Computational discovery of human coding and non-coding transcripts with conserved splice sites
26.05.2011
Rose D, Hiller M, Schutt K, Hackermüller J, Backofen R, Stadler PF.
Bioinformatics. 2011 Jul 15;27(14):1894-1900.
We introduce an approach to predict spliced long non-coding RNAs in vertebrate genomes combining comparative genomics and machine learning. We detect signatures of characteristic splice site evolution in vertebrate whole genome alignments. Since our approach relies only on predicted splice sites, it can uncover both coding and non-coding exons. Overall, we obtain 336 novel multi-exon transcript predictions from human intergenic regions that are conserved in evolution.
