Non-coding genomic regions possessing enhancer and silencer potential are associated with healthy aging and exceptional survival

Abstract

We have completed a genome-wide linkage scan for healthy aging using data collected from a family study, followed by fine-mapping by association in a separate population, the first such attempt reported. The family cohort consisted of parents of age 90 or above and their children ranging in age from 50 to 80. As a quantitative measure of healthy aging, we used a frailty index, called FI34, based on 34 health and function variables. The linkage scan found a single significant linkage peak on chromosome 12. Using an independent cohort of unrelated nonagenarians, we carried out a fine-scale association mapping of the region suggestive of linkage and identified three sites associated with healthy aging. These healthy-aging sites (HASs) are located in intergenic regions at 12q13-14. HAS-1 has been previously associated with multiple diseases, and an enhancer was recently mapped and experimentally validated within the site. HAS-2 is a previously uncharacterized site possessing genomic features suggestive of enhancer activity. HAS-3 contains features associated with Polycomb repression. The HASs also contain variants associated with exceptional longevity, based on a separate analysis. Our results provide insight into functional genomic networks involving non-coding regulatory elements that are involved in healthy aging and longevity.

Figure 1. Graphical summary of MERLIN npl analysis on chromosome 12

(A) From offspring data only (LOD = 2.3, P = 6.0 × 10⁻⁴). (B) From offspring data combined with inferred parental phenotype data (LOD = 3.0, P = 1.0 × 10⁻⁴).

Figure 2. Manhattan plots of association results

(A) −log₁₀ P values from linear regressions of FI₃₄ scores on additive effects of 330 SNPs, with sex and age differences adjusted, were plotted against SNP positions. Applying a Bonferroni adjustment, the cutoff significance P value is 1.52 × 10⁻⁴ and its −log₁₀ counterpart is 3.8. (B) The same as in (A) but using logistic regressions of dichotomized FI₃₄ values. (C) −log₁₀ P values from χ² tests for differences in allele frequencies between oldest-old cases and young controls were plotted against SNP positions.

Figure 3. Summary of results of ChroMoS (Chromatin Modified SNPs) annotation for the SNPs in HAS-1

(A), HAS-2 (B), and HAS-3 (C) SNPs known or suspected to be functional are enclosed in a dotted red rectangle. (D) The genome is functionally segmented into discrete chromatin states through multivariate hidden Markov modeling of ChIP-seq data from multiple cell lines [53]. According to the ‘learned’ chromatin segmentation, ChroMoS graphically assigns individual non-coding SNPs to these chromatin states coded by different colors [19]. Cell lines are NHLF (normal human lung fibroblasts), NHEK (normal human epidermal keratinocytes), K562 (chronic myelogenous leukemia cells), HSMM (human skeletal muscle myoblast cells), HUVEC (human umbilical vein endothelial cells), HMEC (human mammary epithelial cells), HepG2 (human liver carcinoma cells), H1-hESC (human embryonic stem cells), and GM12878 (lymphoblastoid cells).

Figure 4. A close-up view of HAS-1 including rs10877013 (red-dotted line) provided by the UCSC Genome Browser [54]

SNP IDs in black are in introns, green in coding (synonymous), red in coding (non-synonymous), and blue in untranslated regions. Loci in which variants have been associated with complex diseases or disorders are shown in red blocks. The UCSC Gene track is based on gene prediction data from sources indicated. Coding exons are represented by thick blocks, non-coding or untranslated regions by relatively thin blocks, and introns by thin lines. Gene names and blocks in black represent genes entered in the Protein Data Bank (PDB) and those in blue are transcripts reviewed or validated by either the RefSeq, SwissProt or consensus coding sequence (CCDS) project. Different colors in the histone modification tracks represent results from different cell lines, and peak levels show enrichment levels of the corresponding histone marks as determined by ChIP-seq assays. The numbers following ‘CpG’ represent CpG dinucleotide counts. The DNase Clusters track shows DNase hypersensitive sites with the darkness being proportional to the sensitivity. The ‘Txn Factor ChIP’ track shows transcription factor binding sites from ChIP-seq experiments carried out by the ENCODE project [55]. The DNA binding motifs are from the ENCODE Factorbook repository, which can be viewed as a matrix of all ENCODE transcription factor ChIP-seq datasets, arranged by cell lines [56]. The darkness is proportional to the signal strength, and the green highlights indicate the highest scoring-site motifs. The ‘Txn Fac ChIP V2’ track is similar to the other track, but it employs a different computation method. The ChromHMM tracks, like ChroMoS, show chromatin segments corresponding to different functional states as shown in Figure 3D, according to the computational integration of ChIP-seq data from multiple cell lines using a Hidden Markov Model [57].

Figure 5. A close-up view of HAS-2 including rs3847663 (red-dotted line) provided by the UCSC Genome Browser

Track displays are as described in Figure 4. The names to the left of individual transcription factor binding sites are the HGNC gene names for corresponding transcription factors.

Figure 6. A close-up view of HAS-3 including rs7301866 (red-dotted line) provided by the UCSC Genome Browser

The gray-colored block in ChrommHMM tracks represents a Polycomb-repressed site. Other track displays are as described in Figure 4.