Genomic analysis of human microRNA transcripts

Abstract

MicroRNAs (miRNAs) are important genetic regulators of development, differentiation, growth, and metabolism. The mammalian genome encodes approximately 500 known miRNA genes. Approximately 50% are expressed from non-protein-coding transcripts, whereas the rest are located mostly in the introns of coding genes. Intronic miRNAs are generally transcribed coincidentally with their host genes. However, the nature of the primary transcript of intergenic miRNAs is largely unknown. We have performed a large-scale analysis of transcription start sites, polyadenylation signals, CpG islands, EST data, transcription factor-binding sites, and expression ditag data surrounding intergenic miRNAs in the human genome to improve our understanding of the structure of their primary transcripts. We show that a significant fraction of primary transcripts of intergenic miRNAs are 3-4 kb in length, with clearly defined 5' and 3' boundaries. We provide strong evidence for the complete transcript structure of a small number of human miRNAs.

Fig. 1.

Distribution of TSS, CpG, and EST distances from the 5′ end of the pre-miRNAs (positioned at zero) and in random intergenic sequences. (a) TSS predictions. (b) TSS predictions for clustered intergenic pre-miRNAs. (c) CpG predictions. (d) EST predictions. (e) The miRNA cluster hsa-mir-200c∼141 overlapped by six ESTs aligned completely in the upstream and downstream regions.

Fig. 2.

Distribution of TF-binding site distances in intergenic miRNAs and random sequences. (a) TF-binding site predictions. (b) Poly(A) signal predictions. (c) The miRNA cluster hsa-mir-200c∼141 with six matched ESTs and the 5′/3′ ends supported by mapped ditags (U_59235 and U_115145). (d) Structure of a canonical human intergenic pri-miRNA.