{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T18:47:03Z","timestamp":1778870823715,"version":"3.51.4"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T00:00:00Z","timestamp":1756425600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T00:00:00Z","timestamp":1756425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Ministry of Science, Innovation and Universities, Spain.","award":["PID2023-152660NB-I00"],"award-info":[{"award-number":["PID2023-152660NB-I00"]}]},{"name":"Ministry of Science, Innovation and Universities, Spain.","award":["PID2023-152660NB-I00"],"award-info":[{"award-number":["PID2023-152660NB-I00"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"DOI":"10.1186\/s13040-025-00474-5","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T07:16:08Z","timestamp":1756451768000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Improving classification on imbalanced genomic data via KDE\u2013based synthetic sampling"],"prefix":"10.1186","volume":"18","author":[{"given":"Edoardo","family":"Taccaliti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesus S.","family":"Aguilar\u2013Ruiz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,29]]},"reference":[{"key":"474_CR1","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.jnca.2016.04.007","volume":"68","author":"A Abdallah","year":"2016","unstructured":"Abdallah A, Maarof MA, Zainal A. Fraud detection system: A survey. J Netw Comput Appl. 2016;68:90\u2013113. https:\/\/doi.org\/10.1016\/j.jnca.2016.04.007.","journal-title":"J Netw Comput Appl."},{"key":"474_CR2","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","volume":"6","author":"J Johnson","year":"2019","unstructured":"Johnson J, Khoshgoftaar T. Survey on deep learning with class imbalance. J Big Data. 2019;6:27. https:\/\/doi.org\/10.1186\/s40537-019-0192-5.","journal-title":"J Big Data."},{"issue":"3","key":"474_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1541880.1541882","volume":"41","author":"V Chandola","year":"2009","unstructured":"Chandola V, Banerjee A, Kumar V. Anomaly detection: A survey. ACM Comput Surv. 2009;41(3):1\u201358. https:\/\/doi.org\/10.1145\/1541880.1541882.","journal-title":"ACM Comput Surv."},{"issue":"5","key":"474_CR4","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz N, Stephen S. The class imbalance problem: A systematic study1. Intell Data Anal. 2002;6(5):429\u201349. https:\/\/doi.org\/10.3233\/IDA-2002-6504.","journal-title":"Intell Data Anal."},{"key":"474_CR5","doi-asserted-by":"publisher","unstructured":"Haibo He, Garcia EA. Learning from Imbalanced Data. IEEE Trans Knowl Data Eng. 2009;21(9):1263\u201384. https:\/\/doi.org\/10.1109\/TKDE.2008.239.","DOI":"10.1109\/TKDE.2008.239"},{"key":"474_CR6","doi-asserted-by":"publisher","unstructured":"Van\u00a0Hulse J, Khoshgoftaar TM, Napolitano A. Experimental perspectives on learning from imbalanced data. In: Ghahramani Z, editor. Proceedings of the 24th International Conference on Machine Learning. Corvalis: ACM; 2007. pp. 935\u2013942. https:\/\/doi.org\/10.1145\/1273496.1273614.","DOI":"10.1145\/1273496.1273614"},{"issue":"1","key":"474_CR7","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/1007730.1007734","volume":"6","author":"GM Weiss","year":"2004","unstructured":"Weiss GM. Mining with rarity: a unifying framework. ACM SIGKDD Explor Newsl. 2004;6(1):7\u201319. https:\/\/doi.org\/10.1145\/1007730.1007734.","journal-title":"ACM SIGKDD Explor Newsl."},{"key":"474_CR8","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.ins.2014.05.042","volume":"282","author":"V Bol\u00f3n-Canedo","year":"2014","unstructured":"Bol\u00f3n-Canedo V, S\u00e1nchez-Maro\u00f1o N, Alonso-Betanzos A, Ben\u00edtez JM, Herrera F. A review of microarray datasets and applied feature selection methods. Inf Sci. 2014;282:111\u201335. https:\/\/doi.org\/10.1016\/j.ins.2014.05.042.","journal-title":"Inf Sci."},{"issue":"1","key":"474_CR9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s13040-022-00294-x","volume":"15","author":"RE Wellinger","year":"2022","unstructured":"Wellinger RE, Aguilar-Ruiz JS. A new challenge for data analytics: transposons. BioData Min. 2022;15(1):9. https:\/\/doi.org\/10.1186\/s13040-022-00294-x.","journal-title":"BioData Min."},{"issue":"6","key":"474_CR10","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/TNNLS.2013.2246188","volume":"24","author":"CL Castro","year":"2013","unstructured":"Castro CL, Braga AP. Novel Cost-Sensitive Approach to Improve the Multilayer Perceptron Performance on Imbalanced Data. IEEE Trans Neural Netw Learn Syst. 2013;24(6):888\u201399. https:\/\/doi.org\/10.1109\/TNNLS.2013.2246188.","journal-title":"IEEE Trans Neural Netw Learn Syst."},{"issue":"1","key":"474_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1007730.1007733","volume":"6","author":"NV Chawla","year":"2004","unstructured":"Chawla NV, Japkowicz N, Kotcz A. Editorial: special issue on learning from imbalanced data sets. ACM SIGKDD Explor Newsl. 2004;6(1):1\u20136. https:\/\/doi.org\/10.1145\/1007730.1007733.","journal-title":"ACM SIGKDD Explor Newsl."},{"issue":"6","key":"474_CR12","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10462-024-10759-6","volume":"57","author":"W Chen","year":"2024","unstructured":"Chen W, Yang K, Yu Z, Shi Y, Chen CLP. A survey on imbalanced learning: latest research, applications and future directions. Artif Intell Rev. 2024;57(6):137. https:\/\/doi.org\/10.1007\/s10462-024-10759-6.","journal-title":"Artif Intell Rev."},{"key":"474_CR13","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic Minority Over-sampling Technique. J Artif Intell Res. 2002;16:321\u201357.","journal-title":"J Artif Intell Res."},{"key":"474_CR14","volume-title":"International Conference on Intelligent Computing","author":"H Han","year":"2005","unstructured":"Han H, Wang W, Mao B. Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning. In: Huang D, Zhang XS, Huang G, editors. International Conference on Intelligent Computing. Berlin, Heidelberg: Springer; 2005."},{"key":"474_CR15","doi-asserted-by":"crossref","unstructured":"He H, Bai Y, Garcia EA, Li S. ADASYN: Adaptive synthetic sampling approach for imbalanced learning. 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).\u00a0NY, US: IEEE Press;\u00a02008. pp. 1322\u20131328.","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"474_CR16","unstructured":"Brandt J, Lanzen E. A Comparative Review of SMOTE and ADASYN in Imbalanced Data Classification. Uppsala University, Department of Statistics; 2021."},{"key":"474_CR17","doi-asserted-by":"publisher","first-page":"7940","DOI":"10.1109\/ACCESS.2016.2619719","volume":"4","author":"A Amin","year":"2016","unstructured":"Amin A, Anwar S, Adnan A, Nawaz M, Howard N, Qadir J, et al. Comparing Oversampling Techniques to Handle the Class Imbalance Problem: A Customer Churn Prediction Case Study. IEEE Access. 2016;4:7940\u201357. https:\/\/doi.org\/10.1109\/ACCESS.2016.2619719.","journal-title":"IEEE Access."},{"key":"474_CR18","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","volume":"61","author":"A Fernandez","year":"2018","unstructured":"Fernandez A, Garcia S, Herrera F, Chawla NV. SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary. J Artif Intell Res. 2018;61:863\u2013905. https:\/\/doi.org\/10.1613\/jair.1.11192.","journal-title":"J Artif Intell Res."},{"key":"474_CR19","doi-asserted-by":"publisher","unstructured":"Riston T, Suherman SN, Yonnatan Y, Indrayatna F, Pravitasari AA, Sari EN, et\u00a0al. Oversampling Methods for Handling Imbalance Data in Binary Classification. In: Gervasi O, Murgante B, Rocha AMAC, Garau C, Scorza F, Karaca Y, et\u00a0al., editors. Computational Science and Its Applications \u2013 ICCSA 2023 Workshops, vol. 14105. Springer Nature; 2023. pp. 3\u201323. https:\/\/doi.org\/10.1007\/978-3-031-37108-0_1.","DOI":"10.1007\/978-3-031-37108-0_1"},{"issue":"2","key":"474_CR20","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1109\/TKDE.2020.2985965","volume":"34","author":"Y Xie","year":"2022","unstructured":"Xie Y, Qiu M, Zhang H, Peng L, Chen Z. Gaussian Distribution Based Oversampling for Imbalanced Data Classification. IEEE Trans Knowl Data Eng. 2022;34(2):667\u201379. https:\/\/doi.org\/10.1109\/TKDE.2020.2985965.","journal-title":"IEEE Trans Knowl Data Eng."},{"key":"474_CR21","doi-asserted-by":"publisher","unstructured":"Gonz\u00e1lez-Barcenas VM, Rend\u00f3n E, Alejo R, Granda-Guti\u00e9rrez EE, Valdovinos RM. Addressing the Big Data Multi-class Imbalance Problem with Oversampling and Deep Learning Neural Networks. In: Morales A, Fierrez J, S\u00e1nchez JS, Ribeiro B, editors. Pattern Recognition and Image Analysis, vol. 11867. Springer International Publishing; 2019. pp. 216\u2013224. https:\/\/doi.org\/10.1007\/978-3-030-31332-6_19.","DOI":"10.1007\/978-3-030-31332-6_19"},{"key":"474_CR22","doi-asserted-by":"publisher","unstructured":"Welvaars K, Oosterhoff JHF, Van Den\u00a0Bekerom MPJ, Doornberg JN, Van\u00a0Haarst EP, OLVG Urology Consortium, and the Machine Learning Consortium, et\u00a0al. Implications of resampling data to address the class imbalance problem (IRCIP): an evaluation of impact on performance between classification algorithms in medical data. JAMIA Open. 2023;6(2):ooad033. https:\/\/doi.org\/10.1093\/jamiaopen\/ooad033.","DOI":"10.1093\/jamiaopen\/ooad033"},{"key":"474_CR23","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1016\/j.ins.2019.10.017","volume":"512","author":"F Kamalov","year":"2020","unstructured":"Kamalov F. Kernel density estimation based sampling for imbalanced class distribution. Inf Sci. 2020;512:1192\u2013201. https:\/\/doi.org\/10.1016\/j.ins.2019.10.017.","journal-title":"Inf Sci."},{"key":"474_CR24","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/j.neucom.2014.02.006","volume":"138","author":"M Gao","year":"2014","unstructured":"Gao M, Hong X, Chen S, Harris CJ, Khalaf E. PDFOS: PDF estimation based over-sampling for imbalanced two-class problems. Neurocomputing. 2014;138:248\u201359.","journal-title":"Neurocomputing."},{"key":"474_CR25","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/j.procs.2021.10.046","volume":"193","author":"E Plesovskaya","year":"2021","unstructured":"Plesovskaya E, Ivanov S. An Empirical Analysis of KDE-based Generative Models on Small Datasets. Procedia Comput Sci. 2021;193:442\u201352. https:\/\/doi.org\/10.1016\/j.procs.2021.10.046.","journal-title":"Procedia Comput Sci."},{"key":"474_CR26","unstructured":"Dua D, Graff C. UCI Machine Learning Repository. 2017. http:\/\/archive.ics.uci.edu\/ml. Accessed\u00a020 Jan 2025."},{"key":"474_CR27","doi-asserted-by":"publisher","unstructured":"Scott DW. Multivariate Density Estimation: Theory, Practice, and Visualization. Wiley Series in Probability and Statistics. Wiley; 1992. https:\/\/doi.org\/10.1002\/9780470316849.","DOI":"10.1002\/9780470316849"},{"key":"474_CR28","unstructured":"Silverman BW. Density estimation for statistics and data analysis. Chapman and Hall; 1986."},{"issue":"4","key":"474_CR29","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1089\/cmb.2018.0238","volume":"26","author":"BC Feltes","year":"2019","unstructured":"Feltes BC, Chandelier EB, Grisci BI, Dorn M. CuMiDa: An Extensively Curated Microarray Database for Benchmarking and Testing of Machine Learning Approaches in Cancer Research. J Comput Biol. 2019;26(4):376\u201386.","journal-title":"J Comput Biol."},{"key":"474_CR30","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-1-4939-3578-9_5","volume":"1418","author":"E Clough","year":"2016","unstructured":"Clough E, Barrett T. The Gene Expression Omnibus Database. Methods Mol Biol (Clifton, NJ). 2016;1418:93\u2013110. https:\/\/doi.org\/10.1007\/978-1-4939-3578-9_5.","journal-title":"Methods Mol Biol (Clifton, NJ)."},{"issue":"1","key":"474_CR31","doi-asserted-by":"publisher","first-page":"10759","DOI":"10.1038\/s41598-024-61365-z","volume":"14","author":"JS Aguilar-Ruiz","year":"2024","unstructured":"Aguilar-Ruiz JS, Michalak M. Classification performance assessment for imbalanced multiclass data. Sci Rep. 2024;14(1):10759. https:\/\/doi.org\/10.1038\/s41598-024-61365-z.","journal-title":"Sci Rep."},{"issue":"16","key":"474_CR32","doi-asserted-by":"publisher","first-page":"5261","DOI":"10.1128\/AEM.00062-07","volume":"73","author":"Q Wang","year":"2007","unstructured":"Wang Q, Garrity GM, Tiedje JM, Cole JR. Naive Bayesian Classifier for Rapid Assignment of rRNA Sequences into the New Bacterial Taxonomy. Appl Environ Microbiol. 2007;73(16):5261\u20137. https:\/\/doi.org\/10.1128\/AEM.00062-07.","journal-title":"Appl Environ Microbiol."},{"key":"474_CR33","doi-asserted-by":"publisher","unstructured":"Rokach L, Maimon O. Decision Trees. In: Maimon O, Rokach L, editors. Data Mining and Knowledge Discovery Handbook. Springer-Verlag; 2005. pp. 165\u2013192. https:\/\/doi.org\/10.1007\/0-387-25465-X_9.","DOI":"10.1007\/0-387-25465-X_9"},{"issue":"1","key":"474_CR34","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(1):5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324.","journal-title":"Mach Learn."},{"key":"474_CR35","volume-title":"Predictive accuracy: A misleading performance measure for highly imbalanced data","author":"J Akosa","year":"2017","unstructured":"Akosa J. Predictive accuracy: A misleading performance measure for highly imbalanced data. Cary: SAS Institute Inc.; 2017."},{"issue":"1","key":"474_CR36","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s13040-021-00244-z","volume":"14","author":"D Chicco","year":"2021","unstructured":"Chicco D, T\u00f6tsch N, Jurman G. The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation. BioData Min. 2021;14(1):13. https:\/\/doi.org\/10.1186\/s13040-021-00244-z.","journal-title":"BioData Min."},{"issue":"8","key":"474_CR37","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T. An introduction to ROC analysis. Pattern Recogn Lett. 2006;27(8):861\u201374.","journal-title":"Pattern Recogn Lett."},{"key":"474_CR38","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine Learning in Python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res."},{"issue":"17","key":"474_CR39","first-page":"1","volume":"18","author":"G Lema\u00eetre","year":"2017","unstructured":"Lema\u00eetre G, Nogueira F, Aridas CK. Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning. J Mach Learn Res. 2017;18(17):1\u20135.","journal-title":"J Mach Learn Res."},{"key":"474_CR40","doi-asserted-by":"publisher","first-page":"68915","DOI":"10.1109\/ACCESS.2022.3186444","volume":"10","author":"JS Aguilar-Ruiz","year":"2022","unstructured":"Aguilar-Ruiz JS, Michalak M. Multiclass Classification Performance Curve. IEEE. Access. 2022;10:68915\u201321. https:\/\/doi.org\/10.1109\/ACCESS.2022.3186444.","journal-title":"Access."},{"key":"474_CR41","doi-asserted-by":"crossref","unstructured":"Aguilar-Ruiz JS. Beyond the ROC Curve: The IMCP Curve. Analytics. 2024;3:221\u20134.","DOI":"10.3390\/analytics3020012"},{"key":"474_CR42","doi-asserted-by":"publisher","unstructured":"Aguilar-Ruiz JS, Michalak M, \u0141ukasz Wr\u00f3bel. IMCP: a Python package for imbalanced and multiclass data classifier performance comparison. SoftwareX. 2024;28:101877. https:\/\/doi.org\/10.1016\/j.softx.2024.101877.","DOI":"10.1016\/j.softx.2024.101877"}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-025-00474-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13040-025-00474-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-025-00474-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T20:39:13Z","timestamp":1757450353000},"score":1,"resource":{"primary":{"URL":"https:\/\/biodatamining.biomedcentral.com\/articles\/10.1186\/s13040-025-00474-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,29]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["474"],"URL":"https:\/\/doi.org\/10.1186\/s13040-025-00474-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6513655\/v1","asserted-by":"object"}]},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,29]]},"assertion":[{"value":"23 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"60"}}