Prediction of Antimicrobial Resistance in Gram-Negative Bacteria From Whole-Genome Sequencing Data.

Pieter-Jan Van Camp,David B Haslam,Aleksey Porollo

doi:10.3389/fmicb.2020.01013

Abstract

BackgroundEarly detection of antimicrobial resistance in pathogens and prescription of more effective antibiotics is a fast-emerging need in clinical practice. High-throughput sequencing technology, such as whole genome sequencing (WGS), may have the capacity to rapidly guide the clinical decision-making process. The prediction of antimicrobial resistance in Gram-negative bacteria, often the cause of serious systemic infections, is more challenging as genotype-to-phenotype (drug resistance) relationship is more complex than for most Gram-positive organisms.Methods and FindingsWe have used NCBI BioSample database to train and cross-validate eight XGBoost-based machine learning models to predict drug resistance to cefepime, cefotaxime, ceftriaxone, ciprofloxacin, gentamicin, levofloxacin, meropenem, and tobramycin tested in Acinetobacter baumannii, Escherichia coli, Enterobacter cloacae, Klebsiella aerogenes, and Klebsiella pneumoniae. The input is the WGS data in terms of the coverage of known antibiotic resistance genes by shotgun sequencing reads. Models demonstrate high performance and robustness to class imbalanced datasets.ConclusionWhole genome sequencing enables the prediction of antimicrobial resistance in Gram-negative bacteria. We present a tool that provides an in silico antibiogram for eight drugs. Predictions are accompanied with a reliability index that may further facilitate the decision making process. The demo version of the tool with pre-processed samples is available at https://vancampn.shinyapps.io/wgs2amr/. The stand-alone version of the predictor is available at https://github.com/pieterjanvc/wgs2amr/.

Highlights

Since the discovery and widespread use of antibiotics (AB) in the early 20th century, resistance to those same AB has generally developed rapidly; often even within the first years of introduction (Marston et al, 2016)
Whole genome sequencing enables the prediction of antimicrobial resistance in Gram-negative bacteria
We present a tool that provides an in silico antibiogram for eight drugs

Summary

Introduction

Since the discovery and widespread use of antibiotics (AB) in the early 20th century, resistance to those same AB has generally developed rapidly; often even within the first years of introduction (Marston et al, 2016). Many bacteria have developed antibiotic resistance (ABR) to most of the major classes of AB, often seen in the Gramnegatives (Centers for Disease Control and Prevention, 2018). Effective treatment of these infections requires knowledge of the organism’s susceptibility to the various AB, currently obtained by culturing bacteria in the clinical laboratory and subsequent testing for commonly used AB. Detection of antimicrobial resistance in pathogens and prescription of more effective antibiotics is a fast-emerging need in clinical practice. The prediction of antimicrobial resistance in Gram-negative bacteria, often the cause of serious systemic infections, is more challenging as genotype-to-phenotype (drug resistance) relationship is more complex than for most Gram-positive organisms

Methods

Results

Discussion

Conclusion