{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:00:15Z","timestamp":1762506015531},"reference-count":6,"publisher":"Oxford University Press (OUP)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Summary: Computational workloads for genome-wide association studies (GWAS) are growing in scale and complexity outpacing the capabilities of single-threaded software designed for personal computers. The BlueSNP R package implements GWAS statistical tests in the R programming language and executes the calculations across computer clusters configured with Apache Hadoop, a de facto standard framework for distributed data processing using the MapReduce formalism. BlueSNP makes computationally intensive analyses, such as estimating empirical p-values via data permutation, and searching for expression quantitative trait loci over thousands of genes, feasible for large genotype\u2013phenotype datasets.<\/jats:p>\n               <jats:p>Availability and implementation: \u00a0http:\/\/github.com\/ibm-bioinformatics\/bluesnp<\/jats:p>\n               <jats:p>Contact: \u00a0rjprill@us.ibm.com<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/bts647","type":"journal-article","created":{"date-parts":[[2012,12,1]],"date-time":"2012-12-01T01:16:58Z","timestamp":1354324618000},"page":"135-136","source":"Crossref","is-referenced-by-count":31,"title":["BlueSNP: R package for highly scalable genome-wide association studies using Hadoop clusters"],"prefix":"10.1093","volume":"29","author":[{"given":"Hailiang","family":"Huang","sequence":"first","affiliation":[{"name":"1 Healthcare Informatics, IBM Almaden Research Center, San Jose, CA 95120, 2Analytic and Translational Genetics Unit, Massachusetts General Hospital, Boston, MA 02114 and 3Information Management, IBM Almaden Research Center, San Jose, CA 95120, USA"},{"name":"1 Healthcare Informatics, IBM Almaden Research Center, San Jose, CA 95120, 2Analytic and Translational Genetics Unit, Massachusetts General Hospital, Boston, MA 02114 and 3Information Management, IBM Almaden Research Center, San Jose, CA 95120, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandeep","family":"Tata","sequence":"additional","affiliation":[{"name":"1 Healthcare Informatics, IBM Almaden Research Center, San Jose, CA 95120, 2Analytic and Translational Genetics Unit, Massachusetts General Hospital, Boston, MA 02114 and 3Information Management, IBM Almaden Research Center, San Jose, CA 95120, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert J.","family":"Prill","sequence":"additional","affiliation":[{"name":"1 Healthcare Informatics, IBM Almaden Research Center, San Jose, CA 95120, 2Analytic and Translational Genetics Unit, Massachusetts General Hospital, Boston, MA 02114 and 3Information Management, IBM Almaden Research Center, San Jose, CA 95120, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2012,11,29]]},"reference":[{"key":"2023020303202176600_bts647-B1","article-title":"Computing environment for the statistical analysis of large and complex data","author":"Guha","year":"2010"},{"key":"2023020303202176600_bts647-B2","doi-asserted-by":"crossref","first-page":"R134","DOI":"10.1186\/gb-2009-10-11-r134","article-title":"Searching for SNPs with cloud computing","volume":"10","author":"Langmead","year":"2009","journal-title":"Genome Biol."},{"key":"2023020303202176600_bts647-B3","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1086\/519795","article-title":"Plink: a tool set for whole-genome association and population-based linkage analyses","volume":"81","author":"Purcell","year":"2007","journal-title":"Am. J. Hum. Genet."},{"key":"2023020303202176600_bts647-B4"},{"key":"2023020303202176600_bts647-B5","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1038\/nature01434","article-title":"Genetics of gene expression surveyed in maize, mouse and man","volume":"422","author":"Schadt","year":"2003","journal-title":"Nature"},{"key":"2023020303202176600_bts647-B6","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1038\/nrg2857","article-title":"Computational solutions to large-scale data management and analysis","volume":"11","author":"Schadt","year":"2010","journal-title":"Nat. Rev. Genet."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/1\/135\/49060214\/bioinformatics_29_1_135.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/1\/135\/49060214\/bioinformatics_29_1_135.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T03:20:50Z","timestamp":1675394450000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/29\/1\/135\/273087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,29]]},"references-count":6,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bts647","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2013,1]]},"published":{"date-parts":[[2012,11,29]]}}}