@Article{Will:etal:_infer_non_codin_rna_famil:PLOS2007,
  author =	 {Sebastian Will and Kristin Reiche and Ivo L. Hofacker and
                  Peter F. Stadler and Rolf Backofen},
  title =	 {Inferring Non-Coding {RNA} Families and Classes by Means of
                  Genome-Scale Structure-Based Clustering},
  journal =	 {PLoS Comput Biol},
  year =	 2007,
  volume =       {3},
  number =       {4},
  pages =        {e65},
  issn =         {1553-7358},
  issn =         {1553-734X},
  pmid =         {17432929},
  doi =          {10.1371/journal.pcbi.0030065},
  user =	 {will},
  abstract =	 {The RFAM database defines families of ncRNAs by means of
                  sequence similarities that are sufficientto establish
                  homology. In some cases, such as microRNAs, box H/ACA
                  snoRNAs, functional commonalities define classes of RNAs
                  that are characterized by structural similarities, and
                  typically consist ofmultiple RNA families. Recent advances
                  in high-throughput transcriptomics and comparative genomics
                  have produced very large sets of putative non-coding RNAs
                  and regulatory RNA signals. For many ofthem, evidence for
                  stabilizing selection acting on their secondary structures
                  has been derived, and at least approximate models of their
                  structures have been computed. The overwhelming majority of
                  these hypo-thetical RNAs cannot be assigned to established
                  families or classes. We present here a structure-based
                  clustering approach that is capable of extracting putative
                  RNA classesfrom genome-wide surveys for structured RNAs. The
                  LocARNA tool implements a novel variant of theSankoff
                  algorithm that is sufficiently fast to deal with several
                  thousand candidate sequences. The method is also robust
                  against false positive predictions, i.e., a contamination of
                  the input data with unstructured ornon-conserved
                  sequences. We have successfully tested the LocARNA-based
                  clustering approach on the sequences of the
                  RFAM-seedalignments. Furthermore, we have applied it to a
                  previously published set of 3332 predicted structured
                  elements in the Ciona intestinalis genomes (Missal et al.,
                  Bioinformatics 21(S2), i77-i78). In addition torecovering
                  e.g. tRNAs as a structure-based class, the method identifies
                  several RNA families, including microRNA and snoRNA
                  candidates, and suggests several novel classes of ncRNAs for
                  which to-date norepresentative has been experimentally
                  characterized.}
}