy of 0.8 and AUC value of 0.95 were achieved; 5701 previously unresolved N-glycan structures were assigned by matched structure-diagnostic ions; and by using an explainable learning algorithm, two new fragmentation features of m/z = 674.25 and m/z = 835.28 were found to be significant to three N-glycan structure motifs with fucose, NeuAc, and NeuGc, proving the capability of FISD to discover new features in the MS/MS spectra.

Dietary fiber monosaccharide content alters gut microbiome composition and fermentation

Members of the mammalian gut microbiota metabolize diverse complex carbohydrates that are not digested by the host, which are collectively labeled "dietary fiber." While the enzymes and transporters that each strain uses to establish a nutrient niche in the gut are often exquisitely specific, the relationship between carbohydrate structure and microbial ecology is imperfectly understood. The present study takes advantage of recent advances in complex carbohydrate structure determination to test the effects of fiber monosaccharide composition on microbial fermentation. Fifty-five fibers with varied monosaccharide composition were fermented by a pooled feline fecal inoculum in a modified MiniBioReactor array system over a period of 72 hours. The content of the monosaccharides glucose and xylose was significantly associated with the reduction of pH during fermentation, which was also predictable from the concentrations of the short-chain fatty acids lactic acid, propionic acid, and the signaling molecule indole-3-acetic acid. Microbiome diversity and composition were also predictable from monosaccharide content and SCFA concentration. In particular, the concentrations of lactic acid and propionic acid correlated with final alpha diversity and were significantly associated with the relative abundance of several of the genera, including Lactobacillus and Dubosiella. Our results suggest that monosaccharide composition offers a generalizable method to compare any dietary fiber of interest and uncover links between diet, gut microbiota, and metabolite production.

IMPORTANCE

The survival of a microbial species in the gut depends on the availability of the nutrients necessary for that species to survive. Carbohydrates in the form of non-host digestible fiber are of particular importance, and the set of genes possessed by each species for carbohydrate consumption can vary considerably. Here, differences in the monosaccharides that are the building blocks of fiber are considered for their impact on both the survival of different species of microbes and on the levels of microbial fermentation products produced. This work demonstrates that foods with similar monosaccharide content will have consistent effects on the survival of microbial species and on the production of microbial fermentation products.

Functional implications of glycans and their curation: insights from the workshop held at the 16th Annual International Biocuration Conference in Padua, Italy

Dynamic changes in protein glycosylation impact human health and disease progression. However, current resources that capture disease and phenotype information focus primarily on the macromolecules within the central dogma of molecular biology (DNA, RNA, proteins). To gain a better understanding of organisms, there is a need to capture the functional impact of glycans and glycosylation on biological processes. A workshop titled "Functional impact of glycans and their curation" was held in conjunction with the 16th Annual International Biocuration Conference to discuss ongoing worldwide activities related to glycan function curation. This workshop brought together subject matter experts, tool developers, and biocurators from over 20 projects and bioinformatics resources. Participants discussed four key topics for each of their resources: (i) how they curate glycan function-related data from publications and other sources, (ii) what type of data they would like to acquire, (iii) what data they currently have, and (iv) what standards they use. Their answers contributed input that provided a comprehensive overview of state-of-the-art glycan function curation and annotations. This report summarizes the outcome of discussions, including potential solutions and areas where curators, data wranglers, and text mining experts can collaborate to address current gaps in glycan and glycosylation annotations, leveraging each other's work to improve their respective resources and encourage impactful data sharing among resources. Database URL: https://wiki.glygen.org/Glycan_Function_Workshop_2023.

Significance of Artificial Intelligence in the Study of Virus-Host Cell Interactions

A highly critical event in a virus's life cycle is successfully entering a given host. This process begins when a viral glycoprotein interacts with a target cell receptor, which provides the molecular basis for target virus-host cell interactions for novel drug discovery. Over the years, extensive research has been carried out in the field of virus-host cell interaction, generating a massive number of genetic and molecular data sources. These datasets are an asset for predicting virus-host interactions at the molecular level using machine learning (ML), a subset of artificial intelligence (AI). In this direction, ML tools are now being applied to recognize patterns in these massive datasets to predict critical interactions between virus and host cells at the protein-protein and protein-sugar levels, as well as to perform transcriptional and translational analysis. On the other end, deep learning (DL) algorithms-a subfield of ML-can extract high-level features from very large datasets to recognize the hidden patterns within genomic sequences and images to develop models for rapid drug discovery predictions that address pathogenic viruses displaying heightened affinity for receptor docking and enhanced cell entry. ML and DL are pivotal forces, driving innovation with their ability to perform analysis of enormous datasets in a highly efficient, cost-effective, accurate, and high-throughput manner. This review focuses on the complexity of virus-host cell interactions at the molecular level in light of the current advances of ML and AI in viral pathogenesis to improve new treatments and prevention strategies.

Predicting glycan structure from tandem mass spectrometry via deep learning

Glycans constitute the most complicated post-translational modification, modulating protein activity in health and disease. However, structural annotation from tandem mass spectrometry (MS/MS) data is a bottleneck in glycomics, preventing high-throughput endeavors and relegating glycomics to a few experts. Trained on a newly curated set of 500,000 annotated MS/MS spectra, here we present CandyCrunch, a dilated residual neural network predicting glycan structure from raw liquid chromatography-MS/MS data in seconds (top-1 accuracy: 90.3%). We developed an open-access Python-based workflow of raw data conversion and prediction, followed by automated curation and fragment annotation, with predictions recapitulating and extending expert annotation. We demonstrate that this can be used for de novo annotation, diagnostic fragment identification and high-throughput glycomics. For maximum impact, this entire pipeline is tightly interlaced with our glycowork platform and can be easily tested at https://colab.research.google.com/github/BojarLab/CandyCrunch/blob/main/CandyCrunch.ipynb . We envision CandyCrunch to democratize structural glycomics and the elucidation of biological roles of glycans.

Safeguarding Mail-Order DNA Synthesis in the Age of Artificial Intelligence

Introduction

Artificial intelligence (AI) tools continue to be developed and used within the life sciences. The impact of these tools on the biosecurity landscape surrounding mail-order DNA synthesis and how to address the impacts have not been critically examined in the literature.

Methods

The impacts of AI-driven chatbots and biological design tools on the biosecurity landscape surrounding mail-order DNA synthesis were analyzed and described. The findings are informed by the authors' experience in the field.

Results

Generally, chatbots lower barriers to access of information that could be misused while biological design tools may provide new abilities to users with the intent of misuse. Six recommendations to the United States Government that attempt to maximize the benefits of these new technologies while mitigating risks are provided.

Conclusion

Mandating mail-order DNA synthesis providers to screen DNA synthesis orders is a critical safeguarding step that should be taken as soon as possible. Over time, biological design tools will reduce the effectiveness of such a regulation and actions should be taken now to limit the negative impacts in the future.

Decoding glycosylation potential from protein structure across human glycoproteins with a multi-view recurrent neural network

Glycosylation is described as a non-templated biosynthesis. Yet, the template-free premise is antithetical to the observation that different N-glycans are consistently placed at specific sites. It has been proposed that glycosite-proximal protein structures could constrain glycosylation and explain the observed microheterogeneity. Using site-specific glycosylation data, we trained a hybrid neural network to parse glycosites (recurrent neural network) and match them to feasible N-glycosylation events (graph neural network). From glycosite-flanking sequences, the algorithm predicts most human N-glycosylation events documented in the GlyConnect database and proposed structures corresponding to observed monosaccharide composition of the glycans at these sites. The algorithm also recapitulated glycosylation in Enhanced Aromatic Sequons, SARS-CoV-2 spike, and IgG3 variants, thus demonstrating the ability of the algorithm to predict both glycan structure and abundance. Thus, protein structure constrains glycosylation, and the neural network enables predictive in silico glycosylation of uncharacterized or novel protein sequences and genetic variants.

Syntactic sugars: crafting a regular expression framework for glycan structures

Motivation

Structural analysis of glycans poses significant challenges in glycobiology due to their complex sequences. Research questions such as analyzing the sequence content of the α1-6 branch in N-glycans, are biologically meaningful yet can be hard to automate.

Results

Here, we introduce a regular expression system, designed for glycans, feature-complete, and closely aligned with regular expression formatting. We use this to annotate glycan motifs of arbitrary complexity, perform differential expression analysis on designated sequence stretches, or elucidate branch-specific binding specificities of lectins in an automated manner. We are confident that glycan regular expressions will empower computational analyses of these sequences.

Availability and implementation

Our regular expression framework for glycans is implemented in Python and is incorporated into the open-source glycowork package (version 1.1+). Code and documentation are available at https://github.com/BojarLab/glycowork/blob/master/glycowork/motif/regex.py.

Holistic One Health Surveillance Framework: Synergizing Environmental, Animal, and Human Determinants for Enhanced Infectious Disease Management

Recent pandemics, including the COVID-19 outbreak, have brought up growing concerns about transmission of zoonotic diseases from animals to humans. This highlights the requirement for a novel approach to discern and address the escalating health threats. The One Health paradigm has been developed as a responsive strategy to confront forthcoming outbreaks through early warning, highlighting the interconnectedness of humans, animals, and their environment. The system employs several innovative methods such as the use of advanced technology, global collaboration, and data-driven decision-making to come up with an extraordinary solution for improving worldwide disease responses. This Review deliberates environmental, animal, and human factors that influence disease risk, analyzes the challenges and advantages inherent in using the One Health surveillance system, and demonstrates how these can be empowered by Big Data and Artificial Intelligence. The Holistic One Health Surveillance Framework presented herein holds the potential to revolutionize our capacity to monitor, understand, and mitigate the impact of infectious diseases on global populations.

Glycan Shape, Motions, and Interactions Explored by NMR Spectroscopy

Glycans in the form of oligosaccharides, polysaccharides, and glycoconjugates are ubiquitous in nature, and their structures range from linear assemblies to highly branched and decorated constructs. Solution state NMR spectroscopy facilitates elucidation of preferred conformations and shapes of the saccharides, motions, and dynamic aspects related to processes over time as well as the study of transient interactions with proteins. Identification of intermolecular networks at the atomic level of detail in recognition events by carbohydrate-binding proteins known as lectins, unraveling interactions with antibodies, and revealing substrate scope and action of glycosyl transferases employed for synthesis of oligo- and polysaccharides may efficiently be analyzed by NMR spectroscopy. By utilizing NMR active nuclei present in glycans and derivatives thereof, including isotopically enriched compounds, highly detailed information can be obtained by the experiments. Subsequent analysis may be aided by quantum chemical calculations of NMR parameters, machine learning-based methodologies and artificial intelligence. Interpretation of the results from NMR experiments can be complemented by extensive molecular dynamics simulations to obtain three-dimensional dynamic models, thereby clarifying molecular recognition processes involving the glycans.

The leading global health challenges in the artificial intelligence era

Millions of people's health is at risk because of several factors and multiple overlapping crises, all of which hit the vulnerable the most. These challenges are dynamic and evolve in response to emerging health challenges and concerns, which need effective collaboration among countries working toward achieving Sustainable Development Goals (SDGs) and securing global health. Mental Health, the Impact of climate change, cardiovascular diseases (CVDs), diabetes, Infectious diseases, health system, and population aging are examples of challenges known to pose a vast burden worldwide. We are at a point known as the "digital revolution," characterized by the expansion of artificial intelligence (AI) and a fusion of technology types. AI has emerged as a powerful tool for addressing various health challenges, and the last ten years have been influential due to the rapid expansion in the production and accessibility of health-related data. The computational models and algorithms can understand complicated health and medical data to perform various functions and deep-learning strategies. This narrative mini-review summarizes the most current AI applications to address the leading global health challenges. Harnessing its capabilities can ultimately mitigate the Impact of these challenges and revolutionize the field. It has the ability to strengthen global health through personalized health care and improved preparedness and response to future challenges. However, ethical and legal concerns about individual or community privacy and autonomy must be addressed for effective implementation.

Leveraging artificial intelligence in the fight against infectious diseases

Despite advances in molecular biology, genetics, computation, and medicinal chemistry, infectious disease remains an ominous threat to public health. Addressing the challenges posed by pathogen outbreaks, pandemics, and antimicrobial resistance will require concerted interdisciplinary efforts. In conjunction with systems and synthetic biology, artificial intelligence (AI) is now leading to rapid progress, expanding anti-infective drug discovery, enhancing our understanding of infection biology, and accelerating the development of diagnostics. In this Review, we discuss approaches for detecting, treating, and understanding infectious diseases, underscoring the progress supported by AI in each case. We suggest future applications of AI and how it might be harnessed to help control infectious disease outbreaks and pandemics.

BioAutoMATED: An end-to-end automated machine learning tool for explanation and design of biological sequences

The design choices underlying machine-learning (ML) models present important barriers to entry for many biologists who aim to incorporate ML in their research. Automated machine-learning (AutoML) algorithms can address many challenges that come with applying ML to the life sciences. However, these algorithms are rarely used in systems and synthetic biology studies because they typically do not explicitly handle biological sequences (e.g., nucleotide, amino acid, or glycan sequences) and cannot be easily compared with other AutoML algorithms. Here, we present BioAutoMATED, an AutoML platform for biological sequence analysis that integrates multiple AutoML methods into a unified framework. Users are automatically provided with relevant techniques for analyzing, interpreting, and designing biological sequences. BioAutoMATED predicts gene regulation, peptide-drug interactions, and glycan annotation, and designs optimized synthetic biology components, revealing salient sequence characteristics. By automating sequence modeling, BioAutoMATED allows life scientists to incorporate ML more readily into their work.

Impact of the gut microbiota on angiotensin Ⅱ-related disorders and its mechanisms

The renin-angiotensin system (RAS) consists of multiple angiotensin peptides and performs various biological functions mediated by distinct receptors. Angiotensin II (Ang II) is the major effector of the RAS and affects the occurrence and development of inflammation, diabetes mellitus and its complications, hypertension, and end-organ damage via the Ang II type 1 receptor. Recently, considerable interest has been given to the association and interaction between the gut microbiota and host. Increasing evidence suggests that the gut microbiota may contribute to cardiovascular diseases, obesity, type 2 diabetes mellitus, chronic inflammatory diseases, and chronic kidney disease. Recent data have confirmed that Ang II can induce an imbalance in the intestinal flora and further aggravate disease progression. Furthermore, angiotensin converting enzyme 2 is another player in RAS, alleviates the deleterious effects of Ang II, modulates gut microbial dysbiosis, local and systemic immune responses associated with coronavirus disease 19. Due to the complicated etiology of pathologies, the precise mechanisms that link disease processes with specific characteristics of the gut microbiota remain obscure. This review aims to highlight the complex interactions between the gut microbiota and its metabolites in Ang II-related disease progression, and summarize the possible mechanisms. Deciphering these mechanisms will provide a theoretical basis for novel therapeutic strategies for disease prevention and treatment. Finally, we discuss therapies targeting the gut microbiota to treat Ang II-related disorders.

Translational informatics for human microbiota: data resources, models and applications

With the rapid development of human intestinal microbiology and diverse microbiome-related studies and investigations, a large amount of data have been generated and accumulated. Meanwhile, different computational and bioinformatics models have been developed for pattern recognition and knowledge discovery using these data. Given the heterogeneity of these resources and models, we aimed to provide a landscape of the data resources, a comparison of the computational models and a summary of the translational informatics applied to microbiota data. We first review the existing databases, knowledge bases, knowledge graphs and standardizations of microbiome data. Then, the high-throughput sequencing techniques for the microbiome and the informatics tools for their analyses are compared. Finally, translational informatics for the microbiome, including biomarker discovery, personalized treatment and smart healthcare for complex diseases, are discussed.

Influence of glycan structure on the colonization of Streptococcus pneumoniae on human respiratory epithelial cells

Virtually all living cells are encased in glycans. They perform key cellular functions such as immunomodulation and cell-cell recognition. Yet, how their composition and configuration affect their functions remains enigmatic. Here, we constructed isogenic capsule-switch mutants harboring 84 types of capsular polysaccharides (CPSs) in Streptococcus pneumoniae. This collection enables us to systematically measure the affinity of structurally related CPSs to primary human nasal and bronchial epithelial cells. Contrary to the paradigm, the surface charge does not appreciably affect epithelial cell binding. Factors that affect adhesion to respiratory cells include the number of rhamnose residues and the presence of human-like glycomotifs in CPS. Besides, pneumococcal colonization stimulated the production of interleukin 6 (IL-6), granulocyte-macrophage colony-stimulating factor (GM-CSF), and monocyte chemoattractantprotein-1 (MCP-1) in nasal epithelial cells, which also appears to be dependent on the serotype. Together, our results reveal glycomotifs of surface polysaccharides that are likely to be important for colonization and survival in the human airway.

Glycosaminoglycans: What Remains To Be Deciphered?

Glycosaminoglycans (GAGs) are complex polysaccharides exhibiting a vast structural diversity and fulfilling various functions mediated by thousands of interactions in the extracellular matrix, at the cell surface, and within the cells where they have been detected in the nucleus. It is known that the chemical groups attached to GAGs and GAG conformations comprise "glycocodes" that are not yet fully deciphered. The molecular context also matters for GAG structures and functions, and the influence of the structure and functions of the proteoglycan core proteins on sulfated GAGs and vice versa warrants further investigation. The lack of dedicated bioinformatic tools for mining GAG data sets contributes to a partial characterization of the structural and functional landscape and interactions of GAGs. These pending issues will benefit from the development of new approaches reviewed here, namely (i) the synthesis of GAG oligosaccharides to build large and diverse GAG libraries, (ii) GAG analysis and sequencing by mass spectrometry (e.g., ion mobility-mass spectrometry), gas-phase infrared spectroscopy, recognition tunnelling nanopores, and molecular modeling to identify bioactive GAG sequences, biophysical methods to investigate binding interfaces, and to expand our knowledge and understanding of glycocodes governing GAG molecular recognition, and (iii) artificial intelligence for in-depth investigation of GAGomic data sets and their integration with proteomics.

Simple and practical sialoglycan encoding system reveals vast diversity in nature and identifies a universal sialoglycan-recognizing probe derived from AB5 toxin B subunits

Vertebrate sialic acids (Sias) display much diversity in modifications, linkages, and underlying glycans. Slide microarrays allow high-throughput explorations of sialoglycan-protein interactions. A microarray presenting ~150 structurally defined sialyltrisaccharides with various Sias linkages and modifications still poses challenges in planning, data sorting, visualization, and analysis. To address these issues, we devised a simple 9-digit code for sialyltrisaccharides with terminal Sias and underlying two monosaccharides assigned from the nonreducing end, with 3 digits assigning a monosaccharide, its modifications, and linkage. Calculations based on the encoding system reveal >113,000 likely linear sialyltrisaccharides in nature. Notably, a biantennary N-glycan with 2 terminal sialyltrisaccharides could thus have >1010 potential combinations and a triantennary N-glycan with 3 terminal sequences, >1015 potential combinations. While all possibilities likely do not exist in nature, sialoglycans encode enormous diversity. While glycomic approaches are used to probe such diverse sialomes, naturally occurring bacterial AB5 toxin B subunits are simpler tools to track the dynamic sialome in biological systems. Sialoglycan microarray was utilized to compare sialoglycan-recognizing bacterial toxin B subunits. Unlike the poor correlation between B subunits and species phylogeny, there is stronger correlation with Sia-epitope preferences. Further supporting this pattern, we report a B subunit (YenB) from Yersinia enterocolitica (broad host range) recognizing almost all sialoglycans in the microarray, including 4-O-acetylated-Sias not recognized by a Yersinia pestis orthologue (YpeB). Differential Sia-binding patterns were also observed with phylogenetically related B subunits from Escherichia coli (SubB), Salmonella Typhi (PltB), Salmonella Typhimurium (ArtB), extra-intestinal E.coli (EcPltB), Vibrio cholera (CtxB), and cholera family homologue of E. coli (EcxB).

A Useful Guide to Lectin Binding: Machine-Learning Directed Annotation of 57 Unique Lectin Specificities

Glycans are critical to every facet of biology and medicine, from viral infections to embryogenesis. Tools to study glycans are rapidly evolving; however, the majority of our knowledge is deeply dependent on binding by glycan binding proteins (e.g., lectins). The specificities of lectins, which are often naturally isolated proteins, have not been well-defined, making it difficult to leverage their full potential for glycan analysis. Herein, we use a combination of machine learning algorithms and expert annotation to define lectin specificity for this important probe set. Our analysis uses comprehensive glycan microarray analysis of commercially available lectins we obtained using version 5.0 of the Consortium for Functional Glycomics glycan microarray (CFGv5). This data set was made public in 2011. We report the creation of this data set and its use in large-scale evaluation of lectin-glycan binding behaviors. Our motif analysis was performed by integrating 68 manually defined glycan features with systematic probing of computational rules for significant binding motifs using mono- and disaccharides and linkages. Combining machine learning with manual annotation, we create a detailed interpretation of glycan-binding specificity for 57 unique lectins, categorized by their major binding motifs: mannose, complex-type N-glycan, O-glycan, fucose, sialic acid and sulfate, GlcNAc and chitin, Gal and LacNAc, and GalNAc. Our work provides fresh insights into the complex binding features of commercially available lectins in current use, providing a critical guide to these important reagents.

Glycoinformatics in the Artificial Intelligence Era

Artificial intelligence (AI) methods have been and are now being increasingly integrated in prediction software implemented in bioinformatics and its glycoscience branch known as glycoinformatics. AI techniques have evolved in the past decades, and their applications in glycoscience are not yet widespread. This limited use is partly explained by the peculiarities of glyco-data that are notoriously hard to produce and analyze. Nonetheless, as time goes, the accumulation of glycomics, glycoproteomics, and glycan-binding data has reached a point where even the most recent deep learning methods can provide predictors with good performance. We discuss the historical development of the application of various AI methods in the broader field of glycoinformatics. A particular focus is placed on shining a light on challenges in glyco-data handling, contextualized by lessons learnt from related disciplines. Ending on the discussion of state-of-the-art deep learning approaches in glycoinformatics, we also envision the future of glycoinformatics, including development that need to occur in order to truly unleash the capabilities of glycoscience in the systems biology era.

An analytical study on the identification of N-linked glycosylation sites using machine learning model

N-linked is the most common type of glycosylation which plays a significant role in identifying various diseases such as type I diabetes and cancer and helps in drug development. Most of the proteins cannot perform their biological and psychological functionalities without undergoing such modification. Therefore, it is essential to identify such sites by computational techniques because of experimental limitations. This study aims to analyze and synthesize the progress to discover N-linked places using machine learning methods. It also explores the performance of currently available tools to predict such sites. Almost seventy research articles published in recognized journals of the N-linked glycosylation field have shortlisted after the rigorous filtering process. The findings of the studies have been reported based on multiple aspects: publication channel, feature set construction method, training algorithm, and performance evaluation. Moreover, a literature survey has developed a taxonomy of N-linked sequence identification. Our study focuses on the performance evaluation criteria, and the importance of N-linked glycosylation motivates us to discover resources that use computational methods instead of the experimental method due to its limitations.

Alternative Antibiotics in Dentistry: Antimicrobial Peptides

The rise of antibiotic resistant bacteria due to overuse and misuse of antibiotics in medicine and dentistry is a growing concern. New approaches are needed to combat antibiotic resistant (AR) bacterial infections. There are a number of methods available and in development to address AR infections. Dentists conventionally use chemicals such as chlorohexidine and calcium hydroxide to kill oral bacteria, with many groups recently developing more biocompatible antimicrobial peptides (AMPs) for use in the oral cavity. AMPs are promising candidates in the treatment of (oral) infections. Also known as host defense peptides, AMPs have been isolated from animals across all kingdoms of life and play an integral role in the innate immunity of both prokaryotic and eukaryotic organisms by responding to pathogens. Despite progress over the last four decades, there are only a few AMPs approved for clinical use. This review summarizes an Introduction to Oral Microbiome and Oral Infections, Traditional Antibiotics and Alternatives & Antimicrobial Peptides. There is a focus on cationic AMP characteristics and mechanisms of actions, and an overview of animal-derived natural and synthetic AMPs, as well as observed microbial resistance.

GlyNet: a multi-task neural network for predicting protein-glycan interactions

Advances in diagnostics, therapeutics, vaccines, transfusion, and organ transplantation build on a fundamental understanding of glycan-protein interactions. To aid this, we developed GlyNet, a model that accurately predicts interactions (relative binding strengths) between mammalian glycans and 352 glycan-binding proteins, many at multiple concentrations. For each glycan input, our model produces 1257 outputs, each representing the relative interaction strength between the input glycan and a particular protein sample. GlyNet learns these continuous values using relative fluorescence units (RFUs) measured on 599 glycans in the Consortium for Functional Glycomics glycan arrays and extrapolates these to RFUs from additional, untested glycans. GlyNet's output of continuous values provides more detailed results than the standard binary classification models. After incorporating a simple threshold to transform such continuous outputs the resulting GlyNet classifier outperforms those standard classifiers. GlyNet is the first multi-output regression model for predicting protein-glycan interactions and serves as an important benchmark, facilitating development of quantitative computational glycobiology.

Machine learning approaches for biomolecular, biophysical, and biomaterials research

A fluent conversation with a virtual assistant, person-tailored news feeds, and deep-fake images created within seconds-all those things that have been unthinkable for a long time are now a part of our everyday lives. What these examples have in common is that they are realized by different means of machine learning (ML), a technology that has fundamentally changed many aspects of the modern world. The possibility to process enormous amount of data in multi-hierarchical, digital constructs has paved the way not only for creating intelligent systems but also for obtaining surprising new insight into many scientific problems. However, in the different areas of biosciences, which typically rely heavily on the collection of time-consuming experimental data, applying ML methods is a bit more challenging: Here, difficulties can arise from small datasets and the inherent, broad variability, and complexity associated with studying biological objects and phenomena. In this Review, we give an overview of commonly used ML algorithms (which are often referred to as "machines") and learning strategies as well as their applications in different bio-disciplines such as molecular biology, drug development, biophysics, and biomaterials science. We highlight how selected research questions from those fields were successfully translated into machine readable formats, discuss typical problems that can arise in this context, and provide an overview of how to resolve those encountered difficulties.

Glycan-mediated molecular interactions in bacterial pathogenesis

Glycans are expressed on the surface of nearly all host and bacterial cells. Not surprisingly, glycan-mediated molecular interactions play a vital role in bacterial pathogenesis and host responses against pathogens. Glycan-mediated host-pathogen interactions can benefit the pathogen, host, or both. Here, we discuss (i) bacterial glycans that play a critical role in bacterial colonization and/or immune evasion, (ii) host glycans that are utilized by bacteria for pathogenesis, and (iii) bacterial and host glycans involved in immune responses against pathogens. We further discuss (iv) opportunities and challenges for transforming these research findings into more effective antibacterial strategies, and (v) technological advances in glycoscience that have helped to accelerate progress in research. These studies collectively offer valuable insights into new perspectives on antibacterial strategies that may effectively tackle the drug-resistant pathogens that are rapidly spreading globally.

Chemistry-informed macromolecule graph representation for similarity computation, unsupervised and supervised learning

The near-infinite chemical diversity of natural and artificial macromolecules arises from the vast range of possible component monomers, linkages, and polymers topologies. This enormous variety contributes to the ubiquity and indispensability of macromolecules but hinders the development of general machine learning methods with macromolecules as input. To address this, we developed a chemistry-informed graph representation of macromolecules that enables quantifying structural similarity, and interpretable supervised learning for macromolecules. Our work enables quantitative chemistry-informed decision-making and iterative design in the macromolecular chemical space.

Systemic Lectin-Glycan Interaction of Pathogenic Enteric Bacteria in the Gastrointestinal Tract

Microorganisms, such as bacteria, viruses, and fungi, and host cells, such as plants and animals, have carbohydrate chains and lectins that reciprocally recognize one another. In hosts, the defense system is activated upon non-self-pattern recognition of microbial pathogen-associated molecular patterns. These are present in Gram-negative and Gram-positive bacteria and fungi. Glycan-based PAMPs are bound to a class of lectins that are widely distributed among eukaryotes. The first step of bacterial infection in humans is the adhesion of the pathogen's lectin-like proteins to the outer membrane surfaces of host cells, which are composed of glycans. Microbes and hosts binding to each other specifically is of critical importance. The adhesion factors used between pathogens and hosts remain unknown; therefore, research is needed to identify these factors to prevent intestinal infection or treat it in its early stages. This review aims to present a vision for the prevention and treatment of infectious diseases by identifying the role of the host glycans in the immune response against pathogenic intestinal bacteria through studies on the lectin-glycan interaction.

LectinOracle: A Generalizable Deep Learning Model for Lectin-Glycan Binding Prediction

Ranging from bacterial cell adhesion over viral cell entry to human innate immunity, glycan-binding proteins or lectins are abound in nature. Widely used as staining and characterization reagents in cell biology and crucial for understanding the interactions in biological systems, lectins are a focal point of study in glycobiology. Yet the sheer breadth and depth of specificity for diverse oligosaccharide motifs has made studying lectins a largely piecemeal approach, with few options to generalize. Here, LectinOracle, a model combining transformer-based representations for proteins and graph convolutional neural networks for glycans to predict their interaction, is presented. Using a curated data set of 564,647 unique protein-glycan interactions, it is shown that LectinOracle predictions agree with literature-annotated specificities for a wide range of lectins. Using a range of specialized glycan arrays, it is shown that LectinOracle predictions generalize to new glycans and lectins, with qualitative and quantitative agreement with experimental data. It is further demonstrated that LectinOracle can be used to improve lectin classification, accelerate lectin directed evolution, predict epidemiological outcomes in the context of influenza virus, and analyze whole lectomes in host-microbe interactions. It is envisioned that the herein presented platform will advance both the study of lectins and their role in (glyco)biology.

Identification microbial glycans substructure associate with disease and species

The microbial glycans mediate many significant biological acts, such as pathogen survival, host-microbe interactions, and immune evasion. The systematic study of microbial glycans structure remains challenging because of its high complexity and variability. In this study, we screened all the microbial glycans structures in the CSDB (Carbohydrate Structure Database), disassembled them into substructures, and calculated all the substructures' numbers. The results showed that a large number of glycan substructures are shared among different microorganisms. Further analysis showed that the glycan substructures appeared in specific bacterial groups may be related to the species and pathogenicity of microorganisms. Broadly, these findings provided an alternative approach or clue to discover the hidden information and the biological functions of glycans. The results can be used to detect broad-scope pathogen or prepare broad-spectrum vaccines.

Glycan Biosynthesis Ability of Gut Microbiota Increased in Primary Hypertension Patients Taking Antihypertension Medications and Potentially Promoted by Macrophage-Adenosine Monophosphate-Activated Protein Kinase

Increasing evidences suggest that the gut microbiota have their contributions to the hypertension, but the metagenomic characteristics and potential regulating mechanisms in primary hypertension patients taking antihypertension drugs are not clear yet. We carried out a metagenomic analysis in 30 primary hypertension patients taking antihypertension medications and eight healthy adults without any medication. We found that bacterial strains from species, such as Bacteroides fragilis, Bacteroides vulgatus, Escherichia coli, Klebsiella pneumoniae, and Streptococcus vestibularis, were highly increased in patients; and these strains were reported to generate glycan, short-chain fatty acid (SCFA) and trimethylamine (TMA) or be opportunistic pathogens. Meanwhile, Dorea longicatena, Eubacterium hallii, Clostridium leptum, Faecalibacterium prausnitzii, and some other strains were greatly decreased in the patient group. The Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis found that ortholog groups and pathways related to glycan biosynthesis and multidrug resistance were significantly increased in the patient group, and some of the hub genes related to N-glycan biosynthesis were increased in the patient group, while those related to TMA precursor metabolism and amino acid metabolism both increased and decreased in the patient group. Metabolites tested by untargeted liquid chromatography–mass spectrometry (LC-MS) proved the decrease of acetic acid, choline, betaine, and several amino acids in patients’ fecal samples. Moreover, meta-analysis of recent studies found that almost all patients were taking at least one kind of drugs that were reported to regulate adenosine monophosphate-activated protein kinase (AMPK) pathway, so we further investigated if AMPK regulated the metagenomic changes by using angiotensin II-induced mouse hypertensive model on wild-type and macrophage-specific AMPK-knockout mice. We found that the changes in E. coli and Dorea and glycan biosynthesis-related orthologs and pathways were similar in our cohort and hypertensive wild-type mice but reversed after AMPK knockout. These results suggest that the gut microbiota-derived glycan, SCFA, TMA, and some other metabolites change in medication-taking primary hypertension patients and that medications might promote gut microbiota glycan biosynthesis through activating macrophage-AMPK.

Glycowork: A Python package for glycan data science and machine learning

While glycans are crucial for biological processes, existing analysis modalities make it difficult for researchers with limited computational background to include these diverse carbohydrates into workflows. Here, we present glycowork, an open-source Python package designed for glycan-related data science and machine learning by end users. Glycowork includes functions to, for instance, automatically annotate glycan motifs and analyze their distributions via heatmaps and statistical enrichment. We also provide visualization methods, routines to interact with stored databases, trained machine learning models and learned glycan representations. We envision that glycowork can extract further insights from glycan datasets and demonstrate this with workflows that analyze glycan motifs in various biological contexts. Glycowork can be freely accessed at https://github.com/BojarLab/glycowork/.

The Role of Fucose-Containing Glycan Motifs Across Taxonomic Kingdoms

The extraordinary diversity of glycans leads to large differences in the glycomes of different kingdoms of life. Yet, while most monosaccharides are solely found in certain taxonomic groups, there is a small set of monosaccharides with widespread distribution across nearly all domains of life. These general monosaccharides are particularly relevant for glycan motifs, as they can readily be used by commensals and pathogens to mimic host glycans or hijack existing glycan recognition systems. Among these, the monosaccharide fucose is especially interesting, as it frequently presents itself as a terminal monosaccharide, primed for interaction with proteins. Here, we analyze fucose-containing glycan motifs across all taxonomic kingdoms. Using a hereby presented large species-specific glycan dataset and a plethora of methods for glycan-focused bioinformatics and machine learning, we identify characteristic as well as shared fucose-containing glycan motifs for various taxonomic groups, demonstrating clear differences in fucose usage. Even within domains, fucose is used differentially based on an organism’s physiology and habitat. We particularly highlight differences in fucose-containing motifs between vertebrates and invertebrates. With the example of pathogenic and non-pathogenic Escherichia coli strains, we also demonstrate the importance of fucose-containing motifs in molecular mimicry and thereby pathogenic potential. We envision that this study will shed light on an important class of glycan motifs, with potential new insights into the role of fucosylated glycans in symbiosis, pathogenicity, and immunity.

Correcting for sparsity and interdependence in glycomics by accounting for glycan biosynthesis

Glycans are fundamental cellular building blocks, involved in many organismal functions. Advances in glycomics are elucidating the essential roles of glycans. Still, it remains challenging to properly analyze large glycomics datasets, since the abundance of each glycan is dependent on many other glycans that share many intermediate biosynthetic steps. Furthermore, the overlap of measured glycans can be low across samples. We address these challenges with GlyCompare, a glycomic data analysis approach that accounts for shared biosynthetic steps for all measured glycans to correct for sparsity and non-independence in glycomics, which enables direct comparison of different glycoprofiles and increases statistical power. Using GlyCompare, we study diverse N-glycan profiles from glycoengineered erythropoietin. We obtain biologically meaningful clustering of mutant cell glycoprofiles and identify knockout-specific effects of fucosyltransferase mutants on tetra-antennary structures. We further analyze human milk oligosaccharide profiles and find mother’s fucosyltransferase-dependent secretor-status indirectly impact the sialylation. Finally, we apply our method on mucin-type O-glycans, gangliosides, and site-specific compositional glycosylation data to reveal tissues and disease-specific glycan presentations. Our substructure-oriented approach will enable researchers to take full advantage of the growing power and size of glycomics data.

Glycomics can uncover important molecular changes but measured glycans are highly interconnected and incompatible with common statistical methods, introducing pitfalls during analysis. Here, the authors develop an approach to identify glycan dependencies across samples to facilitate comparative glycomics.

Using graph convolutional neural networks to learn a representation for glycans

As the only nonlinear and the most diverse biological sequence, glycans offer substantial challenges for computational biology. These carbohydrates participate in nearly all biological processes—from protein folding to viral cell entry—yet are still not well understood. There are few computational methods to link glycan sequences to functions, and they do not fully leverage all available information about glycans. SweetNet is a graph convolutional neural network that uses graph representation learning to facilitate a computational understanding of glycobiology. SweetNet explicitly incorporates the nonlinear nature of glycans and establishes a framework to map any glycan sequence to a representation. We show that SweetNet outperforms other computational methods in predicting glycan properties on all reported tasks. More importantly, we show that glycan representations, learned by SweetNet, are predictive of organismal phenotypic and environmental properties. Finally, we use glycan-focused machine learning to predict viral glycan binding, which can be used to discover viral receptors.

Burkholz et al. develop an analysis platform for glycans, using graph convolutional neural networks, that considers the branched nature of these carbohydrates. They demonstrate that glycan-focused machine learning can be employed for various purposes, such as to cluster species according to their glycomic similarity or to identify viral receptors.