A transcriptome-wide atlas of RNP composition reveals diverse classes of mRNAs and lncRNAs

Abstract

Eukaryotic genomes generate a heterogeneous ensemble of mRNAs and long noncoding RNAs (lncRNAs). LncRNAs and mRNAs are both transcribed by Pol II and acquire 5' caps and poly(A) tails, but only mRNAs are translated into proteins. To address how these classes are distinguished, we identified the transcriptome-wide targets of 13 RNA processing, export, and turnover factors in budding yeast. Comparing the maturation pathways of mRNAs and lncRNAs revealed that transcript fate is largely determined during 3' end formation. Most lncRNAs are targeted for nuclear RNA surveillance, but a subset with 3' cleavage and polyadenylation features resembling the mRNA consensus can be exported to the cytoplasm. The Hrp1 and Nab2 proteins act at this decision point, with dual roles in mRNA cleavage/polyadenylation and lncRNA surveillance. Our data also reveal the dynamic and heterogeneous nature of mRNA maturation, and highlight a subset of "lncRNA-like" mRNAs regulated by the nuclear surveillance machinery.

Graphical abstract

Figure 1

Transcriptome-wide Analysis of RNP Composition (A) mRNA maturation and decay factors selected for analysis. (B) Relative recovery of spliced mRNAs versus unspliced pre-mRNAs bound to the tested proteins, expressed as the ratio of RNA fragments spanning exon-exon:intron-exon junctions. (C) Average binding distribution of the tested proteins across mRNAs. For each protein, average hit densities were calculated for 120 bins spanning their 1,000 most abundantly bound mRNAs (including 2 × 10 bins for 100 nt 5′ and 3′ flanking regions). 5′-proximal hits can arise from binding to promoter-proximal ncRNAs or to the 5′ end of full-length mRNAs. (D–I) Total hits for each protein in RPL3 and HTB2 pre-mRNAs, snoRNAs, CUTs, SUTs, and XUTs, as a percentage of all hits in Pol II transcribed RNAs (mRNAs, CUTs, SUTs, snRNAs, and snoRNAs; Table S1). (J–M) Hit distributions along individual transcripts, at the indicated scales (hits per million hits in Pol II transcribed RNAs). Note the different scale used for Hrp1 data in K and M due to the high level of binding. See also Figure S1 and Table S1.

Figure S1

Transcriptome-wide Identification of Targets of Key RNA Maturation and Turnover Proteins, Related to Figure 1 (A) Left: autoradiogram of protein:RNA complexes purified by SDS-PAGE. Red bars indicate the migration of the proteins when analyzed by western blotting, and this information was used to select the appropriate regions (blue boxes) for excision. RNA fragments were then isolated from these excised regions and analyzed by high-throughput sequencing. Right: silver stain analysis of representative protein:RNA complexes following affinity purification. (B) Pairwise Spearman rank comparison of CRAC data sets, based upon the number of hits for each protein in each annotated transcript. (C) Breakdown of recovered RNA fragments by transcript class. We include several published sets of lncRNA annotations: CUTs (cryptic unstable transcripts) and SUTs (stable unannotated transcripts) (Xu et al., 2009), XUTs (Xrn1-sensitive unstable transcripts) (van Dijk et al., 2011), antisense lncRNAs (Yassour et al., 2010), and antisense/intergenic lncRNAs (Granovskaia et al., 2010). We also include our own antisense/intergenic annotations for transcripts not annotated in (Xu et al., 2009): transcripts mapping to genomic regions with no annotated feature on either strand are classed as “intergenic,” and transcripts mapping to the strand opposite to an annotated feature are classed as “antisense.” (D) Distribution of binding sites across the 35S pre-rRNA, scaled to the maximum height for each data set.

Figure S2

Functions of RNA-Binding Proteins in the Biogenesis and Turnover of mRNAs and lncRNAs, Related to Figure 2 (A) Distribution of Ski2- and Xrn1-binding sites around all mRNA stop codons. Overlapping reads are flattened into single contigs to avoid bias toward abundant transcripts. (B) Average binding distribution of the cap-binding complex subunit Cbc1 and TREX components Gbp2 and Tho2 across CUTs, SUTs and snRNAs. Average hit densities were calculated for 120 bins spanning the 500 most abundantly bound CUTs or SUTs, and all snRNAs (including 2x10 bins for 100 nt flanking regions). (C) Top: average binding distribution of Cbc1, Gbp2 and Tho2 across all monocistronic snoRNAs. Average hit densities were calculated for 120 bins (including 2x10 bins for 100 nt flanking regions). Bottom: Cbc1 hits across individual snoRNAs (distance in nt from the 5′ end of the mature snoRNA). (D) Box and whisker plot of the number of hits for each SUT recovered bound to Hek2, Tho2, Gbp2 and Mex67. Transcripts are grouped by RNP profiles (see Figure 2). Asterisks indicate where median values are significantly different from the cluster I-III median (Wilcoxon rank sum test, p < 0.01). (E) Cumulative distribution of log₂ stabilization ratios for SUTs and mRNAs in the indicated surveillance mutants (Gudipati et al., 2012). Transcripts are grouped by RNP profiles (Figure 2). (F) Histogram showing the prevalence of SUTs (left) or mRNAs (right) with different length (CNN)_n motifs. For each transcript, the longest CNN repeat was recorded, and the proportion of transcripts with each CNN repeat length plotted. Transcripts were divided into the clusters defined in Figure 2. For mRNAs, an additional category is included (green), comprising mRNAs with particularly high binding to Hek2 (determined by clustering analysis as per Figure 2, but with Hek2 included). (G) Distribution of Hek2, Cbc1, Nab2 and Pab1 CRAC hits across SUT034. Cytidine frequency within the SUT sequence is indicated. (H) Box and whisker plot of the total number of hits for each SUT or mRNA recovered in ribosome profiling experiments (Brar et al., 2012) (GEO sample GSM843748). Transcripts are divided into the clusters defined in Figure 2. Although cluster X mRNAs are included in the cluster VI-X category, we also show them separately as they appear to be particularly highly translated. For comparison, the number of Gbp2 CRAC hits for each mRNA is shown (right). The upper and lower edges of the boxes are the upper and lower quartiles, respectively. The whiskers extend from these edges to the most extreme value within 1.5 times the length of the box.

Figure 2

RNP Composition Reflects Transcript Function and Reveals Distinct RNA Classes Transcripts arranged by k-medians clustering (n = 4960; k = 10, column 1) based upon their binding to maturation and turnover factors. Column 2: location of CUTs (red), SUTs (blue) and mRNAs (white). Columns 3–8: relative number of hits (per million hits in Pol II transcribed RNAs) in Cbc1, Mtr4, Nab2, Mex67, Xrn1, and Ski2 data sets for each transcript. Column 9: Pab1 peak score, reflecting the specificity of Pab1 interaction. Column 10: significantly overrepresented GO terms (green) and individual transcripts referred to in the text (color coding is indicated in the key). See also Figure S2 and Tables S2, S3, S4.

Figure 3

RNA Classes Are Defined by Alternative Modes of 3′ End Formation (A) Red: average distribution of Pab1 hits across mRNAs, SUTs, and CUTs (300 nt flanks included). Blue: average distribution of poly(A) (pA) sites, defined as the last genome-encoded nucleotide within Pab1-bound RNA fragments with a non-genome-encoded poly(A) tail. (B–F) Analysis of the set of genomic sequences flanking the most frequent pA site for each mRNA (n = 5,453) or SUT (n = 370). (B) Sequence logo of these regions. (C) Sequence logo of the most highly enriched motif in these regions. (D and E) Occurrence of UAUAUA and AAUAAA motifs. (F) Nucleotide frequency distributions.

Figure 4

Dual Roles of Hrp1 and Nab2 in mRNA Cleavage/Polyadenylation and in CUT Surveillance (A) Enrichment scores for 6 nt motifs in Hrp1-bound RNA fragments. Inset: proportion of Hrp1-binding sites containing the UAUAUA motif in mRNAs, CUTs and SUTs. (B) Distribution of Hrp1 hits (black) and deletions (red) around UAUAUA motifs in mRNAs, CUTs, and SUTs. (C) Average distribution of binding sites for Hrp1 (top) and Nab2 (bottom) across mRNAs, SUTs, and CUTs in the wild-type background. For Nab2 binding to CUTs an rrp6Δ strain is also shown. (D) Frequency of UAUAUA motifs in Hrp1-binding sites near the 3′ end of mRNAs, CUTs, and SUTs (Xu et al., 2009). (E) Northern analysis of CUT479, CUT200, and CCW12 abundance in wild-type, P_GAL-NAB2 and P_GAL-HRP1 strains after glucose-dependent repression. Northern signals were quantified for replicate experiments (right). Bottom: western analysis of HA-Hrp1, HA-Nab2, and Mtr4 abundance.

Figure 5

Nuclear Surveillance Factors Bind to Promoter-Proximal lncRNAs Arising from Early Termination within Protein-Coding Genes (A) Frequency of non-genome-encoded A-tails in CRAC data sets. (B) Length distribution of non-genome-encoded A-tails at the 3′ end of mapped reads in selected data sets (relative to the abundance of 2 nt tails). (C) Length distribution of A-tails on raw reads (% of all analyzed reads). In comparison to (B), this analysis can detect longer A-tails but does not distinguish between genome-encoded and nonencoded tails. (D) Prevalence of tRNAs among all (blue) or A-tailed (red) RNA fragments recovered for Mtr4, Ski2, and Xrn1. (E) Average distribution of all (gray) and A-tailed (blue) Ski2 and Mtr4 hits across scaled mRNAs. (F) Distribution of Mtr4 hits across individual mRNAs aligned by their TSSs (n = 1,000). (G) Average distribution of all (gray) and A-tailed (blue) Nab2 hits across scaled mRNAs (left), and average distribution of Nab2 hits with different length A-tails across scaled mRNAs (right). (H) Average distribution around mRNA TSSs and 3′ ends of (1) Mtr4-, Nrd1-, and Nab3-binding sites (CRAC) (Wlotzka et al., 2011), (2) elongating Pol II (Churchman and Weissman, 2011) and (3) 3′ ends of unstable transcripts (“CUT fraction”) (Neil et al., 2009).

Figure 6

Determining the Fate of Pol II Transcripts Early stages in RNP assembly (CBC and TREX binding) are the same for all Pol II transcripts. If transcription is terminated by Nrd1-Nab3 or at a putative promoter-proximal checkpoint (1a), the transcript is rapidly eliminated by the nuclear surveillance machinery. However, SUTs and mRNAs contain signals upon which the cleavage and polyadenylation machinery assembles (1b), and so acquire a stable Pab1-bound polyA tail. Most SUTs remain in the nucleus (2a), but mRNAs and some SUTs undergo additional events (e.g., sequence-specific binding by Hek2) that promote recruitment of the export receptor Mex67 (2b) and export to the cytoplasm. Approximately 10% of mRNAs behave like lncRNAs, with retention and degradation in the nucleus.