HMD-ARG: hierarchical multi-task deep learning for annotating antibiotic resistance genes

A comprehensive review of antibiotic resistance gene contamination in agriculture: Challenges and AI-driven solutions

Since their discovery, the prolonged and widespread use of antibiotics in veterinary and agricultural production has led to numerous problems, particularly the emergence and spread of antibiotic-resistant bacteria (ARB). In addition, other anthropogenic factors accelerate the horizontal transfer of antibiotic resistance genes (ARGs) and amplify their impact. In agricultural environments, animals, manure, and wastewater are the vectors of ARGs that facilitate their spread to the environment and humans via animal products, water, and other environmental pathways. Therefore, this review comprehensively analyzed the current status, removal methods, and future directions of ARGs on farms. This article 1) investigates the origins of ARGs on farms, the pathways and mechanisms of their spread to surrounding environments, and various strategies to mitigate their spread; 2) determines the multiple factors influencing the abundance of ARGs on farms, the pathways through which ARGs spread from farms to the environment, and the effects and mechanisms of non-antibiotic factors on the spread of ARGs; 3) explores methods for controlling ARGs in farm wastes; and 4) provides a comprehensive summary and integration of research across various fields, proposing that in modern smart farms, emerging technologies can be integrated through artificial intelligence to control or even eliminate ARGs. Moreover, challenges and future research directions for controlling ARGs on farms are suggested.

Is there a role for intestinal sporobiota in the antimicrobial resistance crisis?

Antimicrobial resistance (AMR) is a complex issue requiring specific, multi-sectoral measures to slow its spread. When people are exposed to antimicrobial agents, it can cause resistant bacteria to increase. This means that the use, misuse, and excessive use of antimicrobial agents exert selective pressure on bacteria, which can lead to the development of "silent" reservoirs of antimicrobial resistance genes. These genes can later be mobilized into pathogenic bacteria and contribute to the spread of AMR. Many socioeconomic and environmental factors influence the transmission and dissemination of resistance genes, such as the quality of healthcare systems, water sanitation, hygiene infrastructure, and pollution. The sporobiota is an essential part of the gut microbiota that plays a role in maintaining gut homeostasis. However, because spores are highly transmissible and can spread easily, they can be a vector for AMR. The sporobiota resistome, particularly the mobile resistome, is important for tracking, managing, and limiting the spread of antimicrobial resistance genes among pathogenic and commensal bacterial species.

Prediction of antibiotic resistance mechanisms using a protein language model

MOTIVATION

Antibiotic resistance has emerged as a major global health threat, with an increasing number of bacterial infections becoming difficult to treat. Predicting the underlying resistance mechanisms of antibiotic resistance genes (ARGs) is crucial for understanding and combating this problem. However, existing methods struggle to accurately predict resistance mechanisms for ARGs with low similarity to known sequences and lack sufficient interpretability of the prediction models.

RESULTS

In this study, we present a novel approach for predicting ARG resistance mechanisms using ProteinBERT, a protein language model (pLM) based on deep learning. Our method outperforms state-of-the-art techniques on diverse ARG datasets, including those with low homology to the training data, highlighting its potential for predicting the resistance mechanisms of unknown ARGs. Attention analysis of the model reveals that it considers biologically relevant features, such as conserved amino acid residues and antibiotic target binding sites, when making predictions. These findings provide valuable insights into the molecular basis of antibiotic resistance and demonstrate the interpretability of pLMs, offering a new perspective on their application in bioinformatics.

AVAILABILITY AND IMPLEMENTATION

The source code is available for free at https://github.com/hmdlab/ARG-BERT. The output results of the model are published at https://waseda.box.com/v/ARG-BERT-suppl.

Viral Diversity and Ecological Impact of DNA Viruses in Dominant Tick Species in China

Ticks are blood-feeding ectoparasites that also transmit various pathogens, posing severe risks to human and animal health. DNA viruses play a crucial role in the microbial ecology of ticks, but their distribution and ecological significance remain largely undetermined. Here, we assembled an extensive catalog encompassing 4320 viral operational taxonomic units (vOTUs) from six main dominant tick species in China, of which 94.8% have not been found in any other environment. To bridge the knowledge gap in tick DNA virus research and provide a crucial resource platform, we developed the Tick DNA Virus Database. This database includes the vOTUs that are known to cause diseases. Most of the predicted vOTUs are associated with dominant bacterial and archaeal phyla. We identified 105 virus-encoded putative auxiliary metabolic genes (AMGs) that are involved in host metabolism and environmental adaptation, potentially influencing ticks through both top-down and bottom-up mechanisms. The identification of microbial communities and antibiotic resistance in wild tick species suggests that wild ticks are reservoirs of antibiotic resistance and potential spreaders of antibiotic resistance. These findings reveal the potential role of tick viruses in ecosystems, highlighting the importance of monitoring tick microbiomes to address global public health challenges.

Hierarchical multi-task deep learning-assisted construction of human gut microbiota reactive oxygen species-scavenging enzymes database

In the process of oxygen reduction, reactive oxygen species (ROS) are generated as intermediates, including superoxide anion (O2-), hydrogen peroxide (H2O2), and hydroxyl radicals (OH-). ROS can be destructive, and an imbalance between oxidants and antioxidants in the body can lead to pathological inflammation. Inappropriate ROS production can cause oxidative damage, disrupting the balance in the body and potentially leading to DNA damage in intestinal epithelial cells and beneficial bacteria. Microorganisms have evolved various enzymes to mitigate the harmful effects of ROS. Accurately predicting the types of ROS-scavenging enzymes (ROSes) is crucial for understanding the oxidative stress mechanisms and formulating strategies to combat diseases related to the "gut-organ axis." Currently, there are no available ROSes databases (DBs). In this study, we propose a systematic workflow comprising three modules and employ a hierarchical multi-task deep learning approach to collect, expand, and explore ROSes-related entries. Based on this, we have developed the human gut microbiota ROSes DB (http://39.101.72.186/), which includes 7,689 entries. This DB provides user-friendly browsing and search features to support various applications. With the assistance of ROSes DB, various communication-based microbial interactions can be explored, further enabling the construction and analysis of the evolutionary and complex networks of ROSes DB in human gut microbiota species.IMPORTANCEReactive oxygen species (ROS) is generated during the process of oxygen reduction, including superoxide anion, hydrogen peroxide, and hydroxyl radicals. ROS can potentially cause damage to cells and DNA, leading to pathological inflammation within the body. Microorganisms have evolved various enzymes to mitigate the harmful effects of ROS, thereby maintaining a balance of microorganisms within the host. The study highlights the current absence of a ROSes DB, emphasizing the crucial importance of accurately predicting the types of ROSes for understanding oxidative stress mechanisms and developing strategies for diseases related to the "gut-organ axis." This research proposes a systematic workflow and employs a multi-task deep learning approach to establish the human gut microbiota ROSes DB. This DB comprises 7,689 entries and serves as a valuable tool for researchers to delve into the role of ROSes in the human gut microbiota.

Artificial intelligence tools for the identification of antibiotic resistance genes

The fight against bacterial antibiotic resistance must be given critical attention to avert the current and emerging crisis of treating bacterial infections due to the inefficacy of clinically relevant antibiotics. Intrinsic genetic mutations and transferrable antibiotic resistance genes (ARGs) are at the core of the development of antibiotic resistance. However, traditional alignment methods for detecting ARGs have limitations. Artificial intelligence (AI) methods and approaches can potentially augment the detection of ARGs and identify antibiotic targets and antagonistic bactericidal and bacteriostatic molecules that are or can be developed as antibiotics. This review delves into the literature regarding the various AI methods and approaches for identifying and annotating ARGs, highlighting their potential and limitations. Specifically, we discuss methods for (1) direct identification and classification of ARGs from genome DNA sequences, (2) direct identification and classification from plasmid sequences, and (3) identification of putative ARGs from feature selection.

Subtask-Aware Representation Learning for Predicting Antibiotic Resistance Gene Properties via Gating-Controlled Mechanism

The crisis of antibiotic resistance has become a significant global threat to human health. Understanding properties of antibiotic resistance genes (ARGs) is the first step to mitigate this issue. Although many methods have been proposed for predicting properties of ARGs, most of these methods focus only on predicting antibiotic classes, while ignoring other properties of ARGs, such as resistance mechanisms and transferability. However, acquiring all of these properties of ARGs can help researchers gain a more comprehensive understanding of the essence of antibiotic resistance, which will facilitate the development of antibiotics. In this paper, the task of predicting properties of ARGs is modeled as a multi-task learning problem, and an effective subtask-aware representation learning-based framework is proposed accordingly. More specifically, property-specific expert networks and shared expert networks are utilized respectively to learn subtask-specific features for each subtask and shared features among different subtasks. In addition, a gating-controlled mechanism is employed to dynamically allocate weights to subtask-specific semantics and shared semantics obtained respectively from property-specific expert networks and shared expert networks, thus adjusting distinctive contributions of subtask-specific features and shared features to achieve optimal performance for each subtask simultaneously. Extensive experiments are conducted on publicly available data, and experimental results demonstrate the effectiveness of the proposed framework on the task of ARGs properties prediction.

TGC-ARG: Anticipating Antibiotic Resistance via Transformer-Based Modeling and Contrastive Learning

In various domains, including everyday activities, agricultural practices, and medical treatments, the escalating challenge of antibiotic resistance poses a significant concern. Traditional approaches to studying antibiotic resistance genes (ARGs) often require substantial time and effort and are limited in accuracy. Moreover, the decentralized nature of existing data repositories complicates comprehensive analysis of antibiotic resistance gene sequences. In this study, we introduce a novel computational framework named TGC-ARG designed to predict potential ARGs. This framework takes protein sequences as input, utilizes SCRATCH-1D for protein secondary structure prediction, and employs feature extraction techniques to derive distinctive features from both sequence and structural data. Subsequently, a Siamese network is employed to foster a contrastive learning environment, enhancing the model's ability to effectively represent the data. Finally, a multi-layer perceptron (MLP) integrates and processes sequence embeddings alongside predicted secondary structure embeddings to forecast ARG presence. To evaluate our approach, we curated a pioneering open dataset termed ARSS (Antibiotic Resistance Sequence Statistics). Comprehensive comparative experiments demonstrate that our method surpasses current state-of-the-art methodologies. Additionally, through detailed case studies, we illustrate the efficacy of our approach in predicting potential ARGs.

Highly accurate classification and discovery of microbial protein-coding gene functions using FunGeneTyper: an extensible deep learning framework

High-throughput DNA sequencing technologies decode tremendous amounts of microbial protein-coding gene sequences. However, accurately assigning protein functions to novel gene sequences remain a challenge. To this end, we developed FunGeneTyper, an extensible framework with two new deep learning models (i.e., FunTrans and FunRep), structured databases, and supporting resources for achieving highly accurate (Accuracy > 0.99, F1-score > 0.97) and fine-grained classification of antibiotic resistance genes (ARGs) and virulence factor genes. Using an experimentally confirmed dataset of ARGs comprising remote homologous sequences as the test set, our framework achieves by-far-the-best performance in the discovery of new ARGs from human gut (F1-score: 0.6948), wastewater (0.6072), and soil (0.5445) microbiomes, beating the state-of-the-art bioinformatics tools and sequence alignment-based (F1-score: 0.0556-0.5065) and domain-based (F1-score: 0.2630-0.5224) annotation approaches. Furthermore, our framework is implemented as a lightweight, privacy-preserving, and plug-and-play neural network module, facilitating its versatility and accessibility to developers and users worldwide. We anticipate widespread utilization of FunGeneTyper (https://github.com/emblab-westlake/FunGeneTyper) for precise classification of protein-coding gene functions and the discovery of numerous valuable enzymes. This advancement will have a significant impact on various fields, including microbiome research, biotechnology, metagenomics, and bioinformatics.

ARGNet: using deep neural networks for robust identification and classification of antibiotic resistance genes from sequences

BACKGROUND

Emergence of antibiotic resistance in bacteria is an important threat to global health. Antibiotic resistance genes (ARGs) are some of the key components to define bacterial resistance and their spread in different environments. Identification of ARGs, particularly from high-throughput sequencing data of the specimens, is the state-of-the-art method for comprehensively monitoring their spread and evolution. Current computational methods to identify ARGs mainly rely on alignment-based sequence similarities with known ARGs. Such approaches are limited by choice of reference databases and may potentially miss novel ARGs. The similarity thresholds are usually simple and could not accommodate variations across different gene families and regions. It is also difficult to scale up when sequence data are increasing.

RESULTS

In this study, we developed ARGNet, a deep neural network that incorporates an unsupervised learning autoencoder model to identify ARGs and a multiclass classification convolutional neural network to classify ARGs that do not depend on sequence alignment. This approach enables a more efficient discovery of both known and novel ARGs. ARGNet accepts both amino acid and nucleotide sequences of variable lengths, from partial (30-50 aa; 100-150 nt) sequences to full-length protein or genes, allowing its application in both target sequencing and metagenomic sequencing. Our performance evaluation showed that ARGNet outperformed other deep learning models including DeepARG and HMD-ARG in most of the application scenarios especially quasi-negative test and the analysis of prediction consistency with phylogenetic tree. ARGNet has a reduced inference runtime by up to 57% relative to DeepARG.

CONCLUSIONS

ARGNet is flexible, efficient, and accurate at predicting a broad range of ARGs from the sequencing data. ARGNet is freely available at https://github.com/id-bioinfo/ARGNet , with an online service provided at https://ARGNet.hku.hk . Video Abstract.

Causal-ARG: a causality-guided framework for annotating properties of antibiotic resistance genes

MOTIVATION

The crisis of antibiotic resistance, which causes antibiotics used to treat bacterial infections to become less effective, has emerged as one of the foremost challenges to public health. Identifying the properties of antibiotic resistance genes (ARGs) is an essential way to mitigate this issue. Although numerous methods have been proposed for this task, most of these approaches concentrate solely on predicting antibiotic class, disregarding other important properties of ARGs. In addition, existing methods for simultaneously predicting multiple properties of ARGs fail to account for the causal relationships among these properties, limiting the predictive performance.

RESULTS

In this study, we propose a causality-guided framework for annotating properties of ARGs, in which causal inference is utilized for representation learning. More specifically, the hidden biological patterns determining the properties of ARGs are described by a Gaussian Mixture Model, and procedure of causal representation learning is used to derive the hidden features. In addition, a causal graph among different properties is constructed to capture the causal relationships among properties of ARGs, which is integrated into the task of annotating properties of ARGs. The experimental results on a real-world dataset demonstrate the effectiveness of the proposed framework on the task of annotating properties of ARGs.

AVAILABILITY AND IMPLEMENTATION

The data and source codes are available in GitHub at https://github.com/David-WZhao/CausalARG.

Assessment of the causal relationship between gut microbiota and cardiovascular diseases: a bidirectional Mendelian randomization analysis

BACKGROUND

Previous studies have shown an association between gut microbiota and cardiovascular diseases (CVDs). However, the underlying causal relationship remains unclear. This study aims to elucidate the causal relationship between gut microbiota and CVDs and to explore the pathogenic role of gut microbiota in CVDs.

METHODS

In this two-sample Mendelian randomization study, we used genetic instruments from publicly available genome-wide association studies, including single-nucleotide polymorphisms (SNPs) associated with gut microbiota (n = 14,306) and CVDs (n = 2,207,591). We employed multiple statistical analysis methods, including inverse variance weighting, MR Egger, weighted median, MR pleiotropic residuals and outliers, and the leave-one-out method, to estimate the causal relationship between gut microbiota and CVDs. Additionally, we conducted multiple analyses to assess horizontal pleiotropy and heterogeneity.

RESULTS

GWAS summary data were available from a pooled sample of 2,221,897 adult and adolescent participants. Our findings indicated that specific gut microbiota had either protective or detrimental effects on CVDs. Notably, Howardella (OR = 0.955, 95% CI: 0.913-0.999, P = .05), Intestinibacter (OR = 0.908, 95% CI:0.831-0.993, P = .03), Lachnospiraceae (NK4A136 group) (OR = 0.904, 95% CI:0.841-0.973, P = .007), Turicibacter (OR = 0.904, 95% CI: 0.838-0.976, P = .01), Holdemania (OR, 0.898; 95% CI: 0.810-0.995, P = .04) and Odoribacter (OR, 0.835; 95% CI: 0.710-0.993, P = .04) exhibited a protective causal effect on atrial fibrillation, while other microbiota had adverse causal effects. Similar effects were observed with respect to coronary artery disease, myocardial infarction, ischemic stroke, and hypertension. Furthermore, reversed Mendelian randomization analyses revealed that atrial fibrillation and ischemic stroke had causal effects on certain gut microbiotas.

CONCLUSION

Our study underscored the importance of gut microbiota in the context of CVDs and lent support to the hypothesis that increasing the abundance of probiotics or decreasing the abundance of harmful bacterial populations may offer protection against specific CVDs. Nevertheless, further research is essential to translate these findings into clinical practice.

Multimodal learning in clinical proteomics: enhancing antimicrobial resistance prediction models with chemical information

MOTIVATION

Large-scale clinical proteomics datasets of infectious pathogens, combined with antimicrobial resistance outcomes, have recently opened the door for machine learning models which aim to improve clinical treatment by predicting resistance early. However, existing prediction frameworks typically train a separate model for each antimicrobial and species in order to predict a pathogen's resistance outcome, resulting in missed opportunities for chemical knowledge transfer and generalizability.

RESULTS

We demonstrate the effectiveness of multimodal learning over proteomic and chemical features by exploring two clinically relevant tasks for our proposed deep learning models: drug recommendation and generalized resistance prediction. By adopting this multi-view representation of the pathogenic samples and leveraging the scale of the available datasets, our models outperformed the previous single-drug and single-species predictive models by statistically significant margins. We extensively validated the multi-drug setting, highlighting the challenges in generalizing beyond the training data distribution, and quantitatively demonstrate how suitable representations of antimicrobial drugs constitute a crucial tool in the development of clinically relevant predictive models.

AVAILABILITY AND IMPLEMENTATION

The code used to produce the results presented in this article is available at https://github.com/BorgwardtLab/MultimodalAMR.

Microcosm experiments revealed resistome coalescence of sewage treatment plant effluents in river environment

Sewage treatment plant (STP) effluents are important contributors of antibiotic resistance (AR) pollution in rivers. Effluent discharging into rivers causes resistome coalescence. However, their mechanisms and dynamic processes are poorly understood, especially for the effects of dilution, diffusion, and sunlight-induced attenuation on coalescence. In this study, we have constructed microcosmic experiments based on in-situ investigation to explore these issues. The first batch experiment revealed the effects of dilution and diffusion. The coverage of water coalesced resistomes ranged 66.26∼152.18 × /Gb and was positively correlated with effluent volume (Mann-Kendall test, p < 0.01). Principal coordinate analysis (PCoA) and source tracking analysis demonstrated that dilution and diffusion stepwise reduced AR pollution. The second batch experiment explored the temporal dynamics and sunlight attenuation on coalesced resistomes. Under natural light, the coverage and diversity of water resistomes posed decreasing trends, primarily attributed to drastic erasure of effluent traces. The proportion of effluent-specific ARGs in coalesced resistomes significantly declined over time (Spearman's r = -0.83 and -0.94 in coverage and richness). While under dark condition, the coverage and diversity increased. Sunlight radiation intensified the interactions between water and sediment resistomes, as evidenced by more shared ARGs and less dissimilarities across niches. Network analysis, metagenome-assembled genome (MAG) analysis and variation partitioning analysis (VPA) showed that microbiome controlled resistome coalescence, explaining 56.5% and 58.4% of resistomes in water and sediment, respectively. Biotic and abiotic factors synergistically explained 40% of water resistomes. This study offers a comprehensive understanding of AR transmission and provides theoretical bases for grasping AR pollution and developing effective suppression strategies.

Application of high-throughput sequencing technologies and analytical tools for pathogen detection in urban water systems: Progress and future perspectives

The ubiquitous presence of pathogenic microorganisms, such as viruses, bacteria, fungi, and protozoa, in urban water systems poses a significant risk to public health. The emergence of infectious waterborne diseases mediated by urban water systems has become one of the leading global causes of mortality. However, the detection and monitoring of these pathogenic microorganisms have been limited by the complexity and diversity in the environmental samples. Conventional methods were restricted by long assay time, high benchmarks of identification, and narrow application sceneries. Novel technologies, such as high-throughput sequencing technologies, enable potentially full-spectrum detection of trace pathogenic microorganisms in complex environmental matrices. This review discusses the current state of high-throughput sequencing technologies for identifying pathogenic microorganisms in urban water systems with a concise summary. Furthermore, future perspectives in pathogen research emphasize the need for detection methods with high accuracy and sensitivity, the establishment of precise detection standards and procedures, and the significance of bioinformatics software and platforms. We have compiled a list of pathogens analysis software/platforms/databases that boast robust engines and high accuracy for preference. We highlight the significance of analyses by combining targeted and non-targeted sequencing technologies, short and long reads technologies, sequencing technologies, and bioinformatic tools in pursuing upgraded biosafety in urban water systems.

NCRD: A non-redundant comprehensive database for detecting antibiotic resistance genes

Antibiotic resistance genes (ARGs) are emerging pollutants present in various environments. Identifying ARGs has become a growing concern in recent years. Several databases, including the Antibiotic Resistance Genes Database (ARDB), Comprehensive Antibiotic Resistance Database (CARD), and Structured Antibiotic Resistance Genes (SARG), have been applied to detect ARGs. However, these databases have limitations, which hinder the comprehensive profiling of ARGs in environmental samples. To address these issues, we constructed a non-redundant antibiotic resistance genes database (NRD) by consolidating sequences from ARDB, CARD, and SARG. We identified the homologous proteins of NRD from Non-redundant Protein Database (NR) and the Protein DataBank Database (PDB) and clustered them to establish a non-redundant comprehensive antibiotic resistance genes database (NCRD) with similarities of 100% (NCRD100) and 95% (NCRD95). To demonstrate the advantages of NCRD, we compared it with other databases by using metagenome datasets. Results revealed its strong ability in detecting potential ARGs.

Silicon versus Superbug: Assessing Machine Learning's Role in the Fight against Antimicrobial Resistance

In his 1945 Nobel Prize acceptance speech, Sir Alexander Fleming warned of antimicrobial resistance (AMR) if the necessary precautions were not taken diligently. As the growing threat of AMR continues to loom over humanity, we must look forward to alternative diagnostic tools and preventive measures to thwart looming economic collapse and untold mortality worldwide. The integration of machine learning (ML) methodologies within the framework of such tools/pipelines presents a promising avenue, offering unprecedented insights into the underlying mechanisms of resistance and enabling the development of more targeted and effective treatments. This paper explores the applications of ML in predicting and understanding AMR, highlighting its potential in revolutionizing healthcare practices. From the utilization of supervised-learning approaches to analyze genetic signatures of antibiotic resistance to the development of tools and databases, such as the Comprehensive Antibiotic Resistance Database (CARD), ML is actively shaping the future of AMR research. However, the successful implementation of ML in this domain is not without challenges. The dependence on high-quality data, the risk of overfitting, model selection, and potential bias in training data are issues that must be systematically addressed. Despite these challenges, the synergy between ML and biomedical research shows great promise in combating the growing menace of antibiotic resistance.

PLM-ARG: antibiotic resistance gene identification using a pretrained protein language model

MOTIVATION

Antibiotic resistance presents a formidable global challenge to public health and the environment. While considerable endeavors have been dedicated to identify antibiotic resistance genes (ARGs) for assessing the threat of antibiotic resistance, recent extensive investigations using metagenomic and metatranscriptomic approaches have unveiled a noteworthy concern. A significant fraction of proteins defies annotation through conventional sequence similarity-based methods, an issue that extends to ARGs, potentially leading to their under-recognition due to dissimilarities at the sequence level.

RESULTS

Herein, we proposed an Artificial Intelligence-powered ARG identification framework using a pretrained large protein language model, enabling ARG identification and resistance category classification simultaneously. The proposed PLM-ARG was developed based on the most comprehensive ARG and related resistance category information (>28K ARGs and associated 29 resistance categories), yielding Matthew's correlation coefficients (MCCs) of 0.983 ± 0.001 by using a 5-fold cross-validation strategy. Furthermore, the PLM-ARG model was verified using an independent validation set and achieved an MCC of 0.838, outperforming other publicly available ARG prediction tools with an improvement range of 51.8%-107.9%. Moreover, the utility of the proposed PLM-ARG model was demonstrated by annotating resistance in the UniProt database and evaluating the impact of ARGs on the Earth's environmental microbiota.

AVAILABILITY AND IMPLEMENTATION

PLM-ARG is available for academic purposes at https://github.com/Junwu302/PLM-ARG, and a user-friendly webserver (http://www.unimd.org/PLM-ARG) is also provided.

A Comprehensive Bioinformatics Resource Guide for Genome-Based Antimicrobial Resistance Studies

The use of high-throughput sequencing technologies and bioinformatic tools has greatly transformed microbial genome research. With the help of sophisticated computational tools, it has become easier to perform whole genome assembly, identify and compare different species based on their genomes, and predict the presence of genes responsible for proteins, antimicrobial resistance, and toxins. These bioinformatics resources are likely to continuously improve in quality, become more user-friendly to analyze the multiple genomic data, efficient in generating information and translating it into meaningful knowledge, and enhance our understanding of the genetic mechanism of AMR. In this manuscript, we provide an essential guide for selecting the popular resources for microbial research, such as genome assembly and annotation, antibiotic resistance gene profiling, identification of virulence factors, and drug interaction studies. In addition, we discuss the best practices in computer-oriented microbial genome research, emerging trends in microbial genomic data analysis, integration of multi-omics data, the appropriate use of machine-learning algorithms, and open-source bioinformatics resources for genome data analytics.

Combined network analysis and interpretable machine learning reveals the environmental adaptations of more than 10,000 ruminant microbial genomes

Background

The ruminant gastrointestinal contains numerous microbiomes that serve a crucial role in sustaining the host's productivity and health. In recent times, numerous studies have revealed that variations in influencing factors, including the environment, diet, and host, contribute to the shaping of gastrointestinal microbial adaptation to specific states. Therefore, understanding how host and environmental factors affect gastrointestinal microbes will help to improve the sustainability of ruminant production systems.

Results

Based on a graphical analysis perspective, this study elucidates the microbial topology and robustness of the gastrointestinal of different ruminant species, showing that the microbial network is more resistant to random attacks. The risk of transmission of high-risk metagenome-assembled genome (MAG) was also demonstrated based on a large-scale survey of the distribution of antibiotic resistance genes (ARG) in the microbiota of most types of ecosystems. In addition, an interpretable machine learning framework was developed to study the complex, high-dimensional data of the gastrointestinal microbial genome. The evolution of gastrointestinal microbial adaptations to the environment in ruminants were analyzed and the adaptability changes of microorganisms to different altitudes were identified, including microbial transcriptional repair.

Conclusion

Our findings indicate that the environment has an impact on the functional features of microbiomes in ruminant. The findings provide a new insight for the future development of microbial resources for the sustainable development in agriculture.

Recovery of the gut microbiome following enteric infection and persistence of antimicrobial resistance genes in specific microbial hosts

Enteric pathogens cause widespread foodborne illness and are increasingly resistant to important antibiotics yet their ecological impact on the gut microbiome and resistome is not fully understood. Herein, shotgun metagenome sequencing was applied to stool DNA from 60 patients (cases) during an enteric bacterial infection and after recovery (follow-ups). Overall, the case samples harbored more antimicrobial resistance genes (ARGs) with greater resistome diversity than the follow-up samples (p < 0.001), while follow-ups had more diverse gut microbiota (p < 0.001). Although cases were primarily defined by genera Escherichia, Salmonella, and Shigella along with ARGs for multi-compound and multidrug resistance, follow-ups had a greater abundance of Bacteroidetes and Firmicutes phyla and resistance genes for tetracyclines, macrolides, lincosamides, and streptogramins, and aminoglycosides. A host-tracking analysis revealed that Escherichia was the primary bacterial host of ARGs in both cases and follow-ups, with a greater abundance occurring during infection. Eleven distinct extended spectrum beta-lactamase (ESBL) genes were identified during infection, with some detectable upon recovery, highlighting the potential for gene transfer within the community. Because of the increasing incidence of disease caused by foodborne pathogens and their role in harboring and transferring resistance determinants, this study enhances our understanding of how enteric infections impact human gut ecology.

Predicting the antigenic evolution of SARS-COV-2 with deep learning

The relentless evolution of SARS-CoV-2 poses a significant threat to public health, as it adapts to immune pressure from vaccines and natural infections. Gaining insights into potential antigenic changes is critical but challenging due to the vast sequence space. Here, we introduce the Machine Learning-guided Antigenic Evolution Prediction (MLAEP), which combines structure modeling, multi-task learning, and genetic algorithms to predict the viral fitness landscape and explore antigenic evolution via in silico directed evolution. By analyzing existing SARS-CoV-2 variants, MLAEP accurately infers variant order along antigenic evolutionary trajectories, correlating with corresponding sampling time. Our approach identified novel mutations in immunocompromised COVID-19 patients and emerging variants like XBB1.5. Additionally, MLAEP predictions were validated through in vitro neutralizing antibody binding assays, demonstrating that the predicted variants exhibited enhanced immune evasion. By profiling existing variants and predicting potential antigenic changes, MLAEP aids in vaccine development and enhances preparedness against future SARS-CoV-2 variants.

Comparative metagenomics reveals poultry and swine farming are hotspots for multidrug and tetracycline resistance

Antibiotic misuse in livestock is a major threat to human health, as bacteria are quickly developing resistance to them. We performed a comparative analysis of 25 faecal metagenomes from swine, poultry, cattle, and humans to investigate their resistance profiles. Our analysis revealed that all genes conferring resistance to antibiotic classes assessed except tetracyclines were more prevalent in poultry manure than in the remaining species. We detected clinically relevant antibiotic resistance genes, such as mcr-1 which confers resistance to polymyxins. Among them, extended-spectrum β-lactamase blaCTX-M genes were particularly abundant in all species. Poultry manure was identified as a hotspot for multidrug resistance, which may compromise medical treatment options. Urgent actions in the livestock industry are imperative to hamper the emergence and spread of antibiotic resistance.

Artificial Intelligence for Antimicrobial Resistance Prediction: Challenges and Opportunities towards Practical Implementation

Antimicrobial resistance (AMR) is emerging as a potential threat to many lives worldwide. It is very important to understand and apply effective strategies to counter the impact of AMR and its mutation from a medical treatment point of view. The intersection of artificial intelligence (AI), especially deep learning/machine learning, has led to a new direction in antimicrobial identification. Furthermore, presently, the availability of huge amounts of data from multiple sources has made it more effective to use these artificial intelligence techniques to identify interesting insights into AMR genes such as new genes, mutations, drug identification, conditions favorable to spread, and so on. Therefore, this paper presents a review of state-of-the-art challenges and opportunities. These include interesting input features posing challenges in use, state-of-the-art deep-learning/machine-learning models for robustness and high accuracy, challenges, and prospects to apply these techniques for practical purposes. The paper concludes with the encouragement to apply AI to the AMR sector with the intention of practical diagnosis and treatment, since presently most studies are at early stages with minimal application in the practice of diagnosis and treatment of disease.

Genomic Investigation of Salmonella Typhi in Hong Kong Revealing the Predominance of Genotype 3.2.2 and the First Case of an Extensively Drug-Resistant H58 Genotype

Typhoid fever is a notable disease in Hong Kong. We noticed two local cases of typhoid fever caused by Salmonella Typhi within a two-week period in late 2022, which had no apparent epidemiological linkage except for residing in the same region of Hong Kong. A phylogenetic study of Salmonella Typhi isolates from Hong Kong Island from 2020 to 2022 was performed, including a whole-genome analysis, the typing of plasmids, and the analysis of antibiotic-resistance genes (ARGs), to identify the dominant circulating strain and the spread of ARGs. A total of seven isolates, from six local cases and an imported case, were identified from positive blood cultures in two hospitals in Hong Kong. Five antibiotic-sensitive strains of genotype 3.2.2 were found, which clustered with another 30 strains originating from Southeast Asia. Whole-genome sequencing revealed clonal transmission between the two index cases. The remaining two local cases belong to genotype 2.3.4 and genotype 4.3.1.1.P1 (also known as the H58 lineage). The genotype 4.3.1.1.P1 strain has an extensively drug-resistant (XDR) phenotype (co-resistance to ampicillin, chloramphenicol, ceftriaxone, ciprofloxacin, and co-trimoxazole). Although the majority of local strains belong to the non-H58 genotype 3.2.2 with a low degree of antibiotic resistance, the introduction of XDR strains with the global dissemination of the H58 lineage remains a concern.

HyperVR: a hybrid deep ensemble learning approach for simultaneously predicting virulence factors and antibiotic resistance genes

Infectious diseases emerge unprecedentedly, posing serious challenges to public health and the global economy. Virulence factors (VFs) enable pathogens to adhere, reproduce and cause damage to host cells, and antibiotic resistance genes (ARGs) allow pathogens to evade otherwise curable treatments. Simultaneous identification of VFs and ARGs can save pathogen surveillance time, especially in situ epidemic pathogen detection. However, most tools can only predict either VFs or ARGs. Few tools that predict VFs and ARGs simultaneously usually have high false-negative rates, are sensitive to the cutoff thresholds and can only identify conserved genes. For better simultaneous prediction of VFs and ARGs, we propose a hybrid deep ensemble learning approach called HyperVR. By considering both best hit scores and statistical gene sequence patterns, HyperVR combines classical machine learning and deep learning to simultaneously and accurately predict VFs, ARGs and negative genes (neither VFs nor ARGs). For the prediction of individual VFs and ARGs, in silico spike-in experiment (the VFs and ARGs in real metagenomic data), and pseudo-VFs and -ARGs (gene fragments), HyperVR outperforms the current state-of-the-art prediction tools. HyperVR uses only gene sequence information without strict cutoff thresholds, hence making prediction straightforward and reliable.

Evaluation of a Lateral Flow Immunoassay for Rapid Detection of CTX-M Producers from Blood Cultures

Bacteremia caused by extended-spectrum β-lactamases-producing Enterobacterales has increased rapidly and is mainly attributed to CTX-M enzymes. This study aimed to evaluate the NG-Test^® CTX-M MULTI lateral flow assay (CTX-M LFA) for rapid detection of CTX-M producers in blood cultures (BCs) positive for Gram-negative bacilli in spiked and clinical BCs. Retrospective testing was performed on BC bottles spiked with a collection of well-characterized Enterobacterales isolates producing CTX-M (n = 15) and CTX-M-like (n = 27) β-lactamases. Prospective testing of clinical, non-duplicate BCs (n = 350) was performed in two hospital microbiology laboratories from April 2021 to March 2022 following detection of Gram-negative bacilli by microscopic examination. Results were compared against molecular testing as the reference. In the spiked BCs, the CTX-M LFA correctly detected all CTX-M producers including 5 isolates with hybrid CTX-M variants. However, false-positive results were observed for several CTX-M-like β-lactamases, including OXY-1-3, OXY-2-8, OXY-5-3, FONA-8, -9, -10, 11, 13 and SFO-1. In clinical BCs, the CTX-M LFA showed 100% (95% CI, 96.0-100%) sensitivity and 99.6% (97.9-100%) specificity. In conclusion, this study showed that rapid detection of CTX-M producers in BC broths can be reliably achieved using the CTX-M LFA, thus providing an opportunity for early optimization of antibiotics.

Deep Learning and Antibiotic Resistance

Antibiotic resistance (AR) is a naturally occurring phenomenon with the capacity to render useless all known antibiotics in the fight against bacterial infections. Although bacterial resistance appeared before any human life form, this process has accelerated in the past years. Important causes of AR in modern times could be the over-prescription of antibiotics, the presence of faulty infection-prevention strategies, pollution in overcrowded areas, or the use of antibiotics in agriculture and farming, together with a decreased interest from the pharmaceutical industry in researching and testing new antibiotics. The last cause is primarily due to the high costs of developing antibiotics. The aim of the present review is to highlight the techniques that are being developed for the identification of new antibiotics to assist this lengthy process, using artificial intelligence (AI). AI can shorten the preclinical phase by rapidly generating many substances based on algorithms created by machine learning (ML) through techniques such as neural networks (NN) or deep learning (DL). Recently, a text mining system that incorporates DL algorithms was used to help and speed up the data curation process. Moreover, new and old methods are being used to identify new antibiotics, such as the combination of quantitative structure-activity relationship (QSAR) methods with ML or Raman spectroscopy and MALDI-TOF MS combined with NN, offering faster and easier interpretation of results. Thus, AI techniques are important additional tools for researchers and clinicians in the race for new methods of overcoming bacterial resistance.

Microbial Dark Matter: from Discovery to Applications

With the rapid increase of the microbiome samples and sequencing data, more and more knowledge about microbial communities has been gained. However, there is still much more to learn about microbial communities, including billions of novel species and genes, as well as countless spatiotemporal dynamic patterns within the microbial communities, which together form the microbial dark matter. In this work, we summarized the dark matter in microbiome research and reviewed current data mining methods, especially artificial intelligence (AI) methods, for different types of knowledge discovery from microbial dark matter. We also provided case studies on using AI methods for microbiome data mining and knowledge discovery. In summary, we view microbial dark matter not as a problem to be solved but as an opportunity for AI methods to explore, with the goal of advancing our understanding of microbial communities, as well as developing better solutions to global concerns about human health and the environment.

Intestinal microbiome-mediated resistance against vibriosis for Cynoglossus semilaevis

BACKGROUND

Infectious diseases have caused huge economic loss and food security issues in fish aquaculture. Current management and breeding strategies heavily rely on the knowledge of regulative mechanisms underlying disease resistance. Though the intestinal microbial community was linked with disease infection, there is little knowledge about the roles of intestinal microbes in fish disease resistance. Cynoglossus semilaevis is an economically important and widely cultivated flatfish species in China. However, it suffers from outbreaks of vibriosis, which results in huge mortalities and economic loss.

RESULTS

Here, we used C. semilaevis as a research model to investigate the host-microbiome interactions in regulating vibriosis resistance. The resistance to vibriosis was reflected in intestinal microbiome on both taxonomic and functional levels. Such differences also influenced the host gene expressions in the resistant family. Moreover, the intestinal microbiome might control the host immunological homeostasis and inflammation to enhance vibriosis resistance through the microbe-intestine-immunity axis. For example, Phaeobacter regulated its hdhA gene and host cyp27a1 gene up-expressed in bile acid biosynthesis pathways, but regulated its trxA gene and host akt gene down-expressed in proinflammatory cytokines biosynthesis pathways, to reduce inflammation and resist disease infection in the resistant family. Furthermore, the combination of intestinal microbes and host genes as biomarkers could accurately differentiate resistant family from susceptible family.

CONCLUSION

Our study uncovered the regulatory patterns of the microbe-intestine-immunity axis that may contribute to vibriosis resistance in C. semilaevis. These findings could facilitate the disease control and selective breeding of superior germplasm with high disease resistance in fish aquaculture. Video Abstract.

The combined effect of an integrated reclaimed water system on the reduction of antibiotic resistome

The reuse of urban reclaimed water is conducive to alleviate the current serious shortage of water resources. However, antibiotic resistance genes (ARGs) in reclaimed water have received widespread attention due to their potential risks to public health. Deciphering the fate of ARGs in reclaimed water benefits the development of effective strategies to control resistome risk and guarantees the safety of water supply of reclaimed systems. In this study, the characteristics of ARGs in an integrated reclaimed water system (sewage treatment plant-constructed wetland, STP-CW) in Beijing (China) have been identified using metagenomic assembly-based analysis, as well as the combined effect of the STP-CW system on the reduction of antibiotic resistome. Results showed a total of 29 ARG types and 813 subtypes were found in the reclaimed water system. As expected, the STP-CW system improved the removal of ARGs, and about 58% of ARG subtypes were removed from the effluent of the integrated STP-CW system, which exceeded 43% for the STP system and 37% for the CW system. Although the STP-CW system had a great removal on ARGs, abundant and diverse ARGs were still found in the downstream river. Importantly, network analysis revealed the co-occurrence of ARGs, mobile genetic elements and virulence factors in the downstream water, implying potential resistome dissemination risk in the environment. Source identification with SourceTracker showed the STP-effluent was the largest contributor of ARGs in the downstream river, with a contribution of 45%. Overall, the integrated STP-CW system presented a combined effect on the reduction of antibiotic resistome, however, the resistome dissemination risk was still non-negligible in the downstream reclaimed water. This study provides a comprehensive analysis on the fate of ARGs in the STP-CW-river system, which would benefit the development of effective strategies to control resistome risk for the reuse of reclaimed water.

DeepToA: An Ensemble Deep-Learning Approach to Predicting the Theater of Activity of a Microbiome

MOTIVATION

Metagenomics is the study of microbiomes using DNA sequencing. A microbiome consists of an assemblage of microbes that is associated with a "theater of activity" (ToA). An important question is, to what degree does the taxonomic and functional content of the former depend on the (details of the) latter? Here we investigate a related technical question: Given a taxonomic and/or functional profile estimated from metagenomic sequencing data, how to predict the associated ToA? We present a deep-learning approach to this question. We use both taxonomic and functional profiles as input. We apply node2vec to embed hierarchical taxonomic profiles into numerical vectors. We then perform dimension reduction using clustering, to address the sparseness of the taxonomic data and thus make the problem more amenable to deep-learning algorithms. Functional features are combined with textual descriptions of protein families or domains. We present an ensemble deep-learning framework DeepToA for predicting the "theater of activity" of amicrobial community, based on taxonomic and functional profiles. We use SHAP (SHapley Additive exPlanations) values to determine which taxonomic and functional features are important for the prediction.

RESULTS

Based on 7,560 metagenomic profiles downloaded from MGnify, classified into ten different theaters of activity, we demonstrate that DeepToA has an accuracy of 98.30%. We show that adding textual information to functional features increases the accuracy.

AVAILABILITY

Our approach is available at http://ab.inf.uni-tuebingen.de/software/deeptoa.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Emergence of nutriments as a nascent complementary therapy against antimicrobial resistance

With these growing and evolving years, antimicrobial resistance has become a great subject of interest. The idea of using natural productive ways can be an effective measure against antimicrobial resistance. The growing prevalence of antimicrobial resistance indicates that advanced natural approaches are a topic of concern for fighting the resistance. Many natural products including essential oils, flavonoids, alkaloids and botanicals have been demonstrated as effective bactericidal agents. In this review, we will discuss in detail about the relevance of such natural products to tackle the problem of antimicrobial resistance, antibiotic adjuvants that aim towards non-essential bacterial targets to reduce the prevalence of resistant bacterial infections, latest bioinformatics approach towards antibacterial drug discovery along with an understanding of biogenic nanoparticles in antimicrobial activity.

A multi-label learning framework for predicting antibiotic resistance genes via dual-view modeling

The increasing prevalence of antibiotic resistance has become a global health crisis. For the purpose of safety regulation, it is of high importance to identify antibiotic resistance genes (ARGs) in bacteria. Although culture-based methods can identify ARGs relatively more accurately, the identifying process is time-consuming and specialized knowledge is required. With the rapid development of whole genome sequencing technology, researchers attempt to identify ARGs by computing sequence similarity from public databases. However, these computational methods might fail to detect ARGs due to the low sequence identity to known ARGs. Moreover, existing methods cannot effectively address the issue of multidrug resistance prediction for ARGs, which is a great challenge to clinical treatments. To address the challenges, we propose an end-to-end multi-label learning framework for predicting ARGs. More specifically, the task of ARGs prediction is modeled as a problem of multi-label learning, and a deep neural network-based end-to-end framework is proposed, in which a specific loss function is introduced to employ the advantage of multi-label learning for ARGs prediction. In addition, a dual-view modeling mechanism is employed to make full use of the semantic associations among two views of ARGs, i.e. sequence-based information and structure-based information. Extensive experiments are conducted on publicly available data, and experimental results demonstrate the effectiveness of the proposed framework on the task of ARGs prediction.

Ontology-aware neural network: a general framework for pattern mining from microbiome data

With the rapid accumulation of microbiome data around the world, numerous computational bioinformatics methods have been developed for pattern mining from such paramount microbiome data. Current microbiome data mining methods, such as gene and species mining, rely heavily on sequence comparison. Most of these methods, however, have a clear trade-off, particularly, when it comes to big-data analytical efficiency and accuracy. Microbiome entities are usually organized in ontology structures, and pattern mining methods that have considered ontology structures could offer advantages in mining efficiency and accuracy. Here, we have summarized the ontology-aware neural network (ONN) as a novel framework for microbiome data mining. We have discussed the applications of ONN in multiple contexts, including gene mining, species mining and microbial community dynamic pattern mining. We have then highlighted one of the most important characteristics of ONN, namely, novel knowledge discovery, which makes ONN a standout among all microbiome data mining methods. Finally, we have provided several applications to showcase the advantage of ONN over other methods in microbiome data mining. In summary, ONN represents a paradigm shift for pattern mining from microbiome data: from traditional machine learning approach to ontology-aware and model-based approach, which has found its broad application scenarios in microbiome data mining.

Antibiotic resistance: Time of synthesis in a post-genomic age

Antibiotic resistance has been highlighted by international organizations, including World Health Organization, World Bank and United Nations, as one of the most relevant global health problems. Classical approaches to study this problem have focused in infected humans, mainly at hospitals. Nevertheless, antibiotic resistance can expand through different ecosystems and geographical allocations, hence constituting a One-Health, Global-Health problem, requiring specific integrative analytic tools. Antibiotic resistance evolution and transmission are multilayer, hierarchically organized processes with several elements (from genes to the whole microbiome) involved. However, their study has been traditionally gene-centric, each element independently studied. The development of robust-economically affordable whole genome sequencing approaches, as well as other -omic techniques as transcriptomics and proteomics, is changing this panorama. These technologies allow the description of a system, either a cell or a microbiome as a whole, overcoming the problems associated with gene-centric approaches. We are currently at the time of combining the information derived from -omic studies to have a more holistic view of the evolution and spread of antibiotic resistance. This synthesis process requires the accurate integration of -omic information into computational models that serve to analyse the causes and the consequences of acquiring AR, fed by curated databases capable of identifying the elements involved in the acquisition of resistance. In this review, we analyse the capacities and drawbacks of the tools that are currently in use for the global analysis of AR, aiming to identify the more useful targets for effective corrective interventions.