Inactive DNMT3B splice variants modulate de novo DNA methylation

Abstract

Inactive DNA methyltransferase (DNMT) 3B splice isoforms are associated with changes in DNA methylation, yet the mechanisms by which they act remain largely unknown. Using biochemical and cell culture assays, we show here that the inactive DNMT3B3 and DNMT3B4 isoforms bind to and regulate the activity of catalytically competent DNMT3A or DNMT3B molecules. DNMT3B3 modestly stimulated the de novo methylation activity of DNMT3A and also counteracted the stimulatory effects of DNMT3L, therefore leading to subtle and contrasting effects on activity. DNMT3B4, by contrast, significantly inhibited de novo DNA methylation by active DNMT3 molecules, most likely due to its ability to reduce the DNA binding affinity of co-complexes, thereby sequestering them away from their substrate. Immunocytochemistry experiments revealed that in addition to their effects on the intrinsic catalytic function of active DNMT3 enzymes, DNMT3B3 and DNMT34 drive distinct types of chromatin compaction and patterns of histone 3 lysine 9 tri-methylation (H3K9me3) deposition. Our findings suggest that regulation of active DNMT3 members through the formation of co-complexes with inactive DNMT3 variants is a general mechanism by which DNMT3 variants function. This may account for some of the changes in DNA methylation patterns observed during development and disease.

Figure 1. Inactive DNMT3B isoforms interact with active DNMT3 isoforms.

(A) Combinations of Myc- and FLAG- tagged isoforms were expressed in human HEK293 cells as indicated. Expression of Myc-tagged proteins was verified in the whole cell extract (WCE) by western blot (top). FLAG immunoprecipitates (IP) were probed with FLAG antibody to verify the expression of FLAG-tagged DNMT3B1 (center). Myc-tagged proteins associated with FLAG IP were revealed using an anti-Myc antibody (bottom). (B) Myc-tagged DNMT3B3 or Myc-tagged DNMT3B4 and FLAG-tagged DNMT3B2 were expressed in HEK293 cells and their localization was analyzed by immunofluorescence as indicated. All DNMT3B2 and DNMT3B3 dual-expressing cells showed co-localization of expression (100%; n = 49) and most DNMT3B2 and DNMT3B4 dual-expressing cells displayed co-localization (96.2%; n = 52) Representative images of are shown. (C) Representative elution profiles from gel filtration chromatography are shown revealing that DNMT3B co-complexes form high molecular weight aggregates indistinguishable in size. (D) Co-complexes between indicated isoforms were purified through tandem affinity purification and the relative stoichiometry of each isoform in the complex was evaluated by western blot using an anti-6X histidine antibody directed against the internal 6X histidine tag common to all isoforms. A representative blot is shown and relative stoichiometric ratios are indicated below. Experiments were performed at least in triplicate.

Figure 2. DNMT3B3 modulates DNA methylation activity without affecting DNA methylation patterns.

(A) HEK293c18 cells were transfected with the pFC19 target episome and combinations of DNMT3 expression vectors, as indicated. DNA methylation was assessed by Southern blot after digestion of episomal DNA with a methylation-sensitive restriction enzyme. Higher molecular weight bands are indicative of DNA methylation. (B) Bisulfite sequencing was performed on a 500 base pair region of harvested episomal DNA. Co-expression of DNMT3B2 with DNMT3B3 does not lead to a change in DNA methylation patterns as judged by the fact that the ordered ranks of the 48 methylation sites in the region do not shift significantly. (C) Pre-incubation of DNMT3B3 with active DNMT3A2 leads to a stimulation of catalytic activity. The graph displays the result of quantitative in vitro activity assays in which the incorporation of labeled methyl groups into DNA was measured at increasing ratios of DNMT3B3ct to DNMT3A2. (D) DNMT3B3 hinders the stimulatory effect of DNMT3L. Pre-incubation of increasing concentrations of DNMT3B3ct to constant amounts of DNMT3A2 and DNMT3L leads to a progressive decline in DNA methylation activity as measured in quantitative in vitro assays. Results in panels C and D are from triplicate experiments and shown with average and standard deviations.

Figure 3. DNMT3B4 inhibits DNMT3 activity.

(A) Expression of DNMT3B4 inhibits DNA methylation in vivo as measured by Southern blots in transfected HEK293c18 cells. See Figure 2A for further details. (B) In vivo methylation mediated by DNMT3B2 on its own (left) or by DNMT3B2 co-expressed with DNMT3B4 (right) was assessed by bisulfite methylation sequencing. Co-expression of DNMT3B4 significantly reduces the overall methylation efficiency over the entire region analyzed. Two independent transfections were analyzed. Bars: standard deviation. (C) Purified full-length co-complexes that include DNMT3B4 are catalytically deficient as measured in in vitro time course experiments where the incorporation of labeled methyl groups onto DNA is followed. (D) Pre-incubation of purified DNMT3B4 with DNMT3A2 leads to an inhibition of catalytic activity. The graph depicts results from activity assays that followed the incorporation of labeled methyl groups onto DNA at increasing ratios of DNMT3B4ct to DNMT3A2. Results in panels C and D are from duplicate experiments and shown with average and standard deviations.

Figure 4. DNMT3B3 weakens, while DNMT3B4 strongly inhibits, DNA binding by DNMT3B2.

(A) Binding to a 420 base pair DNA fragment was measured by EMSAs for increasing concentrations of C-terminal DNMT3B2, DNMT3B3 and DNMT3B4 proteins. Bound and unbound DNA species are indicated. (B) DNA binding was also measured for C-terminal DNMT3B2:DNMT3B2, DNMT3B2:DNMT3B3, and DNMT3B2:DNMT3B4 co-complexes at increasing protein concentrations. (C and D) Graphical representation of EMSAs from A and B, respectively, performed at least in triplicate. The percent of protein bound to DNA was calculated by band quantification using ImageQuant. Points: mean, bars: standard error. Results were fit using nonlinear regression, saturation-binding (one-site-specific binding with Hill slope). Kd values: 3B2ct = 0.22 µM, 3B3ct = 0.16 µM, 3B4ct = 2.42 µM, 3B2ct+3B2ct = 0.4 µM, 3B2ct+3B3ct = 1.5 µM, 3B2ct+3B4ct = N/A.

Figure 5. DNMT3B isoforms drive unique and distinct localization, DNA staining, and H3K9me3 patterns in human cells.

FLAG-tagged DNMT3B2, DNMT3B3, and DNMT3B4 were transiently transfected into human HEK293 cells. 24 to 36 hours later, cells were fixed and stained with anti-FLAG (Sigma) and anti-H3K9me3 (Abcam) antibodies. Transfections were repeated at least in triplicate and cells were photographed with a fluorescence microscope. Representative DNMT3B (Globular, Diffuse, or Speckled: red), DNA (Condensed or Diffuse: blue), and H3K9me3 (Speckled, Spotty, or Faint: green) staining are depicted. Percentages of each type of staining versus DNMT3B isoform expressed are indicated below each image. The total number of independent cells analyzed: DNMT3B2, n = 237; DNMT3B3, n = 203; DNMT3B4, n = 215; none, n = 356.

Figure 6. Inactive DNMT3 variants modulate DNA methylation activity.

DNMT3L, the prototypic inactive DNMT3 variant stimulates de novo methylation activity up to 20-fold from a baseline level up to maximal methylation levels . Stimulation is graphically depicted by a vertical arrow. DNMT3B3, by contrast, can both hinder the stimulatory effect of DNMT3L (shown by a downward pointing arrow) and stimulate the activity of active DNMT3s from their baseline levels (shown by an upward pointing arrow). DNMT3B4, by contrast, inhibits DNA methylation 3-fold lower than baseline level. Altogether, inactive DNMT3 variants can modulate de novo methylation activity over a 60-fold range.