{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T18:23:00Z","timestamp":1743531780693},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"S2","content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Genomics"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/1471-2164-16-s2-s5","type":"journal-article","created":{"date-parts":[[2015,6,18]],"date-time":"2015-06-18T08:54:46Z","timestamp":1434617686000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Genome-wide association data classification and SNPs selection using two-stage quality-based Random Forests"],"prefix":"10.1186","volume":"16","author":[{"given":"Thanh-Tung","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Joshua Zhexue","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Qingyao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Thuy Thi","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Mark Junjie","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,1,21]]},"reference":[{"issue":"3","key":"6957_CR1","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1038\/ng.327","volume":"41","author":"S Kathiresan","year":"2009","unstructured":"Kathiresan S, Voight BF, Purcell S, Musunuru K, Ardissino D, Mannucci PM, Anand S, Engert JC, Samani NJ, Schunker H, et al: Genome-wide association of early-onset myocardial infarction with single nucleotide polymorphisms and copy number variants. Nature genetics. 2009, 41 (3): 334-341. 10.1038\/ng.327.","journal-title":"Nature genetics"},{"issue":"6822","key":"6957_CR2","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1038\/35057149","volume":"409","author":"R Sachidanandam","year":"2001","unstructured":"Sachidanandam R, Weissman D, Schmidt SC, Kakol JM, Stein LD, Marth G, Sherry S, Mullikin JC, Mortimore BJ, Willey DL, et al: A map of human genome sequence variation containing 1.42 million single nucleotide polymorphisms. Nature. 2001, 409 (6822): 928-933. 10.1038\/35057149.","journal-title":"Nature"},{"issue":"7145","key":"6957_CR3","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1038\/nature05911","volume":"447","author":"PR Burton","year":"2007","unstructured":"Burton PR, Clayton DG, Cardon LR, Craddock N, Deloukas P, Duncanson A, Kwiatkowski DP, McCarthy MI, Ouwehand WH, Samani NJ, et al: Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls. Nature. 2007, 447 (7145): 661-678. 10.1038\/nature05911.","journal-title":"Nature"},{"issue":"10","key":"6957_CR4","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1038\/nrg1916","volume":"7","author":"DJ Balding","year":"2006","unstructured":"Balding DJ: A tutorial on statistical methods for population association studies. Nature Reviews Genetics. 2006, 7 (10): 781-791. 10.1038\/nrg1916.","journal-title":"Nature Reviews Genetics"},{"issue":"20","key":"6957_CR5","doi-asserted-by":"publisher","first-page":"2463","DOI":"10.1093\/hmg\/11.20.2463","volume":"11","author":"HJ Cordell","year":"2002","unstructured":"Cordell HJ: Epistasis: what it means, what it doesn't mean, and statistical methods to detect it in humans. Human molecular genetics. 2002, 11 (20): 2463-2468. 10.1093\/hmg\/11.20.2463.","journal-title":"Human molecular genetics"},{"issue":"4","key":"6957_CR6","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1038\/ng1537","volume":"37","author":"J Marchini","year":"2005","unstructured":"Marchini J, Donnelly P, Cardon LR: Genome-wide strategies for detecting multiple loci that influence complex diseases. Nature genetics. 2005, 37 (4): 413-417. 10.1038\/ng1537.","journal-title":"Nature genetics"},{"issue":"6","key":"6957_CR7","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1038\/nrg2579","volume":"10","author":"HJ Cordell","year":"2009","unstructured":"Cordell HJ: Detecting gene-gene interactions that underlie human diseases. Nature Reviews Genetics. 2009, 10 (6): 392-404. 10.1038\/nrg2579.","journal-title":"Nature Reviews Genetics"},{"issue":"5","key":"6957_CR8","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1046\/j.1469-1809.2000.6450413.x","volume":"64","author":"J Hoh","year":"2000","unstructured":"Hoh J, iWlle A, Zee R, Cheng S, Reynolds R, Lindpaintner K, Ott J: Selecting snps in two-stage analysis of disease association data: a model-free approach. Annals of human genetics. 2000, 64 (5): 413-417. 10.1046\/j.1469-1809.2000.6450413.x.","journal-title":"Annals of human genetics"},{"issue":"1","key":"6957_CR9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L: Random forests. Machine learning. 2001, 45 (1): 5-32. 10.1023\/A:1010933404324.","journal-title":"Machine learning"},{"issue":"2","key":"6957_CR10","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1002\/gepi.20041","volume":"28","author":"A Bureau","year":"2005","unstructured":"Bureau A, Dupuis J, Falls K, Lunetta KL, Hayward B, Keith TP, Van Eerdewegh P: Identifying snps predictive of phenotype using random forests. Genetic epidemiology. 2005, 28 (2): 171-182. 10.1002\/gepi.20041.","journal-title":"Genetic epidemiology"},{"issue":"1","key":"6957_CR11","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/1471-2105-8-25","volume":"8","author":"C Strobl","year":"2007","unstructured":"Strobl C, Boulesteix A-L, Zeileis A, Hothorn T: Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC bioinformatics. 2007, 8 (1): 25-10.1186\/1471-2105-8-25.","journal-title":"BMC bioinformatics"},{"issue":"1","key":"6957_CR12","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/1471-2105-7-3","volume":"7","author":"R D\u00edaz-Uriarte","year":"2006","unstructured":"D\u00edaz-Uriarte R, de Andr\u00e9s A: Gene selection and classification of microarray data using random forest. BMC bioinformatics. 2006, 7 (1): 3-10.1186\/1471-2105-7-3.","journal-title":"BMC bioinformatics"},{"issue":"18","key":"6957_CR13","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1093\/bioinformatics\/btn356","volume":"24","author":"D Amaratunga","year":"2008","unstructured":"Amaratunga D, Cabrera J, Lee Y-S: Enriched random forests. Bioinformatics. 2008, 24 (18): 2010-2014. 10.1093\/bioinformatics\/btn356.","journal-title":"Bioinformatics"},{"issue":"1","key":"6957_CR14","doi-asserted-by":"publisher","first-page":"78.","DOI":"10.1186\/1471-2105-10-78","volume":"10","author":"YA Meng","year":"2009","unstructured":"Meng YA, Yu Y, Cupples LA, Farrer LA, Lunetta KL: Performance of random forest when SNPs are in linkage disequilibrium. BMC bioinformatics. 2009, 10 (1): 78.-10.1186\/1471-2105-10-78.","journal-title":"BMC bioinformatics"},{"key":"6957_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1186\/1753-6561-1-s1-s59","volume":"1","author":"DF Schwarz","year":"2007","unstructured":"Schwarz DF, Szymczak S, Ziegler A, K\u00f6nig IR: Picking single-nucleotide polymorphisms in forests. BMC Proceedings BioMed Central Ltd. 2007, 1: 59-","journal-title":"BMC Proceedings BioMed Central Ltd"},{"key":"6957_CR16","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/1753-6561-1-s1-s62","volume":"1","author":"YV Sun","year":"2007","unstructured":"Sun YV, Cai Z, Desai K, Lawrance R, Leff R, Jawaid A, Kardia SL, Yang H: Classification of rheumatoid arthritis status with candidate gene and genome-wide single-nucleotide polymorphisms using random forests. BMC Proceedings, BioMed Central Ltd. 2007, 1: 62-","journal-title":"BMC Proceedings, BioMed Central Ltd"},{"issue":"3","key":"6957_CR17","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1111\/j.1469-1809.2009.00511.x","volume":"73","author":"M Garc\u00eda-Magari\u00f1os","year":"2009","unstructured":"Garc\u00eda-Magari\u00f1os M, L\u00f3pez-de-Ullibarri I, Cao R, Salas A: Evaluating the ability of tree-based methods and logistic regression for the detection of snp-snp interaction. Annals of human genetics. 2009, 73 (3): 360-369. 10.1111\/j.1469-1809.2009.00511.x.","journal-title":"Annals of human genetics"},{"issue":"4","key":"6957_CR18","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.1016\/j.csda.2007.08.015","volume":"52","author":"KJ Archer","year":"2008","unstructured":"Archer KJ, Kimes RV: Empirical characterization of random forest variable importance measures. Computational Statistics & Data Analysis. 2008, 52 (4): 2249-2260. 10.1016\/j.csda.2007.08.015.","journal-title":"Computational Statistics & Data Analysis"},{"issue":"1","key":"6957_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1186\/1471-2156-5-32","volume":"5","author":"KL Lunetta","year":"2004","unstructured":"Lunetta KL, Hayward LB, Segal J, Van Eerdewegh P: Screening large-scale association study data: exploiting interactions using random forests. BMC genetics. 2004, 5 (1): 32-10.1186\/1471-2156-5-32.","journal-title":"BMC genetics"},{"issue":"14","key":"6957_CR20","doi-asserted-by":"publisher","first-page":"1752","DOI":"10.1093\/bioinformatics\/btq257","volume":"26","author":"DF Schwarz","year":"2010","unstructured":"Schwarz DF, K\u00f6onig IR, Ziegler A: On safari to Random Jungle: a fast implementation of Random Forests for high-dimensional data. Bioinformatics. 2010, 26 (14): 1752-10.1093\/bioinformatics\/btq257.","journal-title":"Bioinformatics"},{"issue":"3","key":"6957_CR21","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1109\/TNB.2012.2214232","volume":"11","author":"Q Wu","year":"2012","unstructured":"Wu Q, Ye Y, Liu Y, Ng MK: Snp selection and classification of genome-wide snp data using stratified sampling random forests. NanoBioscience, IEEE Transactions. 2012, 11 (3): 216-227.","journal-title":"NanoBioscience, IEEE Transactions"},{"issue":"6","key":"6957_CR22","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon F: Individual comparisons by ranking methods. Biometrics. 1945, 1 (6): 80-83. 10.2307\/3001968.","journal-title":"Biometrics"},{"key":"6957_CR23","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-319-06605-9_21","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"T-T Nguyen","year":"2014","unstructured":"Nguyen T-T, Huang JZ, Imran K, Li MJ, Williams G: Extensions to quantile regression forests for very high dimensional data. Advances in Knowledge Discovery and Data Mining. 2014, Lecture Notes in Computer Science, Springer, 8444: 247-258."},{"key":"6957_CR24","volume-title":"Classification and Regression Trees","author":"L Breiman","year":"1984","unstructured":"Breiman L, Friedman J, Stone CJ, Olshen RA: Classification and Regression Trees. 1984, CRC press"},{"issue":"4","key":"6957_CR25","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1016\/j.ajhg.2009.03.011","volume":"84","author":"JA Webster","year":"2009","unstructured":"Webster JA, Gibbs JR, Clarke J, Ray M, Zhang W, Holmans P, Rohrer K, Zhao A, Marlowe L, Kaleem M, et al: Genetic control of human brain transcript expression in Alzheimer disease. The American Journal of Human Genetics. 2009, 84 (4): 445-458. 10.1016\/j.ajhg.2009.03.011.","journal-title":"The American Journal of Human Genetics"},{"issue":"11","key":"6957_CR26","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1016\/S1474-4422(06)70578-6","volume":"5","author":"HC Fung","year":"2006","unstructured":"Fung HC, Scholz S, Matarin M, Sim\u00f3n-S\u00e1nchez J, Hernandez D, Britton A, Gibbs JR, Langefeld C, Stiegert ML, Schymick J, et al: Genome-wide genotyping in Parkinson's disease and neurologically normal controls: first stage analysis and public release of data. The Lancet Neurology. 2006, 5 (11): 911-916. 10.1016\/S1474-4422(06)70578-6.","journal-title":"The Lancet Neurology"},{"issue":"12","key":"6957_CR27","doi-asserted-by":"publisher","first-page":"3483","DOI":"10.1016\/j.patcog.2013.05.018","volume":"46","author":"H Deng","year":"2013","unstructured":"Deng H, Runger G: Gene selection with guided regularized random forest. Pattern Recognition. 2013, 46 (12): 3483-3489. 10.1016\/j.patcog.2013.05.018.","journal-title":"Pattern Recognition"},{"issue":"2","key":"6957_CR28","doi-asserted-by":"publisher","first-page":"44","DOI":"10.4018\/jdwm.2012040103","volume":"8","author":"B Xu","year":"2012","unstructured":"Xu B, Huang JZ, Williams G, Wang Q, Ye Y: Classifying very high-dimensional data with random forests built from small subspaces. International Journal of Data Warehousing and Mining (IJDWM). 2012, 8 (2): 44-63.","journal-title":"International Journal of Data Warehousing and Mining (IJDWM)"},{"issue":"3","key":"6957_CR29","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw A, Wiener M: Classification and regression by randomforest. R news. 2002, 2 (3): 18-22.","journal-title":"R news"},{"key":"6957_CR30","volume-title":"Guided random forest in the rrf package","author":"H Deng","year":"2013","unstructured":"Deng H: Guided random forest in the rrf package. 2013, arXiv preprint arXiv:1306.0237"},{"issue":"1","key":"6957_CR31","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/1471-2105-7-3","volume":"7","author":"R D\u00edaz-Uriarte","year":"2006","unstructured":"D\u00edaz-Uriarte R, De Andres SA: Gene selection and classification of microarray data using random forest. BMC bioinformatics. 2006, 7 (1): 3-10.1186\/1471-2105-7-3.","journal-title":"BMC bioinformatics"}],"container-title":["BMC Genomics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2164-16-S2-S5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,2]],"date-time":"2021-09-02T19:15:53Z","timestamp":1630610153000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcgenomics.biomedcentral.com\/articles\/10.1186\/1471-2164-16-S2-S5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,21]]},"references-count":31,"journal-issue":{"issue":"S2","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["6957"],"URL":"https:\/\/doi.org\/10.1186\/1471-2164-16-s2-s5","relation":{},"ISSN":["1471-2164"],"issn-type":[{"value":"1471-2164","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,21]]},"assertion":[{"value":"21 January 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"S5"}}