Dataset Information

Predicting Phenotypic Polymyxin Resistance in Klebsiella pneumoniae through Machine Learning Analysis of Genomic Data.

ABSTRACT: Polymyxins are used as treatments of last resort for Gram-negative bacterial infections. Their increased use has led to concerns about emerging polymyxin resistance (PR). Phenotypic polymyxin susceptibility testing is resource intensive and difficult to perform accurately. The complex polygenic nature of PR and our incomplete understanding of its genetic basis make it difficult to predict PR using detection of resistance determinants. We therefore applied machine learning (ML) to whole-genome sequencing data from >600 Klebsiella pneumoniae clonal group 258 (CG258) genomes to predict phenotypic PR. Using a reference-based representation of genomic data with ML outperformed a rule-based approach that detected variants in known PR genes (area under receiver-operator curve [AUROC], 0.894 versus 0.791, P?=?0.006). We noted modest increases in performance by using a bacterial genome-wide association study to filter relevant genomic features and by integrating clinical data in the form of prior polymyxin exposure. Conversely, reference-free representation of genomic data as k-mers was associated with decreased performance (AUROC, 0.692 versus 0.894, P?=?0.015). When ML models were interpreted to extract genomic features, six of seven known PR genes were correctly identified by models without prior programming and several genes involved in stress responses and maintenance of the cell membrane were identified as potential novel determinants of PR. These findings are a proof of concept that whole-genome sequencing data can accurately predict PR in K. pneumoniae CG258 and may be applicable to other forms of complex antimicrobial resistance.IMPORTANCE Polymyxins are last-resort antibiotics used to treat highly resistant Gram-negative bacteria. There are increasing reports of polymyxin resistance emerging, raising concerns of a postantibiotic era. Polymyxin resistance is therefore a significant public health threat, but current phenotypic methods for detection are difficult and time-consuming to perform. There have been increasing efforts to use whole-genome sequencing for detection of antibiotic resistance, but this has been difficult to apply to polymyxin resistance because of its complex polygenic nature. The significance of our research is that we successfully applied machine learning methods to predict polymyxin resistance in Klebsiella pneumoniae clonal group 258, a common health care-associated and multidrug-resistant pathogen. Our findings highlight that machine learning can be successfully applied even in complex forms of antibiotic resistance and represent a significant contribution to the literature that could be used to predict resistance in other bacteria and to other antibiotics.

SUBMITTER: Macesic N

PROVIDER: S-EPMC7253370 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting Phenotypic Polymyxin Resistance in Klebsiella pneumoniae through Machine Learning Analysis of Genomic Data.

Macesic Nenad N Bear Don't Walk Oliver J OJ Pe'er Itsik I Tatonetti Nicholas P NP Peleg Anton Y AY Uhlemann Anne-Catrin AC

mSystems 20200526 3

Polymyxins are used as treatments of last resort for Gram-negative bacterial infections. Their increased use has led to concerns about emerging polymyxin resistance (PR). Phenotypic polymyxin susceptibility testing is resource intensive and difficult to perform accurately. The complex polygenic nature of PR and our incomplete understanding of its genetic basis make it difficult to predict PR using detection of resistance determinants. We therefore applied machine learning (ML) to whole-genome se ...[more]

PMID: 32457240

Similar Datasets

Project description:OBJECTIVES:Whole-genome sequencing potentially represents a single, rapid and cost-effective approach to defining resistance mechanisms and predicting phenotype, and strain type, for both clinical and epidemiological purposes. This retrospective study aimed to determine the efficacy of whole genome-based antimicrobial resistance prediction in clinical isolates of Escherichia coli and Klebsiella pneumoniae. METHODS:Seventy-four E. coli and 69 K. pneumoniae bacteraemia isolates from Oxfordshire, UK, were sequenced (Illumina HiSeq 2000). Resistance phenotypes were predicted from genomic sequences using BLASTn-based comparisons of de novo-assembled contigs with a study database of >100 known resistance-associated loci, including plasmid-associated and chromosomal genes. Predictions were made for seven commonly used antimicrobials: amoxicillin, co-amoxiclav, ceftriaxone, ceftazidime, ciprofloxacin, gentamicin and meropenem. Comparisons were made with phenotypic results obtained in duplicate by broth dilution (BD Phoenix). Discrepancies, either between duplicate BD Phoenix results or between genotype and phenotype, were resolved with gradient diffusion analyses. RESULTS:A wide variety of antimicrobial resistance genes were identified, including blaCTX-M, blaLEN, blaOKP, blaOXA, blaSHV, blaTEM, aac(3')-Ia, aac-(3')-IId, aac-(3')-IIe, aac(6')-Ib-cr, aadA1a, aadA4, aadA5, aadA16, aph(6')-Id, aph(3')-Ia, qnrB and qnrS, as well as resistance-associated mutations in chromosomal gyrA and parC genes. The sensitivity of genome-based resistance prediction across all antibiotics for both species was 0.96 (95% CI: 0.94-0.98) and the specificity was 0.97 (95% CI: 0.95-0.98). Very major and major error rates were 1.2% and 2.1%, respectively. CONCLUSIONS:Our method was as sensitive and specific as routinely deployed phenotypic methods. Validation against larger datasets and formal assessments of cost and turnaround time in a routine laboratory setting are warranted.

Project description:Resistance to polymyxin antibiotics is increasing. Without new antibiotic classes, combination therapy is often required. We systematically investigated bacterial killing with polymyxin-based combinations against multidrug-resistant (including polymyxin-resistant), carbapenemase-producing Klebsiella pneumoniae Monotherapies and double- and triple-combination therapies were compared to identify the most efficacious treatment using static time-kill studies (24 h, six isolates), an in vitro pharmacokinetic/pharmacodynamic model (IVM; 48 h, two isolates), and the mouse thigh infection model (24 h, six isolates). In static time-kill studies, all monotherapies (polymyxin B, rifampin, amikacin, meropenem, or minocycline) were ineffective. Initial bacterial killing was enhanced with various polymyxin B-containing double combinations; however, substantial regrowth occurred in most cases by 24 h. Most polymyxin B-containing triple combinations provided greater and more sustained killing than double combinations. Standard dosage regimens of polymyxin B (2.5 mg/kg of body weight/day), rifampin (600 mg every 12 h), and amikacin (7.5 mg/kg every 12 h) were simulated in the IVM. Against isolate ATH 16, no viable bacteria were detected across 5 to 25 h with triple therapy, with regrowth to ∼2-log10 CFU/ml occurring at 48 h. Against isolate BD 32, rapid initial killing of ∼3.5-log10 CFU/ml at 5 h was followed by a slow decline to ∼2-log10 CFU/ml at 48 h. In infected mice, polymyxin B monotherapy (60 mg/kg/day) generally was ineffective. With triple therapy (polymyxin B at 60 mg/kg/day, rifampin at 120 mg/kg/day, and amikacin at 300 mg/kg/day), at 24 h there was an ∼1.7-log10 CFU/thigh reduction compared to the starting inoculum for all six isolates. Our results demonstrate that the polymyxin B-rifampin-amikacin combination significantly enhanced in vitro and in vivo bacterial killing, providing important information for the optimization of polymyxin-based combinations in patients.

Dataset Information

Predicting Phenotypic Polymyxin Resistance in Klebsiella pneumoniae through Machine Learning Analysis of Genomic Data.

Publications

Predicting Phenotypic Polymyxin Resistance in Klebsiella pneumoniae through Machine Learning Analysis of Genomic Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets