Prediction of antimicrobial resistance based on whole-genome sequencing and machine learning

Towards a post-pandemic future for global pathogen genome sequencing

Pathogen genome sequencing has become a routine part of our response to active outbreaks of infectious disease and should be an important part of our preparations for future epidemics. In this Essay, we discuss the innovations that have enabled routine pathogen genome sequencing, as well as how genome sequences can be used to understand and control the spread of infectious disease. We also explore the impact of the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) pandemic on the field of pathogen genomics and outline the challenges we must address to further improve the utility of pathogen genome sequencing in the future.

Whole-Genome Sequencing-Based Screening of MRSA in Patients and Healthcare Workers in Public Hospitals in Benin

Methicillin-resistant Staphylococcus aureus (MRSA) constitutes a serious public health concern, with a considerable impact on patients' health, and substantial healthcare costs. In this study, patients and healthcare workers (HCWs) from six public hospitals in Benin were screened for MRSA. Strains were identified as MRSA using conventional microbiological methods in Benin, and confirmed using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry in Belgium. Whole-genome sequencing (WGS) was used on the confirmed MRSA isolates, to characterize their genomic content and study their relatedness. Amongst the 305 isolates (304 wound swabs and 61 nasal swabs) that were collected from patients and HCWs, we detected 32 and 15 cases of MRSA, respectively. From this collection, 27 high-quality WGS datasets were obtained, which carried numerous genes and mutations associated with antimicrobial resistance. The mecA gene was detected in all the sequenced isolates. These isolates were assigned to five sequence types (STs), with ST8 (55.56%, n = 15/27), ST152 (18.52%, n = 5/27), and ST121 (18.52%, n = 5/27) being the most common. These 27 isolates carried multiple virulence genes, including the genes encoding the Panton-Valentine leukocidin toxin (48.15%, n = 13/27), and the tst gene (29.63%, n = 8/27), associated with toxic shock syndrome. This study highlights the need to implement a multimodal strategy for reducing the risk of the cross-transmission of MRSA in hospitals.

Antibiotic resistance mechanism and diagnosis of common foodborne pathogens based on genotypic and phenotypic biomarkers

The emergence of antibiotic-resistant bacteria due to the overuse or inappropriate use of antibiotics has become a significant public health concern. The agri-food chain, which serves as a vital link between the environment, food, and human, contributes to the large-scale dissemination of antibiotic resistance, posing a concern to both food safety and human health. Identification and evaluation of antibiotic resistance of foodborne bacteria is a crucial priority to avoid antibiotic abuse and ensure food safety. However, the conventional approach for detecting antibiotic resistance heavily relies on culture-based methods, which are laborious and time-consuming. Therefore, there is an urgent need to develop accurate and rapid tools for diagnosing antibiotic resistance in foodborne pathogens. This review aims to provide an overview of the mechanisms of antibiotic resistance at both phenotypic and genetic levels, with a focus on identifying potential biomarkers for diagnosing antibiotic resistance in foodborne pathogens. Furthermore, an overview of advances in the strategies based on the potential biomarkers (antibiotic resistance genes, antibiotic resistance-associated mutations, antibiotic resistance phenotypes) for antibiotic resistance analysis of foodborne pathogens is systematically exhibited. This work aims to provide guidance for the advancement of efficient and accurate diagnostic techniques for antibiotic resistance analysis in the food industry.

PhaVIP: Phage VIrion Protein classification based on chaos game representation and Vision Transformer

MOTIVATION

As viruses that mainly infect bacteria, phages are key players across a wide range of ecosystems. Analyzing phage proteins is indispensable for understanding phages' functions and roles in microbiomes. High-throughput sequencing enables us to obtain phages in different microbiomes with low cost. However, compared to the fast accumulation of newly identified phages, phage protein classification remains difficult. In particular, a fundamental need is to annotate virion proteins, the structural proteins, such as major tail, baseplate, etc. Although there are experimental methods for virion protein identification, they are too expensive or time-consuming, leaving a large number of proteins unclassified. Thus, there is a great demand to develop a computational method for fast and accurate phage virion protein (PVP) classification.

RESULTS

In this work, we adapted the state-of-the-art image classification model, Vision Transformer, to conduct virion protein classification. By encoding protein sequences into unique images using chaos game representation, we can leverage Vision Transformer to learn both local and global features from sequence "images". Our method, PhaVIP, has two main functions: classifying PVP and non-PVP sequences and annotating the types of PVP, such as capsid and tail. We tested PhaVIP on several datasets with increasing difficulty and benchmarked it against alternative tools. The experimental results show that PhaVIP has superior performance. After validating the performance of PhaVIP, we investigated two applications that can use the output of PhaVIP: phage taxonomy classification and phage host prediction. The results showed the benefit of using classified proteins over all proteins.

AVAILABILITY AND IMPLEMENTATION

The web server of PhaVIP is available via: https://phage.ee.cityu.edu.hk/phavip. The source code of PhaVIP is available via: https://github.com/KennthShang/PhaVIP.

AI-based multi-PRS models outperform classical single-PRS models

Polygenic risk scores (PRS) calculate the risk for a specific disease based on the weighted sum of associated alleles from different genetic loci in the germline estimated by regression models. Recent advances in genetics made it possible to create polygenic predictors of complex human traits, including risks for many important complex diseases, such as cancer, diabetes, or cardiovascular diseases, typically influenced by many genetic variants, each of which has a negligible effect on overall risk. In the current study, we analyzed whether adding additional PRS from other diseases to the prediction models and replacing the regressions with machine learning models can improve overall predictive performance. Results showed that multi-PRS models outperform single-PRS models significantly on different diseases. Moreover, replacing regression models with machine learning models, i.e., deep learning, can also improve overall accuracy.

An Optimal Stacked ResNet-BiLSTM-Based Accurate Detection and Classification of Genetic Disorders

Gene is located inside the nuclease and the genetic data is contained in deoxyribonucleic acid (DNA). A person's gene count ranges from 20,000 to 30,000. Even a minor alteration to the DNA sequence can be harmful if it affects the cell's fundamental functions. As a result, the gene begins to act abnormally. The sorts of genetic abnormalities brought on by mutation include chromosomal disorders, complex disorders, and single-gene disorders. Therefore, a detailed diagnosis method is required. Thus, we proposed an Elephant Herd Optimization-Whale Optimization Algorithm (EHO-WOA) optimized Stacked ResNet-Bidirectional Long Term Short Memory (ResNet-BiLSTM) model for detecting genetic disorders. Here, a hybrid EHO-WOA algorithm is presented to assess the Stacked ResNet-BiLSTM architecture's fitness. The ResNet-BiLSTM design uses the genotype and gene expression phenotype as input data. Furthermore, the proposed method identifies rare genetic disorders such as Angelman Syndrome, Rett Syndrome, and Prader-Willi Syndrome. It demonstrates the effectiveness of the developed model with greater accuracy, recall, specificity, precision, and f1-score. Thus, a wide range of DNA deficiencies including Prader-Willi syndrome, Marfan syndrome, Early Onset Morbid Obesity, Rett syndrome, and Angelman syndrome are predicted accurately.

Clinical Diagnostics of Bacterial Infections and Their Resistance to Antibiotics-Current State and Whole Genome Sequencing Implementation Perspectives

Antimicrobial resistance (AMR), defined as the ability of microorganisms to withstand antimicrobial treatment, is responsible for millions of deaths annually. The rapid spread of AMR across continents warrants systematic changes in healthcare routines and protocols. One of the fundamental issues with AMR spread is the lack of rapid diagnostic tools for pathogen identification and AMR detection. Resistance profile identification often depends on pathogen culturing and thus may last up to several days. This contributes to the misuse of antibiotics for viral infection, the use of inappropriate antibiotics, the overuse of broad-spectrum antibiotics, or delayed infection treatment. Current DNA sequencing technologies offer the potential to develop rapid infection and AMR diagnostic tools that can provide information in a few hours rather than days. However, these techniques commonly require advanced bioinformatics knowledge and, at present, are not suited for routine lab use. In this review, we give an overview of the AMR burden on healthcare, describe current pathogen identification and AMR screening methods, and provide perspectives on how DNA sequencing may be used for rapid diagnostics. Additionally, we discuss the common steps used for DNA data analysis, currently available pipelines, and tools for analysis. Direct, culture-independent sequencing has the potential to complement current culture-based methods in routine clinical settings. However, there is a need for a minimum set of standards in terms of evaluating the results generated. Additionally, we discuss the use of machine learning algorithms regarding pathogen phenotype detection (resistance/susceptibility to an antibiotic).

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.

A systematic review on the state-of-the-art strategies for protein representation

The study of drug-target protein interaction is a key step in drug research. In recent years, machine learning techniques have become attractive for research, including drug research, due to their automated nature, predictive power, and expected efficiency. Protein representation is a key step in the study of drug-target protein interaction by machine learning, which plays a fundamental role in the ultimate accomplishment of accurate research. With the progress of machine learning, protein representation methods have gradually attracted attention and have consequently developed rapidly. Therefore, in this review, we systematically classify current protein representation methods, comprehensively review them, and discuss the latest advances of interest. According to the information extraction methods and information sources, these representation methods are generally divided into structure and sequence-based representation methods. Each primary class can be further divided into specific subcategories. As for the particular representation methods involve both traditional and the latest approaches. This review contains a comprehensive assessment of the various methods which researchers can use as a reference for their specific protein-related research requirements, including drug research.

Dissecting microbial communities and resistomes for interconnected humans, soil, and livestock

A debate is currently ongoing as to whether intensive livestock farms may constitute reservoirs of clinically relevant antimicrobial resistance (AMR), thus posing a threat to surrounding communities. Here, combining shotgun metagenome sequencing, machine learning (ML), and culture-based methods, we focused on a poultry farm and connected slaughterhouse in China, investigating the gut microbiome of livestock, workers and their households, and microbial communities in carcasses and soil. For both the microbiome and resistomes in this study, differences are observed across environments and hosts. However, at a finer scale, several similar clinically relevant antimicrobial resistance genes (ARGs) and similar associated mobile genetic elements were found in both human and broiler chicken samples. Next, we focused on Escherichia coli, an important indicator for the surveillance of AMR on the farm. Strains of E. coli were found intermixed between humans and chickens. We observed that several ARGs present in the chicken faecal resistome showed correlation to resistance/susceptibility profiles of E. coli isolates cultured from the same samples. Finally, by using environmental sensing these ARGs were found to be correlated to variations in environmental temperature and humidity. Our results show the importance of adopting a multi-domain and multi-scale approach when studying microbial communities and AMR in complex, interconnected environments.

Accurate and fast clade assignment via deep learning and frequency chaos game representation

BACKGROUND

Since the beginning of the coronavirus disease 2019 pandemic, there has been an explosion of sequencing of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus, making it the most widely sequenced virus in the history. Several databases and tools have been created to keep track of genome sequences and variants of the virus; most notably, the GISAID platform hosts millions of complete genome sequences, and it is continuously expanding every day. A challenging task is the development of fast and accurate tools that are able to distinguish between the different SARS-CoV-2 variants and assign them to a clade.

RESULTS

In this article, we leverage the frequency chaos game representation (FCGR) and convolutional neural networks (CNNs) to develop an original method that learns how to classify genome sequences that we implement into CouGaR-g, a tool for the clade assignment problem on SARS-CoV-2 sequences. On a testing subset of the GISAID, CouGaR-g achieved an $96.29\%$ overall accuracy, while a similar tool, Covidex, obtained a $77,12\%$ overall accuracy. As far as we know, our method is the first using deep learning and FCGR for intraspecies classification. Furthermore, by using some feature importance methods, CouGaR-g allows to identify k-mers that match SARS-CoV-2 marker variants.

CONCLUSIONS

By combining FCGR and CNNs, we develop a method that achieves a better accuracy than Covidex (which is based on random forest) for clade assignment of SARS-CoV-2 genome sequences, also thanks to our training on a much larger dataset, with comparable running times. Our method implemented in CouGaR-g is able to detect k-mers that capture relevant biological information that distinguishes the clades, known as marker variants.

AVAILABILITY

The trained models can be tested online providing a FASTA file (with 1 or multiple sequences) at https://huggingface.co/spaces/BIASLab/sars-cov-2-classification-fcgr. CouGaR-g is also available at https://github.com/AlgoLab/CouGaR-g under the GPL.

Whole genome sequencing and prediction of antimicrobial susceptibilities in non-tuberculous mycobacteria

Non-tuberculous mycobacteria (NTM) are opportunistic pathogens commonly causing chronic, pulmonary disease which is notoriously hard to treat. Current treatment for NTM infections involves at least three active drugs (including one macrolide: clarithromycin or azithromycin) over 12 months or longer. At present there are limited phenotypic in vitro drug susceptibility testing options for NTM which are standardised globally. As seen with tuberculosis, whole genome sequencing has the potential to transform drug susceptibility testing in NTM, by utilising a genotypic approach. The Comprehensive Resistance Prediction for Tuberculosis is a database used to predict Mycobacterium tuberculosis resistance: at present there are no similar databases available to accurately predict NTM resistance. Recent studies have shown concordance between phenotypic and genotypic NTM resistance results. To benefit from the advantages of whole genome sequencing, further advances in resistance prediction need to take place, as well as there being better information on novel drug mutations and an understanding of the impact of whole genome sequencing on NTM treatment outcomes.

Antimicrobial Peptides Prediction method based on sequence multidimensional feature embedding

Antimicrobial peptides (AMPs) are alkaline substances with efficient bactericidal activity produced in living organisms. As the best substitute for antibiotics, they have been paid more and more attention in scientific research and clinical application. AMPs can be produced from almost all organisms and are capable of killing a wide variety of pathogenic microorganisms. In addition to being antibacterial, natural AMPs have many other therapeutically important activities, such as wound healing, antioxidant and immunomodulatory effects. To discover new AMPs, the use of wet experimental methods is expensive and difficult, and bioinformatics technology can effectively solve this problem. Recently, some deep learning methods have been applied to the prediction of AMPs and achieved good results. To further improve the prediction accuracy of AMPs, this paper designs a new deep learning method based on sequence multidimensional representation. By encoding and embedding sequence features, and then inputting the model to identify AMPs, high-precision classification of AMPs and Non-AMPs with lengths of 10-200 is achieved. The results show that our method improved accuracy by 1.05% compared to the most advanced model in independent data validation without decreasing other indicators.

Deep Transfer Learning Enables Robust Prediction of Antimicrobial Resistance for Novel Antibiotics

Antimicrobial resistance (AMR) has become one of the serious global health problems, threatening the effective treatment of a growing number of infections. Machine learning and deep learning show great potential in rapid and accurate AMR predictions. However, a large number of samples for the training of these models is essential. In particular, for novel antibiotics, limited training samples and data imbalance hinder the models' generalization performance and overall accuracy. We propose a deep transfer learning model that can improve model performance for AMR prediction on small, imbalanced datasets. As our approach relies on transfer learning and secondary mutations, it is also applicable to novel antibiotics and emerging resistances in the future and enables quick diagnostics and personalized treatments.

How has microbiology changed 200 years after Pasteur's birth?

The last two centuries have seen major scientific and technological advances that have turned the field of microbiology upside down. If Louis Pasteur came out of his vault to celebrate his two hundredth birthday with us, would he recognize the field of study of which he was one of the founders? Are the objectives of the discipline still the same? What is the influence of new technologies on our scientific approach? What are the new horizons and future challenges?

Identifying cancer cachexia in patients without weight loss information: machine learning approaches to address a real-world challenge

BACKGROUND

Diagnosing cancer cachexia relies extensively on patient-reported historic weight, and failure to accurately recall this information can lead to severe underestimation of cancer cachexia.

OBJECTIVES

The present study aimed to develop inexpensive tools to facilitate the identification of cancer cachexia in patients without weight loss information.

METHODS

This multicenter cohort study included 12,774 patients with cancer. Cachexia was retrospectively diagnosed using Fearon et al.'s framework. Baseline clinical features, excluding weight loss, were modeled to mimic a situation where the patient is unable to recall their weight history. Multiple machine learning (ML) models were trained using 75% of the study cohort to predict cancer cachexia, with the remaining 25% of the cohort used to assess model performance.

RESULTS

The study enrolled 6730 males and 6044 females (median age = 57.5 y). Cachexia was diagnosed in 5261 (41.2%) patients and most diagnoses were made based on the weight loss criterion. A 15-variable logistic regression (LR) model mainly comprising cancer types, gastrointestinal symptoms, tumor stage, and serum biochemistry indexes was selected among the various ML models. The LR model showed good performance for predicting cachexia in the validation data (AUC = 0.763; 95% CI: 0.747, 0.780). The calibration curve of the model demonstrated good agreement between predictions and actual observations (accuracy = 0.714, κ = 0.396, sensitivity = 0.580, specificity = 0.808, positive predictive value = 0.679, negative predictive value = 0.733). Subgroup analyses showed that the model was feasible in patients with different cancer types. The model was deployed as an online calculator and a nomogram, and was exported as predictive model markup language to permit flexible, individualized risk calculation.

CONCLUSIONS

We developed an ML model that can facilitate the identification of cancer cachexia in patients without weight loss information, which might improve decision-making and lead to the development of novel management strategies in cancer care. This trial was registered at https://www.chictr.org.cn as ChiCTR1800020329.

Paving the way for precise diagnostics of antimicrobial resistant bacteria

The antimicrobial resistance (AMR) crisis from bacterial pathogens is frequently emerging and rapidly disseminated during the sustained antimicrobial exposure in human-dominated communities, posing a compelling threat as one of the biggest challenges in humans. The frequent incidences of some common but untreatable infections unfold the public health catastrophe that antimicrobial-resistant pathogens have outpaced the available countermeasures, now explicitly amplified during the COVID-19 pandemic. Nowadays, biotechnology and machine learning advancements help create more fundamental knowledge of distinct spatiotemporal dynamics in AMR bacterial adaptation and evolutionary processes. Integrated with reliable diagnostic tools and powerful analytic approaches, a collaborative and systematic surveillance platform with high accuracy and predictability should be established and implemented, which is not just for an effective controlling strategy on AMR but also for protecting the longevity of valuable antimicrobials currently and in the future.

Operationalizing "One Health" as "One Digital Health" Through a Global Framework That Emphasizes Fair and Equitable Sharing of Benefits From the Use of Artificial Intelligence and Related Digital Technologies

The operationalization of One Health (OH) through digitalization is a means to deploy digital technologies (including Artificial Intelligence (AI), big data and related digital technologies) to better capacitate us to deal with growing climate exigency and related threats to human, animal and plant health. With reference to the concept of One Digital Health (ODH), this paper considers how digital capabilities can help to overcome ‘operational brakes’ in OH through new and deeper insights, better predictions, and more targeted or precise preventive strategies and public health countermeasures. However, the data landscape is fragmented and access to certain types of data is increasingly restrictive as individuals, communities and countries seek to assert greater control over data taken from them. This paper proposes for a dedicated global ODH framework—centered on fairness and equity—to be established to promote data-sharing across all the key knowledge domains of OH and to devise data-driven solutions to challenges in the human-animal-ecosystems interface. It first considers the data landscape in relation to: (1) Human and population health; (2) Pathogens; (3) Animal and plant health; and (4) Ecosystems and biodiversity. The complexification from the application of advance genetic sequencing technology is then considered, with focus on current debates over whether certain types of data like digital (genetic) sequencing information (DSI) should remain openly and freely accessible. The proposed ODH framework must augment the existing access and benefit sharing (ABS) framework currently prescribed under the Nagoya Protocol to the Convention on Biological Diversity (CBD) in at least three different ways. First, the ODH framework should apply to all genetic resources and data, including DSI, whether from humans or non-humans. Second, the FAIRER principles should be implemented, with focus on fair and equitable benefit-sharing. Third, the ODH framework should adopt multilateral approaches to data sharing (such as through federated data systems) and to ABS. By operationalizing OH as ODH, we are more likely to be able to protect and restore natural habitats, secure the health and well-being of all living things, and thereby realize the goals set out in the post-2020 Global Biodiversity Framework under the CBD.

Presence and antimicrobial resistance profiles of Escherichia coli, Enterococcusspp. and Salmonellasp. in 12 species of Australian shorebirds and terns

Antibiotic resistance is an ongoing threat to both human and animal health. Migratory birds are a potential vector for the spread of novel pathogens and antibiotic resistance genes. To date, there has been no comprehensive study investigating the presence of antibiotic resistance (AMR) in the bacteria of Australian shorebirds or terns. In the current study, 1022 individual birds representing 12 species were sampled across three states of Australia (Victoria, South Australia, and Western Australia) and tested for the presence of phenotypically resistant strains of three bacteria with potential to be zoonotic pathogens; Escherichia coli, Enterococcusspp., and Salmonellasp. In total, 206 E. coli, 266 Enterococcusspp., and 20 Salmonellasp. isolates were recovered, with AMR detected in 42% of E. coli, 85% of Enterococcusspp., and 10% of Salmonellasp. Phenotypic resistance was commonly detected to erythromycin (79% of Enterococcusspp.), ciprofloxacin (31% of Enterococcusspp.) and streptomycin (21% of E. coli). Resident birds were more likely to carry AMR bacteria than migratory birds (p ≤ .001). Bacteria isolated from shorebirds and terns are commonly resistant to at least one antibiotic, suggesting that wild bird populations serve as a potential reservoir and vector for AMR bacteria. However, globally emerging phenotypes of multidrug‐resistant bacteria were not detected in Australian shorebirds. This study provides baseline data of the carriage of AMR bacteria in Australian shorebirds and terns.

Whole-genome sequencing and gene sharing network analysis powered by machine learning identifies antibiotic resistance sharing between animals, humans and environment in livestock farming

Anthropogenic environments such as those created by intensive farming of livestock, have been proposed to provide ideal selection pressure for the emergence of antimicrobial-resistant Escherichia coli bacteria and antimicrobial resistance genes (ARGs) and spread to humans. Here, we performed a longitudinal study in a large-scale commercial poultry farm in China, collecting E. coli isolates from both farm and slaughterhouse; targeting animals, carcasses, workers and their households and environment. By using whole-genome phylogenetic analysis and network analysis based on single nucleotide polymorphisms (SNPs), we found highly interrelated non-pathogenic and pathogenic E. coli strains with phylogenetic intermixing, and a high prevalence of shared multidrug resistance profiles amongst livestock, human and environment. Through an original data processing pipeline which combines omics, machine learning, gene sharing network and mobile genetic elements analysis, we investigated the resistance to 26 different antimicrobials and identified 361 genes associated to antimicrobial resistance (AMR) phenotypes; 58 of these were known AMR-associated genes and 35 were associated to multidrug resistance. We uncovered an extensive network of genes, correlated to AMR phenotypes, shared among livestock, humans, farm and slaughterhouse environments. We also found several human, livestock and environmental isolates sharing closely related mobile genetic elements carrying ARGs across host species and environments. In a scenario where no consensus exists on how antibiotic use in the livestock may affect antibiotic resistance in the human population, our findings provide novel insights into the broader epidemiology of antimicrobial resistance in livestock farming. Moreover, our original data analysis method has the potential to uncover AMR transmission pathways when applied to the study of other pathogens active in other anthropogenic environments characterised by complex interconnections between host species.

Livestock have been suggested as an important source of antimicrobial-resistant (AMR) Escherichia coli, capable of infecting humans and carrying resistance to drugs used in human medicine. China has a large intensive livestock farming industry, poultry being the second most important source of meat in the country, and is the largest user of antibiotics for food production in the world. Here we studied antimicrobial resistance gene overlap between E. coli isolates collected from humans, livestock and their shared environments in a large-scale Chinese poultry farm and associated slaughterhouse. By using a computational approach that integrates machine learning, whole-genome sequencing, gene sharing network and mobile genetic elements analysis we characterized the E. coli community structure, antimicrobial resistance phenotypes and the genetic relatedness of non-pathogenic and pathogenic E. coli strains. We uncovered the network of genes, associated with AMR, shared across host species (animals and workers) and environments (farm and slaughterhouse). Our approach opens up new avenues for the development of a fast, affordable and effective computational solutions that provide novel insights into the broader epidemiology of antimicrobial resistance in livestock farming.