A genomic data resource for predicting antimicrobial resistance from laboratory-derived antimicrobial susceptibility phenotypes

Neural network-based predictions of antimicrobial resistance phenotypes in multidrug-resistant Acinetobacter baumannii from whole genome sequencing and gene expression

Whole genome sequencing (WGS) potentially represents a rapid approach for antimicrobial resistance genotype-to-phenotype prediction. However, the challenge still exists to predict fully minimum inhibitory concentrations (MICs) and antimicrobial susceptibility phenotypes based on WGS data. This study aimed to establish an artificial intelligence-based computational approach in predicting antimicrobial susceptibilities of multidrug-resistant Acinetobacter baumannii from WGS and gene expression data. Antimicrobial susceptibility testing (AST) was performed using the broth microdilution method for 10 antimicrobial agents. In silico multilocus sequence typing (MLST), antimicrobial resistance genes, and phylogeny based on cgSNP and cgMLST strategies were analyzed. High-throughput qPCR was performed to measure the expression level of antimicrobial resistance (AMR) genes. Most isolates exhibited a high level of resistance to most of the tested antimicrobial agents, with the majority belonging to the IC2/CC92 lineage. Phylogenetic analysis revealed undetected transmission events or local outbreaks. The percentage agreements between AMR phenotype and genotype ranged from 70.08% to 89.96%, with the coefficient of agreement (κ) extending from 0.025 and 0.881. The prediction of AST employed by deep neural network models achieved an accuracy of up to 98.64% on the testing data set. Additionally, several linear regression models demonstrated high prediction accuracy, reaching up to 86.15% within an error range of one gradient, indicating a linear relationship between certain gene expressions and the corresponding antimicrobial MICs. In conclusion, neural network-based predictions could be used as a tool for the surveillance of antimicrobial resistance in multidrug-resistant A. baumannii.

Integrating genomic and molecular data to predict antimicrobial minimum inhibitory concentration in Klebsiella pneumoniae

Minimum inhibitory concentration (MIC) denotes the in vitro benchmark indicating the quantity of antibiotic required to inhibit proliferation of specific bacterial strains. Determining MIC values corresponding to the infecting bacterial strain is paramount for tailoring appropriate antibiotic therapy. In the interim between specimen collection and laboratory-derived MIC outcomes, clinicians frequently resort to empirical therapy informed by retrospective analyses. Here introduces two deep learning approaches, a Convolutional Neural Network (CNN)-based model and an Enformer-based model, integrating genomic data of Klebsiella Pneumoniae and molecular structural data of 20 antibiotics to anticipate the MIC value of the bacterium for each antibiotic under consideration. These models demonstrate enhanced raw accuracy over the existing state-of-the-art model, which rely exclusively on genomic data. The CNN-based model achieves a notable 20% increase in raw accuracy while further mirroring the 1-tier accuracy of the state-of-the-art model. Although the Enformer-based model does not quite reach the performance levels of the CNN-based model, it offers an advantage by eliminating the need for arbitrary data processing steps. This streamlining of the data processing pipeline facilitates fast updates and improves the model interpretability. It is expected that these deep learning paradigms can significantly inform and bolster clinician decision-making during the empirical treatment phase.

Integrating whole genome sequencing and machine learning for predicting antimicrobial resistance in critical pathogens: a systematic review of antimicrobial susceptibility tests

BACKGROUND

Infections caused by antibiotic-resistant bacteria pose a major challenge to modern healthcare. This systematic review evaluates the efficacy of machine learning (ML) approaches in predicting antimicrobial resistance (AMR) in critical pathogens (CP), considering Whole Genome Sequencing (WGS) and antimicrobial susceptibility testing (AST).

METHODS

The search covered databases including PubMed/MEDLINE, EMBASE, Web of Science, SCOPUS, and SCIELO, from their inception until June 2024. The review protocol was officially registered on PROSPERO (CRD42024543099).

RESULTS

The review included 26 papers, analyzing data from 104,141 microbial samples. Random Forest (RF), XGBoost, and logistic regression (LR) emerged as the top-performing models, with mean Area Under the Receiver Operating Characteristic (AUC) values of 0.89, 0.87, and 0.87, respectively. RF showed superior performance with AUC values ranging from 0.66 to 0.97, while XGBoost and LR showed similar performance with AUC values ranging from 0.83 to 0.91 and 0.76 to 0.96, respectively. Most studies indicate that integrating WGS and AST data into ML models enhances predictive performance, improves antibiotic stewardship, and provides valuable clinical decision support. ML shows significant promise for predicting AMR by integrating WGS and AST data in CP. Standardized guidelines are needed to ensure consistency in future research.

Identification of key drivers of antimicrobial resistance in Enterococcus using machine learning

With antimicrobial resistance (AMR) rapidly evolving in pathogens, quick and accurate identification of genetic determinants of phenotypic resistance is essential for improving surveillance, stewardship, and clinical mitigation. Machine learning (ML) models show promise for AMR prediction in diagnostics but require a deep understanding of internal processes to use effectively. Our study utilised AMR gene, pangenomic, and predicted plasmid features from 647 Enterococcus faecium and Enterococcus faecalis genomes across the One Health continuum, along with corresponding resistance phenotypes, to develop interpretive ML classifiers. Vancomycin resistance could be predicted with 99% accuracy with AMR gene features, 98% with pangenome features, and 96% with plasmid clusters. Top pangenome features overlapped with the resistance genes of the vanA operon, which are often laterally transmitted via plasmids. Doxycycline resistance prediction achieved approximately 92% accuracy with pangenome features, with the top feature being elements of Tn916 conjugative transposon, a tet(M) carrier. Erythromycin resistance prediction models achieved about 90% accuracy, but top features were negatively correlated with resistance due to the confounding effect of population structure. This work demonstrates the importance of reviewing ML models' features to discern biological relevance even when achieving high-performance metrics. Our workflow offers the potential to propose hypotheses for experimental testing, enhancing the understanding of AMR mechanisms, which are crucial for combating the AMR crisis.

Tackling the Antimicrobial Resistance "Pandemic" with Machine Learning Tools: A Summary of Available Evidence

Antimicrobial resistance is recognised as one of the top threats healthcare is bound to face in the future. There have been various attempts to preserve the efficacy of existing antimicrobials, develop new and efficient antimicrobials, manage infections with multi-drug resistant strains, and improve patient outcomes, resulting in a growing mass of routinely available data, including electronic health records and microbiological information that can be employed to develop individualised antimicrobial stewardship. Machine learning methods have been developed to predict antimicrobial resistance from whole-genome sequencing data, forecast medication susceptibility, recognise epidemic patterns for surveillance purposes, or propose new antibacterial treatments and accelerate scientific discovery. Unfortunately, there is an evident gap between the number of machine learning applications in science and the effective implementation of these systems. This narrative review highlights some of the outstanding opportunities that machine learning offers when applied in research related to antimicrobial resistance. In the future, machine learning tools may prove to be superbugs' kryptonite. This review aims to provide an overview of available publications to aid researchers that are looking to expand their work with new approaches and to acquaint them with the current application of machine learning techniques in this field.

Accessory genes define species-specific routes to antibiotic resistance

A deeper understanding of the relationship between the antimicrobial resistance (AMR) gene carriage and phenotype is necessary to develop effective response strategies against this global burden. AMR phenotype is often a result of multi-gene interactions; therefore, we need approaches that go beyond current simple AMR gene identification tools. Machine-learning (ML) methods may meet this challenge and allow the development of rapid computational approaches for AMR phenotype classification. To examine this, we applied multiple ML techniques to 16,950 bacterial genomes across 28 genera, with corresponding MICs for 23 antibiotics with the aim of training models to accurately determine the AMR phenotype from sequenced genomes. This resulted in a >1.5-fold increase in AMR phenotype prediction accuracy over AMR gene identification alone. Furthermore, we revealed 528 unique (often species-specific) genomic routes to antibiotic resistance, including genes not previously linked to the AMR phenotype. Our study demonstrates the utility of ML in predicting AMR phenotypes across diverse clinically relevant organisms and antibiotics. This research proposes a rapid computational method to support laboratory-based identification of the AMR phenotype in pathogens.

Analysis of Whole Genome Sequencing Data for Detection of Antimicrobial Resistance Determinants

Genomic sequencing has revolutionized microbial typing methods and transformed high-throughput methods in reference, clinical, and research laboratories. The detection of antimicrobial-resistant (AMR) determinants using genomic methods can provide valuable information on the emergence of resistance. Here we describe an approach to detecting AMR determinants using an open access and freely available platform which does not require bioinformatic expertise.

Global pathogenomic analysis identifies known and candidate genetic antimicrobial resistance determinants in twelve species

Surveillance programs for managing antimicrobial resistance (AMR) have yielded thousands of genomes suited for data-driven mechanism discovery. We present a workflow integrating pangenomics, gene annotation, and machine learning to identify AMR genes at scale. When applied to 12 species, 27,155 genomes, and 69 drugs, we 1) find AMR gene transfer mostly confined within related species, with 925 genes in multiple species but just eight in multiple phylogenetic classes, 2) demonstrate that discovery-oriented support vector machines outperform contemporary methods at recovering known AMR genes, recovering 263 genes compared to 145 by Pyseer, and 3) identify 142 AMR gene candidates. Validation of two candidates in E. coli BW25113 reveals cases of conditional resistance: ΔcycA confers ciprofloxacin resistance in minimal media with D-serine, and frdD V111D confers ampicillin resistance in the presence of ampC by modifying the overlapping promoter. We expect this approach to be adaptable to other species and phenotypes.

Plasmid-mediated colistin resistance from fresh meat and slaughtered animals in the Czech Republic: nation-wide surveillance 2020-2021

The aim of this study was to determine the occurrence of plasmid-mediated colistin resistance in domestic and imported meat and slaughter animals in the Czech Republic during 2020-2021 by using selective cultivation and direct PCR testing. A total of 111 colistin-resistant Escherichia coli isolates with mcr-1 gene were obtained from 65 (9.9%, n = 659) samples and subjected to whole-genome sequencing. Isolates with mcr were frequently found in fresh meat from domestic production (14.2%) as well as from import (28.8%). The mcr-1-positive E. coli isolates predominantly originated from meat samples (16.6%), mainly poultry (27.1%), and only minor part of the isolates came from the cecum (1.7%). In contrast to selective cultivation, 205 (31.1%) samples of whole-community DNA were positive for at least one mcr variant, and other genes besides mcr-1 were detected. Analysis of whole-genome data of sequenced E. coli isolates revealed diverse sequence types (STs) including pathogenic lineages and dominance of ST1011 (15.6%) and ST162 (12.8%). Most isolates showed multidrug-resistant profile, and 9% of isolates produced clinically important beta-lactamases. The mcr-1 gene was predominantly located on one of three conjugative plasmids of IncX4 (83.5%), IncI2 (7.3%), and IncHI2 (7.3%) groups. Seventy-two percent isolates of several STs carried ColV plasmids. The study revealed high prevalence of mcr genes in fresh meat of slaughter animals. Our results confirmed previous assumptions that the livestock, especially poultry production, is an important source of colistin-resistant E. coli with the potential of transfer to humans via the food chain. IMPORTANCE We present the first data on nation-wide surveillance of plasmid-mediated colistin resistance in the Czech Republic. High occurrence of plasmid-mediated colistin resistance was found in meat samples, especially in poultry from both domestic production and import, while the presence of mcr genes was lower in the gut of slaughter animals. In contrast to culture-based approach, testing of whole-community DNA showed higher prevalence of mcr and presence of various mcr variants. Our results support the importance of combining cultivation methods with direct culture-independent techniques and highlight the need for harmonized surveillance of plasmid-mediated colistin resistance. Our study confirmed the importance of livestock as a major reservoir of plasmid-mediated colistin resistance and pointed out the risks of poultry meat for the transmission of mcr genes toward humans. We identified several mcr-associated prevalent STs, especially ST1011, which should be monitored further as they represent zoonotic bacteria circulating between different environments.

Predicting variable gene content in Escherichia coli using conserved genes

Having the ability to predict the protein-encoding gene content of an incomplete genome or metagenome-assembled genome is important for a variety of bioinformatic tasks. In this study, as a proof of concept, we built machine learning classifiers for predicting variable gene content in Escherichia coli genomes using only the nucleotide k-mers from a set of 100 conserved genes as features. Protein families were used to define orthologs, and a single classifier was built for predicting the presence or absence of each protein family occurring in 10%-90% of all E. coli genomes. The resulting set of 3,259 extreme gradient boosting classifiers had a per-genome average macro F1 score of 0.944 [0.943-0.945, 95% CI]. We show that the F1 scores are stable across multi-locus sequence types and that the trend can be recapitulated by sampling a smaller number of core genes or diverse input genomes. Surprisingly, the presence or absence of poorly annotated proteins, including "hypothetical proteins" was accurately predicted (F1 = 0.902 [0.898-0.906, 95% CI]). Models for proteins with horizontal gene transfer-related functions had slightly lower F1 scores but were still accurate (F1s = 0.895, 0.872, 0.824, and 0.841 for transposon, phage, plasmid, and antimicrobial resistance-related functions, respectively). Finally, using a holdout set of 419 diverse E. coli genomes that were isolated from freshwater environmental sources, we observed an average per-genome F1 score of 0.880 [0.876-0.883, 95% CI], demonstrating the extensibility of the models. Overall, this study provides a framework for predicting variable gene content using a limited amount of input sequence data. IMPORTANCE Having the ability to predict the protein-encoding gene content of a genome is important for assessing genome quality, binning genomes from shotgun metagenomic assemblies, and assessing risk due to the presence of antimicrobial resistance and other virulence genes. In this study, we built a set of binary classifiers for predicting the presence or absence of variable genes occurring in 10%-90% of all publicly available E. coli genomes. Overall, the results show that a large portion of the E. coli variable gene content can be predicted with high accuracy, including genes with functions relating to horizontal gene transfer. This study offers a strategy for predicting gene content using limited input sequence data.

Exploring the Inhibitory Activity of Selected Lactic Acid Bacteria against Bread Rope Spoilage Agents

In this study, a wide pool of lactic acid bacteria strains deposited in two recognized culture collections was tested against ropy bread spoilage bacteria, specifically belonging to Bacillus spp., Paenibacillus spp., and Lysinibacillus spp. High-throughput and ex vivo screening assays were performed to select the best candidates. They were further investigated to detect the production of active antimicrobial metabolites and bacteriocins. Moreover, technological and safety features were assessed to value their suitability as biocontrol agents for the production of clean-label bakery products. The most prominent inhibitory activities were shown by four strains of Lactiplantibacillus plantarum (NFICC19, NFICC 72, NFICC163, and NFICC 293), two strains of Pediococcus pentosaceus (NFICC10 and NFICC341), and Leuconostoc citreum NFICC28. Moreover, the whole genome sequencing of the selected LAB strains and the in silico analysis showed that some of the strains contain operons for bacteriocins; however, no significant evidence was observed phenotypically.

Introducing the Bacterial and Viral Bioinformatics Resource Center (BV-BRC): a resource combining PATRIC, IRD and ViPR

The National Institute of Allergy and Infectious Diseases (NIAID) established the Bioinformatics Resource Center (BRC) program to assist researchers with analyzing the growing body of genome sequence and other omics-related data. In this report, we describe the merger of the PAThosystems Resource Integration Center (PATRIC), the Influenza Research Database (IRD) and the Virus Pathogen Database and Analysis Resource (ViPR) BRCs to form the Bacterial and Viral Bioinformatics Resource Center (BV-BRC) https://www.bv-brc.org/. The combined BV-BRC leverages the functionality of the bacterial and viral resources to provide a unified data model, enhanced web-based visualization and analysis tools, bioinformatics services, and a powerful suite of command line tools that benefit the bacterial and viral research communities.

Application of Artificial Intelligence in Combating High Antimicrobial Resistance Rates

Artificial intelligence (AI) is a branch of science and engineering that focuses on the computational understanding of intelligent behavior. Many human professions, including clinical diagnosis and prognosis, are greatly useful from AI. Antimicrobial resistance (AMR) is among the most critical challenges facing Pakistan and the rest of the world. The rising incidence of AMR has become a significant issue, and authorities must take measures to combat the overuse and incorrect use of antibiotics in order to combat rising resistance rates. The widespread use of antibiotics in clinical practice has not only resulted in drug resistance but has also increased the threat of super-resistant bacteria emergence. As AMR rises, clinicians find it more difficult to treat many bacterial infections in a timely manner, and therapy becomes prohibitively costly for patients. To combat the rise in AMR rates, it is critical to implement an institutional antibiotic stewardship program that monitors correct antibiotic use, controls antibiotics, and generates antibiograms. Furthermore, these types of tools may aid in the treatment of patients in the event of a medical emergency in which a physician is unable to wait for bacterial culture results. AI’s applications in healthcare might be unlimited, reducing the time it takes to discover new antimicrobial drugs, improving diagnostic and treatment accuracy, and lowering expenses at the same time. The majority of suggested AI solutions for AMR are meant to supplement rather than replace a doctor’s prescription or opinion, but rather to serve as a valuable tool for making their work easier. When it comes to infectious diseases, AI has the potential to be a game-changer in the battle against antibiotic resistance. Finally, when selecting antibiotic therapy for infections, data from local antibiotic stewardship programs are critical to ensuring that these bacteria are treated quickly and effectively. Furthermore, organizations such as the World Health Organization (WHO) have underlined the necessity of selecting the appropriate antibiotic and treating for the shortest time feasible to minimize the spread of resistant and invasive resistant bacterial strains.

A Practical Approach for Predicting Antimicrobial Phenotype Resistance in Staphylococcus aureus Through Machine Learning Analysis of Genome Data

With the reduction in sequencing price and acceleration of sequencing speed, it is particularly important to directly link the genotype and phenotype of bacteria. Here, we firstly predicted the minimum inhibitory concentrations of ten antimicrobial agents for Staphylococcus aureus using 466 isolates by directly extracting k-mer from whole genome sequencing data combined with three machine learning algorithms: random forest, support vector machine, and XGBoost. Considering one two-fold dilution, the essential agreement and the category agreement could reach >85% and >90% for most antimicrobial agents. For clindamycin, cefoxitin and trimethoprim-sulfamethoxazole, the essential agreement and the category agreement could reach >91% and >93%, providing important information for clinical treatment. The successful prediction of cefoxitin resistance showed that the model could identify methicillin-resistant S. aureus. The results suggest that small datasets available in large hospitals could bypass the existing basic research and known antimicrobial resistance genes and accurately predict the bacterial phenotype.

Towards routine employment of computational tools for antimicrobial resistance determination via high-throughput sequencing

Antimicrobial resistance (AMR) is a growing threat to public health and farming at large. In clinical and veterinary practice, timely characterization of the antibiotic susceptibility profile of bacterial infections is a crucial step in optimizing treatment. High-throughput sequencing is a promising option for clinical point-of-care and ecological surveillance, opening the opportunity to develop genotyping-based AMR determination as a possibly faster alternative to phenotypic testing. In the present work, we compare the performance of state-of-the-art methods for detection of AMR using high-throughput sequencing data from clinical settings. We consider five computational approaches based on alignment (AMRPlusPlus), deep learning (DeepARG), k-mer genomic signatures (KARGA, ResFinder) or hidden Markov models (Meta-MARC). We use an extensive collection of 585 isolates with available AMR resistance profiles determined by phenotypic tests across nine antibiotic classes. We show how the prediction landscape of AMR classifiers is highly heterogeneous, with balanced accuracy varying from 0.40 to 0.92. Although some algorithms-ResFinder, KARGA and AMRPlusPlus-exhibit overall better balanced accuracy than others, the high per-AMR-class variance and related findings suggest that: (1) all algorithms might be subject to sampling bias both in data repositories used for training and experimental/clinical settings; and (2) a portion of clinical samples might contain uncharacterized AMR genes that the algorithms-mostly trained on known AMR genes-fail to generalize upon. These results lead us to formulate practical advice for software configuration and application, and give suggestions for future study designs to further develop AMR prediction tools from proof-of-concept to bedside.

Increase in antimicrobial resistance in Escherichia coli in food animals between 1980 and 2018 assessed using genomes from public databases

BACKGROUND

Next-generation sequencing has considerably increased the number of genomes available in the public domain. However, efforts to use these genomes for surveillance of antimicrobial resistance have thus far been limited and geographically heterogeneous. We inferred global resistance trends in Escherichia coli in food animals using genomes from public databases.

METHODS

We retrieved 7632 E. coli genomes from public databases (NCBI, PATRIC and EnteroBase) and screened for antimicrobial resistance genes (ARGs) using ResFinder. Selection bias towards resistance, virulence or specific strains was accounted for by screening BioProject descriptions. Temporal trends for MDR, resistance to antimicrobial classes and ARG prevalence were inferred using generalized linear models for all genomes, including those not subjected to selection bias.

RESULTS

MDR increased by 1.6 times between 1980 and 2018, as genomes carried, on average, ARGs conferring resistance to 2.65 antimicrobials in swine, 2.22 in poultry and 1.58 in bovines. Highest resistance levels were observed for tetracyclines (42.2%-69.1%), penicillins (19.4%-47.5%) and streptomycin (28.6%-56.6%). Resistance trends were consistent after accounting for selection bias, although lower mean absolute resistance estimates were associated with genomes not subjected to selection bias (difference of 3.16%±3.58% across years, hosts and antimicrobial classes). We observed an increase in extended-spectrum cephalosporin ARG blaCMY-2 and a progressive substitution of tetB by tetA. Estimates of resistance prevalence inferred from genomes in the public domain were in good agreement with reports from systematic phenotypic surveillance.

CONCLUSIONS

Our analysis illustrates the potential of using the growing volume of genomes in public databases to track AMR trends globally.