Sen1 has unique structural features grafted on the architecture of the Upf1-like helicase family

Abstract

The superfamily 1B (SF1B) helicase Sen1 is an essential protein that plays a key role in the termination of non-coding transcription in yeast. Here, we identified the ~90 kDa helicase core of Saccharomyces cerevisiae Sen1 as sufficient for transcription termination in vitro and determined the corresponding structure at 1.8 Å resolution. In addition to the catalytic and auxiliary subdomains characteristic of the SF1B family, Sen1 has a distinct and evolutionarily conserved structural feature that "braces" the helicase core. Comparative structural analyses indicate that the "brace" is essential in shaping a favorable conformation for RNA binding and unwinding. We also show that subdomain 1C (the "prong") is an essential element for 5'-3' unwinding and for Sen1-mediated transcription termination in vitro Finally, yeast Sen1 mutant proteins mimicking the disease forms of the human orthologue, senataxin, show lower capacity of RNA unwinding and impairment of transcription termination in vitro The combined biochemical and structural data thus provide a molecular model for the specificity of Sen1 in transcription termination and more generally for the unwinding mechanism of 5'-3' helicases.

Keywords: RNA helicases; non‐coding transcription; transcription termination.

Figure 1. A recombinant version of the Saccharomyces cerevisiae Sen1 helicase core retains the main biochemical properties of the full‐length protein

1. Analysis of RNA‐dependent ATPase activity of Sen1 proteins. Top: Schematic diagram of full‐length Sen1 purified from yeast (ySen1 FL), and recombinant Sen1_Hel and Sen1_Hel E1591Q mutant. An asterisk denotes the presence of a mutation in the helicase domain. Bottom, left: SDS–PAGE analysis of the purified proteins used in these assays (M: molecular weight marker). 2 pmol of ySen1 FL and 25 pmol of Sen1_Hel proteins were loaded. Bottom, right: Graphical representation of the ATP hydrolyzed by the different Sen1 proteins as a function of time. Values represent the average and standard deviation (SD) from three independent experiments.

2. Time course analysis of the ATP‐dependent 5′‐3′ duplex unwinding activity of Sen1 proteins. Reactions contained 5 nM of Sen1 and 2 nM of substrate. An RNA:DNA duplex composed of a 44‐mer RNA annealed to a 19‐mer DNA molecule to provide a 5′‐end 25‐nt single‐strand overhang was used as the substrate (see Appendix Table S1 for sequence details). The asterisk (*) denotes the presence of a FAM at the 5′ end of the DNA. The first lanes correspond to heat‐denatured (95°C) samples, and the last lanes are control reactions incubated with Sen1 proteins in the absence of ATP. The graph on the right shows the fraction of duplex unwound as a function of time. Data were fitted with Kaleidagraph to the Michaelis–Menten equation. Values represent the average and standard deviation (SD) from three independent experiments.

3. In vitro transcription termination (IVTT) assays with 20 nM of ySen1 FL and 40 nM of Sen1_Hel proteins. Left: Scheme of an IVTT assay. Ternary ECs composed of Pol II, fluorescently labeled nascent RNA, and DNA templates are assembled and attached to streptavidin beads via the 5′ biotin of the non‐template strand to allow subsequent separation of beads‐associated (B) and supernatant (S) fractions. An asterisk (*) denotes the presence of a FAM at the 5′ end of the RNA. The transcription template contains a G‐less cassette followed by a G‐stretch in the non‐template strand. After adding an ATP, UTP, CTP mix, Pol II transcribes until it encounters the G‐rich sequence. Sen1 dissociates ECs paused at the G‐stretch and releases Pol II and the associated transcripts to the supernatant. Right: PAGE analysis of RNAs from a representative IVTT assay. The fraction of transcripts released from ECs stalled at the G‐stretch is used as a measure of the termination efficiency. Representative gel of one out of two independent experiments (values of RNA released in both experiments can be found in the corresponding source data file).

Source data are available online for this figure.

Figure EV1. Identification and characterization of a recombinant helicase core of Saccharomyces cerevisiae Sen1 suitable for structural studies

1. SDS–PAGE analysis of Sen1_976‐1880 tagged with C‐terminal CPD‐His₈. Lane E shows the elution fraction after Ni²⁺‐affinity purification step, and lane InsP6 shows the tag cleavage after the protein was incubated with 400 μM inositol hexakisphosphate (InsP6) for 20 min at 4°C. The protein before and after tag cleavage is smaller than expected: Theoretical molecular weights of Sen1_976‐1880‐CPD‐His₈ and Sen1_976‐1880 are ˜126 kDa and ˜102 kDa, respectively. Left lane M shows a molecular weight marker.

2. Time course analysis of the ATP‐dependent 3′‐5′ duplex unwinding activity of Sen1 proteins. Reactions were performed in the presence of 5 nM of Sen1 and 2 nM of substrate. An RNA:DNA duplex composed of a 44‐mer RNA annealed to a 19‐mer DNA molecule to provide a 3′‐end 25‐nt single‐strand overhang was used as the substrate (see Appendix Table S1 for sequence details). The asterisk (*) denotes the presence of a FAM at the 5′ end of the DNA.

3. Snapshots of the electron density maps at important regions of the structure described in the text. The 2Fo‐Fc maps are contoured at 1.7σ.

Figure 2. Common and unique structural features of the Sen1 helicase core

Structures of yeast Sen1_Hel‐ADP (left), Upf1_Hel‐AMPPNP (middle, PDB: 2GJK, Cheng et al, 2007), and IGHMBP2_Hel (right, PDB: 4B3F, Lim et al, 2012) determined in the absence of RNA are shown in a similar orientation after optimal superposition of their respective RecA1 domains (on the right in this front‐view orientation). Dotted lines indicate disordered loops not modeled in the present structure. On top, there is a scheme with the domain organization of the full‐length proteins, with predicted structured and unstructured regions shown as rectangles and lines, respectively. The fragments crystallized are highlighted in color. The RecA1 and RecA2 domains are in yellow, the “stalk” in gray, subdomain 1B (the “barrel”) in orange and subdomain 1C (the “prong”) in red. In the case of Sen1_Hel, the N‐terminal “brace” is shown in blue. CH domain, cysteine and histidine rich domain; R3H domain, Arg‐x‐x‐x‐His motif containing domain.

Figure EV2. Biochemical and structural properties of Sen1, and comparison with Upf1

1. A

   Zoom‐in view of the nucleotide binding site in Sen1 (left) and Upf1 (right) (PDB: 2XZO, Chakrabarti et al, 2011). The adenine ring is sandwiched between an apolar surface of RecA1 and an aromatic residue protruding from the short linker that connects RecA1 to RecA2 (Tyr1655, corresponding to Tyr638_Upf1 and Tyr442_IMGMBP2). In addition, the conserved side chain of Gln1339 (corresponding to Gln413_Upf1 and Gln196_IMGMBP2) forms a bidentate hydrogen‐bond interaction with the N6 and N7 moieties of the adenine ring.

2. B

   Comparison of the structures of yeast Sen1_Hel‐ADP, human UPF1_Hel‐AMPPNPP (PDB: 2GJK, Cheng et al, 2007), UPF1_Hel‐ADP:AlF₄ ⁻‐RNA (PDB: 2XZO, Chakrabarti et al, 2011), and yeast Upf1_Hel‐CH‐ADP:AlF₄ ⁻‐RNA (PDB: 2XZL, Chakrabarti et al, 2011). The molecules in a side‐view orientation (90° clockwise rotation around a vertical axis with respect to the front‐view in Fig 4A).

3. C

   Comparison of the RNA‐binding sites of Sen1 (left) and Upf1 (right) (PDB: 2XZO, Chakrabarti et al, 2011).

4. D–F

   Functional analysis of the Sen1_Hel T1289A, R1293A mutant harboring substitutions at conserved positions at the predicted RNA‐binding surface. (D) Fluorescence anisotropy assays. Curves represent three independent measurements. (E) ATP hydrolysis assays. Values correspond to the average and SD of three independent experiments. (F) IVTT assays performed in the same conditions as in Fig 1C. The images correspond to different gels migrated and processed in parallel. The values of nascent RNA released correspond to one out of two independent experiments.

Figure 3. The evolutionarily conserved interactions of the N‐terminal “brace” of Sen1

1. A, B

   Zoom‐in views (with the corresponding overall views) showing the extensive hydrophobic interactions the “brace” makes with RecA1, the “stalk” helices, and the “barrel”. Selected residues are shown in stick representation. Panels (A and B) show the molecule in a side‐view and back‐view orientations (90° and 180° clockwise rotation around a vertical axis with respect to the front‐view in Fig 2).

2. C

   Structure‐based sequence alignment of the “brace” showing the amino acid conservation (highlighted in blue) and the interactions with RecA1 (yellow circles), the “stalk” helices (gray circles), and the “barrel” (orange circles).

Figure 4. Analysis of RNA binding features of Sen1

1. Comparison of the structures of yeast Sen1_Hel‐ADP, human UPF1_Hel‐AMPPNPP (PDB: 2GJK, Cheng et al, 2007), UPF1_Hel‐ADP:AlF₄ ⁻‐RNA (PDB: 2XZO, Chakrabarti et al, 2011), and yeast Upf1_Hel‐CH‐ADP:AlF₄ ⁻‐RNA (PDB: 2XZL, Chakrabarti et al, 2011). Colors are the same as in Fig 2. The nucleotides and RNA are shown in black. On the bottom, schematic representation of the subdomain organization of Sen1 and Upf1 illustrating the different location of the “barrel” (in orange) and its repositioning in Upf1 upon RNA binding. Note that the CH domain of Upf1 pushes the “barrel” and changes its orientation extending the RNA‐interaction region. The molecules in a side‐view orientation are shown in Fig EV2B.

2. RNase protection assays with yeast Sen1_Hel, Upf1_Hel, and Upf1_CH‐Hel in the presence of different nucleotides (ADP:BeF₃ ⁻ and ADP:AlF₄ ⁻, which mimic the ground state and the transition state of the nucleotide in the ATPase cycle). A Coomassie‐stained SDS–PAGE with the different proteins used is shown on the left (M: molecular weight marker). RNA fragments were obtained by digesting ³²P body‐labeled (CU)₂₈C 57‐mer RNA in the presence of the indicated proteins with RNase A and RNase T1. The left lane was loaded with 10‐mer and 15‐mer radioactively labeled transcripts as size markers. The asterisks (*) identify minor fragments likely due to the contiguous binding of more than one protein to the same RNA.

Source data are available online for this figure.

Figure 5. A critical role for the “prong” in duplex unwinding and transcription termination

1. On top is a schematic presentation of the Sen1_Hel variants analyzed in the experiments below. At the bottom is a zoom‐in view of the “prong”. The dotted lines indicate the approximate positions of the “prong” deletion mutants ΔUP for the removal of the upper part and ΔLP for the removal of also lower part. Selected residues are shown in stick representation.

2. RNase protection assays with Sen1 proteins as in Fig 4B in the presence of ADP:AlF₄ ⁻.

3. Analysis of the ATPase activity of the different Sen1_Hel variants. Values correspond to the average and SD of three independent experiments.

4. Analysis of the effect of the different “prong” mutations on Sen1_Hel unwinding activity. Reaction conditions are the same as in Fig 1B. The graph shows the fraction of duplex unwound as a function of time. Data were fitted with Kaleidagraph to the Michaelis–Menten equation. The values reflect the average and standard deviations (SD) from three independent measurements.

5. IVTT assays in the absence and in the presence of the different Sen1_Hel versions (80 nM in the reaction). Representative gel of one out of two to three independent experiments (values of RNA released in additional experiments are provided in the corresponding source data file).

Source data are available online for this figure.

Figure EV3. Analysis of the impact of the “prong” mutations on the affinity of Sen1_Hel for the RNA

Electrophoretic mobility shift assay (EMSA) using a 5′‐end fluorescently labeled 44‐mer RNA as the substrate (DL3316, see Appendix Table S1) at 2 nM and Sen1_Hel variants at 10, 20, 40, 80, and 160 nM at the final concentrations. Gels were migrated and processed in parallel. The values correspond to the mean of two independent experiments. At high protein concentrations, Sen1_Hel forms high‐order complexes with the RNA that are retained in the wells of the gel.

Figure EV4. Analysis of the phenotype of the ΔLP mutant in vivo

1. A Sen1 variant harboring the ΔLP cannot support cell viability. A Δsen1 strain (YDL2767) covered by an URA3‐containing plasmid (pFL38) expressing wild‐type (wt)Sen1 was transformed with a TRP1‐plasmid (pFL39) carrying either the wt or a ΔLP version of SEN1. After over‐night growth in non‐selective medium, cells initially harboring both plasmids were plated on minimal medium (CSM) containing 5‐fluoroorotic acid (5‐FOA) to select for cells that have lost the URA3 plasmid (and can therefore survive thanks to the TRP1 plasmid‐borne SEN1 copy). The absence of cells growing in 5‐FOA and containing the TRP1 plasmid expressing Sen1 ΔLP indicates that the ΔLP deletion is lethal.

2. The Sen1ΔLP mutant is strongly defective in transcription termination in vivo. Northern blot analyses of two well‐characterized NNS‐targets, snR47 and snR13, in a Sen1‐AID (auxin‐induced degron, Nishimura et al, 2009) strain carrying a plasmid (pFL39) expressing either the wt or a ΔLP version of SEN1. A strain harboring an empty vector was included as a positive control for termination defects. To detect the primary products of NNS‐dependent termination that are processed/degraded by the exosome, the strain was also deleted in the exonuclease RRP6. Sen1‐AID was depleted for 1 h by the addition of 100 μM indole‐3‐acetic acid (a natural auxin) to monitor the capacity of the plasmid‐borne versions of SEN1 to induce transcription termination. The strong accumulation of longer RNA species in the sen1ΔLP mutant compared to the wt is indicative of major termination defects. Under non‐depletion conditions, the strain harboring the mutant protein exhibits a dominant‐negative phenotype (partial termination defects), indicating that Sen1ΔLP has similar expression levels compared to the endogenous Sen1. The ACT1 transcript is used as a loading control.

Figure EV5. Multiple sequence alignment of the helicase domain of Upf1‐like helicases

The multiple alignment was done using Clustal Omega, and the conservation was calculated using BLOSUM62 and is shown in purple.

Figure 6. Functional characterization of Sen1_Hel mutants harboring AOA2‐associated substitutions

1. Mapping of selected AOA2‐associated substitutions (shown in magenta) introduced at the equivalent positions in Sen1_Hel for their functional analysis. The mutations are reported in Chen et al (2014) and in the UCLA Neurogenetics SETX Database.

2. Quantitative measurements of RNA binding affinities of the mutants by fluorescence anisotropy using fluorescently labeled AU‐rich RNA as the substrate. The data were fitted to a binding equation describing a single‐site binding model to obtain the dissociation constants (K _D, indicated on the left of the curves). The best fit was plotted as a solid line. The K _Ds and their corresponding errors are the mean and standard deviation (SD) of a minimum of three independent experiments.

3. Analysis of the ATPase activity of the Sen1_Hel R1820Q mutant predicted to be affected in nucleotide binding. Values correspond to the average and SD of three independent experiments.

4. Assessment of the effect of several AOA2‐associated mutations on Sen1_Hel unwinding activity. RNA:DNA duplex unwinding reactions using a 75‐mer RNA annealed to a 20‐mer DNA oligonucleotide (see Appendix Table S1) leaving a 5′‐end 55 nt single‐strand overhang as the substrate. Reactions contained 30 nM of Sen1_Hel variants and 0.5 nM of substrate. The efficiency of unwinding indicated corresponds to the fraction of substrate unwound by the different proteins at 30 min. Values correspond to the average and SD of three independent experiments.

5. Analysis of the impact of AOA2‐associated mutations on the efficiency of transcription termination. IVTT assays performed in the presence of 80 nM of the different Sen1 variants. The values of nascent RNA released correspond to one out of two independent experiments. Quantification of both experiments is included in the corresponding source data file.

Source data are available online for this figure.