The analysis of transcriptomes has become an important tool to study aging-associated processes, but has yet to deliver consistent datasets across tissues and experimental platforms. Gene expression studies comparing tissues from flies, worms, mice and humans have revealed tissue- and organism-specific aging profiles [1], with commonalities in gene ontology classifications centered around metabolism, specifically mitochondrial function [2, 3]. A recent comprehensive assessment of gene expression profiles in tissues has confirmed the diversity of gene expression profiles in human aging [4]. To what extent cellular heterogeneity, epigenetics or stochastic processes play a role in this diversity is unknown [5–7]. Another unresolved issue is the relevance of replicative in-vitro senescence to biologically aged tissues [8–10]. Specifically, in-vitro replicative senescence represents a permanent post-mitotic state with a specific gene expression pattern whereas fibroblasts isolated from very old donors (>90 years) retain mitotic potential [11, 12]. In one study, no senescence-associated transcripts were found in human tissues [13]. Furthermore, it is unclear to which extent other experimental platforms reveal molecular alterations relevant to biologically aged tissues, for example cells from patients suffering from Progeria syndromes, rare genetic disorders characterized by symptoms of premature aging [14, 15].

To gain a better understanding of changes in the transcriptome associated with aging in these different settings, we performed a transcription factor (TF) meta-analysis across multiple tissue datasets derived from tissues aged in-vivo as compared to experimental in-vitro aging models. Prior TF analyses of the aging process have been limited to specific TFs including Forkhead box TFs (FOXOs), signal transducer and activators of transcription (STATs), E2 family TFs (E2F) or nuclear factor kappa-b (NF-κB) [16–20]. These TFs participate in a wide range of cellular functions, yet present only a small fraction of all potentially relevant TF proteins.

Alternatively, TF activities can be estimated from gene expression data [21–23]. To interrogate age-associated changes in TF activities across experimental platforms we scanned promoter regions of differentially expressed target genes using TF position weight matrices (PWM) or motifs, provided by JASPAR and TRANSAC [24, 25]. The task required comparative analysis of gene expression datasets from diverse tissues and experimental studies, both in reference to study design and platforms. A number of techniques have been developed to harmonize otherwise incompatible gene expression data, such as re-annotations, re-scaling, median rank scoring and supervised classifications across datasets [26, 27]. However, limited overlap of transcripts between cells, tissues or studies in aging restricts transcript harmonization [2, 5]. Secondly, inclusion of smaller experimental studies with less statistical rigor hinder application of a uniform significance thresholds required by meta-analyses [3, 28]. Methods of abstracting from specific transcripts and expression values include (i) gene set enrichment, (ii) gene ontologies and (iii) transcription factor analyses, exploring shared commonalities in gene function, ontology or regulation, respectively. Thus, transcription factor analyses provide a method to decipher commonalities in transcriptional regulation based on prioritized target genes independent of specific platforms. Shorter lists may reduce potential false positives, specifically in experimental studies [29, 30], but enrichment scores will be more significant if more transcripts are taken into account. Here, a minimum number of transcripts was estimated with respect to the strength of rank correlation analyses, which are an essential method deployed in this study to determine similarities between samples.

Since transcription factors can both activate and repress genes based on cell type, cellular context and a complex dynamic of TF interactions [31], we performed a sign-less approach targeting both, the most up- and down-regulated target genes. Finally, to distinguish aging phenotypes, we restricted our subsequent comparative analyses of TF signatures on ranks to further diminish variances with respect to experimental design differences. This analysis was carried out using consistently trimmed gene expression data from 18 datasets portraying biological aging in different human tissues and 7 experimental cell aging studies and. Our analysis revealed three distinct tissue groups, which can be aligned with TF signatures of specific experimental models: classical replicative senescence in proliferative cells, senescence compared to quiescence excluding the influence of cell cycle, and an energy restriction model in quiescence (ERiQ), i.e. forced restriction of ATP supply. Furthermore, we identified subsets of unique motifs distinct for senescence and energy restriction. These anti-correlating motifs appeared to be enriched in one phenotype and avoided in the other. Our results suggest the existence of distinct gene regulatory phenotypes contributing to the aging process in response to DNA damage or metabolic stress in-vivo and in-vitro.

Aging may be viewed as a process requiring continuous adaptive responses to chronic cellular stress caused by cumulative molecular damage and energetic challenges. It is poorly understood how this process is reflected at the transcriptional level. The meta-analysis presented here provides pivotal insights into gene regulatory signatures in biologically aged tissues in comparison to experimental cell models of aging. To enable cross-comparison of heterogeneous datasets, we restricted our exploratory examination to trimmed sets of differentially expressed target genes derived from gene expression studies providing whole genome coverage. Inclusion of both up- and downregulated transcripts in combination with subsequent analyses of ranked motifs allowed inclusion of smaller experimental studies. Motif enrichments provide initial global maps of transcriptional regulation in human aging that are suitable to generate new hypotheses (Fig 1, S1 Fig). Despite a limited overlap of single genes between tissues, the most salient finding of this study is the prediction of three distinct cellular aging phenotypes, associated with either DNA damage-induced senescence or energy deprivation, whereby the former can be distinguished further by the influence of cell cycle motifs. For the promotor regions considered here, each of the tissue signatures can be associated with a specific experimental model (Table 2).

Senescence presents as a multi-stage, diversifying process rather than a static endpoint [54]. This diversity was evident in our classifications and allowed aggregation of senescent samples in two main groups. Comparing TF motifs in replicative senescence with proliferating cells showed enriched TF motifs not only involved in DNA damage, but also cell cycle regulation and cell fate, such as nuclear factor Y (NFY), paired-box (PAX), and activating transcription factor (ATF) [55–57]. The Progeria sample in this group was obtained from an experimental model comparing immortalized skin fibroblasts with cells carrying Progerin, a truncated version of Lamin A protein. Liver was one tissue related to this group (Figs 2 and 3). Telomere shortening, senescence and chronic inflammation are known hallmarks of liver aging [58, 59]. Furthermore, studies in mice have indicated increase of γ-H2AX foci in liver, a proxy marker of DNA damage, but not in post-mitotic heart and muscle [8]. This senescence cluster also included the ischemic heart, consistent with the accumulation of senescent fibroblasts after myocardial infarction [60].

The second senescence cluster aggregated samples lacking enrichment of cell cycle related motifs. Two experimental samples compared senescence with quiescent, growth factor-starved fibroblasts. Although both datasets were obtained with different platforms and analyses, they correlated closely in signatures and classifications (Figs 1, 2 and 3). The Progeria sample associated with this group compared proliferating control fibroblasts with proliferating HGPS fibroblasts, precluding analysis of the effect of quiescence on gene expression patterns. Tissues included in this senescent cluster were female skin and kidney, which have been associated with inflammation, senescence and differences in gender [18, 61, 62]. An experimental study on kidney aging had identified NF-κB and STAT TFs as transcriptional regulators [18], which were enriched in our JASPAR and TRANSFAC signatures.

There is an apparent lack of suitable experimental models for aging in post-mitotic tissues. Here we show that a major cluster of samples was associated with the energy-restricted (ERiQ) model described by us earlier [41, 42], which combined inhibition of glucose uptake with mitochondrial dysfunction in quiescent cells. ERiQ grouped together with adipose, artery, brain, blood, heart, lung, muscle, skin and Parkinson’s brain samples. The fibroblast panel included in this group, representing differences between quiescent cells from young and old male donors, clustered borderline. It has been suggested that this particular experimental platform may portray the in-vivo situation more closely, but comparable studies of fibroblasts aged in-situ had also found early markers of senescence [63, 64]. Within the energetically compromised cluster, there was a noticeable difference in signatures between the frontal cortex and hippocampal brain areas, as there was also a noticeable gender difference amongst this group. Similarly, female skin samples originating from a smaller study that compared young and old donors [35], were different to skin samples from males, which were in close proximity to the signature from a more comprehensive set of both male and female skin samples [4]. Both differences in hormone status and immune cell composition have been suggested to contribute to disparities in skin and brain aging [65, 66]. Gender differences were similarly apparent between samples from Parkinson’s brain, compared to age-matched controls. The etiology of Parkinson’s disease attributes this to mitochondrial dysfunction, bioenergetics failure and gender dimorphisms [67–69].

A sign-less transcription factor analysis as conducted here limits inferences to function. Sign-sensitive approaches, until now, can utilize only very small TF catalogs [21]. However, some conclusions on the inner functioning of the protein-protein network constructed by switching motifs using current experimental knowledge can be drawn (Fig 4). Switching motifs were either enriched in senescence, and avoided in energy starvation, or vice versa. One group of senescence-associated proteins, indicated by switching motifs, connected to ATM and ATR as proximal sensors for DNA damage response [43, 70], which network under DNA damage stress with the p53 pathway [71]. In contrast, a different subset of proteins was connected to energy stress sensors AMPK [44, 45] and PTEN [72, 73]. Suppressed PTEN stimulates the Akt pathway, consistent with experimental findings of increased Akt signaling in ERiQ [41]. Increased Akt protein activity, but reduced p53 expression, are specific hallmarks of the ERiQ phenotype. Furthermore, interaction of Akt with CREB and FOXO transcription factors support a pro-survival cell state under energy stress [74, 75]. The exact function of HDACs and HATs in senescence [76, 77] or in response to low ATP [78, 79], as predicted by the PPI, still needs to be determined. In summary, senescence and energy restriction motifs relate to specific chronic stress sensors in distinct regulatory networks, causing anti-correlating clusters when ranked.

The mechanisms of transcription are complex and fine-tuned by cell specific transcriptional networks, epigenetics, methylation and ubiquitination [80–82], cell turnover rates [83] and heterogeneities in the functional elements of transcription [84]. Moreover, mitochondrial dysfunction and retrograde response mechanisms have been identified as factors influential for changes in gene expression [85–87]. Therefore, it is reasonable to assume that aging interferes with the transcriptional machinery in multiple ways, increasing diversity and heterogeneities. This may contribute to a mosaic of cellular phenotypes in some tissues. For instance, energy stress may play a primary role in tissues maintaining proliferative capacity, such as skin, but mitochondrial dysfunction has also been considered as an entry point into replicative senescence [88, 89]. Nevertheless, we were able to identify distinct gene regulatory signatures that share prevailing gene regulatory patterns during aging and demonstrate the validity of different experimental fibroblast models addressing these phenotypes. Specifically, our findings emphasize the role of mitochondrial dysfunction and energetic stress in post-mitotic tissues [90–93], involving AMPK and PTEN previously associated with longevity [94, 95]. Our results support the utility of transcription factor analyses in aging and application to tissues, experimental models and cell types. The transcription factors and related proteins identified here provide additional experimental targets for future in-depth analyses of transcriptional regulation in aging.