A systematic search for new mammalian noncoding RNAs indicates little conserved intergenic transcription

Abstract

Background: Systematic identification and functional characterization of novel types of noncoding (nc)RNA in genomes is more difficult than it is for protein coding mRNAs, since ncRNAs typically do not possess sequence features such as splicing or translation signals, or long open reading frames. Recent "tiling" microarray studies have reported that a surprisingly larger proportion of mammalian genomes is transcribed than was previously anticipated. However, these non-genic transcripts often appear to be low in abundance, and their functional significance is not known.

Results: To systematically search for functional ncRNAs, we designed microarrays to detect 3,478 intergenic and intronic sequences that are conserved between the human, mouse, and rat genomes, and that score highly by other criteria that characterize ncRNAs. We probed these arrays with total RNA isolated from 16 wild-type mouse tissues. Among 55 candidates for highly-expressed novel ncRNAs tested by northern blotting, eight were confirmed as small, highly-and ubiquitously-expressed RNAs in mouse. Of the eight, five were also detected in rat tissues, but none were detected at appreciable levels in human tissues or cultured cells.

Conclusion: Since the sequence and expression of most known coding transcripts and functional ncRNAs is conserved between human and mouse, the lack of northern-detectable expression in human cells and tissues of the novel mouse and rat ncRNAs that we identified suggests that they are not functional or possibly have rodent-specific functions. Our results confirm that relatively little of the intergenic sequence conserved between human, mouse and rat is transcribed at high levels in mammalian tissues, possibly suggesting a limited role for transcribed intergenic and intronic sequences as independent functional elements.

Figure 1

Summary of computational prediction and sorting of novel mammalian noncoding RNA. (a) Whole genome alignments were downloaded from UCSC [18], subset to regions of greater than 85% sequence identity, and analyzed with QRNA [14]. Removal of redundant and coding sequences left 36,756 ncRNA candidates containing 62 known ncRNAs (of approximately 400 known ncRNAs). Candidates were then sorted and the top 3,478 predicted RNAs, which contained 38 known ncRNAs (representing a 1,700 fold enrichment of real ncRNAs over random selection from genomic sequence), were selected for further screening. (b) Sorting was based on the QRNA score, stability (measured as a predicted free energy change using Mfold [44]), overlap with rat-mouse QRNA predictions, and genomic clustering (many predictions close to one another are likely the same transcript). This combination of four criteria was more powerful in identifying real ncRNAs than using the QRNA score alone. *UCSC [18], **See (b).

Figure 2

Screening, selection, and confirmation of novel ncRNA predictions. (a) Total RNA from 16 tissues was hybridized to custom Agilent microarrays containing probes to the QRNA predictions. (b) Most intensity measurements overlapped negative-control intensities (both random probe sequences and probes corresponding to randomly sampled intergenic regions), although a right-tailed distribution overlapping rRNA levels indicated detection of potential abundant novel transcripts. (c) Expanded y-axis region from (b), axes denote absolute probe intensity counts. (d) Sample schematic of microarray spots corresponding to a transcript that was tested further by northern analysis. (e) 55 transcripts in total were screened by Northern analysis.

Figure 3

Abundantly and ubiquitously expressed novel mouse transcripts are not expressed in human tissues or cells. (a) Northern analysis of mouse transcripts using mouse-specific probes. U5 and U4 probes were used as loading controls as indicated and were co-hybridized with test probes. (b) No signal was detected in Northern analyses using human-specific probes. Human tissues were analyzed with a longer exposure (right panel) since short RNAs were slightly underrepresented in these commercially-obtained samples. Mouse-, and human-specific probe sequences complementary to the novel ncRNA predictions and images of all full-scale northern blots are available in Additional files 4 and 5.

Figure 4

Overlap between known and predicted ncRNA types. (a) 3,478 QRNA predictions, 390 mouse annotated ncRNAs, and 716 human ribosomal exons were mapped to the human genome (hg17) regions surveyed by Cheng et al. [9] using poly-A minus RNA derived from HepG2 cells. 833 QRNA predictions, 151 mouse ncRNAs, and 260 exons are located in regions surveyed by Cheng et al. (b) Shown are distributions of the percentage of overlap of each sequence with a transfrag for actual genomic positions versus randomly positioned sequences in regions surveyed by Cheng et al. [9]. (c) Schematic of how an overlap was calculated for one QRNA prediction that overlaps a transfrag. This was repeated for all overlaps and the distributions are shown in (b).