@Article{Mendes_Heyne_Freitas-Navig_the_unexp-2012,
  author =	 {Mendes, Nuno D. and Heyne, Steffen and Freitas, Ana T. and 
                  Sagot, Marie-France and Backofen, Rolf},
  title =	 {Navigating the unexplored seascape of pre-{miRNA} 
                  candidates in single-genome approaches},
  journal =	 {Bioinformatics},
  year =	 {2012},
  volume =	 {28},
  number =	 {23},
  pages =	 {3034-41},
  user =	 {heyne},
  pmid =	 {23052038},
  doi = 	 {10.1093/bioinformatics/bts574},
  issn = 	 {1367-4811},
  issn = 	 {1367-4803},
  abstract =	 {MOTIVATION: The computational search for novel microRNA 
                  (miRNA) precursors often involves some sort of structural 
                  analysis with the aim of identifying which type of 
                  structures are prone to being recognized and processed by 
                  the cellular miRNA-maturation machinery. A natural way to 
                  tackle this problem is to perform clustering over the 
                  candidate structures along with known miRNA precursor 
                  structures. Mixed clusters allow then the identification of 
                  candidates that are similar to known precursors. Given the 
                  large number of pre-miRNA candidates that can be identified 
                  in single-genome approaches, even after applying several 
                  filters for precursor robustness and stability, a 
                  conventional structural clustering approach is unfeasible. 
                  RESULTS: We propose a method to represent candidate 
                  structures in a feature space, which summarizes key 
                  sequence/structure characteristics of each candidate. We 
                  demonstrate that proximity in this feature space is related 
                  to sequence/structure similarity, and we select candidates 
                  that have a high similarity to known precursors. Additional 
                  filtering steps are then applied to further reduce the 
                  number of candidates to those with greater transcriptional 
                  potential. Our method is compared with another single-genome 
                  method (TripletSVM) in two datasets, showing better 
                  performance in one and comparable performance in the other, 
                  for larger training sets. Additionally, we show that our 
                  approach allows for a better interpretation of the results. 
                  AVAILABILITY AND IMPLEMENTATION: The MinDist method is 
                  implemented using Perl scripts and is freely available at 
                  http://www.cravela.org/?mindist=1. CONTACT: 
                  backofen@informatik.uni-freiburg.de SUPPLEMENTARY 
                  INFORMATION: Supplementary data are available at 
                  Bioinformatics online.}
}