Human subcutaneous abdominal adipose tissue was collected from abdominal wall resection of two healthy subjects who underwent cosmetic surgery, male and female Caucasian Italians (BMIs < 25) ages 62 and 52 years, respectively. Written informed consent was obtained, and the clinical protocol was approved by the Institutional Review Board of the Department of Experimental Medicine, Sapienza University of Rome (Italy). All human genome-wide DNA methylation data have been uploaded to the NCBI Gene Expression Omnibus database (GSE139157): https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139157.

The tissue procurement, cellular treatment, and data analysis pipeline was performed as illustrated in Figure 1. Adipose tissue was transferred to the laboratory and processed under sterile conditions within 24 h. Isolation of ASCs was performed as previously described (Ceccarelli et al., 2018). Briefly, tissue fragments were washed extensively with sterile phosphate-buffered saline containing 2% penicillin/streptomycin and minced. The extracellular matrix was digested with 0.075% collagenase type I for 30–60 min at 37°C and 5% CO₂. The suspension was filtered to remove debris and centrifuged for 5 min at 2000 rpm. The pellets of stromal vascular fraction (SVF) containing ASCs were washed with PBS, then resuspended in the culture medium and transferred to a culture flask. ASCs were self-selected out of the SVF, since they were adherent to the plastic tissue cultureware. ASC cells were cultured in DMEM-Ham’s F-12 medium (vol/vol, 1:1) (DMEM/F12; Gibco) supplemented with 10% FBS, 100 U/ml penicillin, 100 mg/ml streptomycin, and 2 mM L-glutamine, and maintained in a 5% CO₂ incubator at 37°C in a humidified atmosphere, with medium change twice a week. When reaching 80–90% confluence, cells were detached with 0.5 mM EDTA/0.05% trypsin (Gibco) for 5 min at 37°C and then replated. ASCs were expanded and cell viability was assessed by using the trypan blue exclusion assay. Cell morphology was evaluated by phase contrast microscopy. Experiments were conducted between passage numbers 7,8. Absence of mycoplasma contamination was confirmed by PCR with specific primers.

The DNA methyltransferase inhibitor 5′-AZA was purchased from Sigma-Aldrich (Milan, Italy) and was reconstituted at 10 mM using dimethyl sulfoxide (DMSO). ASCs were seeded at a cell density of 5 × 10³ cells/cm². After cell attachment, the medium was changed to freshly made culture medium containing 10 μM 5′-AZA. After 24 h, the 5′-AZA containing culture medium was refreshed for another 24 h (total treatment 48 h). Control samples were treated with DMSO alone at 0.1% (v/v) concentration.

Pooled genomic DNA was isolated from ASCs treated with or without 24-h of 10 μM 5′-AZA using the GeneJET Genomic DNA Purification Kit (Thermo Scientific). DNA concentration and purity were determined using Qubit 3 Fluorometer (Invitrogen) and NanoDrop 2000 (Thermo Scientific). DNA integrity was checked on 1% agarose gel.

Sequencing was performed at the Genomix4Life S.r.l. with subsequent bioinformatics performed at the University of Alabama at Birmingham (United States). Briefly, 2 μg of genomic DNA were used for each library preparation. Each DNA sample was digested by MspI restriction enzyme. The digested products were purified with the GeneJet PCR Purification Kit (Thermo Fisher Scientific) and libraries were prepared by TruSeq Library Prep Kit (Illumina, Inc., United States). Fragments were bisulfite converted using the EZ DNA Methylation-Gold Kit (Zymo Research, United States). The converted DNA was amplified using PfuTurbo Cx Hotstart DNA Polymerase (Agilent Technologies, United States). The amplified fragments were purified by AMPure XP Beads and further quantified by the Agilent 4200 TapeStation (Agilent Technologies, United States). Each DNA library was analyzed by paired-end sequencing read (2 × 75 cycles) on Illumina Nextseq 500.

Unless otherwise indicated, statistical significance was determined via unpaired two-tailed Bonferroni-adjusted P-value (Q) < 0.05. Pathway analysis and motif enrichment both employed an unadjusted P-value using the Fisher’s exact test.

The computation of differentially methylated regions (DMRs) identified 4,797 DMRs (Q-value < 0.05) associated with 3,625 annotated genes (Supplementary Table S1), among which was an equivalent proportion of hyper-methylated (2,588) and hypo-methylated (2,209) regions was uncovered. A volcano plot was used to examine the genes associated with differentially methylated promoters with 5′-AZA treatment (Figure 2A). Because the transcriptional effects of DNA methylation are highly dependent on the position of DMRs relative to known genomic features, with promoter methylation classically inversely associated with transcriptional activity (Bird, 1986; Jjingo et al., 2012), we examined the distribution of DMRs in relation to genomic locations most impacted by changes in DNA methylation following treatment with 5′-AZA. Annotated DMRs were mapped onto both genic location (promoter, 5′UTR, gene body, and 3′UTR) as well as according to their distance from established CpG Islands (CGIs). Methylation dynamics were modestly concentrated among CpG islands located in the promoter region (Figure 2B). Illustrating DMRs using a circular genome plot demonstrated the genome-wide distribution of methylation changes, numerous hyper-dynamic regions, and a broad array of genes with DMRs reaching genome-wide significance (P < 10^–8) (Figure 2C).

Hierarchical clustering and heatmap visualization was then used to understand the degree of consistency between 5′-AZA and DMSO-treated ASCs, which revealed robust separation of differential promoter methylation between 5′-AZA and vehicle-treated ASCs with no apparent outliers (Figure 3A). Gene set enrichment analysis (GSEA) was performed using the genes possessing differentially methylated promoters, separating the hyper-methylated from hypo-methylated DMRs to interpret the possible impact of methylation dynamics on the enriched pathway(s). This approach identified phagocytosis (P = 10^–5), type 2 diabetes (P = 10^–4), and numerous metabolic pathways as disproportionately impacted by promoter hypo-methylation (Figure 3B and Supplementary Table S2), whereas white-adipocyte differentiation was the top most-enriched pathway among genes with hyper-methylated promoters (Figure 3C and Supplementary Table S3). Altogether, these findings suggest that 5′-AZA-mediated promoter methylation influences the metabolic phenotype of ASCs.

To identify novel networks affected by 5′-AZA treatment, we used the STRING database (Szklarczyk et al., 2017) to generate a network of DMRs based on known and predicted interactions among their encoded proteins, with Markov Clustering (MCL) to separate DMR networks according to both the degree and number of adjacent interactions (Figure 4). After ranking nodes by degree of interaction, the largest cluster was identified to functionally enrich pathways via the KEGG pathway database associated with cellular proliferation and developmental programs: krüppel-associated box (P = 2.9 × 10^–32), antigen processing (P = 6.9 × 10^–26), mRNA splicing (P = 1.1 × 10^–23), cell cycle regulation (P = 5.7 × 10^–17), clathrin-mediated endocytosis (P = 1.2 × 10^–15), and cell cycle (BH-adjusted P = 2.9 × 10^–13). Because we and others have previously found Krüppel-like factors (KLFs) to possess methylation-sensitive response elements (Pepin et al., 2019), the current analysis further supports that 5′-AZA treatment is sufficient to induce disproportionate differential methylation of KLF target gene promoters.

Promoter DNA methylation regulates gene expression in-part by interfering with the binding of transcription factors, particularly those possessing CpG-rich response elements (Medvedeva et al., 2014). Therefore, to identify candidate transcription factors likely disrupted by co-localizing promoter methylation, a de novo motif enrichment was performed via HOMER (Heinz et al., 2010). To correct for the CpG density of DMRs, background genomic regions were selected according to CpG content when performing hypergeometric enrichment. From this analysis, we found that ZNF711 was significantly associated with hypo-methylated promoter DMRs (Log₁₀(P) = −9.9) (Supplementary Figure S1A), whereas the ELK4 motif disproportionately co-localized among hyper-methylated promoters (Figure 5A). The ENCODE dataset (GSE31477) was then used to identify genes associated with hyper-methylated DMRs (Q < 0.05, |Methylation| >10%) found in the promoter of ELK4 target genes, revealing (Figure 5B). Gene-set enrichment of co-localized DMRs within ELK4 target promoters identified AKT signaling as disproportinately affected by DMR co-localization, supporting prior studies demonstrating the role of ELK4 and HDAC (Figure 5C). A preliminary evaluation of ELK4 expression revealed its induction in ASC’s treated with 5′AZA (Supplementary Figure S1B). Taken together, these observations support the hypothesis that 5′-AZA-induced promoter methylation may interfere with the downstream targets of ELK4 signaling and may therefore disrupt its role as a regulator of cellular proliferation (Boog, 1993).