Obesity risk gene TMEM18 encodes a sequence-specific DNA-binding protein

Abstract

Transmembrane protein 18 (TMEM18) has previously been connected to cell migration and obesity. However, the molecular function of the protein has not yet been described. Here we show that TMEM18 localises to the nuclear membrane and binds to DNA in a sequence-specific manner. The protein binds DNA with its positively charged C-terminus that contains also a nuclear localisation signal. Increase in the amount of TMEM18 in cells suppresses expression from a reporter vector with the TMEM18 target sequence. TMEM18 is a small protein of 140 residues and is predicted to be mostly alpha-helical with three transmembrane parts. As a consequence the DNA binding by TMEM18 would bring the chromatin very near to nuclear membrane. We speculate that this closed perinuclear localisation of TMEM18-bound DNA might repress transcription from it.

Figure 1. TMEM18 localises to nuclear membrane and cytoplasm.

(A) The localisation of TMEM18-GFP in cells was studied by fluorescence microscopy. The cells in the first row express GFP alone and in the second TMEM18-GFP. The first column shows GFP expression, the second DAPI stained nuclei, and the third the superimposition of the two pictures. (B) Western blot analysis of cell fractions from TMEM18-HA overexpressing cells. TMEM18 is mainly in cytosolic and nuclear detergent soluble fractions. A small amount of TMEM18 can be seen also in detergent insoluble nuclear fraction containing proteins bound to DNA. Laminin A/C was used as the control for the purity of the cell fractionation.

Figure 2. The positively charged C-terminus of TMEM18 binds DNA.

(A) Robetta server-predicted (robetta.bakerlab.org) structure model of TMEM18. Dashed lines depict nuclear membrane, the three transmembrane domains are in gray, the C-terminal DNA-binding domain, ERRKEKKRRRKED, is coloured black, and white C's indicate the sites of cysteines. The structural model was edited with PyMOL. (B) TMEM18 binds to dsDNA and ssDNA-cellulose resin. Western blot of Flag-tagged TMEM18 shows the amount of TMEM18 in flow through (FT), wash, and elute. DNase I treatment of the DNA-cellulose resins erased the TMEM18 binding demonstrating that TMEM18 does not bind to the cellulose matrix. (C) TMEM18 lacking the last 13 C-terminal amino acids was unable to bind DNA-cellulose. Western blot results are shown for both dsDNA and ssDNA-cellulose binding assays.

Figure 3. TMEM18 oligomerises independently of the DNA-binding domain.

(A) Flag-tagged TMEM18 binds HA-tagged TMEM18 as shown in a Western blot. Untransfected cells (empty ctrl), vector transfected (Vector ctrl), or HA and Flag double-tagged TMEM18 (TMEM18-Flag-HA), Flag-tagged TMEM18 (TMEM18-Flag), HA-tagged TMEM18 (TMEM18-HA), or both HA and Flag-tagged TMEM18 expressing cells were immunoprecipitated with Flag and detected with anti-HA antibody. The relative amounts of HA-tagged TMEM18 in the cell extracts before immunoprecipitation are shown under the immunoprecipitated samples. (B) TMEM18 C-terminus is not needed for self-binding but the interaction is facilitated by cysteines. Co-immunoprecipitation assays were done using TMEM18-Flag with TMEM18-HA, C-terminal deletion TMEM18 (TMEM18ΔC), or TMEM18 with all the four cysteines mutated into alanines (TMEM18C→A). The samples were immunoprecipitated with Flag antibody, Western blot was probed with HA antibody, and the signal intensities were estimated from the blot. The results are a combination of three separate experiments and the error bars show the experimental variation. (C) TMEM18 dimerisation facilitates DNA binding. TMEM18 was purified from insect cells and bound to DNA-cellulose. Unbound proteins were in flow through (FT). Samples on DNA-cellulose were washed (W) and then eluted with increasing salt concentration (0.5 M, 1 M, and 2 M). The numbers under the Western blot indicate the ratio of the dimer form (approx. 34 kDa) of TMEM18 to the monomer form (approx. 17 kDa).

Figure 4. TMEM18 binds to GCT sequence.

(A) SELEX was used to identify the specific sequences TMEM18 binds. The TMEM18 binding oligonucleotides were enriched by six rounds of SELEX before they were cloned and sequenced. (B) The obtained sequences were analysed by comparing the observed frequency of three nucleotide words to that expected of a random distribution (Wordcount at Mobyle@pasteur). The results show that 11 nucleotide triplets were found to have higher than expected frequency and of these GCT was the most enriched by ratio of almost 2.5. (C) Biotin-labelled oligonucleotides with eight repeats of either GCT or non-target sequence GTG were used in EMSA to confirm the SELEX results. In competition experiment an unlabelled (GCT)₈ oligonucleotide was used in increasing amounts (2.5 and 6.25-fold excess) shown by a black triangle. An arrow indicates the unbound free probe as well as the TMEM18 shifted oligonucleotides.

Figure 5. TMEM18 suppresses gene expression.

(A) An enhancerless reporter vector pGL3 (light gray bars) and the same vector with 15 repeats of GCT upstream of the promoter (dark gray bars) were used in the luciferase assay. Luciferase readings (RLU / mg of protein) were recorded one day after transfection of the reporter vector to empty vector (Vector ctrl), TMEM18, or TMEM18-C-JUN expressing cells. In TMEM18-C-JUN the c-JUN DNA-binding domain, RKRMRNRIAASKSRKRK, replaced the last 13 C-terminal amino acids of TMEM18. The experiment was done in triplicate and the error bars indicate the standard deviation. (B) TMEM18 inhibits YY1 expression. Cells were transfected with an empty or TMEM18 expressing vector and analysed two days later. TMEM18 and YY1 mRNA levels were normalised to UBC. The quantative real-time PCR results for YY1 are shown as a bar chart and the TMEM18 mRNA levels are visualised in an ethidium bromide stained agarose gel. The results are from three separate experiments and the error bars denote standard deviation. (C) Hypothetical model of how TMEM18 suppresses gene transcription by bringing the chromatin to the nuclear periphery. Two TMEM18 molecules are shown at the nuclear membrane indicated by black solid lines, interweaving dashed lines represent DNA.