{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T07:15:29Z","timestamp":1782371729829,"version":"3.54.5"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031047480","type":"print"},{"value":"9783031047497","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-04749-7_6","type":"book-chapter","created":{"date-parts":[[2022,5,11]],"date-time":"2022-05-11T16:13:24Z","timestamp":1652285604000},"page":"86-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Fast, Provably Accurate Approximation Algorithm for\u00a0Sparse Principal Component Analysis Reveals Human Genetic Variation Across the\u00a0World"],"prefix":"10.1007","author":[{"given":"Agniva","family":"Chowdhury","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8665-056X","authenticated-orcid":false,"given":"Aritra","family":"Bose","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samson","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David P.","family":"Woodruff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1994-8670","authenticated-orcid":false,"given":"Petros","family":"Drineas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,4,29]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Asteris, M., Papailiopoulos, D., Karystinos, G.N.: Sparse principal component of a rank-deficient matrix. In: 2011 IEEE International Symposium on Information Theory Proceedings, pp. 673\u2013677 (2011)","DOI":"10.1109\/ISIT.2011.6034216"},{"key":"6_CR2","unstructured":"Asteris, M., Papailiopoulos, D., Kyrillidis, A., Dimakis, A.G.: Sparse PCA via bipartite matchings. In: Advances in Neural Information Processing Systems, pp. 766\u2013774 (2015)"},{"issue":"1","key":"6_CR3","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s10957-016-0934-x","volume":"170","author":"A Beck","year":"2016","unstructured":"Beck, A., Vaisbourd, Y.: The sparse principal component analysis problem: optimality conditions and algorithms. J. Optim. Theory Appl. 170(1), 119\u2013143 (2016). https:\/\/doi.org\/10.1007\/s10957-016-0934-x","journal-title":"J. Optim. Theory Appl."},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Bose, A., Burch, M.C., Chowdhury, A., Paschou, P., Drineas, P.: Clustrat: a structure informed clustering strategy for population stratification. bioRxiv (2020)","DOI":"10.1101\/2020.01.15.908228"},{"issue":"19","key":"6_CR5","doi-asserted-by":"publisher","first-page":"3679","DOI":"10.1093\/bioinformatics\/btz157","volume":"35","author":"A Bose","year":"2019","unstructured":"Bose, A., Kalantzis, V., Kontopoulou, E.M., Elkady, M., Paschou, P., Drineas, P.: TeraPCA: a fast and scalable software package to study genetic variation in tera-scale genotypes. Bioinformatics 35(19), 3679\u20133683 (2019)","journal-title":"Bioinformatics"},{"issue":"D1","key":"6_CR6","doi-asserted-by":"publisher","first-page":"D1005","DOI":"10.1093\/nar\/gky1120","volume":"47","author":"A Buniello","year":"2019","unstructured":"Buniello, A., et al.: The NHGRI-EBI GWAS catalog of published genome-wide association studies, targeted arrays and summary statistics 2019. Nucleic Acids Res. 47(D1), D1005\u2013D1012 (2019)","journal-title":"Nucleic Acids Res."},{"issue":"2","key":"6_CR7","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1080\/757584614","volume":"22","author":"J Cadima","year":"1995","unstructured":"Cadima, J., Jolliffe, I.T.: Loading and correlations in the interpretation of principal components. J. Appl. Stat. 22(2), 203\u2013214 (1995)","journal-title":"J. Appl. Stat."},{"key":"6_CR8","unstructured":"Chan, S.O., Papailliopoulos, D., Rubinstein, A.: On the approximability of sparse PCA. In: Proceedings of the 29th Conference on Learning Theory, pp. 623\u2013646 (2016)"},{"issue":"1","key":"6_CR9","doi-asserted-by":"publisher","first-page":"s13742","DOI":"10.1186\/s13742-015-0047-8","volume":"4","author":"CC Chang","year":"2015","unstructured":"Chang, C.C., Chow, C.C., Tellier, L.C., Vattikuti, S., Purcell, S.M., Lee, J.J.: Second-generation plink: rising to the challenge of larger and richer datasets. Gigascience 4(1), s13742-015 (2015)","journal-title":"Gigascience"},{"key":"6_CR10","unstructured":"Consortium, G.P., et al.: A global reference for human genetic variation. Nature 526(7571), 68 (2015)"},{"issue":"3","key":"6_CR11","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1137\/050645506","volume":"49","author":"A d\u2019Aspremont","year":"2007","unstructured":"d\u2019Aspremont, A., Ghaoui, L.E., Jordan, M.I., Lanckriet, G.R.G.: A direct formulation for sparse PCA using semidefinite programming. SIAM Rev. 49(3), 434\u2013448 (2007)","journal-title":"SIAM Rev."},{"issue":"9","key":"6_CR12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1001117","volume":"6","author":"BE Engelhardt","year":"2010","unstructured":"Engelhardt, B.E., Stephens, M.: Analysis of population structure: a unifying framework and novel methods based on sparse factor analysis. PLoS Genet. 6(9), e1001117 (2010)","journal-title":"PLoS Genet."},{"issue":"3","key":"6_CR13","first-page":"182","volume":"3","author":"YL Hsu","year":"2014","unstructured":"Hsu, Y.L., Huang, P.Y., Chen, D.T.: Sparse principal component analysis in cancer research. Transl. Cancer Res. 3(3), 182 (2014)","journal-title":"Transl. Cancer Res."},{"issue":"1","key":"6_CR14","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1080\/757584395","volume":"22","author":"IT Jolliffe","year":"1995","unstructured":"Jolliffe, I.T.: Rotation of principal components: choice of normalization constraints. J. Appl. Stat. 22(1), 29\u201335 (1995)","journal-title":"J. Appl. Stat."},{"issue":"3","key":"6_CR15","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1198\/1061860032148","volume":"12","author":"IT Jolliffe","year":"2003","unstructured":"Jolliffe, I.T., Trendafilov, N.T., Uddin, M.: A modified principal component technique based on the LASSO. J. Comput. Graph. Stat. 12(3), 531\u2013547 (2003)","journal-title":"J. Comput. Graph. Stat."},{"issue":"4","key":"6_CR16","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1002\/gepi.21621","volume":"36","author":"S Lee","year":"2012","unstructured":"Lee, S., et al.: Sparse principal component analysis for identifying ancestry-informative markers in genome-wide association studies. Genet. Epidemiol. 36(4), 293\u2013302 (2012)","journal-title":"Genet. Epidemiol."},{"issue":"5866","key":"6_CR17","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1126\/science.1153717","volume":"319","author":"JZ Li","year":"2008","unstructured":"Li, J.Z., et al.: Worldwide human relationships inferred from genome-wide patterns of variation. Science 319(5866), 1100\u20131104 (2008)","journal-title":"Science"},{"issue":"3","key":"6_CR18","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1073\/pnas.0803205106","volume":"106","author":"MW Mahoney","year":"2009","unstructured":"Mahoney, M.W., Drineas, P.: CUR matrix decompositions for improved data analysis. Proc. Natl. Acad. Sci. 106(3), 697\u2013702 (2009)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"1","key":"6_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-016-0974-4","volume":"17","author":"W McLaren","year":"2016","unstructured":"McLaren, W., et al.: The ensembl variant effect predictor. Genome Biol. 17(1), 1\u201314 (2016)","journal-title":"Genome Biol."},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Moghaddam, B., Weiss, Y., Avidan, S.: Generalized spectral bounds for sparse LDA. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 641\u2013648 (2006)","DOI":"10.1145\/1143844.1143925"},{"key":"6_CR21","unstructured":"Musco, C., Musco, C.: Randomized block krylov methods for stronger and faster approximate singular value decomposition. In: Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems, pp. 1396\u20131404 (2015)"},{"key":"6_CR22","unstructured":"Papailiopoulos, D., Dimakis, A., Korokythakis, S.: Sparse PCA through low-rank approximations. In: Proceedings of the 30th International Conference on Machine Learning, pp. 747\u2013755 (2013)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Patterson, N., Price, A.L., Reich, D.: Population structure and eigenanalysis. PLoS Genet. 2(12), e190 (2006)","DOI":"10.1371\/journal.pgen.0020190"},{"issue":"8","key":"6_CR24","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1038\/ng1847","volume":"38","author":"AL Price","year":"2006","unstructured":"Price, A.L., Patterson, N.J., Plenge, R.M., Weinblatt, M.E., Shadick, N.A., Reich, D.: Principal components analysis corrects for stratification in genome-wide association studies. Nat. Genet. 38(8), 904\u2013909 (2006)","journal-title":"Nat. Genet."},{"issue":"2","key":"6_CR25","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1093\/genetics\/155.2.945","volume":"155","author":"JK Pritchard","year":"2000","unstructured":"Pritchard, J.K., Stephens, M., Donnelly, P.: Inference of population structure using multilocus genotype data. Genetics 155(2), 945\u2013959 (2000)","journal-title":"Genetics"},{"key":"6_CR26","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.39702","volume":"8","author":"M Sohail","year":"2019","unstructured":"Sohail, M., et al.: Polygenic adaptation on height is overestimated due to uncorrected stratification in genome-wide association studies. Elife 8, e39702 (2019)","journal-title":"Elife"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Yu, G., Wang, L.G., Han, Y., He, Q.Y.: clusterProfiler: an R package for comparing biological themes among gene clusters. OMICS J. Integr. Biol. 16(5), 284\u2013287 (2012)","DOI":"10.1089\/omi.2011.0118"},{"issue":"2","key":"6_CR28","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Roy. Stat. Soc. B 67(2), 301\u2013320 (2005)","journal-title":"J. Roy. Stat. Soc. B"}],"container-title":["Lecture Notes in Computer Science","Research in Computational Molecular Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-04749-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,11]],"date-time":"2022-05-11T23:04:43Z","timestamp":1652310283000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-04749-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031047480","9783031047497"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-04749-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 April 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RECOMB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Research in Computational Molecular Biology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Diego, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"recomb2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/recomb2022.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"188","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"9% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}