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

Hospital air sampling enables surveillance of respiratory virus infections and genomes

There is an urgent need for early detection and comprehensive surveillance of respiratory pathogens. Environmental surveillance may be key to timely responses for newly emerging pathogens and infections that are unreported or underreported. Here, we employed air sampling in a large urban hospital. Air samples (n = 358) were collected weekly at five locations, including two in the emergency department, two in hospital common areas and one in a storage room, for two respiratory virus seasons (November 2022 to June 2024). Air samples were tested for eight respiratory pathogens by qPCR, including RNA and DNA viruses and a bacterium. Air samples had an average of four detected pathogens per sample and 97 % samples contained SARS-CoV-2. Air sample pathogen positivity and quantity were strongly correlated with clinical surveillance for four seasonal respiratory pathogens: influenza A and B, respiratory syncytial virus, and human metapneumovirus. Targeted amplicon sequencing of SARS-CoV-2 showed that lineages detected in air samples reflected those in contemporaneous regional clinical specimens. Metagenomic sequencing with viral capture enrichment detected myriad human pathogens, including respiratory-associated viruses with recovery of full viral genomes. Detection of viral pathogens correlated well between virus capture sequencing and qPCR. Overall, this suggests air sampling can be an agile and effective tool for pathogen early warning, surveillance and genome characterization.

Plasmid-bacteria associations in the clinical context

Antimicrobial resistance (AMR) is one of the most pressing global health problems, with plasmids playing a central role in its evolution and dissemination. Over the past decades, many studies have investigated the ecoevolutionary dynamics between plasmids and their bacterial hosts. However, what drives the epidemiological success of certain plasmid-bacterium associations remains unclear. In this opinion article, we review which factors influence these associations and underline that studying plasmid-host interactions of clinical relevance is critical for understanding the evolution and spread of AMR. We also highlight the increasing importance of integrating experimental research with bioinformatics and machine learning tools to study plasmid-bacteria dynamics. This combined approach will assist researchers to dissect the molecular mechanisms underlying successful plasmid-host associations and to design strategies to prevent and predict future high-risk associations.

Estimating the deferred value of pathogen genomic data for secondary use

The COVID-19 pandemic has illuminated the utility of pathogen genomics and highlighted roadblocks to international data sharing. This article describes the deferred value of pathogen genomics data for secondary use using a set of 10,110 assembled genomes of Vibrio cholerae shared via international repositories between 2010 and 2024 as an illustrative representation of a pandemic disease. Trends in the quality, representativeness, and timeliness of data sharing as well as the increasing role of microbiology services as genomic data providers resulting from gradually improving access to sequencing technologies in countries with a high burden of disease were identified. The deferred value of individual and aggregated genomic data was tracked over time and mapped to geographical hot spots of cholera. The time lag between the collection of the samples for V. cholerae cultures and the submission of the genome to an international database remained eight years on average. The data value assessment described here paves the way for the international mobilization of quality microbial genomic data for global health and knowledge discovery.

Artificial intelligence in drug resistance management

This review highlights the application of artificial intelligence (AI), particularly deep learning and machine learning (ML), in managing antimicrobial resistance (AMR). Key findings demonstrate that AI models, such as Naïve Bayes, Decision Trees (DT), Random Forest (RF), Support Vector Machines (SVM), and Artificial Neural Networks (ANN), have significantly advanced the prediction of drug resistance patterns and the identification of novel antibiotics. These algorithms have effectively optimized antibiotic use, predicted resistance phenotypes, and identified new drug candidates. AI has also facilitated the detection of AMR-associated mutations, offering new insights into the spread of resistance and potential interventions. Despite data privacy and algorithm transparency challenges, AI presents a promising tool in combating AMR, with implications for improving patient outcomes, enhancing disease management, and addressing global public health concerns. However, realizing its full potential requires overcoming issues related to data scarcity, ethical considerations, and fostering interdisciplinary collaboration.

AMRLearn: Protocol for a machine learning pipeline for characterization of antimicrobial resistance determinants in microbial genomic data

Single-nucleotide polymorphisms (SNPs) are useful biomarkers for linking genotype to phenotype. Machine learning is powerful for predicting antimicrobial resistance (AMR) from bacterial genome sequence data. Here, we present AMRLearn, a machine learning pipeline to assist users in the prediction and visualization of AMR phenotypes associated with SNP genotypes. We describe the steps needed for input data preparation, prediction model selection, and result visualization. AMRLearn is useful for researchers wanting to extract information relevant to AMR from whole-genome sequence data.

ARGai 1.0: A GAN augmented in silico approach for identifying resistant genes and strains in E. coli using vision transformer

The emergence of infectious disease and antibiotic resistance in bacteria like Escherichia coli (E. coli) shows the necessity for novel computational techniques for identifying essential genes that contribute to resistance. The task of identifying resistant strains and multi-drug patterns in E. coli is a major challenge with whole genome sequencing (WGS) and next-generation sequencing (NGS) data. To address this issue, we suggest ARGai 1.0 a deep learning architecture enhanced with generative adversarial networks (GANs). We mitigate data scarcity difficulties by augmenting limited experimental datasets with synthetic data generated by GANs. Our in-silico method (augmentation with feature selection) improves the identification of resistance genes in E. coli by using feature extraction techniques to identify valuable features from actual and GAN-generated data. Employing comprehensive validation, we exhibit the effectiveness of our ARGai 1.0 in precisely identifying the informative and resistant genes. In addition, our ARGai 1.0 identifies the resistant strains with a classification accuracy of 98.96 % on Deep Convolutional Generative Adversarial Network (DCGAN) augmented data. Additionally, ARGai 1.0 achieves more than 98 % of sensitivity and specificity. We also benchmark our ARGai 1.0 with several state-of-the-art AI models for resistant strain classification. In the fight against antibiotic resistance, ARGai 1.0 offers a promising avenue for computational genomics. With implications for research and clinical practice, this work shows the potential of deep networks with GAN augmentation as a practical and successful method for gene identification in E. coli.

The Application of artificial intelligence in periprosthetic joint infection

Periprosthetic joint infection (PJI) represents one of the most devastating complications following total joint arthroplasty, often necessitating additional surgeries and antimicrobial therapy, and potentially leading to disability. This significantly increases the burden on both patients and the healthcare system. Given the considerable suffering caused by PJI, its prevention and treatment have long been focal points of concern. However, challenges remain in accurately assessing individual risk, preventing the infection, improving diagnostic methods, and enhancing treatment outcomes. The development and application of artificial intelligence (AI) technologies have introduced new, more efficient possibilities for the management of many diseases. In this article, we review the applications of AI in the prevention, diagnosis, and treatment of PJI, and explore how AI methodologies might achieve individualized risk prediction, improve diagnostic algorithms through biomarkers and pathology, and enhance the efficacy of antimicrobial and surgical treatments. We hope that through multimodal AI applications, intelligent management of PJI can be realized in the future.

Quantitative prediction of disinfectant tolerance in Listeria monocytogenes using whole genome sequencing and machine learning

Listeria monocytogenes is a potentially severe disease-causing bacteria mainly transmitted through food. This pathogen is of great concern for public health and the food industry in particular. Many countries have implemented thorough regulations, and some have even set 'zero-tolerance' thresholds for particular food products to minimise the risk of L. monocytogenes outbreaks. This emphasises that proper sanitation of food processing plants is of utmost importance. Consequently, in recent years, there has been an increased interest in L. monocytogenes tolerance to disinfectants used in the food industry. Even though many studies are focusing on laboratory quantification of L. monocytogenes tolerance, the possibility of predictive models remains poorly studied. Within this study, we explore the prediction of tolerance and minimum inhibitory concentrations (MIC) using whole genome sequencing (WGS) and machine learning (ML). We used WGS data and MIC values to quaternary ammonium compound (QAC) disinfectants from 1649 L. monocytogenes isolates to train different ML predictors. Our study shows promising results for predicting tolerance to QAC disinfectants using WGS and machine learning. We were able to train high-performing ML classifiers to predict tolerance with balanced accuracy scores up to 0.97 ± 0.02. For the prediction of MIC values, we were able to train ML regressors with mean squared error as low as 0.07 ± 0.02. We also identified several new genes related to cell wall anchor domains, plasmids, and phages, putatively associated with disinfectant tolerance in L. monocytogenes. The findings of this study are a first step towards prediction of L. monocytogenes tolerance to QAC disinfectants used in the food industry. In the future, predictive models might be used to monitor disinfectant tolerance in food production and might support the conceptualisation of more nuanced sanitation programs.

How AI can help us beat AMR

Antimicrobial resistance (AMR) is an urgent public health threat. Advancements in artificial intelligence (AI) and increases in computational power have resulted in the adoption of AI for biological tasks. This review explores the application of AI in bacterial infection diagnostics, AMR surveillance, and antibiotic discovery. We summarize contemporary AI models applied to each of these domains, important considerations when applying AI across diverse tasks, and current limitations in the field.

Prophages are Infrequently Associated With Antibiotic Resistance in Pseudomonas aeruginosa Clinical Isolates

Lysogenic bacteriophages can integrate their genome into the bacterial chromosome in the form of a prophage and can promote genetic transfer between bacterial strains in vitro . However, the contribution of lysogenic phages to the incidence of antimicrobial resistance (AMR) in clinical settings is poorly understood. Here, in a set of 186 clinical isolates of Pseudomonas aeruginosa collected from respiratory cultures from 82 patients with cystic fibrosis (CF), we evaluate the links between prophage counts and both genomic and phenotypic resistance to six anti-pseudomonal antibiotics: tobramycin, colistin, ciprofloxacin, meropenem, aztreonam, and piperacillin-tazobactam. We identified 239 different prophages in total. We find that P. aeruginosa isolates contain on average 3.06 +/- 1.84 (SD) predicted prophages. We find no significant association between the number of prophages per isolate and the minimum inhibitory concentration (MIC) for any of these antibiotics. We then investigate the relationship between particular prophages and AMR. We identify a single lysogenic phage associated with phenotypic resistance to the antibiotic tobramycin and, consistent with this association, we observe that AMR genes associated with resistance to tobramycin are more likely to be found when this prophage is present. However we find that they are not encoded directly on prophage sequences. Additionally, we identify a single prophage statistically associated with ciprofloxacin resistance but do not identify any genes associated with ciprofloxacin phenotypic resistance. These findings suggest that prophages are only infrequently associated with the AMR genes in clinical isolates of P. aeruginosa .

Importance

Antibiotic-resistant infections of Pseudomonas aeruginosa , a leading pathogen in patients with Cystic Fibrosis (CF) are a global health threat. While lysogenic bacteriophages are known to facilitate horizontal gene transfer, their role in promoting antibiotic resistance in clinical settings remains poorly understood. In our analysis of 186 clinical isolates of P. aeruginosa from CF patients, we find that prophage abundance does not predict phenotypic resistance to key antibiotics but that specific prophages are infrequently associated with tobramycin resistance genes. In addition, we do not find antimicrobial resistance (AMR) genes encoded directly on prophages. These results highlight that while phages can be associated with AMR, phage-mediated AMR transfer may be rare in clinical isolates and difficult to identify. This work is important for future efforts on mitigating AMR in Cystic Fibrosis and other vulnerable populations affected by Pseudomonas aeruginosa infections and advances our understanding of bacterial-phage dynamics in clinical infections.

Incomplete human reference genomes can drive false sex biases and expose patient-identifying information in metagenomic data

As next-generation sequencing technologies produce deeper genome coverages at lower costs, there is a critical need for reliable computational host DNA removal in metagenomic data. We find that insufficient host filtration using prior human genome references can introduce false sex biases and inadvertently permit flow-through of host-specific DNA during bioinformatic analyses, which could be exploited for individual identification. To address these issues, we introduce and benchmark three host filtration methods of varying throughput, with concomitant applications across low biomass samples such as skin and high microbial biomass datasets including fecal samples. We find that these methods are important for obtaining accurate results in low biomass samples (e.g., tissue, skin). Overall, we demonstrate that rigorous host filtration is a key component of privacy-minded analyses of patient microbiomes and provide computationally efficient pipelines for accomplishing this task on large-scale datasets.

The role of artificial intelligence and machine learning in predicting and combating antimicrobial resistance

Antimicrobial resistance (AMR) is a major threat to global public health. The current review synthesizes to address the possible role of Artificial Intelligence and Machine Learning (AI/ML) in mitigating AMR. Supervised learning, unsupervised learning, deep learning, reinforcement learning, and natural language processing are some of the main tools used in this domain. AI/ML models can use various data sources, such as clinical information, genomic sequences, microbiome insights, and epidemiological data for predicting AMR outbreaks. Although AI/ML are relatively new fields, numerous case studies offer substantial evidence of their successful application in predicting AMR outbreaks with greater accuracy. These models can provide insights into the discovery of novel antimicrobials, the repurposing of existing drugs, and combination therapy through the analysis of their molecular structures. In addition, AI-based clinical decision support systems in real-time guide healthcare professionals to improve prescribing of antibiotics. The review also outlines how can AI improve AMR surveillance, analyze resistance trends, and enable early outbreak identification. Challenges, such as ethical considerations, data privacy, and model biases exist, however, the continuous development of novel methodologies enables AI/ML to play a significant role in combating AMR.

Role of artificial intelligence in early diagnosis and treatment of infectious diseases

Infectious diseases remain a global health challenge, necessitating innovative approaches for their early diagnosis and effective treatment. Artificial Intelligence (AI) has emerged as a transformative force in healthcare, offering promising solutions to address this challenge. This review article provides a comprehensive overview of the pivotal role AI can play in the early diagnosis and treatment of infectious diseases. It explores how AI-driven diagnostic tools, including machine learning algorithms, deep learning, and image recognition systems, enhance the accuracy and efficiency of disease detection and surveillance. Furthermore, it delves into the potential of AI to predict disease outbreaks, optimise treatment strategies, and personalise interventions based on individual patient data and how AI can be used to gear up the drug discovery and development (D3) process.The ethical considerations, challenges, and limitations associated with the integration of AI in infectious disease management are also examined. By harnessing the capabilities of AI, healthcare systems can significantly improve their preparedness, responsiveness, and outcomes in the battle against infectious diseases.

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.

Revisiting mutational resistance to ampicillin and cefotaxime in Haemophilus influenzae

BACKGROUND

Haemophilus influenzae is an opportunistic bacterial pathogen that can cause severe respiratory tract and invasive infections. The emergence of β-lactamase-negative ampicillin-resistant (BLNAR) strains and unclear correlations between genotypic (i.e., gBLNAR) and phenotypic resistance are challenging empirical treatments and patient management. Thus, we sought to revisit molecular resistance mechanisms and to identify new resistance determinants of H. influenzae.

METHODS

We performed a systematic meta-analysis of H. influenzae isolates (n = 291) to quantify the association of phenotypic ampicillin and cefotaxime resistance with previously defined resistance groups, i.e., specific substitution patterns of the penicillin binding protein PBP3, encoded by ftsI. Using phylogenomics and a genome-wide association study (GWAS), we investigated evolutionary trajectories and novel resistance determinants in a public global cohort (n = 555) and a new clinical cohort from three European centers (n = 298), respectively.

RESULTS

Our meta-analysis confirmed that PBP3 group II- and group III-related isolates were significantly associated with phenotypic resistance to ampicillin (p < 0.001), while only group III-related isolates were associated with resistance to cefotaxime (p = 0.02). The vast majority of H. influenzae isolates not classified into a PBP3 resistance group were ampicillin and cefotaxime susceptible. However, particularly group II isolates had low specificities (< 16%) to rule in ampicillin resistance due to clinical breakpoints classifying many of them as phenotypically susceptible. We found indications for positive selection of multiple PBP3 substitutions, which evolved independently and often step-wise in different phylogenetic clades. Beyond ftsI, other possible candidate genes (e.g., oppA, ridA, and ompP2) were moderately associated with ampicillin resistance in the GWAS. The PBP3 substitutions M377I, A502V, N526K, V547I, and N569S were most strongly related to ampicillin resistance and occurred in combination in the most prevalent resistant haplotype H1 in our clinical cohort.

CONCLUSIONS

Gradient agar diffusion strips and broth microdilution assays do not consistently classify isolates from PBP3 groups as phenotypically resistant. Consequently, when the minimum inhibitory concentration is close to the clinical breakpoints, and genotypic data is available, PBP3 resistance groups should be prioritized over susceptible phenotypic results for ampicillin. The implications on treatment outcome and bacterial fitness of other extended PBP3 substitution patterns and novel candidate genes need to be determined.

Using genomic data and machine learning to predict antibiotic resistance: A tutorial paper

Antibiotic resistance is a global public health concern. Bacteria have evolved resistance to most antibiotics, which means that for any given bacterial infection, the bacteria may be resistant to one or several antibiotics. It has been suggested that genomic sequencing and machine learning (ML) could make resistance testing more accurate and cost-effective. Given that ML is likely to become an ever more important tool in medicine, we believe that it is important for pre-health students and others in the life sciences to learn to use ML tools. This paper provides a step-by-step tutorial to train 4 different ML models (logistic regression, random forests, extreme gradient-boosted trees, and neural networks) to predict drug resistance for Escherichia coli isolates and to evaluate their performance using different metrics and cross-validation techniques. We also guide the user in how to load and prepare the data used for the ML models. The tutorial is accessible to beginners and does not require any software to be installed as it is based on Google Colab notebooks and provides a basic understanding of the different ML models. The tutorial can be used in undergraduate and graduate classes for students in Biology, Public Health, Computer Science, or related fields.

NeuralBeds: Neural embeddings for efficient DNA data compression and optimized similarity search

The availability of high throughput sequencing tools coupled with the declining costs in the production of DNA sequences has led to the generation of enormous amounts of omics data curated in several databases such as NCBI and EMBL. Identification of similar DNA sequences from these databases is one of the fundamental tasks in bioinformatics. It is essential for discovering homologous sequences in organisms, phylogenetic studies of evolutionary relationships among several biological entities, or detection of pathogens. Improving DNA similarity search is of outmost importance because of the increased complexity of the evergrowing repositories of sequences. Therefore, instead of using the conventional approach of comparing raw sequences, e.g., in fasta format, a numerical representation of the sequences can be used to calculate their similarities and optimize the search process. In this study, we analyzed different approaches for numerical embeddings, including Chaos Game Representation, hashing, and neural networks, and compared them with classical approaches such as principal component analysis. It turned out that neural networks generate embeddings that are able to capture the similarity between DNA sequences as a distance measure and outperform the other approaches on DNA similarity search, significantly.

Biochemistry and Future Perspectives of Antibiotic Resistance: An Eye on Active Natural Products

Antibiotic resistance poses a serious threat to the current healthcare system, negatively impacting the effectiveness of many antimicrobial treatments. The situation is exacerbated by the widespread overuse and abuse of available antibiotics, accelerating the evolution of resistance. Thus, there is an urgent need for novel approaches to therapy to overcome established resistance mechanisms. Plants produce molecules capable of inhibiting bacterial growth in various ways, offering promising paths for the development of alternative antibiotic medicine. This review emphasizes the necessity of research efforts on plant-derived chemicals in the hopes of finding and creating novel drugs that can successfully target resistant bacterial populations. Investigating these natural chemicals allows us to improve our knowledge of novel antimicrobial pathways and also expands our antibacterial repertoire with novel molecules. Simultaneously, it is still necessary to utilize present antibiotics sparingly; prudent prescribing practices must be encouraged to extend the effectiveness of current medications. The combination of innovative drug research and responsible drug usage offers an integrated strategy for managing the antibiotic resistance challenge.

Machine Learning Approaches for Microorganism Identification, Virulence Assessment, and Antimicrobial Susceptibility Evaluation Using DNA Sequencing Methods: A Systematic Review

Microbial infections pose a substantial global health challenge, particularly impacting immunocompromised individuals and exacerbating the issue of antimicrobial resistance (AMR). High virulence of pathogens can lead to severe infections and prolonged antimicrobial treatment, increasing the risk of developing resistant strains. Integrating machine-learning (ML) with DNA sequencing technologies offers potential solutions by enhancing microbial identification, virulence assessment, and antimicrobial susceptibility evaluation. This review explores recent advancements in these integrated approaches, addressing current limitations and identifying gaps in the literature. A comprehensive literature search was conducted across databases including PubMed, Scopus, Web of Science, and IEEE Xplore, covering publications from January 2014 to June 2024. Using a detailed Boolean search string, relevant studies focusing on ML applications in microorganism identification, antimicrobial susceptibility testing, and microbial virulence were included. The screening process involved a two-stage review of titles, abstracts, and full texts, with data extraction and critical appraisal performed using the QIAO tool. Data were analyzed through narrative synthesis to identify common themes and innovations. Out of 1,650 initially identified records, 19 studies met the inclusion criteria. These studies primarily focused on AMR, with additional research on microbial virulence and identification. Machine learning algorithms such as Random Forest, Support Vector Machines, and Convolutional Neural Networks, combined with DNA sequencing techniques like Whole Genome Sequencing and Metagenomic Sequencing, demonstrated significant advancements in predictive accuracy and efficiency. High-quality studies achieved impressive performance metrics, including F1-scores up to 0.88 and AUC scores up to 0.96. The integration of ML and DNA sequencing technologies has significantly enhanced microbial analysis, improving the identification of pathogens, assessment of virulence, and evaluation of antimicrobial susceptibility. Despite advancements, challenges such as data quality, high costs, and model interpretability persist. This review highlights the need for continued innovation and provides recommendations for future research to address these limitations and improve disease management and public health strategies. The systematic review is registered with PROSPERO (CRD42024571347).

Artificial intelligence in predicting pathogenic microorganisms' antimicrobial resistance: challenges, progress, and prospects

The issue of antimicrobial resistance (AMR) in pathogenic microorganisms has emerged as a global public health crisis, posing a significant threat to the modern healthcare system. The advent of Artificial Intelligence (AI) and Machine Learning (ML) technologies has brought about revolutionary changes in this field. These advanced computational methods are capable of processing and analyzing large-scale biomedical data, thereby uncovering complex patterns and mechanisms behind the development of resistance. AI technologies are increasingly applied to predict the resistance of pathogens to various antibiotics based on gene content and genomic composition. This article reviews the latest advancements in AI and ML for predicting antimicrobial resistance in pathogenic microorganisms. We begin with an overview of the biological foundations of microbial resistance and its epidemiological research. Subsequently, we highlight the main AI and ML models used in resistance prediction, including but not limited to Support Vector Machines, Random Forests, and Deep Learning networks. Furthermore, we explore the major challenges in the field, such as data availability, model interpretability, and cross-species resistance prediction. Finally, we discuss new perspectives and solutions for research into microbial resistance through algorithm optimization, dataset expansion, and interdisciplinary collaboration. With the continuous advancement of AI technology, we will have the most powerful weapon in the fight against pathogenic microbial resistance in the future.

Incomplete human reference genomes can drive false sex biases and expose patient-identifying information in metagenomic data

As next-generation sequencing technologies produce deeper genome coverages at lower costs, there is a critical need for reliable computational host DNA removal in metagenomic data. We find that insufficient host filtration using prior human genome references can introduce false sex biases and inadvertently permit flow-through of host-specific DNA during bioinformatic analyses, which could be exploited for individual identification. To address these issues, we introduce and benchmark three host filtration methods of varying throughput, with concomitant applications across low biomass samples such as skin and high microbial biomass datasets including fecal samples. We find that these methods are important for obtaining accurate results in low biomass samples (e.g., tissue, skin). Overall, we demonstrate that rigorous host filtration is a key component of privacy-minded analyses of patient microbiomes and provide computationally efficient pipelines for accomplishing this task on large-scale datasets.

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.

Using interpretable machine learning to predict bloodstream infection and antimicrobial resistance in patients admitted to ICU: Early alert predictors based on EHR data to guide antimicrobial stewardship

Nosocomial infections and Antimicrobial Resistance (AMR) stand as formidable healthcare challenges on a global scale. To address these issues, various infection control protocols and personalized treatment strategies, guided by laboratory tests, aim to detect bloodstream infections (BSI) and assess the potential for AMR. In this study, we introduce a machine learning (ML) approach based on Multi-Objective Symbolic Regression (MOSR), an evolutionary approach to create ML models in the form of readable mathematical equations in a multi-objective way to overcome the limitation of standard single-objective approaches. This method leverages readily available clinical data collected upon admission to intensive care units, with the goal of predicting the presence of BSI and AMR. We further assess its performance by comparing it to established ML algorithms using both naturally imbalanced real-world data and data that has been balanced through oversampling techniques. Our findings reveal that traditional ML models exhibit subpar performance across all training scenarios. In contrast, MOSR, specifically configured to minimize false negatives by optimizing also for the F1-Score, outperforms other ML algorithms and consistently delivers reliable results, irrespective of the training set balance with F1-Score.22 and.28 higher than any other alternative. This research signifies a promising path forward in enhancing Antimicrobial Stewardship (AMS) strategies. Notably, the MOSR approach can be readily implemented on a large scale, offering a new ML tool to find solutions to these critical healthcare issues affected by limited data availability.

PanKA: Leveraging population pangenome to predict antibiotic resistance

Machine learning has the potential to be a powerful tool in the fight against antimicrobial resistance (AMR), a critical global health issue. Machine learning can identify resistance mechanisms from DNA sequence data without prior knowledge. The first step in building a machine learning model is a feature extraction from sequencing data. Traditional methods like single nucleotide polymorphism (SNP) calling and k-mer counting yield numerous, often redundant features, complicating prediction and analysis. In this paper, we propose PanKA, a method using the pangenome to extract a concise set of relevant features for predicting AMR. PanKA not only enables fast model training and prediction but also improves accuracy. Applied to the Escherichia coli and Klebsiella pneumoniae bacterial species, our model is more accurate than conventional and state-of-the-art methods in predicting AMR.

Prediction of antimicrobial resistance of Klebsiella pneumoniae from genomic data through machine learning

Antimicrobials, such as antibiotics or antivirals are medications employed to prevent and treat infectious diseases in humans, animals, and plants. Antimicrobial Resistance occurs when bacteria, viruses, and parasites no longer respond to these medicines. This resistance renders antibiotics and other antimicrobial drugs ineffective, making infections challenging or impossible to treat. This escalation in drug resistance heightens the risk of disease spread, severe illness, disability, and mortality. With datasets now containing hundreds or even thousands of pathogen genomes, machine learning techniques are on the rise for predicting antibiotic resistance in pathogens, prediction based on gene content and genome composition. Aim of this work is to combine and incorporate machine learning methods on bacterial genomic data to predict antimicrobial resistance, we will focus on the case of Klebsiella pneumoniae in order to support clinicians in selecting appropriate therapy.

Predicting Pseudomonas aeruginosa drug resistance using artificial intelligence and clinical MALDI-TOF mass spectra

Matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS) is widely used in clinical microbiology laboratories for bacterial identification but its use for detection of antimicrobial resistance (AMR) remains limited. Here, we used MALDI-TOF MS with artificial intelligence (AI) approaches to successfully predict AMR in Pseudomonas aeruginosa, a priority pathogen with complex AMR mechanisms. The highest performance was achieved for modern β-lactam/β-lactamase inhibitor drugs, namely, ceftazidime/avibactam and ceftolozane/tazobactam. For these drugs, the model demonstrated area under the receiver operating characteristic curve (AUROC) of 0.869 and 0.856, specificity of 0.925 and 0.897, and sensitivity of 0.731 and 0.714, respectively. As part of this work, we developed dynamic binning, a feature engineering technique that effectively reduces the high-dimensional feature set and has wide-ranging applicability to MALDI-TOF MS data. Compared to conventional feature engineering approaches, the dynamic binning method yielded highest performance in 7 of 10 antimicrobials. Moreover, we showcased the efficacy of transfer learning in enhancing the AUROC performance for 8 of 11 antimicrobials. By assessing the contribution of features to the model's prediction, we identified proteins that may contribute to AMR mechanisms. Our findings demonstrate the potential of combining AI with MALDI-TOF MS as a rapid AMR diagnostic tool for Pseudomonas aeruginosa.IMPORTANCEPseudomonas aeruginosa is a key bacterial pathogen that causes significant global morbidity and mortality. Antimicrobial resistance (AMR) emerges rapidly in P. aeruginosa and is driven by complex mechanisms. Drug-resistant P. aeruginosa is a major challenge in clinical settings due to limited treatment options. Early detection of AMR can guide antibiotic choices, improve patient outcomes, and avoid unnecessary antibiotic use. Matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS) is widely used for rapid species identification in clinical microbiology. In this study, we repurposed mass spectra generated by MALDI-TOF and used them as inputs for artificial intelligence approaches to successfully predict AMR in P. aeruginosa for multiple key antibiotic classes. This work represents an important advance toward using MALDI-TOF as a rapid AMR diagnostic for P. aeruginosa in clinical settings.

A rapid approach with machine learning for quantifying the relative burden of antimicrobial resistance in natural aquatic environments

The massive use and discharge of antibiotics have led to increasing concerns about antimicrobial resistance (AMR) in natural aquatic environments. Since the dose-response mechanisms of pathogens with AMR have not yet been fully understood, and the antibiotic resistance genes and bacteria-related data collection via field sampling and laboratory testing is time-consuming and expensive, designing a rapid approach to quantify the burden of AMR in the natural aquatic environment has become a challenge. To cope with such a challenge, a new approach involving an integrated machine-learning framework was developed by investigating the associations between the relative burden of AMR and easily accessible variables (i.e., relevant environmental variables and adjacent land-use patterns). The results, based on a real-world case analysis, demonstrate that the quantification speed has been reduced from 3-7 days, which is typical for traditional measurement procedures with field sampling and laboratory testing, to approximately 0.5 hours using the new approach. Moreover, all five metrics for AMR relative burden quantification exceed the threshold level of 85%, with F1-score surpassing 0.92. Compared to logistic regression, decision trees, and basic random forest, the adaptive random forest model within the framework significantly improves quantification accuracy without sacrificing model interpretability. Two environmental variables, dissolved oxygen and resistivity, along with the proportion of green areas were identified as three key feature variables for the rapid quantification. This study contributes to the enrichment of burden analyses and management practices for rapid quantification of the relative burden of AMR without dose-response information.

Improving the odds: Artificial intelligence and the great plate count anomaly

Next-generation DNA sequencing has shown that the great plate count anomaly, that is, the difference between bacteria present in the environment and those that can be obtained in culture from that environment, is even greater and more persisting than initially thought. This hampers fundamental understanding of bacterial physiology and biotechnological application of the unculture majority. With big sequence data as foundation, artificial intelligence (AI) may be a game changer in bacterial isolation efforts and provide directions for the cultivation media and conditions that are most promising and as such be used to canalize limited human and financial resources. This opinion paper discusses how AI is or can be used to improve the success of bacterial isolation.

From Data to Decisions: Leveraging Artificial Intelligence and Machine Learning in Combating Antimicrobial Resistance - a Comprehensive Review

The emergence of drug-resistant bacteria poses a significant challenge to modern medicine. In response, Artificial Intelligence (AI) and Machine Learning (ML) algorithms have emerged as powerful tools for combating antimicrobial resistance (AMR). This review aims to explore the role of AI/ML in AMR management, with a focus on identifying pathogens, understanding resistance patterns, predicting treatment outcomes, and discovering new antibiotic agents. Recent advancements in AI/ML have enabled the efficient analysis of large datasets, facilitating the reliable prediction of AMR trends and treatment responses with minimal human intervention. ML algorithms can analyze genomic data to identify genetic markers associated with antibiotic resistance, enabling the development of targeted treatment strategies. Additionally, AI/ML techniques show promise in optimizing drug administration and developing alternatives to traditional antibiotics. By analyzing patient data and clinical outcomes, these technologies can assist healthcare providers in diagnosing infections, evaluating their severity, and selecting appropriate antimicrobial therapies. While integration of AI/ML in clinical settings is still in its infancy, advancements in data quality and algorithm development suggest that widespread clinical adoption is forthcoming. In conclusion, AI/ML holds significant promise for improving AMR management and treatment outcome.

Integrative genomics would strengthen AMR understanding through ONE health approach

Emergence of drug-induced antimicrobial resistance (AMR) forms a crippling health and economic crisis worldwide, causing high mortality from otherwise treatable diseases and infections. Next Generation Sequencing (NGS) has significantly augmented detection of culture independent microbes, potential AMR in pathogens and elucidation of mechanisms underlying it. Here, we review recent findings of AMR evolution in pathogens aided by integrated genomic investigation strategies inclusive of bacteria, virus, fungi and AMR alleles. While AMR monitoring is dominated by data from hospital-related infections, we review genomic surveillance of both biotic and abiotic components involved in global AMR emergence and persistence. Identification of pathogen-intrinsic as well as environmental and/or host factors through robust genomics/bioinformatics, along with monitoring of type and frequency of antibiotic usage will greatly facilitate prediction of regional and global patterns of AMR evolution. Genomics-enabled AMR prediction and surveillance will be crucial - in shaping health and economic policies within the One Health framework to combat this global concern.

Interpretable machine learning models for predicting clinical pregnancies associated with surgical sperm retrieval from testes of different etiologies: a retrospective study

BACKGROUND

The relationship between surgical sperm retrieval of different etiologies and clinical pregnancy is unclear. We aimed to develop a robust and interpretable machine learning (ML) model for predicting clinical pregnancy using the SHapley Additive exPlanation (SHAP) association of surgical sperm retrieval from testes of different etiologies.

METHODS

A total of 345 infertile couples who underwent intracytoplasmic sperm injection (ICSI) treatment with surgical sperm retrieval due to different etiologies from February 2020 to March 2023 at the reproductive center were retrospectively analyzed. The six machine learning (ML) models were used to predict the clinical pregnancy of ICSI. After evaluating the performance characteristics of the six ML models, the Extreme Gradient Boosting model (XGBoost) was selected as the best model, and SHAP was utilized to interpret the XGBoost model for predicting clinical pregnancies and to reveal the decision-making process of the model.

RESULTS

Combining the area under the receiver operating characteristic curve (AUROC), accuracy, precision, recall, F1 score, brier score, and the area under the precision-recall (P-R) curve (AP), the XGBoost model has the best performance (AUROC: 0.858, 95% confidence interval (CI): 0.778-0.936, accuracy: 79.71%, brier score: 0.151). The global summary plot of SHAP values shows that the female age is the most important feature influencing the model output. The SHAP plot showed that younger age in females, bigger testicular volume (TV), non-tobacco use, higher anti-müllerian hormone (AMH), lower follicle-stimulating hormone (FSH) in females, lower FSH in males, the temporary ejaculatory disorders (TED) group, and not the non-obstructive azoospermia (NOA) group all resulted in an increased probability of clinical pregnancy.

CONCLUSIONS

The XGBoost model predicts clinical pregnancies associated with testicular sperm retrieval of different etiologies with high accuracy, reliability, and robustness. It can provide clinical counseling decisions for patients with surgical sperm retrieval of various etiologies.

Genetic basis of clarithromycin resistance in Bacillus anthracis

The high-consequence pathogen Bacillus anthracis causes human anthrax and often results in lethal infections without the rapid administration of effective antimicrobial treatment. Antimicrobial resistance profiling is therefore critical to inform post-exposure prophylaxis and treatment decisions, especially during emergencies such as outbreaks or where intentional release is suspected. Whole-genome sequencing using a rapid long-read sequencer can uncover antimicrobial resistance patterns if genetic markers of resistance are known. To identify genomic markers associated with antimicrobial resistance, we isolated B. anthracis derived from the avirulent Sterne strain with elevated minimal inhibitory concentrations to clarithromycin. Mutants were characterized both phenotypically through broth microdilution susceptibility testing and observations during culturing, as well as genotypically with whole-genome sequencing. We identified two different in-frame insertions in the L22 ribosomal protein-encoding gene rplV, which were subsequently confirmed to be involved in clarithromycin resistance through the reversion of the mutant gene to the parent (drug-susceptible) sequence. Detection of the rplV insertions was possible with rapid long-read sequencing, with a time-to-answer within 3 h. The mutations associated with clarithromycin resistance described here will be used in conjunction with known genetic markers of resistance for other antimicrobials to strengthen the prediction of antimicrobial resistance in B. anthracis.IMPORTANCEThe disease anthrax, caused by the pathogen Bacillus anthracis, is extremely deadly if not treated quickly and appropriately. Clarithromycin is an antibiotic recommended for the treatment and post-exposure prophylaxis of anthrax by the Centers for Disease Control and Prevention; however, little is known about the ability of B. anthracis to develop resistance to clarithromycin or the mechanism of that resistance. The characterization of clarithromycin-resistant isolates presented here provides valuable information for researchers and clinicians in the event of a release of the resistant strain. Additionally, knowledge of the genetic basis of resistance provides a foundation for susceptibility prediction through rapid genome sequencing to inform timely treatment decisions.

Improving the diagnosis of tuberculosis: old and new laboratory tools

INTRODUCTION

Despite recent advances in diagnostic technologies and new drugs becoming available, tuberculosis (TB) remains a major global health burden. If detected early, screened for drug resistance, and fully treated, TB could be easily controlled.

AREAS COVERED

Here the authors discuss M. tuberculosis culture methods which are considered the definitive confirmation of M. tuberculosis infection, and limited advances made to build on these core elements of TB laboratory diagnosis. Literature searches showed that molecular techniques provide enhanced speed of turnaround, sensitivity, and richness of data. Sequencing of the whole genome, is becoming well established for identification and inference of drug resistance. PubMed® literature searches were conducted (November 2022-March 2024).

EXPERT OPINION

This section highlights future advances in diagnosis and infection control. Prevention of prolonged hospital admissions and rapid TAT are of the most benefit to the overall patient experience. Host transcriptional blood markers have been used in treatment monitoring studies and, with appropriate evaluation, could be rolled out in a diagnostic setting. Additionally, the MBLA is being incorporated into latest clinical trial designs. Whole genome sequencing has enhanced epidemiological evidence. Artificial intelligence, along with machine learning, have the ability to revolutionize TB diagnosis and susceptibility testing within the next decade.

The potential of machine learning models to identify malnutrition diagnosed by GLIM combined with NRS-2002 in colorectal cancer patients without weight loss information

BACKGROUND & AIMS

The key step of the Global Leadership Initiative on Malnutrition (GLIM) is nutritional risk screening, while the most appropriate screening tool for colorectal cancer (CRC) patients is yet unknown. The GLIM diagnosis relies on weight loss information, and bias or even failure to recall patients' historical weight can cause misestimates of malnutrition. We aimed to compare the suitability of several screening tools in GLIM diagnosis, and establish machine learning (ML) models to predict malnutrition in CRC patients without weight loss information.

METHODS

This multicenter cohort study enrolled 4487 CRC patients. The capability of GLIM diagnoses combined with four screening tools in predicting survival probability was compared by Kaplan-Meier curves, and the most accurate one was selected as the malnutrition reference standard. Participants were randomly assigned to a training cohort (n = 3365) and a validation cohort (n = 1122). Several ML approaches were adopted to establish models for predicting malnutrition without weight loss data. We estimated feature importance and reserved the top 30% of variables for retraining simplified models. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to assess and compare model performance.

RESULTS

NRS-2002 was the most suitable screening tool for GLIM diagnosis in CRC patients, with the highest hazard ratio (1.59; 95% CI, 1.43-1.77). A total of 2076 (46.3%) patients were malnourished diagnosed by GLIM combined with NRS-2002. The simplified random forest (RF) model outperformed other models with an AUC of 0.830 (95% CI, 0.805-0.854), and accuracy, sensitivity and specificity were 0.775, 0.835 and 0.742, respectively. We deployed an online application based on the simplified RF model to accurately estimate malnutrition probability in CRC patients without weight loss information (https://zzuwtt1998.shinyapps.io/dynnomapp/).

CONCLUSIONS

Nutrition Risk Screening 2002 was the optimal initial nutritional risk screening tool in the GLIM process. The RF model outperformed other models, and an online prediction tool was developed to properly identify patients at high risk of malnutrition.

Predicting S. aureus antimicrobial resistance with interpretable genomic space maps

Increasing antimicrobial resistance (AMR) represents a global healthcare threat. To decrease the spread of AMR and associated mortality, methods for rapid selection of optimal antibiotic treatment are urgently needed. Machine learning (ML) models based on genomic data to predict resistant phenotypes can serve as a fast screening tool prior to phenotypic testing. Nonetheless, many existing ML methods lack interpretability. Therefore, we present a methodology for visualization of sequence space and AMR prediction based on the non-linear dimensionality reduction method - generative topographic mapping (GTM). This approach, applied to AMR data of >5000 S. aureus isolates retrieved from the PATRIC database, yielded GTM models with reasonable accuracy for all drugs (balanced accuracy values ≥0.75). The Generative Topographic Maps (GTMs) represent data in the form of illustrative maps of the genomic space and allow for antibiotic-wise comparison of resistant phenotypes. The maps were also found to be useful for the analysis of genetic determinants responsible for drug resistance. Overall, the GTM-based methodology is a useful tool for both the illustrative exploration of the genomic sequence space and AMR prediction.

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.

Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods

OBJECTIVES

Over-the-counter (OTC) antibiotic use can cause antibiotic resistance, threatening global public health gains. To counter OTC use, this study used machine learning (ML) methods to identify predictors of OTC antibiotic use in rural Pune, India.

METHODS

The features of OTC antibiotic use were selected using stepwise logistic, lasso, random forest, XGBoost, and Boruta algorithms. Regression and tree-based models with all confirmed and tentatively important features were built to predict the use of OTC antibiotics. Five-fold cross-validation was used to tune the models' hyperparameters. The final model was selected based on the highest area under the curve (AUROC) with a 95% confidence interval (CI) and the lowest log-loss.

RESULTS

In rural Pune, the prevalence of OTC antibiotic use was 35.9% (95% CI, 31.6 to 40.5). The perception that buying medicines directly from a medicine shop/pharmacy is useful, using antibiotics for eye-related complaints, more household members consuming antibiotics, and longer duration and higher doses of antibiotic consumption in rural blocks and other social groups were confirmed as important features by the Boruta algorithm. The final model was the XGBoost+Boruta model with 7 predictors (AUROC, 0.934; 95% CI, 0.891 to 0.978; log-loss, 0.279) log-loss.

CONCLUSIONS

XGBoost+Boruta, with 7 predictors, was the most accurate model for predicting OTC antibiotic use in rural Pune. Using OTC antibiotics for eye-related complaints, higher consumption of antibiotics and the perception that buying antibiotics directly from a medicine shop/pharmacy is useful were identified as key factors for planning interventions to improve awareness about proper antibiotic use.

Unraveling resistance mechanisms in combination therapy: A comprehensive review of recent advances and future directions

Antimicrobial resistance is a global health threat. Misuse and overuse of antimicrobials are the main drivers in developing drug-resistant bacteria. The emergence of the rapid global spread of multi-resistant bacteria requires urgent multisectoral action to generate novel treatment alternatives. Combination therapy offers the potential to exploit synergistic effects for enhanced antibacterial efficacy of drugs. Understanding the complex dynamics and kinetics of drug interactions in combination therapy is crucial. Therefore, this review outlines the current advances in antibiotic resistance's evolutionary and genetic dynamics in combination therapies-exposed bacteria. Moreover, we also discussed four pivotal future research areas to comprehend better the development of antibiotic resistance in bacteria treated with combination strategies.

Assessing computational predictions of antimicrobial resistance phenotypes from microbial genomes

The advent of rapid whole-genome sequencing has created new opportunities for computational prediction of antimicrobial resistance (AMR) phenotypes from genomic data. Both rule-based and machine learning (ML) approaches have been explored for this task, but systematic benchmarking is still needed. Here, we evaluated four state-of-the-art ML methods (Kover, PhenotypeSeeker, Seq2Geno2Pheno and Aytan-Aktug), an ML baseline and the rule-based ResFinder by training and testing each of them across 78 species-antibiotic datasets, using a rigorous benchmarking workflow that integrates three evaluation approaches, each paired with three distinct sample splitting methods. Our analysis revealed considerable variation in the performance across techniques and datasets. Whereas ML methods generally excelled for closely related strains, ResFinder excelled for handling divergent genomes. Overall, Kover most frequently ranked top among the ML approaches, followed by PhenotypeSeeker and Seq2Geno2Pheno. AMR phenotypes for antibiotic classes such as macrolides and sulfonamides were predicted with the highest accuracies. The quality of predictions varied substantially across species-antibiotic combinations, particularly for beta-lactams; across species, resistance phenotyping of the beta-lactams compound, aztreonam, amoxicillin/clavulanic acid, cefoxitin, ceftazidime and piperacillin/tazobactam, alongside tetracyclines demonstrated more variable performance than the other benchmarked antibiotics. By organism, Campylobacter jejuni and Enterococcus faecium phenotypes were more robustly predicted than those of Escherichia coli, Staphylococcus aureus, Salmonella enterica, Neisseria gonorrhoeae, Klebsiella pneumoniae, Pseudomonas aeruginosa, Acinetobacter baumannii, Streptococcus pneumoniae and Mycobacterium tuberculosis. In addition, our study provides software recommendations for each species-antibiotic combination. It furthermore highlights the need for optimization for robust clinical applications, particularly for strains that diverge substantially from those used for training.

Generalizability of machine learning in predicting antimicrobial resistance in E. coli: a multi-country case study in Africa

BACKGROUND

Antimicrobial resistance (AMR) remains a significant global health threat particularly impacting low- and middle-income countries (LMICs). These regions often grapple with limited healthcare resources and access to advanced diagnostic tools. Consequently, there is a pressing need for innovative approaches that can enhance AMR surveillance and management. Machine learning (ML) though underutilized in these settings, presents a promising avenue. This study leverages ML models trained on whole-genome sequencing data from England, where such data is more readily available, to predict AMR in E. coli, targeting key antibiotics such as ciprofloxacin, ampicillin, and cefotaxime. A crucial part of our work involved the validation of these models using an independent dataset from Africa, specifically from Uganda, Nigeria, and Tanzania, to ascertain their applicability and effectiveness in LMICs.

RESULTS

Model performance varied across antibiotics. The Support Vector Machine excelled in predicting ciprofloxacin resistance (87% accuracy, F1 Score: 0.57), Light Gradient Boosting Machine for cefotaxime (92% accuracy, F1 Score: 0.42), and Gradient Boosting for ampicillin (58% accuracy, F1 Score: 0.66). In validation with data from Africa, Logistic Regression showed high accuracy for ampicillin (94%, F1 Score: 0.97), while Random Forest and Light Gradient Boosting Machine were effective for ciprofloxacin (50% accuracy, F1 Score: 0.56) and cefotaxime (45% accuracy, F1 Score:0.54), respectively. Key mutations associated with AMR were identified for these antibiotics.

CONCLUSION

As the threat of AMR continues to rise, the successful application of these models, particularly on genomic datasets from LMICs, signals a promising avenue for improving AMR prediction to support large AMR surveillance programs. This work thus not only expands our current understanding of the genetic underpinnings of AMR but also provides a robust methodological framework that can guide future research and applications in the fight against AMR.

Antimicrobial resistance crisis: could artificial intelligence be the solution?

Antimicrobial resistance is a global public health threat, and the World Health Organization (WHO) has announced a priority list of the most threatening pathogens against which novel antibiotics need to be developed. The discovery and introduction of novel antibiotics are time-consuming and expensive. According to WHO's report of antibacterial agents in clinical development, only 18 novel antibiotics have been approved since 2014. Therefore, novel antibiotics are critically needed. Artificial intelligence (AI) has been rapidly applied to drug development since its recent technical breakthrough and has dramatically improved the efficiency of the discovery of novel antibiotics. Here, we first summarized recently marketed novel antibiotics, and antibiotic candidates in clinical development. In addition, we systematically reviewed the involvement of AI in antibacterial drug development and utilization, including small molecules, antimicrobial peptides, phage therapy, essential oils, as well as resistance mechanism prediction, and antibiotic stewardship.

Deciphering complex antibiotic resistance patterns in Helicobacter pylori through whole genome sequencing and machine learning

Introduction

Helicobacter pylori (H.pylori, Hp) affects billions of people worldwide. However, the emerging resistance of Hp to antibiotics challenges the effectiveness of current treatments. Investigating the genotype-phenotype connection for Hp using next-generation sequencing could enhance our understanding of this resistance.

Methods

In this study, we analyzed 52 Hp strains collected from various hospitals. The susceptibility of these strains to five antibiotics was assessed using the agar dilution assay. Whole-genome sequencing was then performed to screen the antimicrobial resistance (AMR) genotypes of these Hp strains. To model the relationship between drug resistance and genotype, we employed univariate statistical tests, unsupervised machine learning, and supervised machine learning techniques, including the development of support vector machine models.

Results

Our models for predicting Amoxicillin resistance demonstrated 66% sensitivity and 100% specificity, while those for Clarithromycin resistance showed 100% sensitivity and 100% specificity. These results outperformed the known resistance sites for Amoxicillin (A1834G) and Clarithromycin (A2147), which had sensitivities of 22.2% and 87%, and specificities of 100% and 96%, respectively.

Discussion

Our study demonstrates that predictive modeling using supervised learning algorithms with feature selection can yield diagnostic models with higher predictive power compared to models relying on single single-nucleotide polymorphism (SNP) sites. This approach significantly contributes to enhancing the precision and effectiveness of antibiotic treatment strategies for Hp infections. The application of whole-genome sequencing for Hp presents a promising pathway for advancing personalized medicine in this context.

Machine learning-based antibiotic resistance prediction models: An updated systematic review and meta-analysis

BACKGROUND

The widespread use of antibiotics has led to a gradual adaptation of bacteria to these drugs, diminishing the effectiveness of treatments.

OBJECTIVE

To comprehensively assess the research progress of antibiotic resistance prediction models based on machine learning (ML) algorithms, providing the latest quantitative analysis and methodological evaluation.

METHODS

Relevant literature was systematically retrieved from databases, including PubMed, Embase and the Cochrane Library, from inception up to December 2023. Studies meeting predefined criteria were selected for inclusion. The prediction model risk of bias assessment tool was employed for methodological quality assessment, and a random-effects model was utilised for meta-analysis.

RESULTS

The systematic review included a total of 22 studies with a combined sample size of 43,628; 10 studies were ultimately included in the meta-analysis. Commonly used ML algorithms included random forest, decision trees and neural networks. Frequently utilised predictive variables encompassed demographics, drug use history and underlying diseases. The overall sensitivity was 0.57 (95% CI: 0.42-0.70; p< 0.001; I2= 99.7%), the specificity was 0.95 (95% CI: 0.79-0.99; p< 0.001; I2 = 99.9%), the positive likelihood ratio was 10.7 (95% CI: 2.9-39.5), the negative likelihood ratio was 0.46 (95% CI: 0.34-0.61), the diagnostic odds ratio was 23 (95% CI: 7-81) and the area under the receiver operating characteristic curve was 0.78 (95% CI: 0.74-0.81; p< 0.001), indicating a good discriminative ability of ML models for antibiotic resistance. However, methodological assessment and funnel plots suggested a high risk of bias and publication bias in the included studies.

CONCLUSION

This meta-analysis provides a current and comprehensive evaluation of ML models for predicting antibiotic resistance, emphasising their potential application in clinical practice. Nevertheless, stringent research design and reporting are warranted to enhance the quality and credibility of future studies. Future research should focus on methodological innovation and incorporate more high-quality studies to further advance this field.

Whole genome sequencing-based cataloguing of antibiotic resistant genes in piggery waste borne samples

The growing use of antibiotics in livestock is one of the main causes of the rapid global spread of antimicrobial resistance (AMR). However, extensive research on AMR in animals is currently absent. In this article, we provide the bacterial antibiotic resistance genes (ARGs) from piggery waste samples in West Bengal, India, based on whole genome sequencing (WGS). According to the study, there are alarmingly high levels of Enterobacteriaceae in piggery waste, especially slaughterhouse waste, that are resistant to beta-lactam, aminoglycoside, sulphonamide, and tetracycline. We found several plasmids carrying multidrug-resistant Enterobacteriaceae including resistant to last-resort medications like colistin and carbapenems. Our findings will serve as a guide for developing AMR management policies for livestock in India and aid in understanding the current AMR profiles of pigs. To grasp the actual situation with AMR in the pig sector, large scale sample screening must be done.

Genetic determinants underlying the progressive phenotype of β-lactam/β-lactamase inhibitor resistance in Escherichia coli

IMPORTANCE

The increased feasibility of whole-genome sequencing has generated significant interest in using such molecular diagnostic approaches to characterize difficult-to-treat, antimicrobial-resistant (AMR) infections. Nevertheless, there are current limitations in the accurate prediction of AMR phenotypes based on existing AMR gene database approaches, which primarily correlate a phenotype with the presence/absence of a single AMR gene. Our study utilized a large cohort of cephalosporin-susceptible Escherichia coli bacteremia samples to determine how increasing the dosage of narrow-spectrum β-lactamase-encoding genes in conjunction with other diverse β-lactam/β-lactamase inhibitor (BL/BLI) genetic determinants contributes to progressively more severe BL/BLI phenotypes. We were able to characterize the complexity of the genetic mechanisms underlying progressive BL/BLI resistance including the critical role of β-lactamase encoding gene amplification. For the diverse array of AMR phenotypes with complex mechanisms involving multiple genomic factors, our study provides an example of how composite risk scores may improve understanding of AMR genotype/phenotype correlations.

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.

Deep learning and single-cell phenotyping for rapid antimicrobial susceptibility detection in Escherichia coli

The rise of antimicrobial resistance (AMR) is one of the greatest public health challenges, already causing up to 1.2 million deaths annually and rising. Current culture-based turnaround times for bacterial identification in clinical samples and antimicrobial susceptibility testing (AST) are typically 18-24 h. We present a novel proof-of-concept methodological advance in susceptibility testing based on the deep-learning of single-cell specific morphological phenotypes directly associated with antimicrobial susceptibility in Escherichia coli. Our models can reliably (80% single-cell accuracy) classify untreated and treated susceptible cells for a lab-reference fully susceptible E. coli strain, across four antibiotics (ciprofloxacin, gentamicin, rifampicin and co-amoxiclav). For ciprofloxacin, we demonstrate our models reveal significant (p < 0.001) differences between bacterial cell populations affected and unaffected by antibiotic treatment, and show that given treatment with a fixed concentration of 10 mg/L over 30 min these phenotypic effects correlate with clinical susceptibility defined by established clinical breakpoints. Deploying our approach on cell populations from six E. coli strains obtained from human bloodstream infections with varying degrees of ciprofloxacin resistance and treated with a range of ciprofloxacin concentrations, we show single-cell phenotyping has the potential to provide equivalent information to growth-based AST assays, but in as little as 30 min.

Innovative applications of artificial intelligence in zoonotic disease management

Zoonotic diseases, transmitted between humans and animals, pose a substantial threat to global public health. In recent years, artificial intelligence (AI) has emerged as a transformative tool in the fight against diseases. This comprehensive review discusses the innovative applications of AI in the management of zoonotic diseases, including disease prediction, early diagnosis, drug development, and future prospects. AI-driven predictive models leverage extensive datasets to predict disease outbreaks and transmission patterns, thereby facilitating proactive public health responses. Early diagnosis benefits from AI-powered diagnostic tools that expedite pathogen identification and containment. Furthermore, AI technologies have accelerated drug discovery by identifying potential drug targets and optimizing candidate drugs. This review addresses these advancements, while also examining the promising future of AI in zoonotic disease control. We emphasize the pivotal role of AI in revolutionizing our approach to managing zoonotic diseases and highlight its potential to safeguard the health of both humans and animals on a global scale.

Ensemble-GNN: federated ensemble learning with graph neural networks for disease module discovery and classification

SUMMARY

Federated learning enables collaboration in medicine, where data is scattered across multiple centers without the need to aggregate the data in a central cloud. While, in general, machine learning models can be applied to a wide range of data types, graph neural networks (GNNs) are particularly developed for graphs, which are very common in the biomedical domain. For instance, a patient can be represented by a protein-protein interaction (PPI) network where the nodes contain the patient-specific omics features. Here, we present our Ensemble-GNN software package, which can be used to deploy federated, ensemble-based GNNs in Python. Ensemble-GNN allows to quickly build predictive models utilizing PPI networks consisting of various node features such as gene expression and/or DNA methylation. We exemplary show the results from a public dataset of 981 patients and 8469 genes from the Cancer Genome Atlas (TCGA).

AVAILABILITY AND IMPLEMENTATION

The source code is available at https://github.com/pievos101/Ensemble-GNN, and the data at Zenodo (DOI: 10.5281/zenodo.8305122).