@Article{Heyne:Costa:Rose:Graph_align_struc:2012,
  author =	 {Heyne, Steffen and Costa, Fabrizio and Rose, Dominic and 
                  Backofen, Rolf},
  title =	 {{GraphClust}: alignment-free structural clustering of local 
                  {RNA} secondary structures},
  journal =	 {Bioinformatics},
  year =	 {2012},
  volume =	 {28},
  number =	 {12},
  pages =	 {i224-i232},
  user =	 {heyne},
  pmid =	 {22689765},
  doi = 	 {10.1093/bioinformatics/bts224},
  issn = 	 {1367-4811},
  issn = 	 {1367-4803},
  abstract =	 {MOTIVATION: Clustering according to sequence-structure 
                  similarity has now become a generally accepted scheme for 
                  ncRNA annotation. Its application to complete genomic 
                  sequences as well as whole transcriptomes is therefore 
                  desirable but hindered by extremely high computational 
                  costs. RESULTS: We present a novel linear-time, 
                  alignment-free method for comparing and clustering RNAs 
                  according to sequence and structure. The approach scales to 
                  datasets of hundreds of thousands of sequences. The quality 
                  of the retrieved clusters has been benchmarked against known 
                  ncRNA datasets and is comparable to state-of-the-art 
                  sequence-structure methods although achieving speedups of 
                  several orders of magnitude. A selection of applications 
                  aiming at the detection of novel structural ncRNAs are 
                  presented. Exemplarily, we predicted local structural 
                  elements specific to lincRNAs likely functionally 
                  associating involved transcripts to vital processes of the 
                  human nervous system. In total, we predicted 349 local 
                  structural RNA elements. AVAILABILITY: The GraphClust 
                  pipeline is available on request. CONTACT: 
                  backofen@informatik.uni-freiburg.de SUPPLEMENTARY 
                  INFORMATION: Supplementary data are available at 
                  Bioinformatics online.}
}