{"PubmedArticle":{"MedlineCitation":{"@attributes":{"Status":"MEDLINE","Owner":"NLM","IndexingMethod":"Manual"},"PMID":{"@attributes":{"Version":"1"},"@text":"28096893"},"DateCompleted":{"Year":"2017","Month":"03","Day":"07"},"DateRevised":{"Year":"2018","Month":"11","Day":"13"},"Article":{"@attributes":{"PubModel":"Print-Electronic"},"Journal":{"ISSN":{"@attributes":{"IssnType":"Electronic"},"@text":"1748-6718"},"JournalIssue":{"@attributes":{"CitedMedium":"Internet"},"Volume":"2016","PubDate":{"Year":"2016"}},"Title":"Computational and mathematical methods in medicine","ISOAbbreviation":"Comput Math Methods Med"},"ArticleTitle":"Determining Cutoff Point of Ensemble Trees Based on Sample Size in Predicting Clinical Dose with DNA Microarray Data.","Pagination":{"StartPage":"6794916","MedlinePgn":"6794916"},"ELocationID":[{"@attributes":{"EIdType":"pii","ValidYN":"Y"},"@text":"6794916"},{"@attributes":{"EIdType":"doi","ValidYN":"Y"},"@text":"10.1155\/2016\/6794916"}],"Abstract":{"AbstractText":["<i>Background\/Aim<\/i>. Evaluating the success of dose prediction based on genetic or clinical data has substantially advanced recently. The aim of this study is to predict various clinical dose values from DNA gene expression datasets using data mining techniques. <i>Materials and Methods<\/i>. Eleven real gene expression datasets containing dose values were included. First, important genes for dose prediction were selected using iterative sure independence screening. Then, the performances of regression trees (RTs), support vector regression (SVR), RT bagging, SVR bagging, and RT boosting were examined. <i>Results<\/i>. The results demonstrated that a regression-based feature selection method substantially reduced the number of irrelevant genes from raw datasets. Overall, the best prediction performance in nine of 11 datasets was achieved using SVR; the second most accurate performance was provided using a gradient-boosting machine (GBM). <i>Conclusion<\/i>. Analysis of various dose values based on microarray gene expression data identified common genes found in our study and the referenced studies. According to our findings, SVR and GBM can be good predictors of dose-gene datasets. Another result of the study was to identify the sample size of <i>n<\/i> = 25 as a cutoff point for RT bagging to outperform a single RT."]},"AuthorList":{"@attributes":{"CompleteYN":"Y"},"Author":[{"@attributes":{"ValidYN":"Y"},"LastName":"Y\u0131lmaz Is\u0131khan","ForeName":"Selen","Initials":"S","Identifier":[{"@attributes":{"Source":"ORCID"},"@text":"0000-0002-3725-2987"}],"AffiliationInfo":[{"Affiliation":"Vocational School of Social Sciences, Hacettepe University, Ankara, Turkey; Department of Biostatistics, Faculty of Medicine, Hacettepe University, Ankara, Turkey."}]},{"@attributes":{"ValidYN":"Y"},"LastName":"Karabulut","ForeName":"Erdem","Initials":"E","AffiliationInfo":[{"Affiliation":"Department of Biostatistics, Faculty of Medicine, Hacettepe University, Ankara, Turkey."}]},{"@attributes":{"ValidYN":"Y"},"LastName":"Alpar","ForeName":"Celal Reha","Initials":"CR","AffiliationInfo":[{"Affiliation":"Department of Biostatistics, Faculty of Medicine, Hacettepe University, Ankara, Turkey."}]}]},"Language":["eng"],"PublicationTypeList":{"PublicationType":[{"@attributes":{"UI":"D016428"},"@text":"Journal Article"}]},"ArticleDate":[{"@attributes":{"DateType":"Electronic"},"Year":"2016","Month":"12","Day":"20"}]},"MedlineJournalInfo":{"Country":"United States","MedlineTA":"Comput Math Methods Med","NlmUniqueID":"101277751","ISSNLinking":"1748-670X"},"ChemicalList":{"Chemical":[{"RegistryNumber":"0","NameOfSubstance":{"@attributes":{"UI":"D004364"},"@text":"Pharmaceutical Preparations"}}]},"CitationSubset":["IM"],"MeshHeadingList":{"MeshHeading":[{"DescriptorName":{"@attributes":{"UI":"D000465","MajorTopicYN":"N"},"@text":"Algorithms"}},{"DescriptorName":{"@attributes":{"UI":"D000818","MajorTopicYN":"N"},"@text":"Animals"}},{"DescriptorName":{"@attributes":{"UI":"D001185","MajorTopicYN":"N"},"@text":"Artificial Intelligence"}},{"DescriptorName":{"@attributes":{"UI":"D003198","MajorTopicYN":"N"},"@text":"Computer Simulation"}},{"DescriptorName":{"@attributes":{"UI":"D057225","MajorTopicYN":"N"},"@text":"Data Mining"},"QualifierName":[{"@attributes":{"UI":"Q000379","MajorTopicYN":"N"},"@text":"methods"}]},{"DescriptorName":{"@attributes":{"UI":"D020869","MajorTopicYN":"N"},"@text":"Gene Expression Profiling"}},{"DescriptorName":{"@attributes":{"UI":"D005786","MajorTopicYN":"N"},"@text":"Gene Expression Regulation"}},{"DescriptorName":{"@attributes":{"UI":"D023281","MajorTopicYN":"N"},"@text":"Genomics"}},{"DescriptorName":{"@attributes":{"UI":"D006801","MajorTopicYN":"N"},"@text":"Humans"}},{"DescriptorName":{"@attributes":{"UI":"D015233","MajorTopicYN":"N"},"@text":"Models, Statistical"}},{"DescriptorName":{"@attributes":{"UI":"D020411","MajorTopicYN":"N"},"@text":"Oligonucleotide Array Sequence Analysis"},"QualifierName":[{"@attributes":{"UI":"Q000379","MajorTopicYN":"Y"},"@text":"methods"}]},{"DescriptorName":{"@attributes":{"UI":"D004364","MajorTopicYN":"N"},"@text":"Pharmaceutical Preparations"}},{"DescriptorName":{"@attributes":{"UI":"D010597","MajorTopicYN":"N"},"@text":"Pharmacogenetics"},"QualifierName":[{"@attributes":{"UI":"Q000379","MajorTopicYN":"Y"},"@text":"methods"}]},{"DescriptorName":{"@attributes":{"UI":"D011336","MajorTopicYN":"N"},"@text":"Probability"}},{"DescriptorName":{"@attributes":{"UI":"D051381","MajorTopicYN":"N"},"@text":"Rats"}},{"DescriptorName":{"@attributes":{"UI":"D012044","MajorTopicYN":"N"},"@text":"Regression Analysis"}},{"DescriptorName":{"@attributes":{"UI":"D015203","MajorTopicYN":"N"},"@text":"Reproducibility of Results"}},{"DescriptorName":{"@attributes":{"UI":"D018401","MajorTopicYN":"N"},"@text":"Sample Size"}},{"DescriptorName":{"@attributes":{"UI":"D013045","MajorTopicYN":"N"},"@text":"Species Specificity"}},{"DescriptorName":{"@attributes":{"UI":"D060388","MajorTopicYN":"N"},"@text":"Support Vector Machine"}},{"DescriptorName":{"@attributes":{"UI":"D015003","MajorTopicYN":"N"},"@text":"Yeasts"},"QualifierName":[{"@attributes":{"UI":"Q000235","MajorTopicYN":"N"},"@text":"genetics"},{"@attributes":{"UI":"Q000378","MajorTopicYN":"N"},"@text":"metabolism"}]}]},"CoiStatement":"The authors declare that there is no conflict of interests regarding the publication of this paper."},"PubmedData":{"History":{"PubMedPubDate":[{"@attributes":{"PubStatus":"received"},"Year":"2016","Month":"7","Day":"29"},{"@attributes":{"PubStatus":"revised"},"Year":"2016","Month":"11","Day":"18"},{"@attributes":{"PubStatus":"accepted"},"Year":"2016","Month":"11","Day":"27"},{"@attributes":{"PubStatus":"entrez"},"Year":"2017","Month":"1","Day":"19","Hour":"6","Minute":"0"},{"@attributes":{"PubStatus":"pubmed"},"Year":"2017","Month":"1","Day":"18","Hour":"6","Minute":"0"},{"@attributes":{"PubStatus":"medline"},"Year":"2017","Month":"3","Day":"8","Hour":"6","Minute":"0"},{"@attributes":{"PubStatus":"pmc-release"},"Year":"2016","Month":"12","Day":"20"}]},"PublicationStatus":"ppublish","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"pubmed"},"@text":"28096893"},{"@attributes":{"IdType":"pmc"},"@text":"PMC5206477"},{"@attributes":{"IdType":"doi"},"@text":"10.1155\/2016\/6794916"}]},"ReferenceList":[{"Reference":[{"Citation":"Segal M. R., Dahlquist K. D., Conklin B. R. Regression approaches for microarray data analysis. Journal of Computational Biology. 2003;10(6):961\u2013980. doi: 10.1089\/106652703322756177.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1089\/106652703322756177"},{"@attributes":{"IdType":"pubmed"},"@text":"14980020"}]}},{"Citation":"Smola A., Vapnik V. N. Advances in Neural Information Processing Systems. Vol. 9. MIT Press; 1997. Support vector regression machines; pp. 155\u2013161."},{"Citation":"Brown M. P. S., Grundy W. N., Lin D., et al. Knowledge-based analysis of microarray gene expression data by using support vector machines. Proceedings of the National Academy of Sciences of the United States of America. 2000;97(1):262\u2013267. doi: 10.1073\/pnas.97.1.262.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1073\/pnas.97.1.262"},{"@attributes":{"IdType":"pmc"},"@text":"PMC26651"},{"@attributes":{"IdType":"pubmed"},"@text":"10618406"}]}},{"Citation":"Ye N. The Handbook of Data Mining. 1st. London, UK: Lawrence Erlbaum Associates Publishers; 2003."},{"Citation":"Boulesteix A.-L., Strobl C., Augustin T., Daumer M. Evaluating microarray-based classifiers: an overview. Cancer Informatics. 2008;6:77\u201397.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"pmc"},"@text":"PMC2623308"},{"@attributes":{"IdType":"pubmed"},"@text":"19259405"}]}},{"Citation":"Abrahantes J. C., Shkedy Z., Molenberghs G. Alternative methods to evaluate trial level surrogacy. Clinical Trials. 2008;5(3):194\u2013208. doi: 10.1177\/1740774508091677.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1177\/1740774508091677"},{"@attributes":{"IdType":"pubmed"},"@text":"18559408"}]}},{"Citation":"Cutler A., Cutler D. R., Stevens J. R. Tree-based methods. In: Li X., Xu R., editors. High-Dimensional Data Analysis in Cancer Research. 1st. New York, NY, USA: Springer; 2009."},{"Citation":"Cosgun E., Karaagaoglu E. Veri Madencili\u011fi Y\u00f6ntemleriyle Mikrodizilim Gen \u0130fade Analizi. Hacettepe T\u0131p Dergisi. 2011;42:180\u2013189."},{"Citation":"Mart\u00ednez-Mu\u00f1oz G., Su\u00e1rez A. Out-of-bag estimation of the optimal sample size in bagging. Pattern Recognition. 2010;43(1):143\u2013152. doi: 10.1016\/j.patcog.2009.05.010.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1016\/j.patcog.2009.05.010"}]}},{"Citation":"Klein T. E., Altman R. B., Eriksson N., et al. Estimation of the warfarin dose with clinical and pharmacogenetic data. The New England Journal of Medicine. 2009;360(8):753\u2013764. doi: 10.1056\/nejmoa0809329.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1056\/nejmoa0809329"},{"@attributes":{"IdType":"pmc"},"@text":"PMC2722908"},{"@attributes":{"IdType":"pubmed"},"@text":"19228618"}]}},{"Citation":"Quackenbush J. Microarray data normalization and transformation. Nature Genetics. 2002;32(5):496\u2013501. doi: 10.1038\/ng1032.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1038\/ng1032"},{"@attributes":{"IdType":"pubmed"},"@text":"12454644"}]}},{"Citation":"Fang Y., Qin Y., Zhang N., Wang J., Wang H., Zheng X. DISIS: prediction of drug response through an iterative sure independence screening. PLoS ONE. 2015;10(3) doi: 10.1371\/journal.pone.0120408.e0120408","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1371\/journal.pone.0120408"},{"@attributes":{"IdType":"pmc"},"@text":"PMC4368776"},{"@attributes":{"IdType":"pubmed"},"@text":"25794193"}]}},{"Citation":"Fan J., Lv J. Sure independence screening for ultrahigh dimensional feature space. Journal of the Royal Statistical Society, Series B: Statistical Methodology. 2008;70(5):849\u2013911. doi: 10.1111\/j.1467-9868.2008.00674.x.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1111\/j.1467-9868.2008.00674.x"},{"@attributes":{"IdType":"pmc"},"@text":"PMC2709408"},{"@attributes":{"IdType":"pubmed"},"@text":"19603084"}]}},{"Citation":"Vapnik V. N. An overview of statistical learning theory. IEEE Transactions on Neural Networks. 1999;10(5):988\u2013999. doi: 10.1109\/72.788640.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1109\/72.788640"},{"@attributes":{"IdType":"pubmed"},"@text":"18252602"}]}},{"Citation":"Li G.-Z., Meng H.-H., Yang M. Q., Yang J. Y. Combining support vector regression with feature selection for multivariate calibration. Neural Computing and Applications. 2009;18(7):813\u2013820. doi: 10.1007\/s00521-008-0202-6.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1007\/s00521-008-0202-6"}]}},{"Citation":"Grubinger T., Kobel C., Pfeiffer K.-P. Regression tree construction by bootstrap: model search for DRG-systems applied to Austrian health-data. BMC Medical Informatics and Decision Making. 2010;10(1, article 9) doi: 10.1186\/1472-6947-10-9.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1186\/1472-6947-10-9"},{"@attributes":{"IdType":"pmc"},"@text":"PMC2828419"},{"@attributes":{"IdType":"pubmed"},"@text":"20122286"}]}},{"Citation":"Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. New York, NY, USA: Springer; 2001. (Springer Series in Statistics).","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1007\/978-0-387-21606-5"}]}},{"Citation":"Yang P., Yang Y. H., Zhou B. B., Zomaya A. Y. A review of ensemble methods in bioinformatics. Current Bioinformatics. 2010;5(4):296\u2013308. doi: 10.2174\/157489310794072508.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.2174\/157489310794072508"}]}},{"Citation":"Breiman L. Bagging predictors. Machine Learning. 1996;24(2):123\u2013140."},{"Citation":"B{\\\"u}hlmann P., Hothorn T. Boosting algorithms: regularization, prediction and model fitting. Statistical Science. 2007;22(4):477\u2013505. doi: 10.1214\/07-sts242.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1214\/07-sts242"}]}},{"Citation":"Ridgeway G. The state of boosting. Computing Science and Statistics. 1999;31:172\u2013181."},{"Citation":"Drucker H., Burges C. J. C., Kaufman L., Smola A., Vapnik V. Advances in Neural Information Processing Systems. Vol. 9. MIT Press; 1997. Support vector regression machines; pp. 155\u2013161."},{"Citation":"Breiman L. 547. Berkeley, Calif, USA: University of California-Department of Statistics; 1999. Using adaptive bagging to debias regressions."},{"Citation":"Ridgeway G. gbm: Generalized boosted regression models. R package version 1.6-3, 2007."},{"Citation":"Friedman J. H. Stochastic gradient boosting. Computational Statistics &amp; Data Analysis. 2002;38(4):367\u2013378. doi: 10.1016\/s0167-9473(01)00065-2.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1016\/s0167-9473(01)00065-2"}]}},{"Citation":"Burton A., Altman D. G., Royston P., Holder R. L. The design of simulation studies in medical statistics. Statistics in Medicine. 2006;25(24):4279\u20134292. doi: 10.1002\/sim.2673.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1002\/sim.2673"},{"@attributes":{"IdType":"pubmed"},"@text":"16947139"}]}},{"Citation":"Jiang W., Simon R. A comparison of bootstrap methods and an adjusted bootstrap approach for estimating the prediction error in microarray classification. Statistics in Medicine. 2007;26(29):5320\u20135334. doi: 10.1002\/sim.2968.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1002\/sim.2968"},{"@attributes":{"IdType":"pubmed"},"@text":"17624926"}]}},{"Citation":"Refaeilzadeh P., Tang L., Liu H. Cross validation. In: Liu L., \u00d6zsu M. T., editors. Encyclopedia of Database Systems (EDBS) 1st. New York, NY, USA: Springer; 2009. pp. 532\u2013538."},{"Citation":"Bensellam M., Van Lommel L., Overbergh L., Schuit F. C., Jonas J. C. Cluster analysis of rat pancreatic islet gene mRNA levels after culture in low-, intermediate- and high-glucose concentrations. Diabetologia. 2009;52(3):463\u2013476. doi: 10.1007\/s00125-008-1245-z.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1007\/s00125-008-1245-z"},{"@attributes":{"IdType":"pubmed"},"@text":"19165461"}]}},{"Citation":"Van Dijk S. J., Feskens E. J. M., Bos M. B., et al. A saturated fatty acid-rich diet induces an obesity-linked proinflammatory gene expression profile in adipose tissue of subjects at risk of metabolic syndrome. American Journal of Clinical Nutrition. 2009;90(6):1656\u20131664. doi: 10.3945\/ajcn.2009.27792.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.3945\/ajcn.2009.27792"},{"@attributes":{"IdType":"pubmed"},"@text":"19828712"}]}},{"Citation":"Song M. O., Li J., Freedman J. H. Physiological and toxicological transcriptome changes in HepG2 cells exposed to copper. Physiological Genomics. 2009;38(3):386\u2013401. doi: 10.1152\/physiolgenomics.00083.2009.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1152\/physiolgenomics.00083.2009"},{"@attributes":{"IdType":"pmc"},"@text":"PMC3774564"},{"@attributes":{"IdType":"pubmed"},"@text":"19549813"}]}},{"Citation":"Harrill J. A., Li Z., Wright F. A., et al. Transcriptional response of rat frontal cortex following acute in vivo exposure to the pyrethroid insecticides permethrin and deltamethrin. BMC Genomics. 2008;9, article no. 546 doi: 10.1186\/1471-2164-9-546.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1186\/1471-2164-9-546"},{"@attributes":{"IdType":"pmc"},"@text":"PMC2626604"},{"@attributes":{"IdType":"pubmed"},"@text":"19017407"}]}},{"Citation":"McQuisten K. A., Peek A. S. Comparing artificial neural networks, general linear models and support vector machines in building predictive models for small interfering RNAs. PLOS ONE. 2009;4(10) doi: 10.1371\/journal.pone.0007522.e7522","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1371\/journal.pone.0007522"},{"@attributes":{"IdType":"pmc"},"@text":"PMC2760777"},{"@attributes":{"IdType":"pubmed"},"@text":"19847297"}]}},{"Citation":"Braga P. L., Oliveira A. L. I., Ribeiro G. H. T., Meira S. R. L. Bagging predictors for estimation of software project effort. Proceedings of the International Joint Conference on Neural Networks (IJCNN '07); August 2007; Orlando, Fla, USA. pp. 1595\u20131600.","ArticleIdList":{"ArticleId":[{"@attributes":{"IdType":"doi"},"@text":"10.1109\/ijcnn.2007.4371196"}]}}]}]}}}