A circular engineered sortase for interrogating histone H3 in chromatin

Abstract

Reversible modification of the histone H3 N-terminal tail is critical in regulating chromatin structure, gene expression, and cell states, while its dysregulation contributes to disease pathogenesis. Understanding the crosstalk between H3 tail modifications in nucleosomes constitutes a central challenge in epigenetics. Here we describe an engineered sortase transpeptidase, cW11, that displays highly favorable properties for introducing scarless H3 tails onto nucleosomes. This approach significantly accelerates the production of both symmetrically and asymmetrically modified nucleosomes. We demonstrate the utility of asymmetrically modified nucleosomes produced in this way in dissecting the impact of multiple modifications on eraser enzyme processing and molecular recognition by a reader protein. Moreover, we show that cW11 sortase is very effective at cutting and tagging histone H3 tails from endogenous histones, facilitating multiplex "cut-and-paste" middle down proteomics with tandem mass tags. This cut-and- paste proteomics approach permits the quantitative analysis of histone H3 modification crosstalk after treatment with different histone deacetylase inhibitors. We propose that these chemoenzymatic tail isolation and modification strategies made possible with cW11 sortase will broadly power epigenetics discovery and therapeutic development.

Figure 1.. ‘Cut-and-paste’ isolation of histone H3 tail peptides with cW11 sortase enables quantitative middle-down proteomics.

(A) Workflow for isolating tandem mass tagged histone H3 tails with cW11 sortase. (B) SDS-PAGE of 14-hour sortase reaction in a nuclear acid extract. (C) Tris-Tricine PAGE of histone H3(1–34) synthetic standards (1: 140 ng; 2: 420 ng) and TCA precipitated H3(1–32)-TMT from the acid extract reaction; bands between 25 and 37 kDa are histone H1. (D) Structure of the TMT-labelled oligoglycine peptide illustrating sortase reactive GGG, charge carrying K and carboxamide, and TMT labelled aminoalanine. (E) Unique proteoforms detected in each 6plex sample and shared between the two samples. (F) Quantifiable proteoforms detected in each 6plex sample and shared between the two samples. Volcano plot of significant (p<0.05) log2-fold change and overall abundance of H3 proteoforms in HEK293T cells following treatment with (G) LSD1/HDAC1/CoREST complex-specific inhibitor Corin, or (H) pan class one HDAC inhibitor MS275.

Figure 2.. Designer nucleosome synthesis by sortase ligation.

Single, combinatorial and asymmetric modifications prepared by sortase nucleosome ligation (ubiquitin structure PDBID: 1UBQ). Isolated yields (bold) and yields estimated by area under the curve (parenthetical) are reported as a value (n = 1), range (n = 2) or mean with standard deviation (n ≥ 3).

Figure 3.. Asymmetric nucleosome synthesis by sortase ligation.

(Top) Asymmetric modifications prepared by sortase nucleosome ligation. Isolated yields (bold) and yields estimated by area under the curve (parenthetical) are reported as a value (n = 1), range (n = 2) or mean with standard deviation (n ≥ 3). (Bottom left) Western blot characterization of 147 bp nucleosomes: (1) H3 (aa33–135) starting material; (2) asymmetric H3K27ac & H3 (aa33–135) intermediate; (3) asymmetric H3K27ac & H3K9ac/K14ac/K18ac/K23ac product. (Bottom right) Deconvoluted mass spectrum of 147 bp asymmetric H3K27ac & H3K9ac/K14ac/K18ac/K23ac nucleosome.

Figure 4.. Trends in histone deacylase activity toward metabolic acylations.

(A) Log10 transformed V/[E] (min⁻¹) of Sirtuins 1, 2 and 6 and MiDAC toward 147 bp nucleosomes with one to eight carbon acylations of H3K9. (B) Log10 transformed V/[E] (min⁻¹) of class one and class three HDACs toward 147 bp nucleosomes with four carbon metabolism-linked acylations of H3K9. (C) Log10 transformed V/[E] (min⁻¹) of class one and class three HDACs toward 147 bp nucleosomes with H3K9 succinylation.

Figure 5.. Symmetric and Asymmetric effects of hyperacetylation on deacylase and demethylase activity.

(A) Sirt2, (B) Sirt6, and (C) MiDAC site-specific deacetylation rates with symmetrical mono-acetylated (1ac/1ac) and penta-acetylated (5ac/5ac) 147 bp nucleosomes. (D) Sirt2, (E) Sirt6, and (F) MiDAC site-specific deacetylation rates with asymmetric 147 bp nucleosomes isolating the specified acetylation site on a single tail; the second H3 tail was modified with either four acetylations (1ac/4ac) at the other predominant acetylation sites, or zero acetylations (1ac/0ac). (G) Illustration of in cis and in trans PTM interactions with a regulatory enzyme acting on a nucleosome substrate. (H) Illustration of an asymmetric nucleosome used to test for an in trans effect on a PTM regulatory enzyme. (I) LSD1-CoREST1 (LC) demethylation rates with asymmetric nucleosomes containing H3K14ac concurrently on the same histone H3 with H3K4me2 (yellow), H3K4me2 and H3K14ac separately on different histone H3 (blue), and without H3K14ac (pink) (* indicates p < 0.05, ** indicates p < 0.01,*** indicates p < 0.001, **** indicates p < 0.0001).

Figure 6.. Combinatorial effect of H3K9me3 and K18Ub/K23Ub on DNMT1 RFTS domain binding.

RFTS-sfGFP EMSA following titration with asymmetric H3K9me3/K18Ub/K23Ub & unmodified H3 nucleosome (left), asymmetric H3K18Ub/K23Ub & H3K9me3 nucleosome (middle), asymmetric H3K18Ub/K23Ub & unmodified H3 nucleosome (right).