Mapping snoRNA-target RNA interactions in an RNA-binding protein-dependent manner with chimeric eCLIP

Abstract

Background: Small nucleolar RNAs (snoRNAs) are non-coding RNAs that function in ribosome and spliceosome biogenesis, primarily by guiding modifying enzymes to specific sites on ribosomal RNA (rRNA) and spliceosomal RNA (snRNA). However, many orphan snoRNAs remain uncharacterized, with unidentified or unvalidated targets, and studies on additional snoRNA-associated proteins are limited.

Results: We adapted an enhanced chimeric eCLIP approach to comprehensively profile snoRNA-target RNA interactions using both core and accessory snoRNA-binding proteins as baits. Using core snoRNA-binding proteins, we confirmed most annotated snoRNA-rRNA and snoRNA-snRNA interactions in mouse and human cell lines and called novel, high-confidence interactions for orphan snoRNAs. While some of these interactions result in chemical modification, others may have modification-independent functions. We showed that snoRNA ribonucleoprotein complexes containing certain accessory proteins, like WDR43 and NOLC1, enriched for specific subsets of snoRNA-target RNA interactions with distinct roles in ribosome and spliceosome biogenesis. Notably, we discovered that SNORD89 guides 2'-O-methylation at two neighboring sites in U2 snRNA that fine-tune splice site recognition.

Conclusions: Chimeric eCLIP of snoRNA-associating proteins enables a comprehensive framework for studying snoRNA-target interactions in an RNA-binding protein-dependent manner, revealing novel interactions and regulatory roles in RNA biogenesis.

Fig. 1

Core snoRNP proteins show consistent RNA interactomes. A Schematic of (left) C/D and (right) H/ACA snoRNA-protein complexes. Red line represents the target RNA complementary to the snoRNA antisense element. B Overview of snoRNA-binding proteins with RNA interactomes profiled by ENCODE or (boldface) this work. C Distribution of reads to (left) major RNA classes and (right) snoRNA classes captured by eCLIP in K562 cells of the indicated core snoRBPs. D Fold-enrichment of different classes of snoRNAs in eCLIP datasets (both from ENCODE and generated in this study). Colors indicate different groups of protein baits (control—FLAG or V5). E Correlation of snoRNA fold-enrichment across (top) core C/D snoRBPs or (bottom) core H/ACA snoRBPs from eCLIP. Pearson correlations (R) are indicated (top left). Correlation between core C/D and H/ACA snoRBPs shown for contrast. Datapoints with less than 5 reads in IP were discarded. F Bubble plot showing pairwise correlation in snoRNA fold-enrichment between snoRBPs. Circle size and color indicate value of Pearson correlation coefficient (R). Data shown is average of 2 replicates per RBP

Fig. 2

Chimeric eCLIP of core C/D snoRNP proteins comprehensively recovers known C/D snoRNA interactions. A Schematic of chimeric eCLIP procedure. B Correlation of non-chimeric versus chimeric snoRNA read abundance from FBL chimeric eCLIP in mouse embryonic stem cells (mESC). Pearson correlation (R) is indicated. C Correlation of snoRNA chimeric read abundance from FBL versus NOP56 chimeric eCLIP in mESC. Pearson correlation (R) is indicated. D Chimeric read abundance for individual snoRNAs colored according to snoRNA functional class. The y-axis indicates average of chimeric RPM in FBL and NOP56 chimeric eCLIP. E Pie chart of total number of snoRNA chimeric reads from mESC according to snoRNA functional class from FBL chimeric eCLIP. F Browser tracks of non-chimeric reads and snoRNA chimeric reads mapped to pre-rRNA as captured by FBL and NOP56 chimeric eCLIP in mESC. Annotated Nm sites are shown. G Heatmap of chimeric read coverage across pre-rRNA and snRNA from FBL and NOP56 chimeric eCLIP for canonical snoRNAs. Known Nm target sites are shown in black. H Metagene plots of mESC chimeric read coverage flanking Nm (red) and pseudouridine (black) sites in rRNA and snRNA. Chimeric RPM, reads per million chimeric reads. Data shown is from 1 replicate per RBP

Fig. 3

Transcriptomic mapping of C/D snoRNA chimeras calls novel, high-confidence interactions in mESCs. A Stacked bars indicate the fraction of C/D snoRNA chimeric reads mapping to distinct classes of possible target RNAs from FBL and NOP56 chimeric eCLIP. B Number of high-confidence snoRNA-target interactions identified by chimeric eCLIP according to interaction status and target class. C Browser tracks of snoRNA chimeric reads mapped to pre-rRNA or snRNA as captured by FBL and NOP56 chimeric eCLIP from mESC. Significant peaks at (black) known or (pink) novel sites. (Right) Base pair complementarity of novel interactions. RiboMeth-seq (RMS) score is shown for the 5th nucleotide from the D/D′ box when high methylation is observed. D (Left) Percent complementarity of base pairing in snoRNA-target interactions for significant peaks at known or novel sites and (right) fraction of interactions associated with D or D′ antisense elements. E Consensus sequence of the D or D′ box predicted to guide the known or novel snoRNA-target interactions. F RMS score at rRNA or snRNA target sites for known versus novel interactions. The 5th nucleotide is the expected position for methylation. (RMS scores are average of 2 biological replicates). G (Left) Snord89 expression following treatment with non-targeting (control) or Snord89-targeting ASO and (right) RMS scores at methylated nucleotides in U2 snRNA. * indicates P < 0.05, two-tailed unpaired Welch’s t-test. N = 2 replicates per condition. H (Left) Snord101 expression following treatment with non-targeting (control) or Snord101-tageting ASO and (right) RMS scores at methylated nucleotides in 28S rRNA. * indicates P < 0.05, two-tailed unpaired Welch’s t-test. N = 2 replicates per condition

Fig. 4

RBPs that function in ribosomal RNA processing recover unique SNORD3 chimeric reads. A Fold-enrichment correlation between (x-axis) H/ACA and (y-axis) C/D snoRNAs across 8 snoRBPs and 223 ENCODE eCLIP datasets. B Correlation of snoRNA fold-enrichment in FBL and ribosomal RNA-associated RBP eCLIP in K562 cells. Correlation (R) is shown. Only snoRNAs with 5 or more reads in IP were plotted. C Box plot showing fold-enrichment of SNORD3 in eCLIP datasets for indicated groups of RBPs. Two-sample Kolmogorov–Smirnov (KS) test was performed. D Browser tracks of SNORD3 chimeric reads mapped to pre-rRNA as captured by chimeric eCLIP for the indicated RBPs in 293 T (FBL, NOP56, NOP58) or K562 (UTP18, WDR43) cells. Check marks indicate the known interactions or novel interactions identified in our study. E Bars indicate the abundance of SNORD3 chimeric reads (Reads Per Million Chimeric reads) at different processing sites in the pre-rRNA across the indicated RBPs. F Schematic of predicted structures of potential SNORD3-rRNA interactions, with labelled regions colored according to D. eCLIP data shown is average of 2 replicates per RBP; chimeric eCLIP results shown are a single replicate per RBP

Fig. 5

Chimeric eCLIP for spliceosomal RNA-associated RBPs enrich for snoRNA-snRNA interactions. A Fold-enrichment of non-chimeric C/D snoRNA reads from FBL versus LARP7 chimeric eCLIP in HepG2 cells. Datapoints for C/D snoRNAs with U6 interactions annotated in snoDB are colored. Datapoints with < 5 IP reads were discarded. B C/D box snoRNA chimeric read abundance (RPM) from FBL versus LARP7 chimeric eCLIP. Datapoints for C/D snoRNAs with U6 interactions annotated in snoDB are colored. C Heatmap of snoRNA chimeric read abundance (RPM) from FBL, LARP7, and NOLC1 chimeric eCLIP replicates for all snoRNAs with annotated U6 interactions. D Browser tracks show read density (per million chimeric reads) for U6-interacting snoRNA chimeras along the U6 snRNA for a single representative replicate. E SnoRNA:U6 chimeric read abundance (RPM) from FBL or LARP7 chimeric eCLIP. Colors indicate snoRNAs classified as (green) LARP7-associated U6 snoRNAs, (light green) non-LARP7-associated U6 snoRNAs, and (gray) all other snoRNAs. * indicates P < 0.05, unpaired two sample t-test. F SnoRNA:rRNA chimeric read abundance (RPM) for snoRNAs with known rRNA target sites from FBL or LAPR7 chimeric eCLIP. * indicates P < 0.05, unpaired two-sample t-test. G Target distribution of snoRNA:snRNA chimeric reads (RPM) recovered in chimeric eCLIP for the indicated RBPs. H Fold-enrichment of non-chimeric snoRNA reads in FBL versus NOLC1 chimeric eCLIP in HepG2 cells. Datapoints with < 5 IP reads were discarded. Circle outline color represents the type of SCARNA with (blue) C/D box motif, including Tandem-C/D SCARNAs, (pink) H/ACA box motif, including Tandem-H/ACA SCARNAs, and (orange) hybrid SCARNAs that possess both C/D and H/ACA box motifs. I SnoRNA chimeric read abundance (RPM) in FBL versus NOLC1 chimeric eCLIP. J Browser tracks show read density (per million chimeric reads) for snoRNA:U2 chimeric reads along the U2 snRNA for known and candidate U2-interacting snoRNAs for a single representative replicate (see Fig. S6L for second replicate). RPM: reads per million sequenced reads. Unless otherwise indicated, data shown is average of two replicates (FBL, NOLC1) or a single replicate (LARP7)

Fig. 6

SNORD89, a guide for U2 2′-O-methylation, plays a unique role in splicing control. A Bars indicate SNORD89 expression (from RT-qPCR) upon SNORD89 antisense oligonucleotide knockdown. B Bars indicate the number of significantly altered alternative splicing events from rMATS (FDR ≤£ 0.01, change in percent spliced in (|ΔΨ|) ≥ 0.1, with ≥ 10 junction reads in all samples), from RNA-seq comparing SNORD89 ASO versus no ASO control (2 replicates each). C–E Scatter plots indicate percent spliced in (Ψ) for (black) all exons, (green) knockdown-excluded, and (blue) knockdown-included cassette exons for C SNORD89, D PTBP1, and E U2AF1 knockdown. PTBP1 and U2AF1 data were obtained from the ENCODE project. Histograms indicate the frequency of Ψ values (in 0.05 bins) for (green) the control sample for knockdown-excluded exons, or (blue) the knockdown sample for knockdown-included samples. F,G Bars indicate the percent of events with Ψ ≥ 0.95 for F the control sample for knockdown-excluded exons, or G the knockdown sample for knockdown-included exons. Shown are (leftmost bar, blue) SNORD89 knockdown and (all other bars) all ENCODE RBP knockdown datasets with at least 100 significantly altered exons