pubmed.ncbi.nlm.nih.gov

CoRAL: predicting non-coding RNAs from small RNA-sequencing data - PubMed

CoRAL: predicting non-coding RNAs from small RNA-sequencing data

Yuk Yee Leung et al. Nucleic Acids Res. 2013 Aug.

Abstract

The surprising observation that virtually the entire human genome is transcribed means we know little about the function of many emerging classes of RNAs, except their astounding diversities. Traditional RNA function prediction methods rely on sequence or alignment information, which are limited in their abilities to classify the various collections of non-coding RNAs (ncRNAs). To address this, we developed Classification of RNAs by Analysis of Length (CoRAL), a machine learning-based approach for classification of RNA molecules. CoRAL uses biologically interpretable features including fragment length and cleavage specificity to distinguish between different ncRNA populations. We evaluated CoRAL using genome-wide small RNA sequencing data sets from four human tissue types and were able to classify six different types of RNAs with ∼80% cross-validation accuracy. Analysis by CoRAL revealed that microRNAs, small nucleolar and transposon-derived RNAs are highly discernible and consistent across all human tissue types assessed, whereas long intergenic ncRNAs, small cytoplasmic RNAs and small nuclear RNAs show less consistent patterns. The ability to reliably annotate loci across tissue types demonstrates the potential of CoRAL to characterize ncRNAs using small RNA sequencing data in less well-characterized organisms.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.

The analysis workflow for differentiating between six different classes of ncRNAs in smRNA-seq data sets.

Figure 2.
Figure 2.

Percentage of small ncRNA loci identified by smRNA-seq for two human tissue types: (a) brain and (b) skin.

Figure 3.
Figure 3.

Feature spectrum plots for three of the ncRNA classes (as specified in the figure), in the (a–c) brain data and (d–f) the skin data. Each box corresponds to one length feature, and each grey line represents one locus. The red dots are outside of the 99th percentile of each distribution.

Figure 4.
Figure 4.

smRNA-seq reads plotted on the predicted RNA secondary structures using SAVoR (14) for (a) an miRNA, (b) a C/D box snoRNA and (c) a transposon-derived RNA. The miRNA and C/D box snoRNA structures are as reported by RFAM, and the transposon-derived RNA structure is as predicted by RNAfold.

Figure 5.
Figure 5.

MDS based projections of the data for (a) brain and (b) skin. The three most discriminative classes are miRNA (yellow), C/D box snoRNA (blue) and transposon-derived RNAs (grey).

Figure 6.
Figure 6.

Selected features in each of the two data sets (as specified) for the six-class classifier: antisense expression (antisense), 5′ and 3′ smRNA positional entropy (pos_entropy5p and pos_entropy3p), nucleotide preference (nuc_A, nucC, nuc_G and nuc_T), MFE value and the smRNA length features from 14 to 30 nt (L14–L30). The sign of the value indicates whether the feature was larger (positive) or smaller (negative) within that class, on average, than the other classes (by difference of means).

Similar articles

Cited by

References

    1. Eddy SR. Non-coding RNA genes and the modern RNA world. Nat. Rev. Genet. 2001;2:919–929. - PubMed
    1. Todd G, Karbstein K. RNA takes center stage. Biopolymers. 2007;87:275–278. - PubMed
    1. Guttman M, Amit I, Garber M, French C, Lin MF, Feldser D, Huarte M, Zuk O, Carey BW, Cassady JP, et al. Chromatin signature reveals over a thousand highly conserved large non-coding RNAs in mammals. Nature. 2009;458:223–227. - PMC - PubMed
    1. Khalil AM, Guttman M, Huarte M, Garber M, Raj A, Rivea Morales D, Thomas K, Presser A, Bernstein BE, Van Oudenaarden A, et al. Many human large intergenic noncoding RNAs associate with chromatin-modifying complexes and affect gene expression. Proc. Natl Acad. Sci. U.S.A. 2009;106:11667–11672. - PMC - PubMed
    1. Black DL, Chabot B, Steitz JA. U2 as well as U1 small nuclear ribonucleoproteins are involved in premessenger RNA splicing. Cell. 1985;42:737–750. - PubMed

Publication types

MeSH terms

Substances