{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T16:03:54Z","timestamp":1775232234294,"version":"3.50.1"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T00:00:00Z","timestamp":1715299200000},"content-version":"vor","delay-in-days":5822,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/3.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["60405001"],"award-info":[{"award-number":["60405001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["60875001"],"award-info":[{"award-number":["60875001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK2004142"],"award-info":[{"award-number":["BK2004142"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>MicroRNAs (miRNAs) are one family of short (21\u201323 nt) regulatory non-coding RNAs processed from long (70\u2013110 nt) miRNA precursors (pre-miRNAs). Identifying true and false precursors plays an important role in computational identification of miRNAs. Some numerical features have been extracted from precursor sequences and their secondary structures to suit some classification methods; however, they may lose some usefully discriminative information hidden in sequences and structures. In this study, pre-miRNA sequences and their secondary structures are directly used to construct an exponential kernel based on weighted Levenshtein distance between two sequences. This string kernel is then combined with support vector machine (SVM) for detecting true and false pre-miRNAs. Based on 331 training samples of true and false human pre-miRNAs, 2 key parameters in SVM are selected by 5-fold cross validation and grid search, and 5 realizations with different 5-fold partitions are executed. Among 16 independent test sets from 3 human, 8 animal, 2 plant, 1 virus, and 2 artificially false human pre-miRNAs, our method statistically outperforms the previous SVM-based technique on 11 sets, including 3 human, 7 animal, and 1 false human pre-miRNAs. In particular, pre-miRNAs with multiple loops that were usually excluded in the previous work are correctly identified in this study with an accuracy of 92.66%.<\/jats:p>","DOI":"10.1016\/s1672-0229(08)60027-3","type":"journal-article","created":{"date-parts":[[2008,10,29]],"date-time":"2008-10-29T08:34:07Z","timestamp":1225269247000},"page":"121-128","source":"Crossref","is-referenced-by-count":15,"title":["Identification of MicroRNA Precursors with Support Vector Machine and String Kernel"],"prefix":"10.1093","volume":"6","author":[{"given":"Jian-Hua","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Nanjing Normal University , Nanjing, 210097 , China"}]},{"given":"Fei","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Entomology, Nanjing Agricultural University , Nanjing, 210095 , China"}]},{"given":"Qiu-Feng","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Nanjing Normal University , Nanjing, 210097 , China"}]}],"member":"286","published-online":{"date-parts":[[2008,10,28]]},"reference":[{"key":"2024051008250798000_bib1","doi-asserted-by":"crossref","first-page":"4663","DOI":"10.1093\/emboj\/cdf476","article-title":"MicroRNA maturation: stepwise processing and subcellular localization","volume":"21","author":"Lee","year":"2002","journal-title":"EMBO J."},{"key":"2024051008250798000_bib2","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/S0092-8674(04)00045-5","article-title":"MicroRNAs: genomics, biogenesis, mechanism, and function","volume":"116","author":"Bartel","year":"2004","journal-title":"Cell"},{"key":"2024051008250798000_bib3","doi-asserted-by":"crossref","first-page":"12753","DOI":"10.1073\/pnas.0403115101","article-title":"Arabidopsis micro-RNA biogenesis through Dicer-like 1 protein functions","volume":"101","author":"Kurihara","year":"2004","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2024051008250798000_bib4","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1002\/jcp.20869","article-title":"MicroRNAs and their regulatory roles in animals and plants","volume":"210","author":"Zhang","year":"2007","journal-title":"J. Cell. Physiol."},{"key":"2024051008250798000_bib5","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.compbiolchem.2006.08.006","article-title":"Computational identification of microRNAs and their targets","volume":"30","author":"Zhang","year":"2006","journal-title":"Comput. Biol. Chem."},{"key":"2024051008250798000_bib6","doi-asserted-by":"crossref","first-page":"95270","DOI":"10.1155\/JBB\/2006\/95270","article-title":"Computational prediction of microRNAs encoded in viral and other genomes","volume":"2006","author":"Thomassen","year":"2006","journal-title":"J. Biomed. Biotechnol."},{"key":"2024051008250798000_bib7","doi-asserted-by":"crossref","first-page":"1281","DOI":"10.1360\/982005-573","article-title":"Gene expression regulators\u2014microRNAs","volume":"50","author":"Chen","year":"2005","journal-title":"Chinese Sci. Bull."},{"key":"2024051008250798000_bib8","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1016\/S1359-6446(05)03399-4","article-title":"A computational view of microRNAs and their targets","volume":"10","author":"Brown","year":"2005","journal-title":"Drug Discov. Today"},{"key":"2024051008250798000_bib9","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/BF00818163","article-title":"Fast folding and comparison of RNA secondary structures","volume":"125","author":"Hofacker","year":"1994","journal-title":"Monatsh. Chem."},{"key":"2024051008250798000_bib10","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1101\/gad.1074403","article-title":"The microRNAs of Caenorhabditis elegans","volume":"17","author":"Lim","year":"2003","journal-title":"Genes Dev."},{"key":"2024051008250798000_bib11","doi-asserted-by":"crossref","first-page":"1540","DOI":"10.1126\/science.1080372","article-title":"Vertebrate microRNA genes","volume":"299","author":"Lim","year":"2003","journal-title":"Science"},{"key":"2024051008250798000_bib12","doi-asserted-by":"crossref","first-page":"R42","DOI":"10.1186\/gb-2003-4-7-r42","article-title":"Computational identification of Drosophila microRNA genes","volume":"4","author":"Lai","year":"2003","journal-title":"Genome Biol."},{"key":"2024051008250798000_bib13","doi-asserted-by":"crossref","first-page":"3610","DOI":"10.1093\/bioinformatics\/bti562","article-title":"MicroRNA identification based on sequence and structure alignment","volume":"21","author":"Wang","year":"2005","journal-title":"Bioinformatics"},{"key":"2024051008250798000_bib14","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.molcel.2004.05.027","article-title":"Computational identification of plant microRNAs and their targets, including a stress-induced miRNA","volume":"14","author":"Jones-Rhoades","year":"2004","journal-title":"Mol. Cell"},{"key":"2024051008250798000_bib15","doi-asserted-by":"crossref","first-page":"11511","DOI":"10.1073\/pnas.0404025101","article-title":"Detection of 91 potential conserved plant microRNAs in Arabidopsis thaliana and Oryza sativa identifies important target genes","volume":"101","author":"Bonnet","year":"2004","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2024051008250798000_bib16","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1186\/1471-2105-6-310","article-title":"Classification of real and pseudo microRNA precursors using local structure-sequence features and support vector machines","volume":"6","author":"Xue","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"2024051008250798000_bib17","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1186\/1471-2105-6-267","article-title":"Identification of clustered microRNAs using an ab initio predication method","volume":"6","author":"Sewer","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"2024051008250798000_bib18","doi-asserted-by":"crossref","first-page":"W339","DOI":"10.1093\/nar\/gkm368","article-title":"MiPred: classification of real and pseudo microRNA precursors using random forest prediction model with combined features","volume":"35","author":"Jiang","year":"2007","journal-title":"Nucleic Acids Res."},{"key":"2024051008250798000_bib19","article-title":"Statistical Learning Theory","author":"Vapnik","year":"1998"},{"key":"2024051008250798000_bib20","article-title":"The Nature of Statistical Learning Theory","author":"Vapnik","year":"1999","edition":"second edition"},{"key":"2024051008250798000_bib21","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"2024051008250798000_bib22","first-page":"3015","article-title":"Kernels based on weighted Levenshtein distance","volume-title":"Proceedings of 2004 IEEE International Joint Conference on Neural Networks","author":"Xu","year":"2004"},{"key":"2024051008250798000_bib23","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1093\/bioinformatics\/btg431","article-title":"Mismatch string kernels for discriminative protein classification","volume":"20","author":"Leslie","year":"2004","journal-title":"Bioinformatics"},{"key":"2024051008250798000_bib24","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1016\/j.febslet.2005.04.045","article-title":"Predication of siRNA functionality using generalized string kernel and support vector machine","volume":"579","author":"Teramoto","year":"2005","journal-title":"FEBS Lett."},{"key":"2024051008250798000_bib25","doi-asserted-by":"crossref","first-page":"D109","DOI":"10.1093\/nar\/gkh023","article-title":"The microRNA registry","volume":"32","author":"Griffiths-Jones","year":"2004","journal-title":"Nucleic Acids Res."},{"key":"2024051008250798000_bib26","doi-asserted-by":"crossref","first-page":"D140","DOI":"10.1093\/nar\/gkj112","article-title":"miRBase: microRNA sequences, targets and gene nomenclature","volume":"34","author":"Griffiths-Jones","year":"2006","journal-title":"Nucleic Acids Res."},{"key":"2024051008250798000_bib27","article-title":"Pattern Classification","author":"Duda","year":"2002","edition":"second edition"},{"key":"2024051008250798000_bib28","article-title":"Syntactic Pattern Recognition and Application","author":"Fu","year":"1982"},{"key":"2024051008250798000_bib29","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions and reversals","volume":"10","author":"Levenshtein","year":"1966","journal-title":"Sov. Phys. Dokl."},{"key":"2024051008250798000_bib30","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1145\/321796.321811","article-title":"The string-to-string correction problem","volume":"21","author":"Wagner","year":"1974","journal-title":"J. ACM"}],"container-title":["Genomics, Proteomics &amp; Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1672022908600273?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1672022908600273?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/gpb\/article-pdf\/6\/2\/121\/57483006\/gpb_6_2_121.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/gpb\/article-pdf\/6\/2\/121\/57483006\/gpb_6_2_121.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T08:26:34Z","timestamp":1715329594000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/gpb\/article\/6\/2\/121\/7210684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,6,1]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2008,6,1]]}},"URL":"https:\/\/doi.org\/10.1016\/s1672-0229(08)60027-3","relation":{},"ISSN":["1672-0229","2210-3244"],"issn-type":[{"value":"1672-0229","type":"print"},{"value":"2210-3244","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2008,6]]},"published":{"date-parts":[[2008,6,1]]}}}