Novel rapid PCR for the detection of Ile491Phe rpoB mutation of Mycobacterium tuberculosis , a rifampicin-resistance-conferring mutation undetected by commercial assays

Wheeler

Sánchez-Busó

et al. 2019

Preprint

20Prediction of antibiotic resistance phenotypes from whole genome sequencing data by 21 machine learning methods has been proposed as a promising platform for the 22 development of sequence-based diagnostics. However, there has been no systematic 23 evaluation of factors that may influence performance of such models, how they might 24 apply to and vary across clinical populations, and what the implications might be in the 25 clinical setting. Here, we performed a meta-analysis of seven large Neisseria 26 gonorrhoeae datasets, as well as Klebsiella pneumoniae and Acinetobacter baumannii 27 datasets, with whole genome sequence data and antibiotic susceptibility phenotypes 28 using set covering machine classification, random forest classification, and random forest 29 regression models to predict resistance phenotypes from genotype. We demonstrate how 30 model performance varies by drug, dataset, resistance metric, and species, reflecting the 31 complexities of generating clinically relevant conclusions from machine learning-derived 32 models. Our findings underscore the importance of incorporating relevant biological and 33 epidemiological knowledge into model design and assessment and suggest that doing so 34 can inform tailored modeling for individual drugs, pathogens, and clinical populations. We 35 further suggest that continued comprehensive sampling and incorporation of up-to-date 36 whole genome sequence data, resistance phenotypes, and treatment outcome data into 37 model training will be crucial to the clinical utility and sustainability of machine learning-38 based molecular diagnostics. 39 40 Author Summary: 41 3 Machine learning-based prediction of antibiotic resistance from bacterial genome 42 sequences represents a promising tool to rapidly determine the antibiotic susceptibility 43 profile of clinical isolates and reduce the morbidity and mortality resulting from 44 inappropriate and ineffective treatment. However, while there has been much focus on 45 demonstrating the diagnostic potential of these modeling approaches, there has been 46 little assessment of potential caveats and prerequisites associated with implementing 47 predictive models of drug resistance in the clinical setting. Our results highlight significant 48 biological and technical challenges facing the application of machine learning-based 49 prediction of antibiotic resistance as a diagnostic tool. By outlining specific factors 50 affecting model performance, our findings provide a framework for future work on 51 modeling drug resistance and underscore the necessity of continued comprehensive 52 sampling and reporting of treatment outcome data for building reliable and sustainable 53 diagnostics. 54 55 56 57 58 4 Introduction: 59

Section: Discussionmentioning

confidence: 99%

Evaluation of parameters affecting performance and reliability of machine learning-based antibiotic susceptibility testing from whole genome sequencing data

Wheeler

Sánchez-Busó

et al. 2019

Preprint

“…These diagnostics must maintain high sensitivity to remain useful clinically. However, the emergence of novel resistance mechanisms will inevitably lead to a decline in sensitivity, perhaps exacerbated by variable prevalence of resistance determinants across populations ( 6 ). Key to maintaining sensitivity is therefore sustained sampling and routine updating of the diagnostics with newly described resistance determinants.…”

mentioning

confidence: 99%

Quantifying the surveillance required to sustain genetic marker-based antibiotic resistance diagnostics

Kissler

Lipsitch

et al. 2019

Preprint

Diagnostics that minimize the time to selection of an appropriate antibiotic treatment represent an important strategy in addressing the challenge of antimicrobial resistance (AMR). Among this class of diagnostics, the use of pathogen genotype to predict AMR phenotype has been facilitated by advances in rapid sequencing platforms. A longstanding objection to this approach, however, is that the emergence of novel resistance mechanisms will inevitably lead to a decline in the sensitivity of these diagnostics. Here, we show that while the sensitivities of some genetic markers of resistance remain stably high, sensitivities of other markers rapidly decline, as expected, due to the emergence of novel resistance variants. We then present a simple mathematical framework that defines the sampling and phenotypic testing rates needed for early detection of novel resistance variants and thus demonstrate how surveillance can help maintain the sensitivity and utility of sequence-based AMR diagnostics.One sentence summaryTargeted sampling strategies are necessary for early detection of novel resistance mechanisms and sustainability of genotype-based detection of novel resistance mechanisms and sustainability of genotype-based diagnostics.

“…Nucleic acid-based diagnostics that enable rapid pathogen identification and prediction of drug susceptibility profiles can improve clinical decision-making, reduce inappropriate antibiotic use, and help address the challenge of antibiotic resistance 1–3 . However, the sensitivity of such diagnostics may be undermined by undetected genetic variants 4–12 . Pathogen surveillance programs aimed at early detection of novel variants are crucial to ensuring the clinical utility and sustainability of these diagnostics.…”

Section: Introductionmentioning

confidence: 99%

“…Diagnostic escape associated with genotype-based diagnostics for antibiotic resistance are the result of resistance-conferring variants ( e.g. , mutations or accessory genes) not accounted for in the diagnostic’s panel of resistance markers 4 and require phenotypic testing to be uncovered.…”

Section: Introductionmentioning

confidence: 99%

Targeted surveillance strategies for efficient detection of novel antibiotic resistance variants

Kissler

Mortimer

et al. 2020

Preprint

20Genotype-based diagnostics for antibiotic resistance represent a promising alternative to 21 empiric therapy, reducing inappropriate and ineffective antibiotic use. However, because 22 103 Results: 104Composition of the datasets. 105The datasets (Table 1) were biased across patient demographics and/or geographic 106 regions (Tables S1 and S2). Isolates from men and men who have sex with men (MSM) 107 were overrepresented in datasets 1 and 2 compared to overall gonorrhea incidence in 108 men and MSM in the US and Australia, respectively, during the study periods (Table S2, 109 P < 0.001 for both datasets by chi-squared test of men vs. women and MSM vs. non-110 MSM in dataset vs. reported incidence). Dataset 4 was comprised exclusively of isolates 111 from men 31 . While it is difficult to estimate the prevalence of pharyngeal gonococcal 112 infections, as they tend to be asymptomatic 32 , pharyngeal isolates represented 4% and 113