Genetic architecture of heart mitochondrial proteome influencing cardiac hypertrophy

Abstract

Mitochondria play an important role in both normal heart function and disease etiology. We report analysis of common genetic variations contributing to mitochondrial and heart functions using an integrative proteomics approach in a panel of inbred mouse strains called the Hybrid Mouse Diversity Panel (HMDP). We performed a whole heart proteome study in the HMDP (72 strains, n=2-3 mice) and retrieved 848 mitochondrial proteins (quantified in ≥50 strains). High-resolution association mapping on their relative abundance levels revealed three trans-acting genetic loci on chromosomes (chr) 7, 13 and 17 that regulate distinct classes of mitochondrial proteins as well as cardiac hypertrophy. DAVID enrichment analyses of genes regulated by each of the loci revealed that the chr13 locus was highly enriched for complex-I proteins (24 proteins, P=2.2E-61), the chr17 locus for mitochondrial ribonucleoprotein complex (17 proteins, P=3.1E-25) and the chr7 locus for ubiquinone biosynthesis (3 proteins, P=6.9E-05). Follow-up high resolution regional mapping identified NDUFS4, LRPPRC and COQ7 as the candidate genes for chr13, chr17 and chr7 loci, respectively, and both experimental and statistical analyses supported their causal roles. Furthermore, a large cohort of Diversity Outbred mice was used to corroborate Lrpprc gene as a driver of mitochondrial DNA (mtDNA)-encoded gene regulation, and to show that the chr17 locus is specific to heart. Variations in all three loci were associated with heart mass in at least one of two independent heart stress models, namely, isoproterenol-induced heart failure and diet-induced obesity. These findings suggest that common variations in certain mitochondrial proteins can act in trans to influence tissue-specific mitochondrial functions and contribute to heart hypertrophy, elucidating mechanisms that may underlie genetic susceptibility to heart failure in human populations.

Keywords: computational biology; genetic, association studies; genetics; genomics; heart failure; hypertrophy; metabolic syndrome; mitochondria; mouse; proteomics; systems biology.

Figure 1.. Genetic architecture of heart mitochondrial proteome.

(A) High-resolution association mapping of 848 heart mitochondrial proteins from 72 HMDP strains to identify pQTL networks. Associations between protein abundance levels and genetic variants located within 1 Mb of the respective gene location were considered as cis-pQTLs (p<1E-05) shown along the diagonal axis and the rest were considered as trans-pQTLs (p<1E-06). Three trans-pQTL hotspots are indicated by arrows. (B) Five WGCNA modules and the respective trans-pQTL hotspots are shown. HMDP, hybrid mouse diversity panel; pQTL, protein quantitative trait locus; WGCNA, weighted gene co-expression network analysis.

Figure 2.. Chr13 locus controls mitochondrial complex-I via miR-27b/NDUFS4 axis.

(A) Circos plot showing chr13 hotspot. Each line signifies a significant association between the genetic variants and the respective protein levels with candidate genes being highlighted. (B) Manhattan and regional plots of chr13 locus (brown module) eigengene, respectively. Red line signifies genome-wide significance threshold (p<4.1E-06). The peak SNPs and the candidate genes are highlighted. Genotype distribution plots of (C) protein levels and eigengenes, and cardiac phenotypes from (D) ISO-induced HF model and (E) female and (F) male DIO model at peak SNP (rs48592660) associated with chr13 locus. (G) Volcano plot showing differentially expressed protein levels between control and heart-specific Ndufs4-cKO mice (n=5 mice/group). Significantly different proteins (significance cutoff: abs[log₂FC]>1 and P_adj <0.001) are highlighted in red. (H) Genotype distribution plots of heart miR-27b expression at peak SNP (rs48592660) associated with chr13 locus. (I) Gene-by-trait correlation plot between heart weight phenotype and heart miR-27b expression. (J) Immunoblot analyses of NDUFS4 protein levels in NRVMs transfected with mature miR-27b in the presence or absence of PE treatment. Data are presented as (C–F and H) boxplots showing median and interquartile range with outliers shown as circles (n=68–72 strains for protein levels; n=92–95 strains for ISO-model; n=92–100 strains for DIO-model; n=78 strains for miRNA levels) or (J) mean ± SEM (n=4–6 per group). p Values were calculated using (A and B) FaST-LMM that uses Likelihood-Ratio test; (C–F and H) Unpaired two-tailed Student’s t test; (I) BicorAndPvalue function of the WGCNA R-package that uses Unpaired two-tailed Student’s t test; (J) two-factor ANOVA corrected by post-hoc “Holm-Sidak’s” multiple comparisons test. ISO, isoproterenol; HF, heart failure; DIO, diet-induced obesity; NRVMs, neonatal rat ventricular myocytes; PE, phenylephrine.

Figure 3.. Chr17 locus controls mitoribosomes via LRPPRC/SLIRP.

(A) Circos plot showing chr17 hotspot. Each line signifies a significant association between the genetic variants and the respective protein levels with candidate genes being highlighted. (B) Manhattan and regional plots of chr17 locus (green module) eigengene, respectively. Red line signifies genome-wide significance threshold (P<4.1E-06). The peak SNPs and the candidate genes are highlighted. Genotype distribution plots of (C) protein levels and eigengenes, and cardiac phenotypes from (D) ISO-induced HF model and (E) female and (F) male DIO model at peak SNP (rs46340181) associated with chr17 locus. (G) Protein-by-protein correlation plot between heart LRPPRC and SLIRP abundance levels. (H) Association p values between mtDNA-encoded mRNA expression or protein abundance levels and peak SNP (rs46340181) associated with chr17 locus in both sexes of HMDP. (I) Genotype distribution plots of heart mt-ND1 mRNA expression from female and male DIO model at peak SNPs associated with chr17 (rs46340181) or chr13 (rs48592660) loci, respectively. (J) Association p values between mtDNA-encoded complex-I related mRNA expression or protein abundance levels and peak SNP (rs48592660) associated with chr13 locus in both sexes of HMDP. Data are presented as (C–F and I) boxplots showing median and interquartile range with outliers shown as circles (n=68–72 strains for protein levels; n=92–95 strains for ISO-model; n=92–100 strains for DIO-model). p Values were calculated using (A, B, H and J) FaST-LMM that uses Likelihood-Ratio test; (C–F and I) Unpaired two-tailed Student’s t test; (G) BicorAndPvalue function of the WGCNA R-package that uses Unpaired two-tailed Student’s t test.

Figure 4.. Lrpprc regulates an mt-encoded eQTL hotspot specifically in heart of DO mice.

(A) Heatmap illustrates all eQTL (LOD >6) for mt-encoded transcripts that were identified in Adipose (Wang et al., 2012), Heart (Ruzzenente et al., 2012), Islet (Gu et al., 2016), Liver (Rath et al., 2021), and Muscle (Wang et al., 2016) from Diversity Outbred mice maintained on a Western-style diet. Mt-eQTL are arranged along x-axis according to genomic position from chr1 to chrX; z-axis depicts LOD score, highlighting a hotspot on chr17 at ~85 Mbp. (B) Allele effect patterns for mt-eQTL mapping to chr17 hotspot in heart. Red illustrates alleles associated with increased expression; blue, decreased expression. LOD scores are shown along right margin. (C) SNP association profile for mt-Nd5 eQTL in heart. Lrpprc contains SNPs with strongest association, yellow highlighted region. (D) Mediation of mt-Nd5 eQTL against all transcripts in heart. The LOD score for mt-Nd5 is significantly reduced when conditioned on a Lrpprc cis-eQTL, consistent with genetic regulation of Lrpprc being required for the regulation of mt-Nd5. The mt-Nd5 eQTL (E) and Lrpprc cis-eQTL (F) in heart demonstrate matched and concordant allele effect patterns, suggesting Lrpprc is a positive driver of mt-Nd5.

Figure 4—figure supplement 1.. Mediation analysis identifies Lrpprc as a driver for the heart-specific mt- eQTL hotspot on chr17.

LOD scores for 14 mt-eQTL at ~85 Mbp on chr17 before and after conditioning on Lrpprc cis-eQTL in the heart. The average percent drop in the LOD score for the mt-eQTL upon condition to Lrpprc was 79%, with a range of 51% (mt-Co2) to 94% (mt-Rnr2).

Figure 5.. Chr7 locus affects CoQ metabolism via COQ7.

(A) Circos plot showing chr7 hotspot. Each line signifies a significant association between the genetic variants and the respective protein levels with candidate genes being highlighted. (B) Manhattan and regional plots of chr7 locus (turquoise module) eigengene, respectively. Red line signifies genome-wide significance threshold (p<4.1E-06). The peak SNPs and the candidate genes are highlighted. Genotype distribution plots of (C) protein levels and eigengenes, and cardiac phenotypes from (D) ISO-induced HF model and (E) female and (F) male DIO model at peak SNP (rs32451909) associated with chr7 locus. Protein-by-protein correlation plots between heart COQ7 and (G) COQ3, (H) COQ6 and (I) COQ9 abundance levels. (J) Genotype distribution plots of CoQ9 or CoQ10 levels in both the mitochondrial fractions and total heart lysates from female DIO model at peak SNPs associated with chr7 (rs32451909) locus. Data are presented as (C–F and J) boxplots showing median and interquartile range with outliers shown as circles (n=68–72 strains for protein levels; n=92–95 strains for ISO-model; n=92–100 strains for DIO-model; n=15 strains for CoQ9 and CoQ10 levels). p Values were calculated using (A and B) FaST-LMM that uses Likelihood-Ratio test; (C–F and J) Unpaired two-tailed Student’s t test; (G–I) BicorAndPvalue function of the WGCNA R-package that uses Unpaired two-tailed Student’s t test.