Acetylation reprograms MITF target selectivity and residence time

Abstract

The ability of transcription factors to discriminate between different classes of binding sites associated with specific biological functions underpins effective gene regulation in development and homeostasis. How this is achieved is poorly understood. The microphthalmia-associated transcription factor MITF is a lineage-survival oncogene that plays a crucial role in melanocyte development and melanoma. MITF suppresses invasion, reprograms metabolism and promotes both proliferation and differentiation. How MITF distinguishes between differentiation and proliferation-associated targets is unknown. Here we show that compared to many transcription factors MITF exhibits a very long residence time which is reduced by p300/CBP-mediated MITF acetylation at K206. While K206 acetylation also decreases genome-wide MITF DNA-binding affinity, it preferentially directs DNA binding away from differentiation-associated CATGTG motifs toward CACGTG elements. The results reveal an acetylation-mediated switch that suppresses differentiation and provides a mechanistic explanation of why a human K206Q MITF mutation is associated with Waardenburg syndrome.

Fig. 1. Acetylation of MITF at K206.

a Western blot using anti-acetyl lysine or anti-GFP antibodies of immunoprecipitated GFP-tagged MITF co-expressed with CBP, p300 or GCN5 in Phoenix-AMPHO cells as indicated. AcK; Acetyl-Lysine. This experiment was repeated 3 times with similar results. Source data for Western blots are provided in Supplementary Fig. S6. b Schematic showing locations of MITF acetylation sites (red) detected in this study, and AcK206 in blue. Acetylated peptides derived from Mass Spec analysis are indicated below and phosphorylation sites and the p300 binding motif are indicated above. c Alignment of amino acids in the basic region of related bHLH-LZ family members. Yellow highlights highly conserved residues, and the red highlight (corresponding to K206 in MITF) indicates lysines conserved only in the MiT subfamily. d Depiction of the MITF-DBD-DNA co-crystal structure highlighting the K206-phosphate backbone interaction. MITF monomers are depicted in red or green, and DNA in blue.

Fig. 2. Confirmation of MITF acetylation at K206.

a Peptide array of 14 amino acid peptides containing indicated acetylated or non-acetylated residues probed with anti-acetyl K206 antibody with AcK206 in pink boxes. Signal was quantified based on the chemiluminescence signal. b–h Western blots probed with indicated antibodies. b HA-MITF expressed in Phoenix-AMPHO cells alone or co-expressed with CBP or p300 +/− 20 nM A485 probed with anti-acetyl lysine or anti-HA antibodies before (top panels) or after (bottom panels) immunoprecipitation using anti-HA. Experiment performed once as presented, but repeated with similar results by using A485 to block TPA-induced MITF acetylation. c IGR37 cells expressing doxycycline-inducible FLAG-tagged MITF and HA-tagged p300 induced for 16 h or 72 h using indicated amounts of doxycycline. Experiment repeated twice with similar results. d Immunoprecipitation of HA-tagged MITF from IGR37 cells engineered to express doxycycline inducible p300 and HA-MITF. Experiment performed once. e Endogenous MITF immunoprecipitated from 501mel cells using anti-MITF antibody or anti-HA as an isotype antibody control and probed with indicated antibodies. Input is shown to the left. FT indicates ‘flow-through’; IP indicates immunoprecipitated. Experiment performed once. f Immunoprecipitation of HA-tagged MITF from 501mel cells treated or not with 10 μM U0126 as indicated. Inputs and immunoprecipitated protein were western blotted using the indicated antibodies with anti-ERK used as a loading control. Experiment has been repeated twice with similar results. g Expression of FLAG-tagged WT or mutant MITF co-expressed with p300 (left) or CBP (right) in Phoenix-AMPHO cells and probed with anti-acetyl lysine or anti-MITF antibody. Experiment has been performed once as presented, but repeated using S73A and S73A, S69A mutants with similar results. h HIS-tagged MITF from 501mel cells engineered to express ectopically inducible 6xHIS tagged MITF treated with or without 200 nM TPA for 6 h purified using nickel beads from urea-dissolved cells and probed with anti-acetyl K206 or anti-MITF antibodies. Two replicates are shown, and purification of a non-his-tagged MITF (ΔHis) was used as a negative control. Source data for Western blots are provided in Supplementary Fig. S6.

Fig. 3. Live-cell single-molecule tracking of HALO-tagged MITF.

a HALO-tagged MITF expression vectors. NLS; nuclear localization sequence. b Western blot of HALO-tagged MITF WT and mutants in 501mel cells with or without treatment with Doxycycline used to ensure similar expression levels performed in parallel with the SMT analysis shown in this figure. Vinculin was a loading control. Induction of HALO-MITF by Dox in 501mel cells has been performed independently at least 3 times with similar results. For Source Data see Supplementary Fig. S6. c Single molecule tracking movies collected at 100 fps tracks were extracted using the FiJi/ImageJ plugin TrackMate and analysed in terms of the distribution of single-molecule displacements between consecutive frames that was then fit with a three component model (one immobile component and two diffusing components), to generate quantitative estimates for HaloTag, WT MITF and mutants. d Quantitative estimates derived from SMT using WT and K206 HALO-tagged MITF for the fraction of molecules in the bound and slow states and the respective diffusion coefficients. Each point represents a single cell, the blue line the median, the box limits represent upper and lower quartiles, and whiskers extend between Q1 − 1.5 IQR and Q3 + 1.5 IQR, where IQR is the interquartile range. For HaloTag, WT MITF, K206R and K206Q mutants respectively N_replicates = 2; N_cells = 19, 30; 30; 30; N_jumps: 130387; 245200; 210929; 172286. Statistical test: non-parametric Kruskal-Wallis (two-sided). e Slower movies (frame rate 2 fps, laser exposure 200 ms) were acquired to calculate the distribution of residence times for immobile MITF molecules, following photobleaching correction using data collected on H2B-HaloTag (see Methods). f The fraction of bound molecules displaying a residence time longer than 100 s (left) and the (restricted) mean survival time (right). N_replicates = 2; N_cells = 30, 30, 30, 30, 35, and 36, and N_molecules = 3836; 3429; 3219; 1185; 3809; 1225 for WT MITF, K206R, K206Q, Δbasic, USF1 and p53 respectively; error bars (SEM) were calculated by the jacknife approach (see Methods); each SMT experiment was performed at least twice after adjustment of doxycycline concentration to ensure similar MITF expression levels.

Fig. 4. Acetylation of K206 specifically decreases binding to an M-box.

a, b DNA-binding affinity of bacterially expressed and purified MITF WT and mutant DNA-binding domains determined using fluorescence anisotropy. Representative titration curves of each fluorescein-labeled oligonucleotide with MITF WT and mutants. The reported anisotropy values are the average of triplicate measurements, from which the base line corresponding to the anisotropy of the free fluorescent probe was subtracted. (*) p < 0.05 based on an unpaired two-tailed t-test with error bars indicating SD calculated for each measurement point. a Graphs are presented in order to optimally compare the affinity of each MITF variant for three different DNA motifs investigated here. b Curves represented on this graph correspond to the titration of two DNA motifs by MITF WT and acetylated MITF. c Quantitative determination of DNA-binding affinities of MITF variants, measured as K_D (nM). The K_D values correspond to the means of three independent measurements and the +/− error numbers represent the standard deviations. Source data are provided in a Supplementary Source Data file.

Fig. 5. K206 affects melanocyte development.

a Amino acid sequence alignment of human and zebrafish MITF showing K206 (human) and K201 (fish) conservation. The fish mitfa coding sequence was placed under the control of the fish mitfa promoter. b Complementation of neural crest mitfa-null nacre zebrafish using MITF WT and K201 (K206 in human MITF) mutants. c Quantification of numbers of melanocytes in the zebrafish complementation assay using Jitter plots in which the dots in the plots represent the numbers of melanocytes in each rescued embryo with at least 1 melanocyte, the line shows mean +/−SEM. Statistical test: Kruskal-Wallis test and Dunn’s multiple comparisons test. Data were obtained from a total of 7 experiments in which a total of 411 fish were analysed: 20 for empty vector control; 132 for WT-MITF; 201 for MITF K201R; and 127 for MITF K201Q. Source data are provided in the Supplementary Source Data file.

Fig. 6. K206 controls MITF genome-wide distribution.

a Western blot of 501mel melanoma cell lines stably expressing HA-tagged doxycycline-inducible MITF WT and K206 mutants after induction with indicated concentrations of doxycycline. MITF inducibility by Dox is highly reproducible and has been repeated independently at least 5 times. Source data are provided in Supplementary Fig. S6. b Heatmap visualization of MITF WT and K206 mutants read density derived from HA-MITF ChIP-seq using indicated concentrations of doxycycline. Input controls are shown to the right. c UCSC genome-browser screenshots of ChIP-seq profiles of HA-MITF WT and mutants at different concentrations of doxycycline as indicated. R1 and R2 indicate two independent replicates. d ChIP-seq peak scores for a set of lysosomal or pigmentation genes as indicated for MITF WT and mutants induced using 20 ng doxycycline. e Relative ratio of ChIP peaks with indicated motifs for MITF WT and mutants expressed at 0, 20, and 100 ng doxycycline. f Consensus motifs detected beneath the ChIP peaks for MITF WT and mutants. g Scatter plots comparing ChIP-seq peak score versus moving average of relative motif incidence (100 peaks window) for MITF WT and mutants. To aid visual comparison the data points were fitted with smoothed line using generalized additive models. The 95% confidence interval is shown in gray shade around the fitted smoothed line.