@Article{Alkhnbashi_Costa_Shah-CRISP_predi_repea-2014,
  author =	 {Alkhnbashi, Omer S. and Costa, Fabrizio and Shah, Shiraz A. 
                  and Garrett, Roger A. and Saunders, Sita J. and Backofen, 
                  Rolf},
  title =	 {{CRISPRstrand}: predicting repeat orientations to determine 
                  the {crRNA}-encoding strand at {CRISPR} loci},
  journal =	 {Bioinformatics},
  year =	 {2014},
  volume =	 {30},
  number =	 {17},
  pages =	 {i489-i496},
  user =	 {sita},
  note =         {In the proceedings of the 13th {E}uropean {C}onference on {C}omputational {B}iology ({ECCB}) 2014.},
  pmid =	 {25161238},
  doi = 	 {10.1093/bioinformatics/btu459},
  issn = 	 {1367-4803},
  issn = 	 {1367-4811},
  abstract =	 {MOTIVATION: The discovery of CRISPR-Cas systems almost 20 
                  years ago rapidly changed our perception of the bacterial 
                  and archaeal immune systems. CRISPR loci consist of several 
                  repetitive DNA sequences called repeats, inter-spaced by 
                  stretches of variable length sequences called spacers. This 
                  CRISPR array is transcribed and processed into multiple 
                  mature RNA species (crRNAs). A single crRNA is integrated 
                  into an interference complex, together with 
                  CRISPR-associated (Cas) proteins, to bind and degrade 
                  invading nucleic acids. Although existing bioinformatics 
                  tools can recognize CRISPR loci by their characteristic 
                  repeat-spacer architecture, they generally output CRISPR 
                  arrays of ambiguous orientation and thus do not determine 
                  the strand from which crRNAs are processed. Knowledge of the 
                  correct orientation is crucial for many tasks, including the 
                  classification of CRISPR conservation, the detection of 
                  leader regions, the identification of target sites 
                  (protospacers) on invading genetic elements and the 
                  characterization of protospacer-adjacent motifs. RESULTS: We 
                  present a fast and accurate tool to determine the 
                  crRNA-encoding strand at CRISPR loci by predicting the 
                  correct orientation of repeats based on an advanced machine 
                  learning approach. Both the repeat sequence and mutation 
                  information were encoded and processed by an efficient graph 
                  kernel to learn higher-order correlations. The model was 
                  trained and tested on curated data comprising >4500 CRISPRs 
                  and yielded a remarkable performance of 0.95 AUC ROC (area 
                  under the curve of the receiver operator characteristic). In 
                  addition, we show that accurate orientation information 
                  greatly improved detection of conserved repeat sequence 
                  families and structure motifs. We integrated CRISPRstrand 
                  predictions into our CRISPRmap web server of CRISPR 
                  conservation and updated the latter to version 2.0. 
                  AVAILABILITY: CRISPRmap and CRISPRstrand are available at 
                  http://rna.informatik.uni-freiburg.de/CRISPRmap. CONTACT: 
                  backofen@informatik.uni-freiburg.de SUPPLEMENTARY 
                  INFORMATION: Supplementary data are available at 
                  Bioinformatics online.}
}