Could n-gram analysis contribute to genomic island determination?

@article{citeulike:2771873, abstract = {There are two approaches to identifying genomic and pathogenesis islands (GI/PAIs) in bacterial genomes: the compositional and the functional, based on DNA or protein level composition and gene function, respectively. We applied n-gram analysis in addition to other compositional features, combined them by union and intersection and defined two measures for evaluating the results-recall and precision. Using the best criteria (by training on the Escherichia coli O157:H7 EDL933 genome), we predicted GIs for 14 Enterobacteriaceae family members and for 21 randomly selected bacterial genomes. These predictions were compared with results obtained from HGT DB (based on the compositional approach) and PAI DB (based on the combined approach). The results obtained show that intersecting n-grams with other compositional features improves relative precision by up to 10\% in case of HGT DB and up to 60\% in case of PAI DB. In addition, it was demonstrated that the union of all compositional features results in maximum recall (up to 37\%). Thus, the application of n-gram analysis alongside existing or newly developed methods may improve the prediction of GI/PAIs.}, address = {Faculty of Mathematics, University of Belgrade, Studentski trg 16, 11001 Belgrade, Serbia and Montenegro.}, author = {Miti\'{c}, Nenad S S. and Pavlovi\'{c}-La\v{z}eti\'{c}, Gordana M M. and Beljanski, Milo\v{s} V V. }, citeulike-article-id = {2771873}, doi = {10.1016/j.jbi.2008.03.007}, issn = {1532-0480}, journal = {Journal of biomedical informatics}, keywords = {n-gram}, month = {March}, posted-at = {2008-05-08 15:24:48}, priority = {2}, title = {Could n-gram analysis contribute to genomic island determination?}, url = {http://dx.doi.org/10.1016/j.jbi.2008.03.007}, year = {2008} }

TY - JOUR ID - citeulike:2771873 L3 - citeulike-article-id:2771873 TI - Could n-gram analysis contribute to genomic island determination? JF - Journal of biomedical informatics AD - Faculty of Mathematics, University of Belgrade, Studentski trg 16, 11001 Belgrade, Serbia and Montenegro. SN - 1532-0480 N2 - There are two approaches to identifying genomic and pathogenesis islands (GI/PAIs) in bacterial genomes: the compositional and the functional, based on DNA or protein level composition and gene function, respectively. We applied n-gram analysis in addition to other compositional features, combined them by union and intersection and defined two measures for evaluating the results-recall and precision. Using the best criteria (by training on the Escherichia coli O157:H7 EDL933 genome), we predicted GIs for 14 Enterobacteriaceae family members and for 21 randomly selected bacterial genomes. These predictions were compared with results obtained from HGT DB (based on the compositional approach) and PAI DB (based on the combined approach). The results obtained show that intersecting n-grams with other compositional features improves relative precision by up to 10% in case of HGT DB and up to 60% in case of PAI DB. In addition, it was demonstrated that the union of all compositional features results in maximum recall (up to 37%). Thus, the application of n-gram analysis alongside existing or newly developed methods may improve the prediction of GI/PAIs. KW - n-gram AU - Mitić, Nenad S AU - Pavlović-Lažetić, Gordana M AU - Beljanski, Miloš V PY - 2008/03/26/ UR - http://dx.doi.org/10.1016/j.jbi.2008.03.007 ER -