{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T18:35:51Z","timestamp":1791398151634,"version":"4.3.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","funder":[{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","award":["R01EY020483"],"award-info":[{"award-number":["R01EY020483"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000071","name":"National Institute of Child Health and Human Development","doi-asserted-by":"publisher","award":["N01HD33348"],"award-info":[{"award-number":["N01HD33348"]}],"id":[{"id":"10.13039\/100000071","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1186\/s13040-016-0087-3","type":"journal-article","created":{"date-parts":[[2016,2,1]],"date-time":"2016-02-01T08:02:01Z","timestamp":1454313721000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["r2VIM: A new variable selection method for random forests in genome-wide association studies"],"prefix":"10.1186","volume":"9","author":[{"given":"Silke","family":"Szymczak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Holzinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhijit","family":"Dasgupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James D.","family":"Malley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne M.","family":"Molloy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James L.","family":"Mills","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lawrence C.","family":"Brody","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dwight","family":"Stambolian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joan E.","family":"Bailey-Wilson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,2,1]]},"reference":[{"key":"87_CR1","doi-asserted-by":"publisher","first-page":"9362","DOI":"10.1073\/pnas.0903103106","volume":"106","author":"L Hindorff","year":"2009","unstructured":"Hindorff L, Sethupathy P, Junkins H, Ramos E, Mehta J, Collins F, et al. Potential etiologic and functional implications of genome-wide association loci for human diseases and traits. Proc Natl Acad Sci U S A. 2009;106:9362\u20137.","journal-title":"Proc Natl Acad Sci U S A"},{"key":"87_CR2","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1038\/nature08494","volume":"461","author":"TA Manolio","year":"2009","unstructured":"Manolio TA, Collins FS, Cox NJ, Goldstein DB, Hindorff LA, Hunter DJ, et al. Finding the missing heritability of complex diseases. Nature. 2009;461:747\u201353.","journal-title":"Nature"},{"key":"87_CR3","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"},{"key":"87_CR4","first-page":"32","volume":"10","author":"BA Goldstein","year":"2011","unstructured":"Goldstein BA, Polley EC, Briggs FBS. Random Forests for genetic association studies. Stat Appl Genet Mol. 2011;10:32.","journal-title":"Stat Appl Genet Mol"},{"key":"87_CR5","doi-asserted-by":"publisher","first-page":"S65","DOI":"10.1186\/1471-2105-10-S1-S65","volume":"10","author":"R Jiang","year":"2009","unstructured":"Jiang R, Tang W, Wu X, Fu W. A random forest approach to the detection of epistatic interactions in case\u2013control studies. BMC Bioinformatics. 2009;10:S65.","journal-title":"BMC Bioinformatics"},{"key":"87_CR6","doi-asserted-by":"publisher","first-page":"1752","DOI":"10.1093\/bioinformatics\/btq257","volume":"26","author":"DF Schwarz","year":"2010","unstructured":"Schwarz DF, K\u00f6nig IR, Ziegler A. On safari to Random Jungle: a fast implementation of Random Forests for high-dimensional data. Bioinformatics. 2010;26:1752\u20138.","journal-title":"Bioinformatics"},{"key":"87_CR7","unstructured":"Genuer R, Poggi J-M, Tuleau C. Random forests: some methodological insights [Internet]. INRIA Research Report RR-6729; 2008. Available from: \n                    http:\/\/hal.inria.fr\/inria-00340725\/en\/"},{"key":"87_CR8","unstructured":"Breiman L, Cutler A. Random forests [Internet]. Available from: \n                    http:\/\/www.stat.berkeley.edu\/~breiman\/RandomForests\/cc_home.htm"},{"key":"87_CR9","unstructured":"Strobl C, Zeileis A. Danger: High Power! - Exploring the Statistical Properties of a Test for Random Forest Variable Importance [Internet]. Department of Statistics University of Munich Technical Report 017; 2008. Available from: \n                    http:\/\/epub.ub.uni-muenchen.de\/2111\/"},{"issue":"Suppl 9","key":"87_CR10","doi-asserted-by":"publisher","first-page":"S104","DOI":"10.1186\/1753-6561-5-S9-S104","volume":"5","author":"Y Kim","year":"2011","unstructured":"Kim Y, Li Q, Cropp CD, Sung H, Cai J, Simpson CL, et al. Performance of random forests and logic regression methods using mini-exome sequence data. BMC Proc. 2011;5 Suppl 9:S104.","journal-title":"BMC Proc"},{"issue":"Suppl 7","key":"87_CR11","doi-asserted-by":"publisher","first-page":"S64","DOI":"10.1186\/1753-6561-3-s7-s64","volume":"3","author":"Y Kim","year":"2009","unstructured":"Kim Y, Wojciechowski R, Sung H, Mathias RA, Wang L, Klein AP, et al. Evaluation of random forests performance for genome-wide association studies in the presence of interaction effects. BMC Proc. 2009;3 Suppl 7:S64.","journal-title":"BMC Proc"},{"key":"87_CR12","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1186\/1471-2105-11-110","volume":"11","author":"KK Nicodemus","year":"2010","unstructured":"Nicodemus KK, Malley JD, Strobl C, Ziegler A. The behaviour of random forest permutation-based variable importance measures under predictor correlation. BMC Bioinformatics. 2010;11:110.","journal-title":"BMC Bioinformatics"},{"key":"87_CR13","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1037\/a0016973","volume":"14","author":"C Strobl","year":"2009","unstructured":"Strobl C, Malley J, Tutz G. An introduction to recursive partitioning: rationale, application and characteristics of classification and regression trees, bagging and random forests. Psychol Methods. 2009;14:323\u201348.","journal-title":"Psychol Methods"},{"key":"87_CR14","unstructured":"R package r2VIM [Internet]. Available from: \n                    http:\/\/research.nhgri.nih.gov\/software\/r2VIM"},{"key":"87_CR15","doi-asserted-by":"crossref","unstructured":"The 1000 Genomes Project Consortium. An integrated map of genetic variation from 1,092 human genomes. Nature. 2012;491:56\u201365.","DOI":"10.1038\/nature11632"},{"key":"87_CR16","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1093\/bioinformatics\/btm549","volume":"24","author":"C Li","year":"2008","unstructured":"Li C, Li M. GWAsimulator: a rapid whole-genome simulation program. Bioinformatics. 2008;24:140\u20132.","journal-title":"Bioinformatics"},{"key":"87_CR17","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1002\/gepi.21850","volume":"39","author":"R-H Chung","year":"2015","unstructured":"Chung R-H, Tsai W-Y, Hsieh C-H, Hung K-Y, Hsiung CA, Hauser ER. SeqSIMLA2: simulating correlated quantitative traits accounting for shared environmental effects in user-specified pedigree structure. Genet Epidemiol. 2015;39:20\u20134.","journal-title":"Genet Epidemiol"},{"key":"87_CR18","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1073\/pnas.1219885110","volume":"110","author":"KC Desch","year":"2013","unstructured":"Desch KC, Ozel AB, Siemieniak D, Kalish Y, Shavit JA, Thornburg CD, et al. Linkage analysis identifies a locus for plasma von Willebrand factor undetected by genome-wide association. Proc Natl Acad Sci U S A. 2013;110:588\u201393.","journal-title":"Proc Natl Acad Sci U S A"},{"key":"87_CR19","doi-asserted-by":"publisher","first-page":"495","DOI":"10.3945\/ajcn.111.014621","volume":"94","author":"J Mills","year":"2011","unstructured":"Mills J, Carter T, Scott J, Troendle J, Gibney E, Shane B, et al. Do high blood folate concentrations exacerbate metabolic abnormalities in people with low vitamin B-12 status? Am J Clin Nutr. 2011;94:495\u2013500.","journal-title":"Am J Clin Nutr"},{"key":"87_CR20","doi-asserted-by":"publisher","first-page":"e21851","DOI":"10.1371\/journal.pone.0021851","volume":"6","author":"N Stone","year":"2011","unstructured":"Stone N, Pangilinan F, Molloy A, Shane B, Scott J, Ueland P, et al. Bioinformatic and genetic association analysis of microRNA target sites in one-carbon metabolism genes. PLoS One. 2011;6:e21851.","journal-title":"PLoS One"},{"key":"87_CR21","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1001\/archopht.119.10.1417","volume":"119","author":"Age-Related Eye Disease Study Research Group","year":"2001","unstructured":"Age-Related Eye Disease Study Research Group. A randomized, placebo-controlled, clinical trial of high-dose supplementation with vitamins c and e, beta carotene, and zinc for age-related macular degeneration and vision loss: AREDS Report No. 8. Arch Ophthalmol. 2001;119:1417\u201336.","journal-title":"Arch Ophthalmol"},{"key":"87_CR22","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1001\/archopht.119.10.1439","volume":"119","author":"Age-Related Eye Disease Study Research Group","year":"2001","unstructured":"Age-Related Eye Disease Study Research Group. A randomized, placebo-controlled, clinical trial of high-dose supplementation with vitamins C and E and beta carotene for age-related cataract and vision loss: AREDS report no. 9. Arch Ophthalmol. 2001;119:1439\u201352.","journal-title":"Arch Ophthalmol"},{"key":"87_CR23","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1001\/archopht.121.2.211","volume":"121","author":"T Clemons","year":"2003","unstructured":"Clemons T, Chew E, Bressler S, McBee W. Age-Related eye disease study research group for the. National eye institute visual function questionnaire in the age-related eye disease study (AREDS): AREDS Report No. 10. Arch Ophthalmol. 2003;121:211\u20137.","journal-title":"Arch Ophthalmol"},{"key":"87_CR24","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1002\/gepi.20533","volume":"34","author":"Y Li","year":"2010","unstructured":"Li Y, Willer CJ, Ding J, Scheet P, Abecasis GR. MaCH: using sequence and genotype data to estimate haplotypes and unobserved genotypes. Genet Epidemiol. 2010;34:816\u201334.","journal-title":"Genet Epidemiol"},{"key":"87_CR25","first-page":"2173","volume":"19","author":"CL Simpson","year":"2013","unstructured":"Simpson CL, Wojciechowski R, Yee SS, Soni P, Bailey-Wilson JE, Stambolian D. Regional replication of association with refractive error on 15q14 and 15q25 in the Age-Related Eye Disease Study cohort. Mol Vis. 2013;19:2173\u201386.","journal-title":"Mol Vis"},{"key":"87_CR26","doi-asserted-by":"publisher","first-page":"2754","DOI":"10.1093\/hmg\/ddt116","volume":"22","author":"D Stambolian","year":"2013","unstructured":"Stambolian D, Wojciechowski R, Oexle K, Pirastu M, Li X, Raffel LJ, et al. Meta-analysis of genome-wide association studies in five cohorts reveals common variants in RBFOX1, a regulator of tissue-specific splicing, associated with refractive error. Hum Mol Genet. 2013;22:2754\u201364.","journal-title":"Hum Mol Genet"},{"key":"87_CR27","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1086\/519795","volume":"81","author":"S Purcell","year":"2007","unstructured":"Purcell S, Neale B, Todd-Brown K, Thomas L, Ferreira MAR, Bender D, et al. PLINK: A tool set for whole-genome association and population-based linkage analyses. Am J Hum Genet. 2007;81:559\u201375.","journal-title":"Am J Hum Genet"},{"key":"87_CR28","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13742-015-0047-8","volume":"4","author":"CC Chang","year":"2015","unstructured":"Chang CC, Chow CC, Tellier LC, Vattikuti S, Purcell SM, Lee JJ. Second-generation PLINK: rising to the challenge of larger and richer datasets. Gigasci. 2015;4:7.","journal-title":"Gigasci"},{"key":"87_CR29","volume-title":"Variable selection method for the identification of epistatic models. Pacific Symposium on Biocomputing (PSB)","author":"ER Holzinger","year":"2015","unstructured":"Holzinger ER, Szymczak S, Dasgupta A, Malley J, Li Q, Bailey Wilson JE. Variable selection method for the identification of epistatic models. Pacific Symposium on Biocomputing (PSB). Maui, HI: World Scientific; 2015."},{"key":"87_CR30","doi-asserted-by":"publisher","first-page":"74","DOI":"10.3414\/ME00-01-0052","volume":"51","author":"J Malley","year":"2012","unstructured":"Malley J, Kruppa J, Dasgupta A, Malley K, Ziegler A. Probability Machines: Consistent Probability Estimation Using Nonparametric Learning Machines. Methods Inf Med. 2012;51:74\u201381.","journal-title":"Methods Inf Med"},{"key":"87_CR31","doi-asserted-by":"publisher","first-page":"30","DOI":"10.3141\/2061-04","volume":"2061","author":"X Qin","year":"2008","unstructured":"Qin X, Han J. Variable selection issues in tree-based regression models. Transport Res Record J Transport Res Board. 2008;2061:30\u20138.","journal-title":"Transport Res Record J Transport Res Board"},{"key":"87_CR32","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;8:25.","journal-title":"BMC Bioinformatics"},{"key":"87_CR33","first-page":"361","volume":"12","author":"W-Y Loh","year":"2002","unstructured":"Loh W-Y. Regression trees with unbiased variable selection and interaction detection. Stat Sinica. 2002;12:361\u201386.","journal-title":"Stat Sinica"},{"key":"87_CR34","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1002\/gepi.20497","volume":"34","author":"J Yang","year":"2010","unstructured":"Yang J, Wray NR, Visscher PM. Comparing apples and oranges: equating the power of case\u2013control and quantitative trait association studies. Genet Epidemiol. 2010;34:254\u20137.","journal-title":"Genet Epidemiol"},{"key":"87_CR35","doi-asserted-by":"publisher","first-page":"1884","DOI":"10.1093\/bioinformatics\/btp331","volume":"25","author":"KK Nicodemus","year":"2009","unstructured":"Nicodemus KK, Malley JD. Predictor correlation impacts machine learning algorithms: implications for genomic studies. Bioinformatics. 2009;25:1884\u201390.","journal-title":"Bioinformatics"},{"key":"87_CR36","doi-asserted-by":"publisher","first-page":"2615","DOI":"10.1093\/bioinformatics\/bts483","volume":"28","author":"R Walters","year":"2012","unstructured":"Walters R, Laurin C, Lubke GH. An integrated approach to reduce the impact of minor allele frequency and linkage disequilibrium on variablen importance measures for genome-wide data. Bioinformatics. 2012;28:2615\u201323.","journal-title":"Bioinformatics"},{"key":"87_CR37","doi-asserted-by":"publisher","first-page":"606","DOI":"10.4065\/mcp.2011.0178","volume":"86","author":"SJ Bielinski","year":"2011","unstructured":"Bielinski SJ, Chai HS, Pathak J, Talwalkar JA, Limburg PJ, Gullerud RE, et al. Mayo Genome Consortia: a genotype-phenotype resource for genome-wide association studies with an application to the analysis of circulating bilirubin levels. Mayo Clin Proc. 2011;86:606\u201314.","journal-title":"Mayo Clin Proc."},{"key":"87_CR38","doi-asserted-by":"publisher","first-page":"2700","DOI":"10.1093\/hmg\/ddp202","volume":"18","author":"AD Johnson","year":"2009","unstructured":"Johnson AD, Kavousi M, Smith AV, Chen M-H, Dehghan A, Aspelund T, et al. Genome-wide association meta-analysis for total serum bilirubin levels. Hum Mol Genet. 2009;18:2700\u201310.","journal-title":"Hum Mol Genet"},{"key":"87_CR39","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1038\/nature10354","volume":"477","author":"K Suhre","year":"2011","unstructured":"Suhre K, Shin S-Y, Petersen A-K, Mohney RP, Meredith D, W\u00e4gele B, et al. Human metabolic individuality in biomedical and pharmaceutical research. Nature. 2011;477:54\u201360.","journal-title":"Nature"},{"key":"87_CR40","doi-asserted-by":"publisher","first-page":"8170","DOI":"10.1073\/pnas.95.14.8170","volume":"95","author":"E Beutler","year":"1998","unstructured":"Beutler E, Gelbart T, Demina A. Racial variability in the UDP-glucuronosyltransferase 1 (UGT1A1) promoter: a balanced polymorphism for regulation of bilirubin metabolism? Proc Natl Acad Sci. National Acad Sci. 1998;95:8170\u20134.","journal-title":"National Acad Sci"}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-016-0087-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-016-0087-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,14]],"date-time":"2020-05-14T08:54:58Z","timestamp":1589446498000},"score":1,"resource":{"primary":{"URL":"https:\/\/biodatamining.biomedcentral.com\/articles\/10.1186\/s13040-016-0087-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,2,1]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["87"],"URL":"https:\/\/doi.org\/10.1186\/s13040-016-0087-3","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,2,1]]},"assertion":[{"value":"14 July 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2016","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2016","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"7"}}