{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:34:12Z","timestamp":1791912852875,"version":"4.3.4"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2019,2,26]],"date-time":"2019-02-26T00:00:00Z","timestamp":1551139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Polygenic risk scores (PRS) combine many single-nucleotide polymorphisms into a score reflecting the genetic risk of developing a disease. Priv\u00e9, Aschard, and Blum present an efficient implementation of penalized logistic regression...<\/jats:p>\n                  <jats:p>Polygenic Risk Scores (PRS) combine genotype information across many single-nucleotide polymorphisms (SNPs) to give a score reflecting the genetic risk of developing a disease. PRS might have a major impact on public health, possibly allowing for screening campaigns to identify high-genetic risk individuals for a given disease. The \u201cClumping+Thresholding\u201d (C+T) approach is the most common method to derive PRS. C+T uses only univariate genome-wide association studies (GWAS) summary statistics, which makes it fast and easy to use. However, previous work showed that jointly estimating SNP effects for computing PRS has the potential to significantly improve the predictive performance of PRS as compared to C+T. In this paper, we present an efficient method for the joint estimation of SNP effects using individual-level data, allowing for practical application of penalized logistic regression (PLR) on modern datasets including hundreds of thousands of individuals. Moreover, our implementation of PLR directly includes automatic choices for hyper-parameters. We also provide an implementation of penalized linear regression for quantitative traits. We compare the performance of PLR, C+T and a derivation of random forests using both real and simulated data. Overall, we find that PLR achieves equal or higher predictive performance than C+T in most scenarios considered, while being scalable to biobank data. In particular, we find that improvement in predictive performance is more pronounced when there are few effects located in nearby genomic regions with correlated SNPs; for instance, in simulations, AUC values increase from 83% with the best prediction of C+T to 92.5% with PLR. We confirm these results in a data analysis of a case-control study for celiac disease where PLR and the standard C+T method achieve AUC values of 89% and of 82.5%. Applying penalized linear regression to 350,000 individuals of the UK Biobank, we predict height with a larger correlation than with the best prediction of C+T (\u223c65% instead of \u223c55%), further demonstrating its scalability and strong predictive power, even for highly polygenic traits. Moreover, using 150,000 individuals of the UK Biobank, we are able to predict breast cancer better than C+T, fitting PLR in a few minutes only. In conclusion, this paper demonstrates the feasibility and relevance of using penalized regression for PRS computation when large individual-level datasets are available, thanks to the efficient implementation available in our R package bigstatsr.<\/jats:p>","DOI":"10.1534\/genetics.119.302019","type":"journal-article","created":{"date-parts":[[2019,2,26]],"date-time":"2019-02-26T23:05:10Z","timestamp":1551222310000},"page":"65-74","source":"Crossref","is-referenced-by-count":81,"title":["Efficient Implementation of Penalized Regression for Genetic Risk Prediction"],"prefix":"10.1093","volume":"212","author":[{"given":"Florian","family":"Priv\u00e9","sequence":"first","affiliation":[{"name":"Laboratoire TIMC-IMAG , UMR 5525, University of Grenoble Alpes, CNRS, 38700 La Tronche, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugues","family":"Aschard","sequence":"additional","affiliation":[{"name":"Centre de Bioinformatique , Biostatistique et Biologie Int\u00e9grative (C3BI), Institut Pasteur, 75015 Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael G B","family":"Blum","sequence":"additional","affiliation":[{"name":"Laboratoire TIMC-IMAG , UMR 5525, University of Grenoble Alpes, CNRS, 38700 La Tronche, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,2,26]]},"reference":[{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/1471-2105-13-88","article-title":"Sparsnp: fast and memory-efficient analysis of all snps for phenotype prediction.","volume":"13","author":"Abraham","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1002\/gepi.21698","article-title":"Performance and robustness of penalized and unpenalized methods for genetic prediction of complex human disease.","volume":"37","author":"Abraham","year":"2013","journal-title":"Genet. Epidemiol."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"e1004137","DOI":"10.1371\/journal.pgen.1004137","article-title":"Accurate and robust genomic prediction of celiac disease using statistical learning.","volume":"10","author":"Abraham","year":"2014","journal-title":"PLoS Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"e93379","DOI":"10.1371\/journal.pone.0093379","article-title":"Exploiting SNP correlations within random forest for genome-wide association studies.","volume":"9","author":"Botta","year":"2014","journal-title":"PLoS One"},{"key":"2023031005055878200_","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests.","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK biobank resource with deep phenotyping and genomic data.","volume":"562","author":"Bycroft","year":"2018","journal-title":"Nature"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1038\/ng.2579","article-title":"Projecting the performance of risk prediction based on polygenic analyses of genome-wide association studies.","volume":"45","author":"Chatterjee","year":"2013","journal-title":"Nat. Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1038\/nrg.2016.27","article-title":"Developing and evaluating polygenic risk prediction models for stratified disease prevention.","volume":"17","author":"Chatterjee","year":"2016","journal-title":"Nat. Rev. Genet."},{"key":"2023031005055878200_","article-title":"Integration of clinical and genomic data: a methodological survey.","author":"Dey","year":"2013"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1111\/1541-0420.00071","article-title":"Partial AUC estimation and regression.","volume":"59","author":"Dodd","year":"2003","journal-title":"Biometrics"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1038\/ng.543","article-title":"Multiple common variants for celiac disease influencing immune gene expression.","volume":"42","author":"Dubois","year":"2010","journal-title":"Nat. Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"e1003348","DOI":"10.1371\/journal.pgen.1003348","article-title":"Power and predictive accuracy of polygenic risk scores.","volume":"9","author":"Dudbridge","year":"2013","journal-title":"PLoS Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"3525","DOI":"10.1093\/hmg\/ddp295","article-title":"Harnessing the information contained within genome-wide association studies to improve individual prediction of complex disease risk.","volume":"18","author":"Evans","year":"2009","journal-title":"Hum. Mol. Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1111\/j.1469-1809.1965.tb00500.x","article-title":"The inheritance of liability to certain diseases, estimated from the incidence among relatives.","volume":"29","author":"Falconer","year":"1965","journal-title":"Ann. Hum. Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to roc analysis.","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent.","volume":"33","author":"Friedman","year":"2010","journal-title":"J. Stat. Softw."},{"key":"2023031005055878200_","first-page":"219","article-title":"Model assessment and selection","volume-title":"The Elements of Statistical Learning","author":"Hastie","year":"2008"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: biased estimation for nonorthogonal problems.","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1097\/GIM.0b013e31812eece0","article-title":"The impact of genotype frequencies on the clinical validity of genomic profiling for predicting common chronic diseases.","volume":"9","author":"Janssens","year":"2007","journal-title":"Genet. Med."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1534\/genetics.118.301267","article-title":"Accurate genomic prediction of human height.","volume":"210","author":"Lello","year":"2018","journal-title":"Genetics"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1126\/science.171.3977.1217","article-title":"Signal detectability and medical decision-making.","volume":"171","author":"Lusted","year":"1971","journal-title":"Science"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1002\/gepi.22083","article-title":"Multiethnic polygenic risk scores improve risk prediction in diverse populations.","volume":"41","author":"M\u00e1rquez-Luna","year":"2017","journal-title":"Genet. Epidemiol."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1016\/j.ajhg.2017.03.004","article-title":"Human demographic history impacts genetic risk prediction across diverse populations.","volume":"100","author":"Martin","year":"2017","journal-title":"Am. J. Hum. Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.ajhg.2018.11.002","article-title":"Polygenic risk scores for prediction of breast cancer and breast cancer subtypes.","volume":"104","author":"Mavaddat","year":"2019","journal-title":"Am. J. Hum. Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1177\/0272989X8900900307","article-title":"Analyzing a portion of the roc curve.","volume":"9","author":"McClish","year":"1989","journal-title":"Med. Decis. Making"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"e1004754","DOI":"10.1371\/journal.pgen.1004754","article-title":"Regularized machine learning in the genetic prediction of complex traits.","volume":"10","author":"Okser","year":"2014","journal-title":"PLoS Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1038\/gim.2014.192","article-title":"Implications of polygenic risk-stratified screening for prostate cancer on overdiagnosis.","volume":"17","author":"Pashayan","year":"2015","journal-title":"Genet. Med."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"2781","DOI":"10.1093\/bioinformatics\/bty185","article-title":"Efficient analysis of large-scale genome-wide data with two R packages: bigstatsr and bigsnpr.","volume":"34","author":"Priv\u00e9","year":"2018","journal-title":"Bioinformatics"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1038\/nature08185","article-title":"Common polygenic variation contributes to risk of schizophrenia and bipolar disorder.","volume":"460","author":"Purcell","year":"2009","journal-title":"Nature"},{"key":"2023031005055878200_","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso.","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. B"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1111\/j.1467-9868.2011.01004.x","article-title":"Strong rules for discarding predictors in lasso-type problems.","volume":"74","author":"Tibshirani","year":"2012","journal-title":"J. R. Stat. Soc. Series B Stat. Methodol."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"e40358","DOI":"10.1371\/journal.pone.0040358","article-title":"Integration of clinical and gene expression data has a synergetic effect on predicting breast cancer outcome.","volume":"7","author":"Van Vliet","year":"2012","journal-title":"PLoS One"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1016\/j.ajhg.2015.09.001","article-title":"Modeling linkage disequilibrium increases accuracy of polygenic risk scores.","volume":"97","author":"Vilhj\u00e1lmsson","year":"2015","journal-title":"Am. J. Hum. Genet."},{"key":"2023031005055878200_","first-page":"106062","article-title":"Heterogeneity in polygenic scores for common human traits.","author":"Ware","year":"2017","journal-title":"bioRxiv"},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"e1000678","DOI":"10.1371\/journal.pgen.1000678","article-title":"From disease association to risk assessment: an optimistic view from genome-wide association studies on type 1 diabetes.","volume":"5","author":"Wei","year":"2009","journal-title":"PLoS Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1016\/j.ajhg.2013.05.002","article-title":"Large sample size, wide variant spectrum, and advanced machine-learning technique boost risk prediction for inflammatory bowel disease.","volume":"92","author":"Wei","year":"2013","journal-title":"Am. J. Hum. Genet."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.1101\/gr.6665407","article-title":"Prediction of individual genetic risk to disease from genome-wide association studies.","volume":"17","author":"Wray","year":"2007","journal-title":"Genome Res."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1038\/ng.608","article-title":"Common snps explain a large proportion of the heritability for human height.","volume":"42","author":"Yang","year":"2010","journal-title":"Nat. Genet."},{"key":"2023031005055878200_","unstructured":"Zeng, Y., and P. Breheny, 2017\u2003The biglasso package: a memory-and computation-efficient solver for lasso model fitting with big data in R. arXiv:1701.05936."},{"key":"2023031005055878200_","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net.","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Soc. Series B Stat. Methodol."}],"container-title":["Genetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/genetics\/article-pdf\/212\/1\/65\/49491686\/genetics0065.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/genetics\/article-pdf\/212\/1\/65\/49491686\/genetics0065.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:40:15Z","timestamp":1721004015000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/genetics\/article\/212\/1\/65\/6087918"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,26]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,2,26]]},"published-print":{"date-parts":[[2019,5,1]]}},"URL":"https:\/\/doi.org\/10.1534\/genetics.119.302019","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/403337","asserted-by":"object"}]},"ISSN":["1943-2631"],"issn-type":[{"value":"1943-2631","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,5,1]]},"published":{"date-parts":[[2019,2,26]]}}}