Enhanced Virus Detection and Metagenomic Sequencing in Patients with Meningitis and Encephalitis

Abstract

Meningitis and encephalitis are leading causes of central nervous system (CNS) disease and often result in severe neurological compromise or death. Traditional diagnostic workflows largely rely on pathogen-specific tests, sometimes over days to weeks, whereas metagenomic next-generation sequencing (mNGS) profiles all nucleic acid in a sample. In this single-center, prospective study, 68 hospitalized patients with known (n = 44) or suspected (n = 24) CNS infections underwent mNGS from RNA and DNA to identify potential pathogens and also targeted sequencing of viruses using hybrid capture. Using a computational metagenomic classification pipeline based on KrakenUniq and BLAST, we detected pathogen nucleic acid in cerebrospinal fluid (CSF) from 22 subjects, 3 of whom had no clinical diagnosis by routine workup. Among subjects diagnosed with infection by serology and/or peripheral samples, we demonstrated the utility of mNGS to detect pathogen nucleic acid in CSF, importantly for the Ixodes scapularis tick-borne pathogens Powassan virus, Borrelia burgdorferi, and Anaplasma phagocytophilum. We also evaluated two methods to enhance the detection of viral nucleic acid, hybrid capture and methylated DNA depletion. Hybrid capture nearly universally increased viral read recovery. Although results for methylated DNA depletion were mixed, it allowed the detection of varicella-zoster virus DNA in two samples that were negative by standard mNGS. Overall, mNGS is a promising approach that can test for multiple pathogens simultaneously, with efficacy similar to that of pathogen-specific tests, and can uncover geographically relevant infectious CNS disease, such as tick-borne infections in New England. With further laboratory and computational enhancements, mNGS may become a mainstay of workup for encephalitis and meningitis. IMPORTANCE Meningitis and encephalitis are leading global causes of central nervous system (CNS) disability and mortality. Current diagnostic workflows remain inefficient, requiring costly pathogen-specific assays and sometimes invasive surgical procedures. Despite intensive diagnostic efforts, 40 to 60% of people with meningitis or encephalitis have no clear cause of CNS disease identified. As diagnostic uncertainty often leads to costly inappropriate therapies, the need for novel pathogen detection methods is paramount. Metagenomic next-generation sequencing (mNGS) offers the unique opportunity to circumvent these challenges using unbiased laboratory and computational methods. Here, we performed comprehensive mNGS from 68 prospectively enrolled patients with known (n = 44) or suspected (n = 24) CNS viral infection from a single center in New England and evaluated enhanced methods to improve the detection of CNS pathogens, including those not traditionally identified in the CNS by nucleic acid detection. Overall, our work helps elucidate how mNGS can become integrated into the diagnostic toolkit for CNS infections.

Keywords: encephalitis; hybrid capture; meningitis; metagenomic sequencing; methylated DNA depletion; next-generation sequencing (NGS); virus.

FIG 1

Overview of methods for subject selection and mNGS. Enrollment (A), laboratory methods (B), and analysis methods (C) are shown. Enhanced laboratory methods for methylated DNA depletion and hybrid capture (dashed lines) were included for a subset of the samples as shown. Abbreviations: CSF, cerebrospinal fluid; WBC, white blood cell.

FIG 2

Number of infectious disease tests ordered and lengths of stay among subjects. (A) Distributions showing the number of infectious disease (ID)-related tests ordered per subject, stratified by clinical diagnosis category. ID tests were counted if ordered between hospital admission day 1 and hospital discharge. Box plots with horizontal bars represent medians and interquartile ranges for ID tests. Diamonds represent data points greater than 1.5× the IQR. (B) Scatterplot showing the number of ID tests versus length of stay per subject. Colors indicate clinical diagnosis categories. The LOS correlated with the number of total ID tests ordered (Spearman’s ρ = 0.65; P < 0.01). The final clinical diagnosis for viral pathogens is stated for cases whose number of ID tests or LOS was an outlier above the 3rd quartile.

FIG 3

Viral taxa identified in cerebrospinal fluid using mNGS with or without enhanced methods. A heat map shows viral taxa identified in each sample. Rows are viral taxa, and columns are samples, some with enhanced sequencing methods (HC and/or MDD). Only classifications with over 100 unique kmers, with at least 1 BLAST-confirmed read, and manually reviewed as noncontaminants are shown. Rows are grouped by RNA viruses (top section) or DNA viruses (bottom section). The color intensity corresponds to the RPM of the taxa. Red boxes correspond to detection in RNA libraries, while blue boxes correspond to detection in DNA libraries. Some DNA viruses were detected in RNA libraries (e.g., adenovirus in subject M121). Gray-shaded columns represent samples that did not undergo DNA or RNA sequencing. Samples in which a contaminant was found are included here as blank columns, and the contaminants are shown in Fig. S4 in the supplemental material. X’s represent the clinical diagnosis. Yellow bars indicate the CSF nucleated cell count for each subject. The four groupings of columns from the top left to the bottom right correspond to infections diagnosed by positive PCR, infections diagnosed by nonmolecular techniques, subjects with an unknown etiology, and negative controls, including extracted water.

FIG 4

Enhanced methods for mNGS. (A) Comparison of specific viral abundances among the non-computationally depleted reports for HC, MDD, and HC plus MDD for RNA samples (orange) and DNA samples (blue). (B to D) Hybrid capture improved the overall coverage for DNA and RNA viruses such as EBV (B), enterovirus (C), and JC polyomavirus 2 (D). Methylated DNA depletion improved the coverage for some DNA viruses such as JC polyomavirus 2 (D) but not others such as EBV, which utilizes host methylation in its life cycle (B).