The genome sequence of the spontaneously hypertensive rat: Analysis and functional significance

Abstract

The spontaneously hypertensive rat (SHR) is the most widely studied animal model of hypertension. Scores of SHR quantitative loci (QTLs) have been mapped for hypertension and other phenotypes. We have sequenced the SHR/OlaIpcv genome at 10.7-fold coverage by paired-end sequencing on the Illumina platform. We identified 3.6 million high-quality single nucleotide polymorphisms (SNPs) between the SHR/OlaIpcv and Brown Norway (BN) reference genome, with a high rate of validation (sensitivity 96.3%-98.0% and specificity 99%-100%). We also identified 343,243 short indels between the SHR/OlaIpcv and reference genomes. These SNPs and indels resulted in 161 gain or loss of stop codons and 629 frameshifts compared with the BN reference sequence. We also identified 13,438 larger deletions that result in complete or partial absence of 107 genes in the SHR/OlaIpcv genome compared with the BN reference and 588 copy number variants (CNVs) that overlap with the gene regions of 688 genes. Genomic regions containing genes whose expression had been previously mapped as cis-regulated expression quantitative trait loci (eQTLs) were significantly enriched with SNPs, short indels, and larger deletions, suggesting that some of these variants have functional effects on gene expression. Genes that were affected by major alterations in their coding sequence were highly enriched for genes related to ion transport, transport, and plasma membrane localization, providing insights into the likely molecular and cellular basis of hypertension and other phenotypes specific to the SHR strain. This near complete catalog of genomic differences between two extensively studied rat strains provides the starting point for complete elucidation, at the molecular level, of the physiological and pathophysiological phenotypic differences between individuals from these strains.

Figure 1.

Receiver operating characteristic (ROC) curves to determine optimal thresholds for SNP calling. Evaluation of sensitivity and specificity of SNP prediction using Illumina paired-end sequencing at various read depths and quality scores compared with 108 SNPs predicted in a 66-kb region of the genome sequenced using capillary sequencing (A) and the STAR SNP data set (B). Each curve represents a different read depth, and each point represents different consensus quality scores.

Figure 2.

Method of calling, distribution, and repeat content of SHR/OlaIpcv deletions. (A) Deletion calling in SHR/OlaIpcv compared with the reference BN genome. SHR/OlaIpcv read pairs (dark blue) align with expected span size to the BN reference (top black line). (Red curve) SHR/OlaIpcv read pairs that align with span size greater than expected, (red box) region of deletion, (brown vertical lines) illustrative SNPs between the SHR/OlaIpcv and BN reference genomes, (green vertical lines) short indels, (light blue arrow) a gene in the BN reference. (B) Distribution of length of deletions identified in the SHR/OlaIpcv genome. (C) Rank analysis of repeat content in SHR deletions; each line represents a different type of repeat element. Deletions were ranked according to size and separated into bins of 500 deletions. Median size of deletion within each bin was plotted against content for each type of repeat element.

Figure 3.

Relationship between distribution of different types of sequence variants. Density of sequence variants was calculated in 1-Mb windows of the BN reference genome, normalized to the number of bases in the window that were covered at threefold coverage or greater in the SHR/OlaIpcv sequence. (A) Correlation between SNP density and indel density. (B) Correlation between number of deletions per megabase and SNP density. (C) Correlation between number of deletions per megabase and indel density.

Figure 4.

Distribution and density of sequence variants. (A) Distribution of SNP density across the SHR/OlaIpcv genome, in 100-kb windows, calculated as in Figure 3. (B) Distribution of density of SNPs (green), indels (red), and larger deletions (blue inner circle) on SHR/OlaIpcv chromosomes 2, 13, and 15. (Blue outer circle) Sequence coverage of the SHR/OlaIpcv genome, (outermost circle) chromosomal banding, (innermost red bars) copy number variations.

Figure 5.

SNP and indel enrichment in cis-eQTL gene regions and promoters. (A) Boxplot showing SNP density in gene regions containing cis-eQTL genes compared with regions containing only non-cis-eQTL genes. (B) Boxplot showing indel density in cis-eQTL-containing gene regions compared with non-cis-eQTL-containing gene regions. (C) Boxplot showing SNP density in a 10-kb region of the promoter, centered on the transcription start site, of cis-eQTL genes and non-cis-eQTL genes. (D) Distribution of SNP density between cis-eQTL genes and non-cis-eQTL genes in a 40-kb region surrounding the transcription start site. (Boxes and whiskers) Median, interquartile range, and 95th percentile.