The finger loop of the SRA domain in the E3 ligase UHRF1 is a regulator of ubiquitin targeting and is required for the maintenance of DNA methylation

Abstract

The Su(var)3-9, enhancer of zeste, and trithorax (SET) and really interesting new gene (RING) finger-associated (SRA) protein domain is conserved across bacteria and eukaryota and coordinates extrahelical or "flipped" DNA bases. A functional SRA domain is required for ubiquitin-like with PHD and RING finger domains 1 (UHRF1) E3 ubiquitin ligase activity toward histone H3, a mechanism for recruiting the DNA methylation maintenance enzyme DNA methyltransferase 1 (DNMT1). The SRA domain supports UHRF1 oncogenic activity in colon cancer cells, highlighting that UHRF1 SRA antagonism could be a cancer therapeutic strategy. Here we used molecular dynamics simulations, DNA binding assays, in vitro ubiquitination reactions, and DNA methylation analysis to identify the SRA finger loop as a regulator of UHRF1 ubiquitin targeting and DNA methylation maintenance. A chimeric UHRF1 (finger swap) with diminished E3 ligase activity toward nucleosomal histones, despite tighter binding to unmodified or asymmetric or symmetrically methylated DNA, uncouples DNA affinity from regulation of E3 ligase activity. Our model suggests that SRA domains sample DNA bases through flipping in the presence or absence of a cytosine modification and that specific interactions of the SRA finger loop with DNA are required for downstream host protein function. Our findings provide insight into allosteric regulation of UHRF1 E3 ligase activity, suggesting that UHRF1's SRA finger loop regulates its conformation and function.

Keywords: DNA methylation; DNA-binding protein; E3 ubiquitin ligase; SRA domain; allosteric regulation; epigenetics; molecular dynamics; string method in collective variables; ubiquitin-like with PHD and RING finger domains 1 (UHRF1).

Figure 1.

Structural analysis of SRA domains reveals divergent finger loops. A, phylogenetic analysis and domain maps of proteins that have annotated SRA domains in reviewed UniProt entries. B, all-atom structural alignment of SRA domains (colored as in D; PDB codes 2ZKD, 3CLZ, 3Q0C, 4NJ5, 4QEN, and 4PW6), performed by align command in PyMOL. For simplicity, only hemimethylated DNA (He5mC) bound to UHRF1 SRA is shown (PDB code 3CLZ). C, overlay of SRA-bound DNA molecules after alignment by all-protein atoms using the align command in PyMOL (colors correspond to Table 1); the root mean square deviation was calculated only for the shared atoms of the flipped 5-methylcytosine and 5-hydroxymethylcytosine. D, amino acids surrounding SRA finger loops aligned with ClustalW.

Figure 2.

Constraining the DNA phosphate backbone destabilizes base pairing and lowers the energy barrier to spontaneous base flipping. A, overlaid structural models of intrahelical (background) and extrahelical (foreground) 5-methylcytosine; the extrahelical position is the start of the simulation and is the bound pose from the UHRF1 SRA–He5mC complex (PDB code 3CLZ). ξ₁ indicates rotation of the nucleoside subunit around the phosphate backbone of 5-methylcytosine as plotted in B–E. ξ₂ measures rotation of the base around the sugar linkage of 5-methylcytosine as plotted in B–E. B–D, free-energy plots of 1-μs molecular dynamics simulations of He5mC in A that is unrestrained (B), 5′ and 3′ phosphates surrounding 5-methylcytosine restrained to match PDB code 3CLZ (C), or restrained at all backbone phosphates (D). E, ξ₁ rotation of 5-methyl-cytosine plotted against free energy from the simulations in B (purple), C (yellow), and D (green).

Figure 3.

Organization of the phosphate backbone and insertion of the SRA thumb are energetic barriers in the SRA–DNA interaction. A, unbound starting pose for the string method in collective variables of the interaction between UHRF1 SRA Δ finger loop and He5mC (Δ finger loop; residues 484–494 were removed, leaving a Gly⁴⁸³-Gln⁴⁹⁵ peptide bond in its place). UHRF1 bound to He5mC (PDB code 3CLZ) served as the structural starting point for the simulation. Spheres indicate atoms included in the collective variables that were required to find their bound pose. B, free-energy plot of the string method (image 1, unbound; image 20, bound) over 80 iterations. C, representation of free energy and representative structural models over the oscillatory phase in the string method from iterations 50 to 79. 5-Methylcytosine and its paired guanosine are shown as sticks in the structural models. Each iteration is shown in light gray, whereas the average is shown in purple; error bars represent the 95% confidence interval. D, representative isothermal titration calorimetry result (n = 3), measuring the interaction between MBP-tagged UHRF1 SRA (35 μm) and 5-methylcytidine (1 mm, left) or He5mC (430 μm, right).

Figure 4.

The UHRF1 SRA finger loop controls selective binding to modified DNA and E3 ligase activity. A, fluorescence polarization binding assays measuring the interaction between MBP-tagged UHRF1 SRA (left panel) or UHRF1 SRA that has residues 484–497 (see colored box in Fig. 1D) replaced with residues 434–445 from the SUVH5 SRA (right panel) and a FAM-labeled 12-bp dsDNA probe containing a single, centrally located CpG that was either unmodified (UnDNA), hemimethylated (He5mC), or symmetrically methylated (Sy5mC). Data were fit to a one-site binding model with the Hill slope, and K_d is presented as ± S.E. of technical triplicate measurements (data shown are representative of two independent experiments). Right panel, SDS-PAGE followed by Coomassie Brilliant Blue staining of recombinant SRA domains. B, in vitro ubiquitination of purified HeLa polynucleosomes by either WT or SUVH5 finger-swapped, full-length UHRF1. Shown is a representative gel imaged for TAMRA-labeled ubiquitin after SDS-PAGE at 2, 5, 15, and 25 min (n = 2). None, control reactions containing all of the ubiquitin machinery and substrate without E3; cbb, Coomassie Brilliant Blue. C, density plot of Infinium MethylationEPIC BeadChip analysis of HCT116 cells 11 days after simultaneous knockdown of UHRF1 and transgenic cover by either NDI1 (− control), UHRF1 WT (+ control), UHRF1 SUVH5 finger, or UHRF1 N489A (β values: 0, unmethylated; 1, methylated). Also shown is a Western blot of HCT116 cells used in the DNA methylation analysis.