The silencing protein SIR2 and its homologs are NAD-dependent protein deacetylases

Abstract

Homologs of the chromatin-bound yeast silent information regulator 2 (SIR2) protein are found in organisms from all biological kingdoms. SIR2 itself was originally discovered to influence mating-type control in haploid cells by locus-specific transcriptional silencing. Since then, SIR2 and its homologs have been suggested to play additional roles in suppression of recombination, chromosomal stability, metabolic regulation, meiosis, and aging. Considering the far-ranging nature of these functions, a major experimental goal has been to understand the molecular mechanism(s) by which this family of proteins acts. We report here that members of the SIR2 family catalyze an NAD-nicotinamide exchange reaction that requires the presence of acetylated lysines such as those found in the N termini of histones. Significantly, these enzymes also catalyze histone deacetylation in a reaction that absolutely requires NAD, thereby distinguishing them from previously characterized deacetylases. The enzymes are active on histone substrates that have been acetylated by both chromatin assembly-linked and transcription-related acetyltransferases. Contrary to a recent report, we find no evidence that these proteins ADP-ribosylate histones. Discovery of an intrinsic deacetylation activity for the conserved SIR2 family provides a mechanism for modifying histones and other proteins to regulate transcription and diverse biological processes.

Figure 1

NAD–nicotinamide exchange reactions with CobB, HST2, or SIR2. (A) Reactions were performed with (lanes 1, 3, 5, and 7) and without (lanes 2, 4, 6, and 8) histones, as indicated. (B) Reactions with acetylated (lanes 1–3, 7–9) or unacetylated (lanes 4–6, 10–12) H4 or H3 peptides. Peptides were acetylated as described in Materials and Methods.

Figure 2

Histone deacetylation by CobB, HST2, and SIR2 depends on NAD. The cpm present in the histones after enzyme incubation are depicted. Error bars show the variation between two independent experiments.

Figure 3

Histone deacetylation analyzed by gel electrophoresis. (A) An SDS/PAGE gel of histones acetylated with [³H]acetyl-CoA by HAT1 or by ESA1, as indicated, and then treated with no enzyme (lane 1), with HST2 (lanes 2 and 3), or with SIR2 (lanes 4 and 5). A fluorogram of the gel is depicted. (B) A Triton–acid–urea gel of chicken erythrocyte histones acetylated with HAT1 followed by deacetylation by HST2. The gel was stained with Coomassie blue to visualize the histone isoforms. The numbers 0–4 on the left refer to isoforms of H4 differing in charge, with 0 corresponding to the most positively charged isoform and 4 corresponding to the least positively charged form. Lane 1, histones incubated without HAT1; lanes 2 and 3, histones acetylated with HAT1, in the presence or absence of NAD; lanes 4 and 5, histones acetylated by HAT1, incubated with HST2, with and without NAD.

Figure 4

Deacetylation of an H4 peptide by HST2. The peptide was initially acetylated by HAT1. (A) H4 peptide deacetylation by HST2 depends on NAD. The cpm present in the peptide after enzyme incubation are depicted. (B) HPLC traces of the input unacetylated H4 peptide, the peptide after acetylation by HAT1, and the peptide after subsequent deacetylation by HST2.