Regulation of 3' splice site selection after step 1 of splicing by spliceosomal C* proteins

Abstract

Alternative precursor messenger RNA splicing is instrumental in expanding the proteome of higher eukaryotes, and changes in 3' splice site (3'ss) usage contribute to human disease. We demonstrate by small interfering RNA-mediated knockdowns, followed by RNA sequencing, that many proteins first recruited to human C* spliceosomes, which catalyze step 2 of splicing, regulate alternative splicing, including the selection of alternatively spliced NAGNAG 3'ss. Cryo-electron microscopy and protein cross-linking reveal the molecular architecture of these proteins in C* spliceosomes, providing mechanistic and structural insights into how they influence 3'ss usage. They further elucidate the path of the 3' region of the intron, allowing a structure-based model for how the C* spliceosome potentially scans for the proximal 3'ss. By combining biochemical and structural approaches with genome-wide functional analyses, our studies reveal widespread regulation of alternative 3'ss usage after step 1 of splicing and the likely mechanisms whereby C* proteins influence NAGNAG 3'ss choices.

Fig. 1.. C* complex proteins regulate NAGNAG 3'ss selection.

(A) Effects of C* protein knockdown on splicing as determined by RNA-seq. Top: rMATS-derived altered splicing changes for skipped exons (SE), retained introns (RI), A5′ss, and A3′ss for the indicated knockdowns. Bottom: %A3′ss of all alternative splicing events affected by each knockdown. Black line, fraction of A3′ss in all targets quantified by rMATS. (B) Scatter dot blot of distances between A3′ss. For each C* protein (indicated above), targets are separated into knockdown-induced proximal 3′ss usage (top) or distal 3′ss usage (middle). Green lines, median distance between A3′ss. Red line, median of three (>50% with a distance of exactly three). Black line, median 3′ss distance among all A3′ss quantified by rMATS. Bottom: Normalized ratio between alternatively spliced NAGNAG 3′ss and A3′ss with a distance larger than 3 nt (DIST > 3). The fraction of NAGNAGs among all A3′ss quantified by rMATS is set to 1 (black line). SLU7 is shown for comparison. (C) Volcano blots summarizing the global effect of FAM32A (left) or NOSIP (right) knockdown on NAGNAG 3′ss selection. See fig. S3D for further details. (D) Correlation coefficients for 10 tested NAGNAG splicing events, comparing RNA-seq and RT-PCR–derived %PSU values. (E) Validation RT-PCRs for NAGNAG alternative splicing of mrpl42 (top) and wwc1 (bottom) upon C* protein knockdown (indicated below). See fig. S3E for further details. (F) Overlap of alternatively spliced NAGNAG sites affected by individual C* protein knockdowns. For each of the eight knockdowns, rMATS-derived P values were correlated with all knockdowns in a pairwise manner. Right: Correlation scores, where darker colors indicate a lower percent of overlapping NAGNAG targets. (G) Cross-talk of C* complex factors during NAGNAG 3′ss selection. Mean PCR-derived %PSU values are shown for seven targets relative to the siCTRL upon single and double C* protein knockdown.

Fig. 2.. 3D cryo-EM model of the hC* complex.

Two different views of the molecular architecture of hC* complexes formed on PM5 pre-mRNA. Bottom: Summary of all modeled proteins and RNAs with color code. Black dot, proteins localized in PM5 hC* that were depleted by siRNA-mediated knockdown experiments.

Fig. 3.. An AC dinucleotide that mimics a 3′ss is docked in the PM5 hC* active site via interactions with the BS-A, 5′ss, and U6-A45.

(A) Schematic of the docking of a 3′ss mimic (A169 and C170) in PM5 C* via interactions with the BS-A, G+1, and U+2 of the intron, and U6-A45 in comparison with the docking of the 3′ss in the hP complex [Protein Data Bank (PDB) 6QDV]. Base pairing and stacking interactions are indicated by shading. (B) Close-up of the 3′ss dinucleotides and neighboring nucleotides in the catalytic core of PM5 hC* (this study) and hP (PDB 6QDV) complexes, and their fit to the respective cryo-EM densities.

Fig. 4.. Path of the PPT loop in hC*.

(A) Schematic of RNAs in the RNP core of the PM5 hC* complexes. Yellow balls, positions of the catalytic Mg²⁺ ions M1 and M2, as well as structural Mg²⁺ ions M3-M5. (B) Overview of the path of the PPT loop and 5′ end of the 3′ exon mimic (3′ exon*). (C and D) Tight fit of the 5′ region (C) and 3′ region (D) of the PPT loop, with space filling models of proteins forming the PPT loop pocket. (E) Electrostatic surface potential of proteins forming the PPT loop pocket, where blue indicates a positive charge and red indicates a negative charge. (F) Extended positive surface of CACTIN. Dashed line, the potential path for nucleotides of introns with a longer distance between the BS-A and 3′ss.

Fig. 5.. Spatial organization of the C* proteins FAM50A, CXORF56, TLS1, SDE2, ESS2, and NOSIP in hC*.

(A) FAM50A, CXORF56, and TLS1 interact with the β-sandwich domain of CACTIN, and FAM50A bridges BRR2 and PRP22. Bottom: Schematic of the domain structures of CACTIN, CXORF56, FAM50A, and TLS1, as predicted primarily by AlphaFold. Light green boxes, predicted domains not modeled in PM5 C*. RS, rich in serine-arginine dipeptides; H, helix; HD, helical domain; BSD; β-sandwich domain; GD, globular domain. (B) SDE2 stabilizes SYF2 and the U2/U6 helix II in hC*. Bottom: Schematic of the domain structures of SDE2 and SYF2. Color code as in (A). Helices that could be localized in C* are indicated by an asterisk. Abbreviations as in (A). SAP: SAF-A/B, Acinus, and PIAS domain. Red box, helical bundle formed by SDE2, SYF1, and CDC5L. (C) Localization of NOSIP and ESS2 in hC*. Bottom: Schematic of the domain structures of NOSIP and ESS2. H, helix; UB, U-box domain. Color code as in (A).

Fig. 6.. Identification of FAM32A, TLS1, and PRKRIP1 residues that regulate NAGNAG 3'ss choice.

(A) NAGNAG alternative splicing after FAM32A knockdown and rescue in HEK293 cells. Top: Sequence of FAM32A’s CT tail. Middle: Representative gel showing RT-PCR products for gpank1, after knockdown of FAM32A and transfection of a construct expressing siRNA-resistant versions of WT FAM32A or deletion mutants thereof, as indicated. Bottom: Quantification of independent RNA samples (n = 2 to 5). The line in each box depicts the median, and whiskers show the minimum to maximum values. All individual data points are shown. Statistical significance was determined by unpaired t tests and indicated by asterisks *P < 0.05, **P < 0.01, ***P < 0.001 and ****P < 0.0001. Green, mutants inducing distal 3′ss usage. (B) FAM32A mutants act in a dominant-negative manner. HEK293 cells were transfected with plasmids encoding the indicated FAM32A mutants and their effect on gpank1 NAGNAG splicing assayed by RT-PCR (n > 3). Quantification as in (A). Significance is indicated relative to the empty vector. (C) Volcano plot illustrating the global impact of FAM32A CT deletion (Δ17) on NAGNAG A3′ss choice (relative to CTRL cells transfected with an empty vector), as determined by RNA-seq. Significant distal AG usage upon overexpression is highlighted red and proximal AG usage is blue (|Δ%PSU| > 15 in dark red/blue). Top: Fraction of NAGNAG 3'ss whose regulation is significantly altered by FAM32AΔ17. (D) TLS1 mutants lacking α helices 159 to 172 and/or 178 to 208 act in a dominant-negative manner on NAGNAG A3′ss selection. Top: Schematic of predicted domains in TLS1’s CT region. HEK293 cells were transfected with the indicated TLS1 variants and their effect on gpank1 NAGNAG splicing (n > 3) investigated by RT-PCR. Quantification as in (B). ns, not significant. (E) PRKRIP1 mutants lacking amino acids 72 to 76, 62 to 75, or 62 to 93 act in a dominant-negative manner on NAGNAG A3′ss selection. Top: Domain structure of PRKRIP1’s central region. Experiments performed as described in (D).

Fig. 7.. Proposed mechanism for preferential selection of the proximal 3′ss AG.

(A) Repositioning of the branched helix during the C-to-C* transition leads to the movement of the PPT and 3′ exon nucleotides, leading to the looping out of the PPT and docking of the 3′ss to nucleotides of the branched intron structure. Organization of the PPT, 3′ exon nucleotides, and branched helix in hC (top) versus PM5 hC*. The proposed path of the first 10 nt of the PPT shown for hC is based on the hC cryo-EM structure (8, 39), whereas that of the next 11 nt is based on the path of the intron in the yeast Ci complex (44). For simplicity, only the NTD, En, RT, α-finger (α), and stalk (St) domains of PRP8, and the helicases PRP16 or PRP22 are shown. (B) Schematic of the PPT loop–binding pocket and docking of the proximal (top) or, upon loss of FAM32A (as an example), of the distal (bottom) 3′ss AG of the celf1 pre-mRNA containing an alternatively spliced NAGNAG 3′ss.