{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T02:47:07Z","timestamp":1792464427960,"version":"4.5.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,1,22]],"date-time":"2016-01-22T00:00:00Z","timestamp":1453420800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1186\/s13040-016-0086-4","type":"journal-article","created":{"date-parts":[[2016,1,22]],"date-time":"2016-01-22T16:11:23Z","timestamp":1453479083000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Prediction of donor splice sites using random forest with a new sequence encoding approach"],"prefix":"10.1186","volume":"9","author":[{"given":"Prabina Kumar","family":"Meher","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanmaya Kumar","family":"Sahu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atmakuri Ramakrishna","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,1,22]]},"reference":[{"key":"86_CR1","doi-asserted-by":"publisher","first-page":"3955","DOI":"10.1093\/nar\/gkl556","volume":"34","author":"N Sheth","year":"2006","unstructured":"Sheth N, Roca X, Hastings ML, Roeder T, Krainer AR, Sachidanandam R. Comprehensive splice site analysis using comparative genomics. Nucleic Acids Res. 2006;34:3955\u201367.","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"86_CR2","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1093\/bioinformatics\/bti025","volume":"21","author":"TM Chen","year":"2005","unstructured":"Chen TM, Lu CC, Li WH. Prediction of splice sites with dependency graphs and their expanded Bayesian networks. Bioinformatics. 2005;21(4):471\u201382.","journal-title":"Bioinformatics"},{"issue":"1","key":"86_CR3","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/S0097-8485(01)00099-7","volume":"26","author":"MG Reese","year":"2001","unstructured":"Reese MG. Application of a time-delay neural network to promoter annotation in the Drosophila melanogaster genome. Comput Chem. 2001;26(1):51\u20136.","journal-title":"Comput Chem"},{"issue":"2","key":"86_CR4","first-page":"131","volume":"2","author":"J Rajapakse","year":"2005","unstructured":"Rajapakse J, CaH LS. Markov encoding for detecting signals in genomic sequences. IEEE Trans Comput. Biol Bioinformatics. 2005;2(2):131\u201342.","journal-title":"Biol Bioinformatics"},{"key":"86_CR5","doi-asserted-by":"publisher","first-page":"2637","DOI":"10.1101\/gr.1679003","volume":"13","author":"XF Zhang","year":"2003","unstructured":"Zhang XF, Katherine HA, Ilana HC, Lawrene LS, Chasin A. Sequence Information for the Splicing of Human Pre-mRNA Identified by Support Vector Machine Classification. Genome Res. 2003;13:2637\u201350.","journal-title":"Genome Res"},{"issue":"Suppl 5","key":"86_CR6","doi-asserted-by":"publisher","first-page":"S15","DOI":"10.1186\/1471-2105-7-S5-S15","volume":"7","author":"A Baten","year":"2006","unstructured":"Baten A, Chang B, Halgamuge S, Li J. Splice site identification using probabilistic parameters and SVM classification. BMC Bioinformatics. 2006;7 Suppl 5:S15.","journal-title":"BMC Bioinformatics"},{"issue":"Suppl 10","key":"86_CR7","doi-asserted-by":"publisher","first-page":"S7","DOI":"10.1186\/1471-2105-8-S10-S7","volume":"8","author":"S S\u00f6ren Sonnenburg","year":"2007","unstructured":"S\u00f6ren Sonnenburg S, Schweikert G, Philips P, Behr J, R\u00e4tsch G. Accurate splice site prediction using support vector machines. BMC Bioinformatics. 2007;8 Suppl 10:S7.","journal-title":"BMC Bioinformatics"},{"issue":"2-3","key":"86_CR8","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1089\/1066527041410418","volume":"11","author":"G Yeo","year":"2004","unstructured":"Yeo G, Burge CB. Maximum entropy modeling of short sequence motifs with applications to RNA splicing signals. J Comput Biol. 2004;11(2-3):377\u201394.","journal-title":"J Comput Biol"},{"key":"86_CR9","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1101\/gr.6859308","volume":"18","author":"X Roca","year":"2008","unstructured":"Roca X, Olson AJ, Rao AR, Enerly E, Kristensen VN, B\u00f8rresen-Dale AL, et al. Features of 5\u2032-splice-site efficiency derived from disease-causing mutations and comparative genomics. Genome Res. 2008;18:77\u201387.","journal-title":"Genome Res"},{"key":"86_CR10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random Forests. Mach Learn. 2001;45:5\u201332.","journal-title":"Mach Learn"},{"issue":"1","key":"86_CR11","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1186\/1471-2105-9-500","volume":"9","author":"SE Hamby","year":"2008","unstructured":"Hamby SE, Hirst JD. Prediction of glycosylation sites using random forests. BMC Bioinformatics. 2008;9(1):500.","journal-title":"BMC Bioinformatics"},{"key":"86_CR12","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.compbiolchem.2009.04.004","volume":"33","author":"P Jain","year":"2009","unstructured":"Jain P, Garibaldi JM, Hirst JD. Supervised machine learning algorithms for protein structure prediction. Comput Biol Chem. 2009;33:216\u201323.","journal-title":"Comput Biol Chem"},{"issue":"6","key":"86_CR13","first-page":"1941","volume":"26","author":"A Dehzangi","year":"2010","unstructured":"Dehzangi A, Phon-Amnuaisuk A, Dehzangi O. Using random forest for protein fold prediction problem: An empirical study. J Inf Sci Eng. 2010;26(6):1941\u201356.","journal-title":"J Inf Sci Eng"},{"key":"86_CR14","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/1472-6947-11-51","volume":"11","author":"M Khalilia","year":"2011","unstructured":"Khalilia M, Chakraborty S, Popescu M. Predicting disease risk from highly imbalanced data using random forest. BMC Med Inform Decis Mak. 2011;11:51.","journal-title":"BMC Med Inform Decis Mak"},{"key":"86_CR15","first-page":"15688","volume":"100","author":"P Pollastro","year":"2003","unstructured":"Pollastro P, Rampone S. HS3D: Homosapiens Splice Site Data Set. Nucleic Acids Res. 2003;100:15688\u201393. Annual Database Issue 36.","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"86_CR16","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/S0968-0004(00)01549-8","volume":"25","author":"BJ Blencowe","year":"2000","unstructured":"Blencowe BJ. Exonic splicing enhancers: mechanism of action, diversity and role in human genetic diseases. Trends Biochem Sci. 2000;25(3):106\u201310.","journal-title":"Trends Biochem Sci"},{"issue":"10","key":"86_CR17","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1017\/S1355838202028030","volume":"8","author":"BJ Lam","year":"2002","unstructured":"Lam BJ, Hertel KJ. A general role for splicing enhancers in exon definition. RNA. 2002;8(10):1233\u201341.","journal-title":"RNA"},{"issue":"6","key":"86_CR18","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1089\/cmb.2005.12.894","volume":"12","author":"X Zhao","year":"2005","unstructured":"Zhao X, Huang H, Speed TP. Finding short DNA motifs using permuted Markov models. J Comput Biol. 2005;12(6):894\u2013906.","journal-title":"J Comput Biol"},{"issue":"12","key":"86_CR19","doi-asserted-by":"publisher","first-page":"6075","DOI":"10.1128\/MCB.11.12.6075","volume":"11","author":"Z Dominski","year":"1991","unstructured":"Dominski Z, Kole R. Selection of splice sites in pre-mRNAs with short internal exons. Mol Cell Biol. 1991;11(12):6075\u201383.","journal-title":"Mol Cell Biol"},{"issue":"4","key":"86_CR20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0010144","volume":"5","author":"J Zhu","year":"2010","unstructured":"Zhu J, He F, Wang D, Liu K, Huang D, Xiao J, et al. A Novel Role for Minimal Introns: Routing mRNAs to the Cytosol. PLoS One. 2010;5(4), e10144.","journal-title":"PLoS One"},{"key":"86_CR21","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/j.2517-6161.1974.tb00994.x","volume":"36","author":"M Stone","year":"1974","unstructured":"Stone M. Cross-validatory choice and assessment of statistical predictions. J Roy Statist Soc Ser B. 1974;36:111\u201347.","journal-title":"J Roy Statist Soc Ser B"},{"key":"86_CR22","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw A, Wiener M. Prediction and regression by randomForest. Rnews. 2002;2:18\u201322.","journal-title":"Rnews"},{"key":"86_CR23","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V. Support-Vector Networks. Mach Learn. 1995;20:273\u201397.","journal-title":"Mach Learn"},{"key":"86_CR24","volume-title":"Neural Networks: a comprehensive foundation","author":"S Haykin","year":"1999","unstructured":"Haykin S. Neural Networks: a comprehensive foundation. Prentice Hall: Upper Saddle River; 1999."},{"key":"86_CR25","volume-title":"e1071: Misc functions of the Department of Statistics (e1071), TU Wien, R package version 1.6-1","author":"D Meyer","year":"2012","unstructured":"Meyer D, Dimitriadou E, Hornik K, Weingessel A, Leisch F, et al. e1071: Misc functions of the Department of Statistics (e1071), TU Wien, R package version 1.6-1. 2012."},{"issue":"7","key":"86_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v046.i07","volume":"46","author":"C Bergmeir","year":"2012","unstructured":"Bergmeir C, Ben\u2019\u0131tez JM. Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS. J Stat Softw. 2012;46(7):1\u201326.","journal-title":"J Stat Softw"},{"key":"86_CR27","unstructured":"Breiman L: Bagging predictors. Technical Report 421, Department of Statistics, UC Berkeley, 1994. http:\/\/statistics.berkeley.edu\/sites\/default\/files\/tech-reports\/421.pdf ."},{"issue":"6","key":"86_CR28","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1162\/neco.1994.6.6.1289","volume":"6","author":"H Drucker","year":"1994","unstructured":"Drucker H, Cortes C, Jackel LD, LeCun Y, Vapnik V. Boosting and other ensemble methods. Neural Comput. 1994;6(6):1289\u2013301.","journal-title":"Neural Comput"},{"key":"86_CR29","volume-title":"Machine Learning","author":"T Mitchell","year":"1997","unstructured":"Mitchell T. Machine Learning. New York: McGraw Hill; 1997."},{"key":"86_CR30","volume-title":"Principles of Data Mining","author":"D Hand","year":"2001","unstructured":"Hand D, Mannila H, Smyth P. Principles of Data Mining. Cambridge, MA: MIT Press; 2001."},{"key":"86_CR31","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21706-2","volume-title":"Modern Applied Statistics with S","author":"WN Venables","year":"2002","unstructured":"Venables WN, Ripley BD. Modern Applied Statistics with S. 4th ed. New York: Springer; 2002. ISBN 0-387-95457-0.","ISBN":"https:\/\/id.crossref.org\/isbn\/0387954570","edition":"4"},{"key":"86_CR32","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/3-540-28397-8_36","volume-title":"Data Analysis and Decision Support","author":"C Weihs","year":"2005","unstructured":"Weihs C, Ligges U, Luebke K, Raabe N. klaR Analyzing German Business Cycles. In: Baier D, Decker R, Schmidt-Thieme L, editors. Data Analysis and Decision Support. Berlin: Springer; 2005. p. 335\u201343."},{"key":"86_CR33","unstructured":"R Development Core Team: R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria, 2012. ISBN 3-900051-07-0, URL http:\/\/www.R-project.org\/"},{"key":"86_CR34","unstructured":"Culp M, Johnson K, Michailidis G: ada: an R package for stochastic boosting. R package version 2.0-3, 2012. http:\/\/CRAN.R-project.org\/package=ada ."},{"key":"86_CR35","unstructured":"Peters A, Hothorn T: ipred: Improved Predictors. R package version 0.9-3, 2013. http:\/\/CRAN.R-project.org\/package=ipred ."},{"issue":"5","key":"86_CR36","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1093\/nar\/29.5.1185","volume":"29","author":"M Pertea","year":"2001","unstructured":"Pertea M, Lin X, Salzberg SL. GeneSplicer: a new computational method for splice sites prediction. Nucleic Acids Res. 2001;29(5):1185\u201390.","journal-title":"Nucleic Acids Res"},{"issue":"9","key":"86_CR37","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1093\/bioinformatics\/16.9.799","volume":"16","author":"A Zien","year":"2000","unstructured":"Zien A, R\u00e4tsch G, Mika S, Sch\u00f6lkopf B, Lengauer T, M\u00fcller KR. Engineering Support Vector Machine Kernels That Recognize Translation Initiation Sites. Bioinformatics. 2000;16(9):799\u2013807.","journal-title":"Bioinformatics"},{"key":"86_CR38","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1093\/nar\/12.1Part2.505","volume":"12","author":"R Staden","year":"1984","unstructured":"Staden R. Computer methods to locate signals in nucleic acid sequences. Nucleic Acids Res. 1984;12:505\u201319.","journal-title":"Nucleic Acids Res"},{"issue":"5","key":"86_CR39","first-page":"499","volume":"9","author":"MQ Zhang","year":"1993","unstructured":"Zhang MQ, Marr TG. A weight array method for splicing signal analysis. Comp Appl Biosci. 1993;9(5):499\u2013509.","journal-title":"Comp Appl Biosci"},{"key":"86_CR40","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1006\/jmbi.1997.0951","volume":"268","author":"C Burge","year":"1997","unstructured":"Burge C, Karlin S. Prediction of complete gene structures in human genomic DNA. J Mol Biol. 1997;268:78\u201394.","journal-title":"J Mol Biol"},{"key":"86_CR41","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1016\/j.biochi.2006.03.006","volume":"88","author":"J Huang","year":"2006","unstructured":"Huang J, Li T, Chen K, Wu J. An approach of encoding for prediction of splice sites using SVM. Biochimie. 2006;88:923\u20139.","journal-title":"Biochimie"},{"key":"86_CR42","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/S0020-0255(01)00160-8","volume":"139","author":"MM Yin","year":"2001","unstructured":"Yin MM, Wang JTL. Effective hidden Markov models for detecting splicing junction sites in DNA sequences. Inform Sciences. 2001;139:139\u201363.","journal-title":"Inform Sciences"},{"issue":"3","key":"86_CR43","doi-asserted-by":"publisher","first-page":"3432","DOI":"10.4238\/2012.September.25.12","volume":"11","author":"JL Li","year":"2012","unstructured":"Li JL, Wang LF, Wang HY, Bai LY, Yuan ZM. High-accuracy splice sites prediction based on sequence component and position features. Genet Mol Res. 2012;11(3):3432\u201351.","journal-title":"Genet Mol Res"}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-016-0086-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13040-016-0086-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-016-0086-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-016-0086-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T22:53:21Z","timestamp":1718319201000},"score":1,"resource":{"primary":{"URL":"http:\/\/biodatamining.biomedcentral.com\/articles\/10.1186\/s13040-016-0086-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1,22]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["86"],"URL":"https:\/\/doi.org\/10.1186\/s13040-016-0086-4","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1,22]]},"article-number":"4"}}