A RNA-Seq Analysis of the Rat Supraoptic Nucleus Transcriptome: Effects of Salt Loading on Gene Expression

Abstract

Magnocellular neurons (MCNs) in the hypothalamo-neurohypophysial system (HNS) are highly specialized to release large amounts of arginine vasopressin (Avp) or oxytocin (Oxt) into the blood stream and play critical roles in the regulation of body fluid homeostasis. The MCNs are osmosensory neurons and are excited by exposure to hypertonic solutions and inhibited by hypotonic solutions. The MCNs respond to systemic hypertonic and hypotonic stimulation with large changes in the expression of their Avp and Oxt genes, and microarray studies have shown that these osmotic perturbations also cause large changes in global gene expression in the HNS. In this paper, we examine gene expression in the rat supraoptic nucleus (SON) under normosmotic and chronic salt-loading SL) conditions by the first time using "new-generation", RNA sequencing (RNA-Seq) methods. We reliably detect 9,709 genes as present in the SON by RNA-Seq, and 552 of these genes were changed in expression as a result of chronic SL. These genes reflect diverse functions, and 42 of these are involved in either transcriptional or translational processes. In addition, we compare the SON transcriptomes resolved by RNA-Seq methods with the SON transcriptomes determined by Affymetrix microarray methods in rats under the same osmotic conditions, and find that there are 6,466 genes present in the SON that are represented in both data sets, although 1,040 of the expressed genes were found only in the microarray data, and 2,762 of the expressed genes are selectively found in the RNA-Seq data and not the microarray data. These data provide the research community a comprehensive view of the transcriptome in the SON under normosmotic conditions and the changes in specific gene expression evoked by salt loading.

Fig 1. RNA-Seq Analysis Results.

(A) Tukey box plot comparing the sample level distributions of gene expression data post normalization (Quantile(Log2(RPKM+2))) for 6 samples (3 controls, green-filled; 3 salt-loaded samples, red-filled). Distributions depicted consist of 26,313 gene expression measurements each. (B) covariance-based Principal Component Analysis (PCA) scatter-plot depicting relationships across 6 samples (3 controls, green-filled; 3 salt-loaded samples, red-filled) when normalized gene expression data (Quantile(Log2(RPKM+2))) is used for the 552 genes which are identified to have significant differential expression between salt-loaded (SL) condition and control. (C) correlation-based unclustered Heat-Map depicting relationships across 6 samples (3 controls, green-outlined; 3 salt-loaded samples, red-outlined) when normalized gene expression data (Quantile(Log2(RPKM+2))) is used for 552 genes identified to have significant differential expression between salt-loaded (SL) condition and control. (D) correlation-based clustered Heat-Map depicting relationships across 6 samples (3 controls, green-outlined; 3 salt-loaded samples, red-outlined) when normalized gene expression data (Quantile(Log2(RPKM+2))) is used for 552 genes identified to have significant differential expression between salt-loaded (SL) condition and control. Results reveal absence of outliers and excellent within and between sample class grouping.

Fig 2. Pie Chart showing Locations and Types of 552 selected, expressed genes (See columns N and O in S9 Table).

Fig 3. Venn diagram of intersections of RNA-Seq and Microarray data of post-noise filtered genes representing 7,506 microarray and 9,228 RNA-Seq genes.

Complete data are shown in S4 Table for RNA-Seq genes and S10 Table for microarray genes. Note that 6,466 unique genes are found in both platforms to intersect.

Fig 4. Venn diagram of intersections of RNA-Seq and microarray data after correcting for noise threshold and statistical analyses (see S2 Fig, Steps 11 and 12, and S4 Fig steps 6 and 7 for microarray).

There are 552 genes selected from the RNA-Seq data (see S9 Table) and 1030 unique genes selected from the microarray analysis (S13 Table). Note that 146 unique genes are found from both platforms to be unequivocally expressed and altered by salt-loading (See S14 and S15 Tables). Lower panel: Shows X-Y scatter plot of the fold changes in the 146 genes observed between Con & SL samples that were found in both the Microarray (X-axis) and RNA-Seq (Y-axis) data.

Fig 5. Network Analysis depicting gene products and known relationships between them for the second-ranked scoring network by Ingenuity (http://www.ingenuity.com/) when provided list of differentially expressed genes observed between salt-loaded and control by RNA-Seq (based on data in S9 Table).

Gene products are represented using circle-shaped symbols with connected edges drawn between them to describe interactions (solid edge = direct interaction, dashed edge = indirect interaction). Color-filled shapes indicate the direction of differential expression observed between salt-loaded and control (green = up, red = down). Circle-shaped symbols not color-filled represent gene products not observed differentially expressed between salt-loaded and control.