@Article{Mitrofanov_Alkhnbashi_Shmakov-CRISP_ident_CRISP-NAR2020,
  author =	 {Mitrofanov, Alexander and Alkhnbashi, Omer S. and Shmakov, 
                  Sergey A. and Makarova, Kira S. and Koonin, Eugene V. and 
                  Backofen, Rolf},
  title =	 {{CRISPRidentify}: identification of {CRISPR} arrays using 
                  machine learning approach},
  journal =	 NAR,
  year =	 {2020},
  volume =	 {},
  number =	 {},
  pages =	 {},
  user =	 {alkhanbo},
  pmid =	 {33290505},
  doi = 	 {10.1093/nar/gkaa1158},
  issn = 	 {1362-4962},
  issn = 	 {0305-1048},
  abstract =	 {CRISPR-Cas are adaptive immune systems that degrade foreign 
                  genetic elements in archaea and bacteria. In carrying out 
                  their immune functions, CRISPR-Cas systems heavily rely on 
                  RNA components. These CRISPR (cr) RNAs are repeat-spacer 
                  units that are produced by processing of pre-crRNA, the 
                  transcript of CRISPR arrays, and guide Cas protein(s) to the 
                  cognate invading nucleic acids, enabling their destruction. 
                  Several bioinformatics tools have been developed to detect 
                  CRISPR arrays based solely on DNA sequences, but all these 
                  tools employ the same strategy of looking for repetitive 
                  patterns, which might correspond to CRISPR array repeats. 
                  The identified patterns are evaluated using a fixed, 
                  built-in scoring function, and arrays exceeding a cut-off 
                  value are reported. Here, we instead introduce a data-driven 
                  approach that uses machine learning to detect and 
                  differentiate true CRISPR arrays from false ones based on 
                  several features. Our CRISPR detection tool, CRISPRidentify, 
                  performs three steps: detection, feature extraction and 
                  classification based on manually curated sets of positive 
                  and negative examples of CRISPR arrays. The identified 
                  CRISPR arrays are then reported to the user accompanied by 
                  detailed annotation. We demonstrate that our approach 
                  identifies not only previously detected CRISPR arrays, but 
                  also CRISPR array candidates not detected by other tools. 
                  Compared to other methods, our tool has a drastically 
                  reduced false positive rate. In contrast to the existing 
                  tools, our approach not only provides the user with the 
                  basic statistics on the identified CRISPR arrays but also 
                  produces a certainty score as a practical measure of the 
                  likelihood that a given genomic region is a CRISPR array.}
}