{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T05:16:33Z","timestamp":1736658993170,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540689706"},{"type":"electronic","value":"9783540689713"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11960669_7","type":"book-chapter","created":{"date-parts":[[2006,11,27]],"date-time":"2006-11-27T18:56:02Z","timestamp":1164653762000},"page":"65-77","source":"Crossref","is-referenced-by-count":4,"title":["Automatic Annotation of Protein Functional Class from Sparse and Imbalanced Data Sets"],"prefix":"10.1007","author":[{"given":"Jaehee","family":"Jung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael R.","family":"Thon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"7_CR1","doi-asserted-by":"crossref","first-page":"195","DOI":"10.2165\/00822942-200504030-00004","volume":"4","author":"A. Al-shahib","year":"2005","unstructured":"Al-shahib, A., Breitling, R., Gilbert, D.: Feature Selection and the Class Imbalance Problem in Predict Protein Function form sequence. Applied Bioinformatics\u00a04, 195\u2013203 (2005)","journal-title":"Applied Bioinformatics"},{"key":"7_CR2","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"N.V. Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K., Hall, L.O., Kegelmeyer, W.P.: SMOTE: Synthetic minority over sampling technique. Journal of artificial Intelligence Research\u00a016, 321\u2013357 (2002)","journal-title":"Journal of artificial Intelligence Research"},{"key":"7_CR3","unstructured":"Drummond, C., Holte, R.C.: C4.5,Class Imbalance, and Cost sensitivity: Why Under-sampling beats Oversampling. In: ICML 2003 Workshop on Learning from Imbalanced Datasets II (2003)"},{"key":"7_CR4","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1162\/153244303322753616","volume":"3","author":"I. Guyon","year":"2003","unstructured":"Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Journal of Machine Learning Research\u00a03, 1157\u20131182 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Hennig, S., Groth, D., Lehrach, H.: Automated Gene Ontology annotation for anonymous sequence data. Nucleic acids Research, 3712\u20133715 (2003)","DOI":"10.1093\/nar\/gkg582"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Huang, J., Lu, J., Ling, C.X.: Comparing Naive Bayes,Decision Trees, and SVM using Accuracy and AUC. In: Proc. of The Third IEEE Inter. Conf. on Data Mining (ICDM), pp. 553\u2013556 (2003)","DOI":"10.1109\/ICDM.2003.1250975"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Japkowics, N., Stepen, S.: The class imbalanced problem: A systematic study. Intelligent Data Analysis\u00a06 (2002)","DOI":"10.3233\/IDA-2002-6504"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Khan, S., Situ, G., Decker, K., Schmidt, C.J.: GoFigure:Automated Gene Ontology annotation. Bioinformatics\u00a019 (2003)","DOI":"10.1093\/bioinformatics\/btg338"},{"key":"7_CR9","unstructured":"King, R.D., Karwath, A., Clare, A., Dephaspe, L.: Genome scale prediction of protein functional class from sequence using data mining. In: Proc. of the sixth ACM SIGKDD Inter. Conf. on Knowledge discovery and data mining (2003)"},{"key":"7_CR10","unstructured":"Kubat, M., Matwin, S.: Addressing the curse of Imbalanced Training sets: One-sided Selection. In: Proc. of the Fourteenth Inter. Conf. on Machine Learning Proc (ICML), pp. 179\u2013186 (1997)"},{"key":"7_CR11","unstructured":"Ling, C., Li, C.: Data mining for direct marketing:problem and solution. In: Proc. of the Fourth Inter. Conf. on Knowledges Discovery and Data Mining (KDD), pp. 73\u201379 (1998)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Martin, D.M., Berriman, M., Barton, G.J.: GOtcha: A new method for prediction of protein function assessed by the annotation of sever genomes. BMC bioinformatics\u00a05 (2004)","DOI":"10.1186\/1471-2105-5-178"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Pavalidis, P., Weston, J., Cai, J., Grundy, W.B.: Gene Functional Classification From Heterogeneous Data. In: Proc. of the Fifth Inter. Conf. on Research in Computational Molecular Biology (RECOMB), pp. 249\u2013255 (2001)","DOI":"10.1145\/369133.369228"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Vinayagam, A., Konig, R., Moormann, J., Schubert, F., Elis, R., Glatting, K.H., Suhai, S.: Applying support vector machine for gene ontology based gene function prediction. BMC Bioinformatics\u00a019 (2003)","DOI":"10.1186\/1471-2105-5-116"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Vinayagam, A., Val, C.D., Schubert, F., Elis, R., Glatting, K.H., Suhai, S., Konig, R.: GOPET: A tool for automated predictions of Gene Ontology terms. BMC Bioinformatics\u00a07 (2006)","DOI":"10.1186\/1471-2105-7-161"},{"key":"7_CR16","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/1007730.1007734","volume":"6","author":"G.M. Weiss","year":"2004","unstructured":"Weiss, G.M.: Mining with rarity: A unifying framework. ACM SIGKDD Explorations Newsletter\u00a06, 7\u201319 (2004)","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"7_CR17","unstructured":"Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: Proc. of the Fourteenth Inter. Conf. on Machine Learning (ICML), pp. 412\u2013420 (1997)"},{"key":"7_CR18","unstructured":"Yu, L., Liu, H.: Feature Selection for high-Dimensional Data: A Fast Correlation-based filter solution. In: Proc. of the Twentieth Inter. Conf. on Machine Learning (ICML) (2003)"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Zehetner, G.: OntoBlast function: from sequence similarities directly to potential functional annotations by ontology terms. Nucleic acids Research, 3799\u20133803 (2003)","DOI":"10.1093\/nar\/gkg555"},{"key":"7_CR20","unstructured":"Zhang, J., Mani, I.: kNN Approach to Unbalanced Data Distributions: A case study involving Information Extraction. In: ICML 2003 Workshop on learning from imbalanced datasets II (2003)"},{"key":"7_CR21","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1145\/1007730.1007741","volume":"6","author":"Z. Zheng","year":"2004","unstructured":"Zheng, Z., Wu, X., Shrihari, R.: Feature selection for text categorization on imbalanced data. ACM SIGKDD Exploration Newsletter\u00a06, 80\u201389 (2004)","journal-title":"ACM SIGKDD Exploration Newsletter"},{"key":"7_CR22","unstructured":"Gene Ontology(GO) Consortium, http:\/\/www.geneontology.org\/"},{"key":"7_CR23","unstructured":"InterPro, http:\/\/www.ebi.ac.uk\/interpro\/"},{"key":"7_CR24","unstructured":"MATLAB, http:\/\/www.mathworks.com\/"},{"key":"7_CR25","unstructured":"Pattern Recognition Toolbox for MATLAB, http:\/\/cmp.felk.cvut.cz\/~xfrancv\/stprtool\/"},{"key":"7_CR26","unstructured":"UniProt, http:\/\/www.uniprot.org\/"},{"key":"7_CR27","unstructured":"WEKA, http:\/\/www.cs.waikato.ac.nz\/~ml\/"}],"container-title":["Lecture Notes in Computer Science","Data Mining and Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11960669_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T04:51:11Z","timestamp":1736657471000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11960669_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540689706","9783540689713"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/11960669_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}