AMR-meta: a k-mer and metafeature approach to classify antimicrobial resistance from high-throughput short-read metagenomics data

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.

Blanket antimicrobial resistance gene database with structural information, BOARDS, provides insights on historical landscape of resistance prevalence and effects of mutations in enzyme structure

Antimicrobial resistance (AMR) in pathogenic bacteria poses a significant threat to public health, yet there is still a need for development in the tools to deeply understand AMR genes based on genetic or structural information. In this study, we present an interactive web database named Blanket Overarching Antimicrobial-Resistance gene Database with Structural information (BOARDS, sbml.unist.ac.kr), a database that comprehensively includes 3,943 reported AMR gene information for 1,997 extended spectrum beta-lactamase (ESBL) and 1,946 other genes as well as a total of 27,395 predicted protein structures. These structures, which include both wild-type AMR genes and their mutants, were derived from 80,094 publicly available whole-genome sequences. In addition, we developed the rapid analysis and detection tool of antimicrobial-resistance (RADAR), a one-stop analysis pipeline to detect AMR genes across whole-genome sequencing (WGSs). By integrating BOARDS and RADAR, the AMR prevalence landscape for eight multi-drug resistant pathogens was reconstructed, leading to unexpected findings such as the pre-existence of the MCR genes before their official reports. Enzymatic structure prediction-based analysis revealed that the occurrence of mutations found in some ESBL genes was found to be closely related to the binding affinities with their antibiotic substrates. Overall, BOARDS can play a significant role in performing in-depth analysis on AMR.IMPORTANCEWhile the increasing antibiotic resistance (AMR) in pathogen has been a burden on public health, effective tools for deep understanding of AMR based on genetic or structural information remain limited. In this study, a blanket overarching antimicrobial-resistance gene database with structure information (BOARDS)-a web-based database that comprehensively collected AMR gene data with predictive protein structural information was constructed. Additionally, we report the development of a RADAR pipeline that can analyze whole-genome sequences as well. BOARDS, which includes sequence and structural information, has shown the historical landscape and prevalence of the AMR genes and can provide insight into single-nucleotide polymorphism effects on antibiotic degrading enzymes within protein structures.

Antimicrobial resistance and machine learning: past, present, and future

Machine learning has become ubiquitous across all industries, including the relatively new application of predicting antimicrobial resistance. As the first bibliometric review in this field, we expect it to inspire further research in this area. The review employs standard bibliometric indicators such as article count, citation count, and the Hirsch index (H-index) to evaluate the relevance and impact of the leading countries, organizations, journals, and authors in this field. VOSviewer and Biblioshiny programs are utilized to analyze citation and co-citation networks, collaboration networks, keyword co-occurrence, and trend analysis. The United States has the highest contribution with 254 articles, accounting for over 37.57% of the total corpus, followed by China (103) and the United Kingdom (78). Among 58 publishers, the top four publishers account for 45% of the publications, with Elsevier leading with 15% of the publications, followed by Springer Nature (12%), MDPI, and Frontiers Media SA with 9% each. Frontiers in Microbiology is the most frequent publication source (33 articles), followed by Scientific Reports (29 articles), PLoS One (17 articles), and Antibiotics (16 articles). The study reveals a substantial increase in research and publications on the use of machine learning to predict antibiotic resistance. Recent research has focused on developing advanced machine learning algorithms that can accurately forecast antibiotic resistance, and a range of algorithms are now being used to address this issue.

The K-mer antibiotic resistance gene variant analyzer (KARGVA)

Characterization of antibiotic resistance genes (ARGs) from high-throughput sequencing data of metagenomics and cultured bacterial samples is a challenging task, with the need to account for both computational (e.g., string algorithms) and biological (e.g., gene transfers, rearrangements) aspects. Curated ARG databases exist together with assorted ARG classification approaches (e.g., database alignment, machine learning). Besides ARGs that naturally occur in bacterial strains or are acquired through mobile elements, there are chromosomal genes that can render a bacterium resistant to antibiotics through point mutations, i.e., ARG variants (ARGVs). While ARG repositories also collect ARGVs, there are only a few tools that are able to identify ARGVs from metagenomics and high throughput sequencing data, with a number of limitations (e.g., pre-assembly, a posteriori verification of mutations, or specification of species). In this work we present the k-mer, i.e., strings of fixed length k, ARGV analyzer - KARGVA - an open-source, multi-platform tool that provides: (i) an ad hoc, large ARGV database derived from multiple sources; (ii) input capability for various types of high-throughput sequencing data; (iii) a three-way, hash-based, k-mer search setup to process data efficiently, linking k-mers to ARGVs, k-mers to point mutations, and ARGVs to k-mers, respectively; (iv) a statistical filter on sequence classification to reduce type I and II errors. On semi-synthetic data, KARGVA provides very high accuracy even in presence of high sequencing errors or mutations (99.2 and 86.6% accuracy within 1 and 5% base change rates, respectively), and genome rearrangements (98.2% accuracy), with robust performance on ad hoc false positive sets. On data from the worldwide MetaSUB consortium, comprising 3,700+ metagenomics experiments, KARGVA identifies more ARGVs than Resistance Gene Identifier (4.8x) and PointFinder (6.8x), yet all predictions are below the expected false positive estimates. The prevalence of ARGVs is correlated to ARGs but ecological characteristics do not explain well ARGV variance. KARGVA is publicly available at https://github.com/DataIntellSystLab/KARGVA under MIT license.

KARGAMobile: Android app for portable, real-time, easily interpretable analysis of antibiotic resistance genes via nanopore sequencing

Nanopore technology enables portable, real-time sequencing of microbial populations from clinical and ecological samples. An emerging healthcare application for Nanopore includes point-of-care, timely identification of antibiotic resistance genes (ARGs) to help developing targeted treatments of bacterial infections, and monitoring resistant outbreaks in the environment. While several computational tools exist for classifying ARGs from sequencing data, to date (2022) none have been developed for mobile devices. We present here KARGAMobile, a mobile app for portable, real-time, easily interpretable analysis of ARGs from Nanopore sequencing. KARGAMobile is the porting of an existing ARG identification tool named KARGA; it retains the same algorithmic structure, but it is optimized for mobile devices. Specifically, KARGAMobile employs a compressed ARG reference database and different internal data structures to save RAM usage. The KARGAMobile app features a friendly graphical user interface that guides through file browsing, loading, parameter setup, and process execution. More importantly, the output files are post-processed to create visual, printable and shareable reports, aiding users to interpret the ARG findings. The difference in classification performance between KARGAMobile and KARGA is minimal (96.2% vs. 96.9% f-measure on semi-synthetic datasets of 1 million reads with known resistance ground truth). Using real Nanopore experiments, KARGAMobile processes on average 1 GB data every 23-48 min (targeted sequencing - metagenomics), with peak RAM usage below 500MB, independently from input file sizes, and an average temperature of 49°C after 1 h of continuous data processing. KARGAMobile is written in Java and is available at https://github.com/Ruiz-HCI-Lab/KargaMobile under the MIT license.

AMR-meta: a k-mer and metafeature approach to classify antimicrobial resistance from high-throughput short-read metagenomics data

BACKGROUND

Antimicrobial resistance (AMR) is a global health concern. High-throughput metagenomic sequencing of microbial samples enables profiling of AMR genes through comparison with curated AMR databases. However, the performance of current methods is often hampered by database incompleteness and the presence of homology/homoplasy with other non-AMR genes in sequenced samples.

RESULTS

We present AMR-meta, a database-free and alignment-free approach, based on k-mers, which combines algebraic matrix factorization into metafeatures with regularized regression. Metafeatures capture multi-level gene diversity across the main antibiotic classes. AMR-meta takes in reads from metagenomic shotgun sequencing and outputs predictions about whether those reads contribute to resistance against specific classes of antibiotics. In addition, AMR-meta uses an augmented training strategy that joins an AMR gene database with non-AMR genes (used as negative examples). We compare AMR-meta with AMRPlusPlus, DeepARG, and Meta-MARC, further testing their ensemble via a voting system. In cross-validation, AMR-meta has a median f-score of 0.7 (interquartile range, 0.2-0.9). On semi-synthetic metagenomic data-external test-on average AMR-meta yields a 1.3-fold hit rate increase over existing methods. In terms of run-time, AMR-meta is 3 times faster than DeepARG, 30 times faster than Meta-MARC, and as fast as AMRPlusPlus. Finally, we note that differences in AMR ontologies and observed variance of all tools in classification outputs call for further development on standardization of benchmarking data and protocols.

CONCLUSIONS

AMR-meta is a fast, accurate classifier that exploits non-AMR negative sets to improve sensitivity and specificity. The differences in AMR ontologies and the high variance of all tools in classification outputs call for the deployment of standard benchmarking data and protocols, to fairly compare AMR prediction tools.