Widespread RNA 3'-end oligouridylation in mammals

Abstract

Nontemplated 3'-end oligouridylation of RNA occurs in many species, including humans. Unlike the familiar phenomenon of polyadenylation, nontemplated addition of uridines to RNA is poorly characterized in higher eukaryotes. Recent studies have reported nontemplated 3'-end oligouridylation of small RNAs and mRNAs. Oligouridylation is involved in many aspects of microRNA biology from biogenesis to turnover of the mature species, and it may also mark long mRNAs for degradation by promoting decapping of the protective 5'-cap structure. To determine the prevalence of oligouridylation in higher eukaryotes, we used next-generation sequencing technology to deeply examine the population of small RNAs in human cells. Our data revealed widespread nontemplated nucleotide addition to the 3' ends of many classes of RNA, with short stretches of uridine being the most frequently added nucleotide.

FIGURE 1.

The nontemplated 3′ ends of small RNAs in human ES cells. (A) The distribution of paired-end-2 sequencing primer reads by RNA gene class. The distribution for all uniquely aligned reads (left) and those reads with nontemplated 3′-end THP (right) are shown. (B–F) The frequency at which each nucleotide was found as the nontemplated THP was calculated for each RNA gene class. The first column is the percent of reads for a specific gene or gene class that had nontemplated 3′ ends. The numbers in the (MM) column are the number of reads with mismatches between the THP and the reference genome. (C) The overall frequency of nontemplated 3′ ends for several classes of RNA genes. Shown are the most highly sequenced genes of miRNAs (B), tRNA anti-codons (D), snRNAs (E), and snoRNAs (F).

FIGURE 2.

Distribution of nontemplated THP lengths. The THP lengths were counted for reads with nontemplated 3′-end nucleotides. Overall, 3.2 million reads covering 11,616 genes were collapsed to 82,176 unique sequences. The cumulative frequency of THP lengths of this collapsed data set is shown; that is, if an RNA had a THP of five uridines, it was included in the totals for lengths of one through five. The expected line is the probability of finding a homopolymer of a given length at random, based on equal representation of all nucleotides.

FIGURE 3.

Characteristics of TSSa-RNA. (A) The length distribution of TSSa-RNAs. (B) The distribution of distances of TSSa-RNAs measured from the TSS to the 3′ end of the read for all TSSa-RNAs and TSSa-RNAs with nontemplated uridine addition. (*) Note the different scales for sense and antisense. The distribution of nontemplated 3′-end THP lengths for sense (C) and antisense (D) TSSa-RNAs.

FIGURE 4.

Characteristics of spliced introns. (A) The distribution of lengths of all splice site reads and splice site reads with nontemplated 3′-end THPs plotted as a fraction of their respective populations. (B) The distribution of nontemplated 3′-end THP lengths sequenced on splice site reads.