Dataset Information

Predicting antimicrobial resistance in Pseudomonas aeruginosa with machine learning-enabled molecular diagnostics.

ABSTRACT: Limited therapy options due to antibiotic resistance underscore the need for optimization of current diagnostics. In some bacterial species, antimicrobial resistance can be unambiguously predicted based on their genome sequence. In this study, we sequenced the genomes and transcriptomes of 414 drug-resistant clinical Pseudomonas aeruginosa isolates. By training machine learning classifiers on information about the presence or absence of genes, their sequence variation, and expression profiles, we generated predictive models and identified biomarkers of resistance to four commonly administered antimicrobial drugs. Using these data types alone or in combination resulted in high (0.8-0.9) or very high (> 0.9) sensitivity and predictive values. For all drugs except for ciprofloxacin, gene expression information improved diagnostic performance. Our results pave the way for the development of a molecular resistance profiling tool that reliably predicts antimicrobial susceptibility based on genomic and transcriptomic markers. The implementation of a molecular susceptibility test system in routine microbiology diagnostics holds promise to provide earlier and more detailed information on antibiotic resistance profiles of bacterial pathogens and thus could change how physicians treat bacterial infections.

SUBMITTER: Khaledi A

PROVIDER: S-EPMC7059009 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting antimicrobial resistance in Pseudomonas aeruginosa with machine learning-enabled molecular diagnostics.

Khaledi Ariane A Weimann Aaron A Schniederjans Monika M Asgari Ehsaneddin E Kuo Tzu-Hao TH Oliver Antonio A Cabot Gabriel G Kola Axel A Gastmeier Petra P Hogardt Michael M Jonas Daniel D Mofrad Mohammad Rk MR Bremges Andreas A McHardy Alice C AC Häussler Susanne S

EMBO molecular medicine 20200212 3

Limited therapy options due to antibiotic resistance underscore the need for optimization of current diagnostics. In some bacterial species, antimicrobial resistance can be unambiguously predicted based on their genome sequence. In this study, we sequenced the genomes and transcriptomes of 414 drug-resistant clinical Pseudomonas aeruginosa isolates. By training machine learning classifiers on information about the presence or absence of genes, their sequence variation, and expression profiles, w ...[more]

PMID: 32048461

Similar Datasets

Project description:BackgroundPredicting antimicrobial resistance (AMR), a top global health threat, nationwide at an aggregate hospital level could help target interventions. Using machine learning, we exploit historical AMR and antimicrobial usage to predict future AMR.MethodsAntimicrobial use and AMR prevalence in bloodstream infections in hospitals in England were obtained per hospital group (Trust) and financial year (FY, April-March) for 22 pathogen-antibiotic combinations (FY2016-2017 to FY2021-2022). Extreme Gradient Boosting (XGBoost) model predictions were compared to the previous value taken forwards, the difference between the previous two years taken forwards and linear trend forecasting (LTF). XGBoost feature importances were calculated to aid interpretability.ResultsHere we show that XGBoost models achieve the best predictive performance. Relatively limited year-to-year variability in AMR prevalence within Trust-pathogen-antibiotic combinations means previous value taken forwards also achieves a low mean absolute error (MAE), similar to or slightly higher than XGBoost. Using the difference between the previous two years taken forward or LTF performs consistently worse. XGBoost considerably outperforms all other methods in Trusts with a larger change in AMR prevalence from FY2020-2021 (last training year) to FY2021-2022 (held-out test set). Feature importance values indicate that besides historical resistance to the same pathogen-antibiotic combination as the outcome, complex relationships between resistance in different pathogens to the same antibiotic/antibiotic class and usage are exploited for predictions. These are generally among the top ten features ranked according to their mean absolute SHAP values.ConclusionsYear-to-year resistance has generally changed little within Trust-pathogen-antibiotic combinations. In those with larger changes, XGBoost models can improve predictions, enabling informed decisions, efficient resource allocation, and targeted interventions.

Project description:UNLABELLED:Antimicrobial-resistant bacteria pose a serious threat in the clinic. This is particularly true for opportunistic pathogens that possess high intrinsic resistance. Though many studies have focused on understanding the acquisition of bacterial resistance upon exposure to antimicrobials, the mechanisms controlling intrinsic resistance are not well understood. In this study, we subjected the model opportunistic superbug Pseudomonas aeruginosa to 14 antimicrobials under highly controlled conditions and assessed its response using expression- and fitness-based genomic approaches. Our results reveal that gene expression changes and mutant fitness in response to sub-MIC antimicrobials do not correlate on a genomewide scale, indicating that gene expression is not a good predictor of fitness determinants. In general, fewer fitness determinants were identified for antiseptics and disinfectants than for antibiotics. Analysis of gene expression and fitness data together allowed the prediction of antagonistic interactions between antimicrobials and insight into the molecular mechanisms controlling these interactions. IMPORTANCE:Infections involving multidrug-resistant pathogens are difficult to treat because the therapeutic options are limited. These infections impose a significant financial burden on infected patients and on health care systems. Despite years of antimicrobial resistance research, we lack a comprehensive understanding of the intrinsic mechanisms controlling antimicrobial resistance. This work uses two fine-scale genomic approaches to identify genetic loci important for antimicrobial resistance of the opportunistic pathogen Pseudomonas aeruginosa. Our results reveal that antibiotics have more resistance determinants than antiseptics/disinfectants and that gene expression upon exposure to antimicrobials is not a good predictor of these resistance determinants. In addition, we show that when used together, genomewide gene expression and fitness profiling can provide mechanistic insights into multidrug resistance mechanisms.

Dataset Information

Predicting antimicrobial resistance in Pseudomonas aeruginosa with machine learning-enabled molecular diagnostics.

Publications

Predicting antimicrobial resistance in Pseudomonas aeruginosa with machine learning-enabled molecular diagnostics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets