CoChat

Machine Learning Prediction of Biomarkers from SNPs and of Disease Risk from Biomarkers in the UK Biobank

Widen, Erik, Raben, Timothy G., Lello, Louis, Hsu, Stephen D. H. · 2021 · Genes

Published version of a preprint

Cited by 32

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

We use UK Biobank data to train predictors for 65 blood and urine markers such as HDL, LDL, lipoprotein A, glycated haemoglobin, etc. from SNP genotype. For example, our Polygenic Score (PGS) predictor correlates ∼0.76 with lipoprotein A level, which is highly heritable and an independent risk factor for heart disease. This may be the most accurate genomic prediction of a quantitative trait that has yet been produced (specifically, for European ancestry groups). We also train predictors of common disease risk using blood and urine biomarkers alone (no DNA information); we call these predictors biomarker risk scores, BMRS. Individuals who are at high risk (e.g., odds ratio of >5× population average) can be identified for conditions such as coronary artery disease (AUC∼0.75), diabetes (AUC∼0.95), hypertension, liver and kidney problems, and cancer using biomarkers alone. Our atherosclerotic cardiovascular disease (ASCVD) predictor uses ∼10 biomarkers and performs in UKB evaluation as well as or better than the American College of Cardiology ASCVD Risk Estimator, which uses quite different inputs (age, diagnostic history, BMI, smoking status, statin usage, etc.). We compare polygenic risk scores (risk conditional on genotype: PRS) for common diseases to the risk predictors which result from the concatenation of learned functions BMRS and PGS, i.e., applying the BMRS predictors to the PGS output.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/genes12070991

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 92

  1. Veenstra, 2010, A formal risk-benefit framework for genomic tests: Facilitating the appropriate translation of genomics into clinical practice, Genet. Med., 12, 686, 10.1097/GIM.0b013e3181eff533 · DOI
  2. Amir, 2010, Assessing women at high risk of breast cancer: A review of risk assessment models, JNCI J. Natl. Cancer Inst., 102, 680, 10.1093/jnci/djq088 · DOI · Paper page
  3. Euesden, 2014, PRSice: Polygenic risk score software, Bioinformatics, 31, 1466, 10.1093/bioinformatics/btu848 · DOI · Paper page
  4. Abraham, 2014, Accurate and Robust Genomic Prediction of Celiac Disease Using Statistical Learning, PLOS Genet., 10, 1, 10.1371/journal.pgen.1004137 · DOI
  5. Priest, J.R., and Ashley, E.A. (2014). Genomics in Clinical Practice, BMJ Publishing Group Ltd and British Cardiovascular Society. · DOI
  6. Jacob, 2013, Genomics in clinical practice: Lessons from the front lines, Sci. Transl. Med., 5, 194cm5, 10.1126/scitranslmed.3006468 · DOI
  7. Shieh, 2016, Breast cancer risk prediction using a clinical risk model and polygenic risk score, Breast Cancer Res. Treat., 159, 513, 10.1007/s10549-016-3953-2 · DOI · Paper page
  8. Bowdin, 2016, Recommendations for the integration of genomics into clinical practice, Genet. Med., 18, 1075, 10.1038/gim.2016.17 · DOI · Paper page
  9. Chatterjee, 2016, Developing and evaluating polygenic risk prediction models for stratified disease prevention, Nat. Rev. Genet., 17, 392, 10.1038/nrg.2016.27 · DOI · Paper page
  10. Lello, 2019, Genomic prediction of 16 complex disease risks including heart attack, diabetes, breast and prostate cancer, Sci. Rep., 9, 15286, 10.1038/s41598-019-51258-x · DOI
  11. Liu, 2018, Genome-wide polygenic risk predictors for kidney disease, Nat. Rev. Nephrol., 14, 723, 10.1038/s41581-018-0067-6 · DOI
  12. Torkamani, 2018, The personal and clinical utility of polygenic risk scores, Nat. Rev. Genet., 19, 581, 10.1038/s41576-018-0018-x · DOI · Paper page
  13. Nelson, 2019, Risk assessment, genetic counseling, and genetic testing for BRCA-related cancer in women: Updated evidence report and systematic review for the US Preventive Services Task Force, JAMA, 322, 666, 10.1001/jama.2019.8430 · DOI
  14. Meisner, 2020, Combined Utility of 25 Disease and Risk Factor Polygenic Risk Scores for Stratifying Risk of All-Cause Mortality, Am. J. Hum. Genet., 107, 418, 10.1016/j.ajhg.2020.07.002 · DOI · Paper page
  15. Lewis, 2020, Polygenic risk scores: From research tools to clinical instruments, Genome Med., 12, 1, 10.1186/s13073-020-00742-5 · DOI · Paper page
  16. Lewis, 2021, Polygenic risk scores: From research tools to clinical instruments, Genome Med., 13, 14, 10.1186/s13073-021-00829-7 · DOI · Paper page
  17. Kulm, S., Marderstein, A., Mezey, J., and Elemento, O. (2021). A systematic framework for assessing the clinical impact of polygenic risk scores. medRxiv. · doi:10.2139/ssrn.3808292
  18. Inouye, 2018, Genomic Risk Prediction of Coronary Artery Disease in 480,000 Adults: Implications for Primary Prevention, J. Am. Coll. Cardiol., 72, 1883, 10.1016/j.jacc.2018.07.079 · DOI · Paper page
  19. Piepoli, 2016, Guidelines: Editor’s choice: 2016 European Guidelines on cardiovascular disease prevention in clinical practice: The Sixth Joint Task Force of the European Society of Cardiology and Other Societies on Cardiovascular Disease Prevention in Clinical Practice (constituted by representatives of 10 societies and by invited experts) Developed with the special contribution of the European Association for Cardiovascular Prevention & Rehabilitation (EACPR), Eur. Heart J., 37, 2315, 10.1093/eurheartj/ehw106 · DOI · Paper page
  20. Wolf, 1994, Stroke risk profile: Adjustment for antihypertensive medication. The Framingham Study, Stroke, 25, 40, 10.1161/01.STR.25.1.40 · DOI · Paper page
  21. Vasan, 2008, General cardiovascular risk profile for use in primary care, Circulation, 117, 743, 10.1161/CIRCULATIONAHA.107.699579 · DOI · Paper page
  22. Conroy, 2003, Estimation of ten-year risk of fatal cardiovascular disease in Europe: The SCORE project, Eur. Heart J., 24, 987, 10.1016/S0195-668X(03)00114-3 · DOI · Paper page
  23. Coupland, 2007, Derivation and validation of QRISK, a new cardiovascular disease risk score for the United Kingdom: Prospective open cohort study, BMJ, 335, 136, 10.1136/bmj.39261.471806.55 · DOI · Paper page
  24. Hippisley-Cox, J., Coupland, C., and Brindle, P. (2017). Development and validation of QRISK3 risk prediction algorithms to estimate future risk of cardiovascular disease: Prospective cohort study. BMJ, 357. · DOI · Paper page
  25. Goff, 2014, 2013 ACC/AHA guideline on the assessment of cardiovascular risk: A report of the American College of Cardiology/American Heart Association Task Force on Practice Guidelines, J. Am. Coll. Cardiol., 63, 2935, 10.1016/j.jacc.2013.11.005 · DOI · Paper page
  26. Colantonio, 2017, Performance of the atherosclerotic cardiovascular disease pooled cohort risk equations by social deprivation status, J. Am. Heart Assoc., 6, e005676, 10.1161/JAHA.117.005676 · DOI
  27. Giampaoli, 2007, CUORE: A Sustainable Cardiovascular Disease Prevention Strategy, Eur. J. Cardiovasc. Prev. Rehabil., 14, 161, 10.1097/HJR.0b013e328157f3e5 · DOI · Paper page
  28. Hajifathalian, 2015, A novel risk score to predict cardiovascular disease risk in national populations (Globorisk): A pooled analysis of prospective cohorts and health examination surveys, Lancet Diabetes Endocrinol., 3, 339, 10.1016/S2213-8587(15)00081-9 · DOI · Paper page
  29. Mendis, 2007, World Health Organization (WHO) and International Society of Hypertension (ISH) risk prediction charts: Assessment of cardiovascular risk for prevention and control of cardiovascular disease in low and middle-income countries, J. Hypertens., 25, 1578, 10.1097/HJH.0b013e3282861fd3 · DOI · Paper page
  30. Nobel, 2014, MyRisk_Stroke calculator: A personalized stroke risk assessment tool for the general population, J. Clin. Neurol., 10, 1, 10.3988/jcn.2014.10.1.1 · DOI
  31. Kothari, 2002, UKPDS 60: Risk of stroke in type 2 diabetes estimated by the UK Prospective Diabetes Study risk engine, Stroke, 33, 1776, 10.1161/01.STR.0000020091.07144.C7 · DOI
  32. Attia, 2020, Artificial intelligence in cardiology: Present and future, Mayo Clinic Proceedings, Volume 95, 1015, 10.1016/j.mayocp.2020.01.038 · DOI · Paper page
  33. Commandeur, 2020, Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium, and epicardial adipose tissue: A prospective study, Cardiovasc. Res., 116, 2216, 10.1093/cvr/cvz321 · DOI
  34. Jamthikar, 2020, Cardiovascular/stroke risk predictive calculators: A comparison between statistical and machine learning models, Cardiovasc. Diagn. Ther., 10, 919, 10.21037/cdt.2020.01.07 · DOI
  35. Lello, 2018, Accurate genomic prediction of human height, Genetics, 210, 477, 10.1534/genetics.118.301267 · DOI · Paper page
  36. Aschard, 2019, Efficient Implementation of Penalized Regression for Genetic Risk Prediction, Genetics, 212, 65, 10.1534/genetics.119.302019 · DOI
  37. Yong, 2020, Genetic Architecture of Complex Traits and Disease Risk Predictors, Sci. Rep., 10, 12055, 10.1038/s41598-020-68881-8 · DOI
  38. Lello, 2020, Sibling validation of polygenic risk scores and complex trait prediction, Sci. Rep., 10, 13190, 10.1038/s41598-020-69927-7 · DOI
  39. Privé, F., Vilhjálmsson, B.J., and Mak, T.S. (2021). lassosum2: An updated version complementing LDpred2. bioRxiv.
  40. Vazquez, 2018, Complex-Trait Prediction in the Era of Big Data, Trends Genet., 34, 746, 10.1016/j.tig.2018.07.004 · DOI
  41. Bycroft, 2018, The UK Biobank resource with deep phenotyping and genomic data, Nature, 562, 203, 10.1038/s41586-018-0579-z · DOI · Paper page
  42. Bycroft, C., Freeman, C., Petkova, D., Band, G., Elliott, L.T., Sharp, K., Motyer, A., Vukcevic, D., Delaneau, O., and O’Connell, J. (2017). Genome-wide genetic data on 500,000 UK Biobank participants. bioRxiv, Available online: https://www.biorxiv.org/content/early/2017/07/20/166298. · DOI · Paper page
  43. Price, 2006, Principal components analysis corrects for stratification in genome-wide association studies, Nat. Genet., 38, 904, 10.1038/ng1847 · DOI · Paper page
  44. Mathieson, 2012, Differential confounding of rare and common variants in spatially structured populations, Nat. Genet., 44, 243, 10.1038/ng.1074 · DOI · Paper page
  45. Bhatia, G., Gusev, A., Loh, P.R., Finucane, H., Vilhjálmsson, B.J., Ripke, S., Purcell, S., Stahl, E., Daly, M., and de Candia, T.R. (2016). Subtle stratification confounds estimates of heritability from rare variants. bioRxiv. · DOI
  46. Bellenguez, 2016, Accuracy of heritability estimations in presence of hidden population stratification, Sci. Rep., 6, 26471, 10.1038/srep26471 · DOI
  47. Guo, 2018, Global genetic differentiation of complex traits shaped by natural selection in humans, Nat. Commun., 9, 1865, 10.1038/s41467-018-04191-y · DOI · Paper page
  48. Sohail, 2019, Polygenic adaptation on height is overestimated due to uncorrected stratification in genome-wide association studies, eLife, 8, e39702, 10.7554/eLife.39702 · DOI · Paper page
  49. Barton, 2019, Population genetics: Why structure matters, eLife, 8, e45380, 10.7554/eLife.45380 · DOI
  50. Berg, 2019, Reduced signal for polygenic adaptation of height in UK Biobank, eLife, 8, e39725, 10.7554/eLife.39725 · DOI · Paper page
  51. Wray, 2019, Complex trait prediction from genome data: Contrasting EBV in livestock to PRS in humans: Genomic prediction, Genetics, 211, 1131, 10.1534/genetics.119.301859 · DOI
  52. Bitarello, 2020, Polygenic scores for height in admixed populations, G3 Genes Genomes Genet., 10, 4027, 10.1534/g3.120.401658 · DOI
  53. Trochet, H., and Hussin, J. (2020). Fine-scale population structure confounds genetic risk scores in the ascertainment population. bioRxiv.
  54. Refoyo-Martínez, A., Liu, S., Jørgensen, A.M., Jin, X., Albrechtsen, A., Martin, A.R., and Racimo, F. (2021). How robust are cross-population signatures of polygenic adaptation in humans?. bioRxiv. · DOI
  55. Marquez-Luna, C., Gazal, S., Loh, P.R., Furlotte, N., Auton, A., and Price, A.L. (2018). Modeling functional enrichment improves polygenic prediction accuracy in UK Biobank and 23andMe data sets. bioRxiv, Available online: https://www.biorxiv.org/content/early/2018/07/24/375337.full.pdf. · DOI · Paper page
  56. Elhaik, E. (2021). Why most Principal Component Analyses (PCA) in population genetic studies are wrong. bioRxiv. · DOI
  57. Wertz, 2019, Using DNA from mothers and children to study parental investment in children’s educational attainment, Child Dev., 19, 1745
  58. Bates, 2018, The nature of nurture: Using a virtual-parent design to test parenting effects on children’s educational attainment in genotyped families, Twin Res. Hum. Genet., 21, 73, 10.1017/thg.2018.11 · DOI
  59. Wand, 2020, Improving reporting standards for polygenic scores in risk prediction studies, Nature, 591, 211, 10.1038/s41586-021-03243-6 · DOI · Paper page
  60. Carlson, 2013, Generalization and Dilution of Association Results from European GWAS in Populations of Non-European Ancestry: The PAGE Study, PLoS Biol., 11, 1, 10.1371/journal.pbio.1001661 · DOI · Paper page
  61. Privé, F., Aschard, H., Carmi, S., Folkersen, L., Hoggart, C., O’Reilly, P.F., and Vilhjálmsson, B.J. (2021). High-resolution portability of 245 polygenic scores when derived and applied in the same cohort. medRxiv. · doi:10.1101/2021.02.05.21251061
  62. Tibshirani, 1996, Regression shrinkage and selection via the lasso, J. R. Stat. Soc. Ser. B, 58, 267, 10.1111/j.2517-6161.1996.tb02080.x · DOI · Paper page
  63. Donoho, 2005, Sparse nonnegative solution of underdetermined linear equations by linear programming, Proc. Natl. Acad. Sci. USA, 102, 9446, 10.1073/pnas.0502269102 · DOI · Paper page
  64. Donoho, D., and Stodden, V. (2006, January 16–21). Breakdown Point of Model Selection When the Number of Variables Exceeds the Number of Observations. Proceedings of the 2006 IEEE International Joint Conference on Neural Network Proceedings, Vancouver, BC, Canada. · doi:10.1109/ijcnn.2006.246934
  65. Donoho, 2009, Message-passing algorithms for compressed sensing, Proc. Natl. Acad. Sci. USA, 106, 18914, 10.1073/pnas.0909892106 · DOI · Paper page
  66. Donoho, 2010, Precise Undersampling Theorems, Proc. IEEE, 98, 913, 10.1109/JPROC.2010.2045630 · DOI
  67. Boerwinkle, 1992, Apolipoprotein (a) gene accounts for greater than 90% of the variation in plasma lipoprotein (a) concentrations, J. Clin. Investig., 90, 52, 10.1172/JCI115855 · DOI · Paper page
  68. Kraft, 1992, The apolipoprotein (a) gene: A transcribed hypervariable locus controlling plasma lipoprotein (a) concentration, Hum. Genet., 90, 220, 10.1007/BF00220066 · DOI · Paper page
  69. Austin, 1992, Lipoprotein (a) in women twins: Heritability and relationship to apolipoprotein (a) phenotypes, Am. J. Hum. Genet., 51, 829
  70. Rao, 2015, Heritability of biomarkers of oxidized lipoproteins: Twin pair study, Arterioscler. Thromb. Vasc. Biol., 35, 1704, 10.1161/ATVBAHA.115.305306 · DOI
  71. Frank, 1988, The apolipoprotein (a) gene resides on human chromosome 6q26–27, in close proximity to the homologous gene for plasminogen, Hum. Genet., 79, 352, 10.1007/BF00282175 · DOI
  72. Drayna, 1988, Genetic linkage between lipoprotein (a) phenotype and a DNA polymorphism in the plasminogen gene, Genomics, 3, 230, 10.1016/0888-7543(88)90084-5 · DOI
  73. Lindahl, 1989, The gene for the Lp (a)-specific glycoprotein is closely linked to the gene for plasminogen on chromosome 6, Hum. Genet., 81, 149, 10.1007/BF00293891 · DOI
  74. Tsimikas, 2012, Lipoprotein (a) as a potential causal genetic risk factor of cardiovascular disease: A rationale for increased efforts to understand its pathophysiology and develop targeted therapies, J. Am. Coll. Cardiol., 60, 716, 10.1016/j.jacc.2012.04.038 · DOI · Paper page
  75. Mack, 2017, A genome-wide association meta-analysis on lipoprotein (a) concentrations adjusted for apolipoprotein (a) isoforms, J. Lipid Res., 58, 1834, 10.1194/jlr.M076232 · DOI · Paper page
  76. Schmidt, 2006, Genetics of the Lp (a)/apo (a) system in an autochthonous Black African population from the Gabon, Eur. J. Hum. Genet., 14, 190, 10.1038/sj.ejhg.5201512 · DOI
  77. Hoekstra, 2021, Genome-wide association study highlights APOH as a novel locus for lipoprotein (a) levels—brief report, Arterioscler. Thromb. Vasc. Biol., 41, 458, 10.1161/ATVBAHA.120.314965 · DOI
  78. Schmidt, 2016, Structure, function, and genetics of lipoprotein (a), J. Lipid Res., 57, 1339, 10.1194/jlr.R067314 · DOI · Paper page
  79. Coltell, O., Asensio, E.M., Sorlí, J.V., Barragán, R., Fernández-Carrión, R., Portolés, O., Ortega-Azorín, C., Martínez-Lacruz, R., González, J.I., and Zanón-Moreno, V. (2019). Genome-wide association study (GWAS) on bilirubin concentrations in subjects with metabolic syndrome: Sex-specific gwas analysis and gene-diet interactions in a mediterranean population. Nutrients, 11. · DOI
  80. Bielinski, S.J., Chai, H.S., Pathak, J., Talwalkar, J.A., Limburg, P.J., Gullerud, R.E., Sicotte, H., Klee, E.W., Ross, J.L., and Kocher, J.P.A. (2011). 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., 86. · doi:10.4016/31593.01
  81. Kathiresan, S., Manning, A.K., Demissie, S., D’Agostino, R.B., Surti, A., Guiducci, C., Gianniny, L., Burtt, N.P., Melander, O., and Orho-Melander, M. (2007). A genome-wide association study for blood lipid phenotypes in the Framingham Heart Study. BMC Med Genet., 8. · DOI · Paper page
  82. Cockcroft, 1976, Prediction of creatinine clearance from serum creatinine, Nephron, 16, 31, 10.1159/000180580 · DOI · Paper page
  83. Miller, 2008, Reporting estimated GFR: A laboratory perspective, Am. J. Kidney Dis., 52, 645, 10.1053/j.ajkd.2008.07.032 · DOI
  84. Levey, 2009, A new equation to estimate glomerular filtration rate, Ann. Intern. Med., 150, 604, 10.7326/0003-4819-150-9-200905050-00006 · DOI · Paper page
  85. Levey, 2010, Estimating GFR using the CKD epidemiology collaboration (CKD-EPI) creatinine equation: More accurate GFR estimates, lower CKD prevalence estimates, and better risk predictions, Am. J. Kidney Dis., 55, 622, 10.1053/j.ajkd.2010.02.337 · DOI · Paper page
  86. Pugh, 1973, Transection of the oesophagus for bleeding oesophageal varices, J. Br. Surg., 60, 646, 10.1002/bjs.1800600817 · DOI · Paper page
  87. Kamath, 2007, The model for end-stage liver disease (MELD), Hepatology, 45, 797, 10.1002/hep.21563 · DOI · Paper page
  88. Lee, 2012, Introduction to the revised American Association for the Study of Liver Diseases Position Paper on acute liver failure 2011, Hepatology, 55, 965, 10.1002/hep.25551 · DOI · Paper page
  89. Loos, 2014, The bigger picture of FTO—the first GWAS-identified obesity gene, Nat. Rev. Endocrinol., 10, 51, 10.1038/nrendo.2013.227 · DOI · Paper page
  90. Vattikuti, 2014, Applying compressed sensing to genome-wide association studies, GigaScience, 3, 10, 10.1186/2047-217X-3-10 · DOI
  91. Pedregosa, 2011, Scikit-learn: Machine Learning in Python, J. Mach. Learn. Res., 12, 2825
  92. Chang, 2015, Second-generation PLINK: Rising to the challenge of larger and richer datasets, Gigascience, 4, s13742-015, 10.1186/s13742-015-0047-8 · DOI · Paper page

Cited by

See all 32

Metadata

Authors
Widen, E., Raben, T. G., Lello, L., & Hsu, S. D. H.
Venue
Genes
Publisher
MDPI AG
Published
2021-06-29
Volume
12
Issue
7
Pages
991
ISSN
2073-4425
Cited by
32
References
35
Language
en

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.