Comparing Viral Metagenomic Extraction Methods

Abstract

A crucial step in the molecular detection of viruses in clinical specimens is the efficient extraction of viral nucleic acids. The total yield of viral nucleic acid from a clinical specimen is dependent on the specimen's volume, the initial virus concentration and the effectiveness provided by the extraction method. Recent Next Generation Sequencing (NGS)-based diagnostic approaches (i.e. metagenomics) provide a molecular 'open view' into the sample, as they theoretically generate sequence reads of any nucleic acid present in a specimen in a statistically representative manner. However, since a higher virus-related read output promises better sensitivity in the subsequent bioinformatic analysis, the extraction method selected determines the reliability of diagnostic NGS. In this study nine commercially available kits for nucleic acid extraction were compared regarding the simultaneous isolation of DNA and RNA by real-time PCR,four of which were selected for subsequent comparison by NGS (QIAamp Viral RNA Mini Kit, QIAamp DNA Blood Mini Kit, QIAamp cador Pathogen Mini Kit and QIAamp MinElute Virus Spin Kit). The nucleic acid yields and the sequence read output were compared for four different model viruses comprising Reovirus, Orthomyxovirus, Orthopoxvirus and Paramyxovirus, each at defined but varying concentrations in the same sample. The total amount of nucleic acid was processed to sequence the RNA (as cDNA) and the DNA with quantification by Qubit and virus-specific quantitative real-time PCRs. NGS libraries were prepared for sequencing on the Illumina HiSeq 1500 system. Finally, the percentage of reads assignable to each virus was determined via mapping. Evaluation of different commercial nucleic acid extraction kits with four different viruses indicates little variation in the read numbers obtained for transcribed RNA or DNA by NGS. Since NGSis increasingly being used as a tool in diagnostics of infectious diseases, the individual steps of the complete process have to be validated carefully. Here we could show that for virus identification in liquid clinical specimens, any nucleic acid extraction kit that is performing well for PCR diagnostics can be used for NGS diagnostics as well and that the selection of the kit has only a minor impact on the yield of viral reads.