Transcriptomics Reveal Antiviral Gene Induction in the Egyptian Rousette Bat Is Antagonized In Vitro by Marburg Virus Infection

Abstract

The Egyptian rousette bat (ERB) is the only known Marburg virus (MARV) reservoir host. ERBs develop a productive MARV infection with low viremia and shedding but no overt disease, suggesting this virus is efficiently controlled by ERB antiviral responses. This dynamic would contrast with humans, where MARV-mediated interferon (IFN) antagonism early in infection is thought to contribute to the severe, often fatal disease. The newly-annotated ERB genome and transcriptome have now enabled us to use a custom-designed NanoString nCounter ERB CodeSet in conjunction with RNA-seq to investigate responses in a MARV-infected ERB cell line. Both transcriptomic platforms correlated well and showed that MARV inhibited the antiviral program in ERB cells, while an IFN antagonism-impaired MARV was less efficient at suppressing the response gene induction, phenotypes previously reported for primate cells. Interestingly, and despite the expansion of IFN loci in the ERB genome, neither MARV showed specific induction of almost any IFN gene. However, we detected an upregulation of putative, unannotated ERB antiviral paralogs, as well as an elevated basal expression in uninfected ERB cells of key antiviral genes.

Keywords: Egyptian rousette bat; Marburg virus; VP35; transcriptomics.

Figure 1

The correlation comparison between nCounter and RNA-seq. DEGs (differentially expressed genes) common to both the transcriptomic platform datasets were graphed against each other. RNA-seq log2FC (fold change) are shown on the x-axis and nCounter log2FC are shown on the y-axis. Pearson’s correlation analysis was performed to determine the relationships between datasets. The line represents the regression analysis. MARV WT correlation comparison is not shown because the two platforms shared no more than one DEG in common. (A) SeV comparison is shown for all three time points. (B) MARV VP35mut comparison is shown for all three time points.

Figure 2

The shared DEGs between viruses within platforms and between platforms at each time point. (A) Numbers found in the center represent the total DEGs shared between all three viruses. The intersection of the green and yellow numbers represent the genes shared between SeV and MARV WT. The intersection of the blue and yellow numbers represent the genes shared between SeV and MARV WT. (B) The total number of DEGs in common for each transcriptomic platform are shown in green. The DEGs only found in the nCounter dataset are shown in blue. The DEGs only found in the RNA-seq dataset are shown in red.

Figure 3

The nCounter codeset matched with DEGs from RNA-seq. A total of 221 ERB genes were chosen for the nCounter codeset, most of them involved in the antiviral responses. The scale is log2FC. *IFNA denotes the combined expression of the IFNA subtypes in the RNA-seq. No individual IFNA was significantly differentially regulated. *LTK and IFI44 probes were developed using the P. alecto genome; these transcripts are not present in the transcriptome used for RNA-seq alignment. Genes described as “-like” are not officially annotated and the locus tags correspond as follows: MX1-like: LOC107507192; MX2-like: LOC107507191; STAT5-like: LOC107513821; ZAP70-like: LOC107509971; IFNL1-like: LOC107521777; IFNL3-like: LOC107520938; IFITM1-like: LOC107506511; IFITM3-like: LOC107506941; OAS3-like: LOC107513228.

Figure 4

The top five canonical pathway and top 20 upstream regulators comparison between nCounter and RNA-seq for MARVmut. (A) The top 5 canonical pathways ranked by p-value. The key indicates which pathways are present in both platforms and which are present in only one. The z-score indicates an activation score calculated by IPA (Ingenuity Pathway Analysis) for each pathway. Positive values indicate that the genes in the dataset are behaving in a way that indicates positive regulation. Negative values indicate that the genes in the dataset are behaving in a way that indicates negative regulation. Black panels indicate canonical pathways that have a significant p-value but lack a z-score. (B) The top 20 upstream regulators ranked by p-value. The key indicates which pathways are present in both platforms and which are present in only one. The z-score indicates an activation score calculated by IPA for each pathway. Positive values indicate that the genes in the dataset are behaving in a way that indicates positive regulation. Negative values indicate that the genes in the dataset are behaving in a way that indicates negative regulation.

Figure 5

The IFN gene induction and baseline expression of innate immune genes. (A) The IFN gene induction in RoNi cells during infection. Transcripts per million (TPM) were graphed for each time point and infection condition. Error bars represent SD of three biological replicates. IFNs labeled with an * indicated aggregated expression of all subtypes. This includes the 12 IFNA subtypes, 22 IFNW subtypes, and 9 IFND subtypes. IFNL has not been annotated in the rousette genome, so this value represents the aggregation of LOC107520937, LOC107521776, LOC107520939, LOC107520938, and LOC107521777, all termed to be “IFNL-like” genes. (B) Samples include RoNi Mock cells (9 replicates) compared to transformed fibroblasts (343 replicates) and kidney-cortex cells (45 replicates) from the GTEx database. Outliers in the datasets were removed if the value fell beyond 2.5 SDs from the mean. Points represent the mean and the error bars correspond to SD. (C) Isoform expression of IFNAR variants is shown. Same datasets as in (B). Isoforms falling into the categories of long, truncated, and soluble were aggregated and plotted. Starred genes correspond as follows: OAS2: LOC107501264; OAS3: LOC107513228; MX1: LOC107498547; MX1_2: LOC107504926; MX1_3: LOC107507190; MX1_4: LOC107507192; MX2: LOC107507191; MX2_2: LOC107507193; IFNL1: LOC107521777; IFNL3: LOC107520938.