Glucose-dependent regulation of NR2F2 promoter and influence of SNP-rs3743462 on whole body insulin sensitivity

Abstract

Background: The Nuclear Receptor 2F2 (NR2F2/COUP-TFII) heterozygous knockout mice display low basal insulinemia and enhanced insulin sensitivity. We previously established that insulin represses NR2F2 gene expression in pancreatic β-cells. The cis-regulatory region of the NR2F2 promoter is unknown and its influence on metabolism in humans is poorly understood. The present study aimed to identify the regulatory regions that control NR2F2 gene transcription and to evaluate the effect of NR2F2 promoter variation on glucose homeostasis in humans.

Methodology/principal findings: Regulation of the NR2F2 promoter was assessed using gene reporter assays, ChIP and gel shift experiments. The effects of variation at SNP rs3743462 in NR2F2 on quantitative metabolic traits were studied in two European prospective cohorts. We identified a minimal promoter region that down-regulates NR2F2 expression by attenuating HNF4α activation in response to high glucose concentrations. Subjects of the French DESIR population, who carried the rs3743462 T-to-C polymorphism, located in the distal glucose-responsive promoter, displayed lower basal insulin levels and lower HOMA-IR index. The C-allele at rs3743462 was associated with increased NR2F2 binding and decreased NR2F2 gene expression.

Conclusions/significance: The rs3743462 polymorphism affects glucose-responsive NR2F2 promoter regulation and thereby may influence whole-body insulin sensitivity, suggesting a role of NR2F2 in the control of glucose homeostasis in humans.

Figure 1. Glucose decreases the ability of HNF4α to activate the transcription of the NR2F2 proximal promoter and to bind its chromatin target.

(A) INS-1 832/13 cells were transiently co-transfected as described in with a luciferase reporter gene driven by various lengths of the NR2F2 promoter, designated by their 5′ and 3′ end positions relative to the defined NR2F2 gene transcription initiation site and a control vector expressing Renilla luciferase. Cells were cultured in the presence of either 5 mM (white bars) or 20 mM (black bars) glucose. Results were calculated from the ratio of luciferase/Renilla activity. Background expression was subtracted using the mean expression level of empty pGL3-basic. Means ± SEM of results obtained from at least three independent transfections performed in triplicate are shown. *Significant differences, P<0.05. (B) Comparison of mRNA levels of NR2F2 and HNF4α relative to those of cyclophilin determined by real-time RT-QPCR in INS-1 832/13 β-cells stimulated with 5 mM (white bars) or 20 mM glucose (black bars) for 24 h as described in (C) ChIP from INS-1 832/13 cells cultured in the presence of either 5 mM or 20 mM glucose. Targets for QPCR amplifications were the proximal NR2F2 promoter containing the DR1 DNA binding site or a downstream coding region (negative control). Amount of target chromatin precipitated by the HNF4α-specific antibody relative to that precipitated by control IgG (mean of three independent experiments ± SEM). *Significant difference, P<0.05. (D) COS cells were transiently co-transfected with the −328/+873 construct and 50 ng of empty KS vector (white bars), or HNF4α (grey bars) expression vectors. Means ± SEM of results from at least three separate transfections performed in triplicate are shown. *Significant difference, P<0.05. (E) INS-1 832/13 cells were transiently co-transfected with the wild-type or mutated −328/+873 constructs containing the DR1 elements. Cells were cultured in the presence of either 5 mM (white bars) or 20 mM (black bars) glucose. Means ± SEM of results from ten independent transfections performed in triplicate are shown. *Statistically significant differences in percentage of expression (where value for 5 mM glucose is 100% relative to −328/+873 construct) at P<0.05.

Figure 2. NR2F2 binds the variant rs3743462-C oligonucleotide with higher affinity than the rs3743462-T oligonucleotide and the C-allele is associated with a strong decrease of NR2F2 gene expression relative to the T-allele.

(A) Multiple alignments of the genomic region between nucleotides −3180 and −3110 of the NR2F2 gene regulatory regions present in the −3210/+873 construct. Deletion is indicated by dashes and points indicate identities. The sequence of the human complementary strand is shown above other sequences. Genomic sequences can be retrieved from GenBank by their accession codes: Homo sapiens (NT_010274.17|:11836273-11840385), Mus musculus (NT_039428.7|Mm7_39468_37:c10507606-10503510; reverse/complementary strand), Rattus norvegicus (NW_047560.2|Rn1_WGA2082_4:c5641306-5636690; reverse/complementary strand). The position of the human SNP is indicated by an asteriskabove the sequences of each species: H. sapiens, −3,138; M. musculus, −3,139; R. norvegicus, −3,152 (where transcription start site is +1). (B) The sense strand sequences (+) of the oligonucleotides used in EMSA are shown. SNP base pairs are shown in lower case letters. (C) The labeled rs3743462-T and rs3743462-C oligonucleotides were incubated with INS-1 832/13 nuclear extracts, and protein binding was analyzed using EMSA. In the representative autoradiograph shown, only the retarded complexes are visible and not the free probe, which was in excess. (D) Comparison of the affinity of protein binding to the rs3743462-T and rs3743462-C variants. The labeled rs3743462-C oligonucleotide (Fig. 2B) was incubated with or without the indicated molar excess of unlabeled rs3743462-T or rs3743462-C oligonucleotide as competitors before addition of INS-1 832/13 nuclear extract. Protein binding was then analyzed using EMSA. In the representative autoradiograph shown, only the retarded complexes are visible and not the free probe, which was in excess. (E) INS-1 832/13 nuclear extracts were incubated with or without of the indicated anti-serum. The labeled oligonucleotide representing the −3153/−3126 NR2F2 regulatory region and containing the rs3743462-C allele was added and protein binding was analyzed using EMSA. In the representative autoradiograph shown, only the retarded complexes are visible and not the free probe, which was in excess. (F) Functional analysis of the rs3743462 alleles in pancreatic β-cells. INS-1 832/13 cells were transiently co-transfected using lipofectamine solution containing either rs3743462 T-allele, C-allele, T-allele with DR-1 mutated site or C-allele with DR-1 mutated site within the context of the 3210/+873 sequences (1.5 µg) and expression vector encoding Renilla luciferase (0.1mg). Cells were then cultured in the presence of 5 mM glucose for 14 h. Results are calculated from the ratio of luciferase/Renilla activity. Means ± SEM of results obtained from at least three independent transfections performed in triplicate are shown. *Significant differences in expression at P<0.05.