Molecular Characterization of Microbiota in Cerebrospinal Fluid From Patients With CSF Shunt Infections Using Whole Genome Amplification Followed by Shotgun Sequencing

Abstract

Understanding the etiology of cerebrospinal fluid (CSF) shunt infections and reinfections requires detailed characterization of associated microorganisms. Traditionally, identification of bacteria present in the CSF has relied on culture methods, but recent studies have used high throughput sequencing of 16S rRNA genes. Here we evaluated the method of shotgun DNA sequencing for its potential to provide additional genomic information. CSF samples were collected from 3 patients near the beginning and end of each of 2 infection episodes. Extracted total DNA was sequenced by: (1) whole genome amplification followed by shotgun sequencing (WGA) and (2) high-throughput sequencing of the 16S rRNA V4 region (16S). Taxonomic assignments of sequences from WGA and 16S were compared with one another and with conventional microbiological cultures. While classification of bacteria was consistent among the 3 approaches, WGA provided additional insights into sample microbiological composition, such as showing relative abundances of microbial versus human DNA, identifying samples of questionable quality, and detecting significant viral load in some samples. One sample yielded sufficient non-human reads to allow assembly of a high-quality Staphylococcus epidermidis genome, denoted CLIMB1, which we characterized in terms of its MLST profile, gene complement (including putative antimicrobial resistance genes), and similarity to other annotated S. epidermidis genomes. Our results demonstrate that WGA directly applied to CSF is a valuable tool for the identification and genomic characterization of dominant microorganisms in CSF shunt infections, which can facilitate molecular approaches for the development of better diagnostic and treatment methods.

Keywords: CSF shunt infection; Staphylococcus epidermidis CLIMB1; cerebrospinal fluid; high throughput DNA sequencing; microbiota.

Figure 1

Relative abundance of sequence reads in CSF samples across major domains of life. 12 CSF samples were analyzed in duplicate by WGA. The samples came from 3 patients (P1, P2, P3), each having 2 infection episodes (I1, I2), with one sample collected near the beginning (B) and the other near the end (E) of the episode. Control samples consisted of a mock bacterial community (Mock) and a negative, no-template sample (Negative). Assignment of sequence reads to major domains of life was performed with Kraken: human (blue), bacteria (yellow), archaea (green), viruses (red), ambiguous, i.e. assignment to more than 1 domain (white), and unclassified, i.e. not assigned to any domain (grey). The lower panel (B) is an expanded view of (A), showing the top percentile range and revealing 2 samples in which viral sequences were detected.

Figure 2

Distribution of bacterial species in sequence reads from 10 CSF samples. Sample labels are as in Figure 1. 2 samples with low human DNA content were excluded. 21 species that yielded 5% or more bacterial reads in at least one sample are shown by name. Less frequent species assignments are grouped into the “Other” category. Reads are plotted as percentages of bacterial reads (A) and counts (B, C). Panel C shows the same data as B, but scaled to highlight the experimental samples, which had much lower counts than the mock positive control. qPCR measurements of 16S RNA are shown for comparison (D) in units of genome equivalents per ml. The gray bar (Mock) represents a computed, non-experimental value. Measurements above the limit of detection are marked with an asterisk.

Figure 3

Assembly of the S. epidermidis CLIMB1 genome. The circular display of the assembly shows, from outer to inner rings, the contigs, coding sequences on the forward strand, coding sequences on the reverse strand, RNA genes, coding sequences of putative antimicrobial resistance genes, coding sequences of putative virulence genes, GC content, and GC skew. The embedded table includes summary statistics of the assembly.

Figure 4

Phylogenetic tree of S. epidermidis, including CLIMB1 (red, center) and the most similar strains with known genomes, based on genomic sequence comparison. MLST profiles are indicated in parentheses and by color coding.