Transcriptome-wide analysis of alternative RNA splicing events in Epstein-Barr virus-associated gastric carcinomas

Abstract

Multiple human diseases including cancer have been associated with a dysregulation in RNA splicing patterns. In the current study, modifications to the global RNA splicing landscape of cellular genes were investigated in the context of Epstein-Barr virus-associated gastric cancer. Global alterations to the RNA splicing landscape of cellular genes was examined in a large-scale screen from 295 primary gastric adenocarcinomas using high-throughput RNA sequencing data. RT-PCR analysis, mass spectrometry, and co-immunoprecipitation studies were also used to experimentally validate and investigate the differential alternative splicing (AS) events that were observed through RNA-seq studies. Our study identifies alterations in the AS patterns of approximately 900 genes such as tumor suppressor genes, transcription factors, splicing factors, and kinases. These findings allowed the identification of unique gene signatures for which AS is misregulated in both Epstein-Barr virus-associated gastric cancer and EBV-negative gastric cancer. Moreover, we show that the expression of Epstein-Barr nuclear antigen 1 (EBNA1) leads to modifications in the AS profile of cellular genes and that the EBNA1 protein interacts with cellular splicing factors. These findings provide insights into the molecular differences between various types of gastric cancer and suggest a role for the EBNA1 protein in the dysregulation of cellular AS.

Fig 1. Identification of alternative splicing events in gastric cancer.

(A) Overview of the strategy used to identify the changes in alternative splicing in GC. (B) Classification of the TCGA RNA sequencing data for GC and healthy tissues. (C) The splicing events list for both EBV-negative gastric adenocarcinomas (TNoV, Tumors, no virus) and EBV-associated gastric carcinomas (EBVaGC, TEBV, Tumors with EBV) compared the global splicing patterns with normal tissues (NNoV, Normal tissues, no virus) was filtered to keep only significant ASEs.

Fig 2. Global profiling of alternative splicing event modifications in EBVaGC.

Hierarchical cluster and heatmap representation of alternative splicing events modified in EBVaGC tissues. The row at the top shows the clustering information in the form of a dendogram and the similarity relationships among the alternative splicing events and patients. The column at the left of the heatmap shows the different clusters associated with the PSI values. The heatmap shows PSI values for EBVaGC tissues (TEBV, Tumors with EBV, in red) compared with normal tissues (NNoV, Normal tissues, no virus, in green).

Fig 3. Comparison between EBV-negative and EBV-associated gastric cancer.

(A) Heatmap representation of isoform ratios (PSI values) for EBV-negative gastric adenocarcinomas tissues. EBV-negative gastric adenocarcinomas tissues (TNoV) are shown in blue, and the comparative healthy tissues are shown in green (NNoV). (B) Comparison of the cellular genes with dysregulated ASEs between EBVaGC and EBV-negative GC tissues. (C) The list displays common differentially spliced transcripts for both EBV-negative and EBVaGC with the corresponding Delta PSI values, the associated gene expression (in Log₂), and the related biological processes.

Fig 4. Validation of ASEs dysregulated in gastric cancer.

(A) Overview of the two isoforms encoded by PTBP2 and TPM1 genes. The exons are represented in red and the intervening introns are displayed as thin black lines (not to scale). The primers used to detect the isoforms by RT-PCR are presented in gray and the sizes of the expected amplicons are also presented. (B) The cDNAs acquired from gastric tissues were analyzed by PCR using specific primers to detect both isoforms of the transcripts encoded by the PTBP2 and TPM1 genes. Capillary electrophoregrams of the PCR reactions are presented. The positions and the amplitude of the detected amplicons are emphasized by red boxes. The positions of the internal markers are also indicated. (C) Correlation between PSI values obtained from RNA-Seq and RT-PCR data. The analysis was performed on seven selected ASEs (CAPN14, PLA2G4F, PTBP2, S100A1, SLC52A1, SOGA2, and TPM1). In all cases, the changes in AS levels detected by RT-PCR and the ones revealed through transcriptome sequencing displayed high levels of correlation (R = 0.93).

Fig 5. RNA splicing factors in gastric cancer.

(A) Changes in expression profile of splicing factors in GC tissues (TNoV, Tumors, no virus) compared with the expression in normal tissues. Genes encoding splicing factors for which expression levels were modified by more than 2-fold are presented. Red indicates an increase in gene expression and blue indicates a decrease in gene expression (B) Misregulation of splicing factors alternative splicing in GC (TNoV, Tumors, no virus). The delta PSI values are represented in red (negative delta PSI values) and in yellow (positive delta PSI values). (C) Expression levels of DHX15 in patients with or without tumors (left panel). Kaplan-Meier overall survival curve (right panel) for patients expressing high (red) or low (blue) levels of DHX15.

Fig 6. Modifications to AS of 96 transcripts in response to knockdown of specific splicing factors with siRNAs.

Using specific siRNAs, eighteen splicing factors (U2AF2, U2AF1, SYNCRIP, SFRS9, SFRS6, SFRS2, NOVA1, KHSRP, KHDRBS1, HNRPU, HNRPR, HNRPM, HNRPK, HNRPH1, HNRPF, HNRPD, HNRPC, and HNRPA1) were individually knocked-down in various cell lines to evaluate their implication in splicing of 96 different transcripts. Asterisks (top) indicate transcripts for which AS was altered in GC. Individual knockdowns and ASEs are presented to indicate which knockdowns produced a shift in AS in various cell lines (PC-3, SKOV3, NIH:OVCAR-3, MDA-MB-231, MCF7). Each individual column represents a different knockdown performed with specific siRNAs. The changes in PSI values are indicated. The map displays the changes in PSI values in a color-coded scale. White areas indicate no shifts.

Fig 7. Involvement of EBNA1 in alternative splicing.

(A) Immunoblotting analysis using anti-HA antibody for the detection of EBNA1-HA-FLAG protein in cell lysates from a stable HEK293T cell line expressing EBNA1. Control HEK293T cells (T(-)) were also used in this assay. (B) List of ASEs common to EBVaGC and EBNA1-expressing cells. (C) Example of a modified ASE following the expression of EBNA1. Overview of the two isoforms encoded by OSBPL9 gene. Exons are represented in red and the intervening introns are displayed as thin black lines (not to scale). The primers used to detect the isoforms by RT-PCR assays are presented in gray and the sizes of the expected amplicons are also specified (top panel). RT-PCR reactions were performed on control cells (T(-)) and cells expressing EBNA1 using specific primers to detect both isoforms of the transcripts encoded by the OSBPL9 gene. Capillary electrophoresis assays were performed and an image of the detected reaction products is presented (lower panel). The positions of the expected amplicons are shown by arrows. (D) Mass spectrometry analysis of nuclear proteins interacting with EBNA1. The average ratios (MS/MS counts) of the EBNA1 affinity purification-mass spectrometry experiments were plotted versus the total intensities. (E) Validation of the interaction between EBNA1 and splicing factor hnRNP H1. Nuclear extracts were immunoprecipitated with anti-HA. The extracts (input) and immunoprecipitates (IP-EBNA1) were analyzed by immunoblotting and probed with the indicated antibodies.