mRNA Deadenylation Is Coupled to Translation Rates by the Differential Activities of Ccr4-Not Nucleases

Abstract

Translation and decay of eukaryotic mRNAs is controlled by shortening of the poly(A) tail and release of the poly(A)-binding protein Pab1/PABP. The Ccr4-Not complex contains two exonucleases-Ccr4 and Caf1/Pop2-that mediate mRNA deadenylation. Here, using a fully reconstituted biochemical system with proteins from the fission yeast Schizosaccharomyces pombe, we show that Pab1 interacts with Ccr4-Not, stimulates deadenylation, and differentiates the roles of the nuclease enzymes. Surprisingly, Pab1 release relies on Ccr4 activity. In agreement with this, in vivo experiments in budding yeast show that Ccr4 is a general deadenylase that acts on all mRNAs. In contrast, Caf1 only trims poly(A) not bound by Pab1. As a consequence, Caf1 is a specialized deadenylase required for the selective deadenylation of transcripts with lower rates of translation elongation and reduced Pab1 occupancy. These findings reveal a coupling between the rates of translation and deadenylation that is dependent on Pab1 and Ccr4-Not.

Keywords: RNA binding protein; deadenylation; exonuclease; gene expression; mRNA decay; poly(A) tail; translation.

Graphical abstract

Figure 1

Pab1 Stimulates Stepwise Deadenylation by Ccr4-Not (A) Deadenylation by purified Ccr4-Not in the presence and absence of Pab1. The RNA substrate comprises 20 non-poly(A) nucleotides followed by a 60-adenosine poly(A) tail. RNA products (4-min time points) were resolved on a denaturing polyacrylamide gel. Pab1-bound substrates were prepared with two Pab1 molecules per RNA. (B) Coomassie-stained SDS-PAGE of pull-down assay showing binding of purified Ccr4-Not (red labels) to immobilized GST-Pab1. Purified proteins (before mixing), Input (proteins mixed before loading on resin), and Pull-down (proteins bound to resin after washing) are shown. The asterisk indicates a contaminant protein. (C) Deadenylation of 5′ fluorescently labeled 23-mer-A30 RNA substrate. Pab1-bound substrates were prepared with one Pab1 molecule per RNA. Poly(A) tail lengths are indicated, and RRM footprints are marked with red asterisks. (D) Deadenylation of 5′ fluorescently labeled 23-mer-A30 RNA substrates in the presence of Pab1 variants. The positions of footprints observed with wild-type Pab1 in (C) are indicated with red asterisks. See also Figures S1 and S2.

Figure 2

Shortening of Pab1-Bound Poly(A) Tails Is Catalyzed by Ccr4 (A) Deadenylation of a 23-mer-A30 RNA in the absence or presence of Pab1 by Ccr4-Not and variant complexes with mutations in the active site of Ccr4 (Ccr4-inactive), Caf1 (Caf1-inactive), or both Ccr4 and Caf1 (double-inactive). Densitometric analyses were performed on selected gels (bottom). (B) Global poly(A) tail length in wild-type (WT) S. cerevisiae and strains containing deletion of CCR4 or CAF1. The red asterisk indicates incomplete deadenylation in the ccr4Δ strain. Densitometric analyses were performed on selected gels (bottom). (C) Deadenylation of a 23-mer-A30 RNA by isolated Caf1 protein, Ccr4 (EEP nuclease domain), or the Caf1-Ccr4 heterodimer. (D) Coomassie-stained SDS-PAGE of pull-down assays showing binding of purified Ccr4 or Caf1 to immobilized GST-Pab1. Contaminant proteins are indicated with asterisks. In (A) and (C), Pab1-bound substrate was prepared with one Pab1 molecule per RNA. See also Figures S2 and S3.

Figure 3

Pab1 Organization on the Poly(A) Tail (A) Deadenylation by Ccr4-inactive Ccr4-Not to map Pab1-binding site on A30 and 23-mer-A30 RNA substrates. Red asterisks indicate accumulated product poly(A) tail lengths. (B) Deadenylation reaction end points (180 min) following addition of Ccr4-inactive Ccr4-Not to A30 (top) and 23-mer-A30 (bottom) RNA substrates in the presence of the indicated Pab1 variants. Red asterisks indicate accumulated product poly(A) tail lengths. Full time courses are shown in Figures S4A and S4B. Models of Pab1 binding to each RNA are shown on the right. (C) Deadenylation by Ccr4-inactive Ccr4-Not on 20-mer-A60 RNA in the absence or presence of Pab1 (2:1 molar ratio to RNA). Densitometric analysis of the reaction with Pab1 shows that the protected RNA fragment is ∼50–55 adenosines. A model for Pab1-RNA binding is shown. See also Figure S4.

Figure 4

Ccr4-Not Releases Pab1 from Short Poly(A) Tails (A) Fluorescence polarization assay showing interaction of Pab1 with 5′ 6-FAM-labeled A22, 10-mer-A12, and A12 RNAs. Error bars are standard error (n = 3 for A12; n = 5 for A22 and 10-mer-A12). K_Ds are represented as the mean ± standard error. (B) Deadenylation of A30 and 23-mer-A30 RNAs by Ccr4-Not analyzed by both denaturing PAGE (upper gels) and native PAGE (lower gels). Samples were collected from the same reaction at the indicated time points after addition of Ccr4-Not to allow a direct comparison between RNA product sizes and Pab1 binding, respectively. Pab1-bound substrate was prepared with one Pab1 molecule per RNA. Upper right panel is reproduced from Figure 1C for comparison. (C) Representative SwitchSENSE sensograms showing the dissociation of Pab1 from the indicated RNA sequences. Rate constants and half-lives for dissociation with standard error are shown for measurements performed in triplicate. See also Figures S4–S6.

Figure 5

Codon Optimality Influences Pab1 Association and mRNA Deadenylation Rate (A) Plot of Pab1-bound mRNA levels relative to total mRNA levels following normalization to poly(A) tail length and binning of mRNAs according to codon optimality. Values were calculated using previously published Pab1 RNA immunoprecipitation sequencing (RIP-seq), total RNA sequencing (RNA-seq), and poly(A) tail length profiling by sequencing (PAL-seq) data. ^∗∗∗p_adj < 10⁻³. (B) High-resolution polyacrylamide northern blots and plots of shortest poly(A) tail lengths of the OPT and NON-OPT mRNAs following GAL1 transcriptional pulse-chase experiments in WT or dhh1Δ cells. A0 indicates the migration of a completely deadenylated mRNA species. Asterisk denotes the accumulation of deadenylated mRNA species. The lane labeled dT is the 0 time point treated with oligo dT and RNaseH to indicate the migration position of fully deadenylated mRNA. Representative gels and plots of experiments done in triplicate are shown.

Figure 6

Caf1 Destabilizes mRNAs with Low Codon Optimality by Accelerating Deadenylation Rate (A) Northern blots of the OPT and NON-OPT reporters following GAL1 transcriptional shut-off experiments in WT, ccr4Δ, caf1Δ, and dhh1Δ yeast. mRNA half-lives are represented as mean ± standard deviation for experiments performed with four (dhh1Δ, ccr4Δ) or five (WT, caf1Δ) replicates. (B) Plots showing the deadenylation rate of the OPT and NON-OPT reporters in rpb1-1, rpb1-1/ccr4Δ, or rpb1-1/caf1Δ yeast determined from transcriptional pulse-chase experiments (see Figure S7). Data points are represented as mean ± standard deviations for experiments performed in triplicate. (C) Northern blots of OPT and NON-OPT reporters in WT yeast and OPT and NON-OPT reporters containing a stem loop (SL) in the 5′ UTR (SL-mRNA) in WT, ccr4Δ, caf1Δ, or dhh1Δ yeast after GAL1 transcriptional shut-off experiments. (D) Plot of S. cerevisiae mRNA half-lives in caf1Δ cells relative to WT cells binned according to codon optimality. ^∗∗: 10⁻² > p_adj > 10⁻³; ^∗∗∗p_adj < 10⁻³. See also Figure S7 and Table S1.

Figure 7

Models for Pab1 Release by Ccr4 and Coupling of Translation and Deadenylation Rates by Caf1 (A) Proposed model for the organization of Pab1 on the poly(A) tail with RRMs depicted linearly. The Pab1 molecule proximal to the 3′ UTR binds ∼22 adenosines through RRMs 1−3, and distal Pab1 molecules bind ∼28 adenosines with RRMs 1–4. Naked poly(A) not bound by Pab1 can be removed by either Caf1 or Ccr4, while RNA within the binding site of Pab1 can only be accessed by Ccr4. Pab1 self-association and interaction with other proteins may lead to higher-order structures on RNA. (B) The modular architecture of Pab1 permits deadenylation to occur before it completely dissociates from the poly(A) tail. (C) Translation elongation rate may contribute to Pab1 occupancy to affect deadenylation rate. Ccr4 is required for deadenylation of all mRNAs, but the requirement for Caf1 is specific to mRNAs with low codon optimality or reduced Pab1 occupancy.