Enrichment of Retroviral Sequences in Brain Tissue from Patients with Severe Demyelinating Diseases

Abstract

Background: Our group has used deep sequencing to identify viral RNA signatures in human brain specimens. We have previously used this method to detect HSV1, GBV-C, and measles virus sequence in brain tissue from deceased donors. Deep sequencing was performed on brain specimens from a cohort of patients who died with progressive forms of MS, revealing evidence of increased expression of some human endogenous retrovirus (HERV) domains.

Objectives: Identify RNA sequences and new antigens involved in the pathogenesis of MS.

Methods: Deep sequencing was performed on RNA extracted from 12 progressive MS, 2 neuromyelitis optica (MS/NMO = demyelination group), 14 normal control, and 7 other neurologic disease (OND) control frozen brain specimens. The resulting single-ended 50 bp sequences (reads) were compared to a non redundant viral database representing (NRVDB) all 1.2 M viral records in GenBank. A retroviral gene catalog (RVGC) was prepared by identifying human genetic loci (GRCh37.p13) homologous to domains contained in the Gypsy 2.0 retro element database. Reads were aligned to the RVGC and human transcriptome with Bowtie2. The resulting viral hit rates (VHRs) were normalized by the number of high quality reads. The expression of human genes, including HERVs, was determined using Cufflinks. Comparisons between the groups were performed using the false discovery rate.

Results: Fifty to 131 million high quality reads per specimen were obtained. Comparison of the reads to the NRVDB suggested that the demyelination and OND specimens had higher VHRs against some retroviral sequences compared with the controls. This was confirmed by retroviral domain averaging. Gene expression analysis showed differential expression among some HERV sequences. Single read mapping revealed one envelope and one reverse transcriptase sequence record that were significantly enriched among the demyelination samples compared to the normal controls. Less restrictive (comprehensive) read mapping showed that 2 integrase, 2 core, 2 envelope, and 3 KRAB sequences that were overexpressed in the demyelination group.

Conclusions: These data demonstrate that some endogenous retroviral sequences are significantly overexpressed in these demyelination brain tissue specimens, but the magnitude of this overexpression is small. This is consistent with the concept of HERV activation as a part of the innate immune response.

Keywords: Deep sequencing; Endogenous retroviruses; HERV; Multiple sclerosis; Next generation sequencing; Progressive MS; RNA-seq.

Figure 1

Hit Rate Comparison of Frozen Brain Specimens. RNA was extracted from 14 normal control, 14 demyelination (including 2 NMO), and 7 other neurologic disease (OND) cryopreserved brain specimens. cDNA libraries were prepared and deep sequencing was performed. High quality sequences were matched to the non-redundant viral database using Mega BLAST with a word size of 28 bp. Hits (matches to the database) were normalized for the total number of high quality reads in each specimen and log₁₀ transformed, providing a ‘Log Hit Rate.’ Sequences mapping to non-vertebrate viruses (phages, plant and insect viruses) and cloning vectors were removed. Viral taxa not significantly enriched in any of the samples (e.g. VZV, EBV, and Enteroviruses) are not shown.

Figure 2

Retroviral Domain Discrimination Analysis. Sequencing hits (matches) to the RVGC database were binned into retroviral domains. Mean log₂ transformed and centered hit rates to the retroviral domain types in RVGC for the demyelination (MS), OND and normal control specimens. The results are clustered using Cluster 3.0 [41], showing distinctly different expression patterns in most demyelination, control and OND specimens.