Dataset Information

Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates.

ABSTRACT: Broadly neutralizing antibodies (bNAbs) targeting the HIV-1 envelope glycoprotein (Env) have promising utility in prevention and treatment of HIV-1 infection, and several are currently undergoing clinical trials. Due to the high sequence diversity and mutation rate of HIV-1, viral isolates are often resistant to specific bNAbs. Currently, resistant isolates are commonly identified by time-consuming and expensive in vitro neutralization assays. Here, we report machine learning classifiers that accurately predict resistance of HIV-1 isolates to 33 bNAbs. Notably, our classifiers achieved an overall prediction accuracy of 96% for 212 clinical isolates from patients enrolled in four different clinical trials. Moreover, use of gradient boosting machine - a tree-based machine learning method - enabled us to identify critical features, which had high accordance with epitope residues that distinguished between antibody resistance and sensitivity. The availability of an in silico antibody resistance predictor should facilitate informed decisions of antibody usage and sequence-based monitoring of viral escape in clinical settings.

SUBMITTER: Rawi R

PROVIDER: S-EPMC6789020 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates.

Rawi Reda R Mall Raghvendra R Shen Chen-Hsiang CH Farney S Katie SK Shiakolas Andrea A Zhou Jing J Bensmail Halima H Chun Tae-Wook TW Doria-Rose Nicole A NA Lynch Rebecca M RM Mascola John R JR Kwong Peter D PD Chuang Gwo-Yu GY

Scientific reports 20191011 1

Broadly neutralizing antibodies (bNAbs) targeting the HIV-1 envelope glycoprotein (Env) have promising utility in prevention and treatment of HIV-1 infection, and several are currently undergoing clinical trials. Due to the high sequence diversity and mutation rate of HIV-1, viral isolates are often resistant to specific bNAbs. Currently, resistant isolates are commonly identified by time-consuming and expensive in vitro neutralization assays. Here, we report machine learning classifiers that ac ...[more]

PMID: 31604961

Similar Datasets

Project description:Bacteroides fragilis group (BFG) are the most frequently recovered anaerobic bacteria from human infections, and resistance to frontline antibiotics is emerging. In the absence of routine antimicrobial susceptibility testing (AST) for BFG in most clinical settings, we assessed the utility of clinical and modern genomics tools to determine BFG species-level identification and resistance patterns. A total of 174 BFG clinical isolates supplemented with 20 archived carbapenem-resistant B. fragilis sensu stricto (BFSS) isolates underwent antimicrobial susceptibility testing, MALDI-ToF mass-spectrometry, and whole-genome sequencing (WGS). Bruker BioTyper and VITEK-MS MALDI-ToF systems demonstrated accurate species-level identifications (91% and 90% agreement, respectively) compared to average nucleotide identity (ANI) analysis of WGS data. Distinct β-lactamase gene profiles were observed between BFSS and non-fragilis Bacteroides species, with significantly higher MICs to piperacillin-tazobactam in B. vulgatus and B. thetaiotaomicron relative to BFSS (P ≤ 0.034). We also uncovered phylogenetic diversity at the genomospecies level between division I and division II BFSS (ANI <0.95) and demonstrate that division II BFSS strains harbor an increased capacity to achieve carbapenem resistance through chromosomal activation of the CfiA carbapenemase. Finally, we report that CfiA detection by the Bruker BioTyper Subtyping Module accurately detected carbapenem resistance in BFSS with positive and negative percent agreement of 94%/90% and 95%/95% compared to ertapenem and meropenem susceptibility, respectively. These comparative analyses indicate that resistance mechanisms are distinct at both the phenotypic and genomic level across species within the BFG and that modern MALDI-ToF identification systems can be used for accurate species-level identification and resistance prediction of the BFG. IMPORTANCE Anaerobic infections present unique challenges in terms of detecting and identifying the etiologic agent and selecting the optimal antimicrobial therapy. Antimicrobial resistance is increasing in anaerobic pathogens, and it is critical to understand the prevalence and mechanisms of resistance to commonly prescribed antimicrobial therapies. This study uses comparative genomics to validate clinical tools for species-level identification and phenotypic resistance prediction in 194 isolates of Bacteroides fragilis group (BFG) bacteria, which represent the most commonly isolated organisms among anaerobic infections. We demonstrate species-specific patterns in antimicrobial resistance and validate new strategies for species-level organism identification and phenotypic resistance prediction in a routine clinical laboratory setting. These findings expand our understanding and management of anaerobic infections and justify further investigations into the molecular basis for species-specific resistance patterns observed within this study.

Dataset Information

Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates.

Publications

Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets