Prediction of genome-wide imipenem resistance features in Klebsiella pneumoniae using machine learning

Li, Shanshan; Wu, Jun; Ma, Nan; Liu, Wenjia; Shao, Mengjie; Ying, Nanjiao; Zhu, Lei

doi:10.1099/jmm.0.001657

Cited by 3 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reduction in the cost and time required for WGS has enabled researchers to develop WGS-based antimicrobial susceptibility/resistance testing using machine-learning computational methods [ 86 , 87 ]. Machine-learning methods can effectively predict the imipenem resistance feature in K. pneumoniae and provide resistance sequence profiles for predicting resistance phenotypes and exploring potential resistance mechanisms [ 88 ]. By combining WGS of 1,113 pre- and post-treatment bacterial isolates with machine-learning analysis of 140,349 urinary tract infections and 7,365 wound infections, Stracy et al [ 89 ] reported that treatment-induced emergence of AMR could be predicted and minimized at the individual-patient level.…”

Section: Identification Of Amr Genes/determinants By Wgsmentioning

confidence: 99%

Whole Genome Sequencing: Applications in Clinical Bacteriology

Mustafa

2024

Med Princ Pract

View full text Add to dashboard Cite

The success in determining the whole genome sequence of a bacterial pathogen was first achieved in 1995 by determining the complete nucleotide sequence of Haemophilus influenzae Rd using the chain-termination method established by Sanger et al. in 1977 and automated by Hood et al. in 1987. However, this technology was laborious, costly, and time-consuming to obtain whole genome sequences. Since 2004, high-throughput next-generation sequencing technologies have been developed, which are highly efficient, require less time, and are cost-effective to perform whole genome sequencing (WGS) of all organisms, including bacterial pathogens. In recent years, the data obtained using WGS technologies coupled with bioinformatics analyses of the sequenced genomes have been projected to revolutionize clinical bacteriology practices. The WGS technologies have been used in the identification of bacterial species, strains, and genotypes from cultured organisms and directly from clinical specimens. WGS has also helped in determining resistance to antibiotics by the detection of antimicrobial resistance genes and point mutations. Furthermore, WGS data have helped in the epidemiological tracking and surveillance of pathogenic bacteria in healthcare settings as well as in communities. This review focuses on the above-mentioned applications of WGS in clinical bacteriology.

show abstract

Section: Identification Of Amr Genes/determinants By Wgsmentioning

confidence: 99%

Whole Genome Sequencing: Applications in Clinical Bacteriology

Mustafa

2024

Med Princ Pract

View full text Add to dashboard Cite

show abstract

Prediction of antimicrobial resistance in Klebsiella pneumoniae using genomic and metagenomic next-generation sequencing data

Zhou,

Yang,

Chen

et al. 2024

Journal of Antimicrobial Chemotherapy

View full text Add to dashboard Cite

Objectives Klebsiella pneumoniae is a significant pathogen with increasing resistance and high mortality rates. Conventional antibiotic susceptibility testing methods are time-consuming. Next-generation sequencing has shown promise for predicting antimicrobial resistance (AMR). This study aims to develop prediction models using whole-genome sequencing data and assess their feasibility with metagenomic next-generation sequencing data from clinical samples. Methods On the basis of 4170 K. pneumoniae genomes, the main genetic characteristics associated with AMR were identified using a LASSO regression model. Consequently, the prediction model was established, validated and optimized using clinical isolate read simulation sequences. To evaluate the efficacy of the model, clinical specimens were collected. Results Four predictive models for amikacin, ciprofloxacin, levofloxacin and piperacillin/tazobactam, initially had positive predictive values (PPVs) of 90%, 85%, 84% and 94%, respectively, when they were originally constructed. When applied to clinical specimens, their PPVs increased to 96%, 96%, 95% and 100%, respectively. Meanwhile, there were negative predictive values (NPVs) of 100% for ciprofloxacin and levofloxacin, and ‘not applicable’ (NA) for amikacin and piperacillin/tazobactam. Our method achieved antibacterial phenotype classification accuracy rates of 96.08% for amikacin, 96.15% for ciprofloxacin, 95.31% for levofloxacin and 100% for piperacillin/tazobactam. The sequence-based prediction antibiotic susceptibility testing (AST) reported results in an average time of 19.5 h, compared with the 67.9 h needed for culture-based AST, resulting in a significant reduction of 48.4 h. Conclusions These preliminary results demonstrated that the performance of prediction model for a clinically significant antimicrobial–species pair was comparable to that of phenotypic methods, thereby encouraging the expansion of sequence-based susceptibility prediction and its clinical validation and application.

show abstract

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

Kim,

Manuele,

Maguire

et al. 2024

Can. J. Microbiol.

View full text Add to dashboard Cite

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 utilized 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.

show abstract

Prediction of genome-wide imipenem resistance features in Klebsiella pneumoniae using machine learning

Abstract: Introduction. The resistance rate of Klebsiella pneumoniae ( K. pneumoniae ) to imipenem is increasing year by year, and the imipenem resistance mechanism of K. pneumoniae is complex. Therefore, it is urgent to develop new strategies to explore the resi… Show more

Cited by 3 publications

References 51 publications

Whole Genome Sequencing: Applications in Clinical Bacteriology

Whole Genome Sequencing: Applications in Clinical Bacteriology

Prediction of antimicrobial resistance in Klebsiella pneumoniae using genomic and metagenomic next-generation sequencing data

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

Contact Info

Product

Resources

About