A machine-learning heuristic to improve gene score prediction of polygenic traits
Open accessPublished version of a preprint
Abstract
Machine-learning techniques have helped solve a broad range of prediction problems, yet are not widely used to build polygenic risk scores for the prediction of complex traits. We propose a novel heuristic based on machine-learning techniques (GraBLD) to boost the predictive performance of polygenic risk scores. Gradient boosted regression trees were first used to optimize the weights of SNPs included in the score, followed by a novel regional adjustment for linkage disequilibrium. A calibration set with sample size of ~200 individuals was sufficient for optimal performance. GraBLD yielded prediction R 2 of 0.239 and 0.082 using GIANT summary association statistics for height and BMI in the UK Biobank study ( N = 130 K; 1.98 M SNPs), explaining 46.9% and 32.7% of the overall polygenic variance, respectively. For diabetes status, the area under the receiver operating characteristic curve was 0.602 in the UK Biobank study using summary-level association statistics from the DIAGRAM consortium. GraBLD outperformed other polygenic score heuristics for the prediction of height ( p < 2.2 × 10 −16 ) and BMI ( p < 1.57 × 10 −4 ), and was equivalent to LDpred for diabetes. Results were independently validated in the Health and Retirement Study ( N = 8,292; 688,398 SNPs). Our report demonstrates the use of machine-learning techniques, coupled with summary-level data from large genome-wide meta-analyses to improve the prediction of polygenic traits.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Some machine learning approaches may modestly improve PRS accuracy beyond current approaches for some phenotypes, but most likely for atypical traits with simpler architectures, known interactions, and poor prediction generalizability across populations, such as skin pigmentation.
“Some machine learning approaches may thus modestly improve PRS accuracy beyond current approaches for some phenotypes52, but most likely for atypical traits with simpler architectures, known interactions, and poor prediction generalizability across populations, such as skin pigmentation53.”
From Clinical use of current polygenic risk scores may exacerbate health disparities (2019) · cites this paper as [52]
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013) · Wiley Series in Probability and Statistics · doi:10.1002/9781118548387 · Cited by 13,861 · see citing works
Common polygenic variation contributes to risk of schizophrenia and bipolar disorder
The International Schizophrenia Consortium (2009) · Nature · doi:10.1038/nature08185 · Cited by 4,821 · see citing works
Berndt, S. I., Gustafsson, S., Mägi, R., Ganna, A., Wheeler, E., Feitosa, M. F., Justice, A. E., Monda, K. L., Croteau-Chonka, D. C., Day, F. R., et al. (2013) · Nature Genetics · doi:10.1038/ng.2606 · Cited by 646 · see citing works
Flagged first, then by citations
Research works printed but not linked: 18
- [1]Yang J Common SNPs explain a large proportion of the heritability for human height Nature genetics 2010 42 565 569 10.1038/ng.608 20562875 PMC3232052 · DOI · Paper page
- [2]Abraham G Genomic prediction of coronary heart disease Eur Heart J 2016 37 3267 3278 10.1093/eurheartj/ehw450 27655226 PMC5146693 · DOI · Paper page
- [4]Vilhjalmsson BJ Modeling Linkage Disequilibrium Increases Accuracy of Polygenic Risk Scores Am J Hum Genet 2015 97 576 592 10.1016/j.ajhg.2015.09.001 26430803 PMC4596916 · DOI · Paper page
- [5]Hastie, T., Tibshirani, R. & Friedman, J. H. The elements of statistical learning: data mining, inference, and prediction. 2nd edn, (Springer, 2009).
- [6]Schapire, R. E. & Freund, Y. Boosting: Foundations and algorithms. (MIT Press, 2012).
- [7]Evangelou E Ioannidis JP Meta-analysis methods for genome-wide association studies and beyond Nat Rev Genet 2013 14 379 389 10.1038/nrg3472 23657481 · DOI · Paper page
- [8]Lohmueller KE Pearce CL Pike M Lander ES Hirschhorn JN Meta-analysis of genetic association studies supports a contribution of common variants to susceptibility to common disease Nature genetics 2003 33 177 182 10.1038/ng1071 12524541 · DOI · Paper page
- [9]Zeggini E Ioannidis JP Meta-analysis in genome-wide association studies Pharmacogenomics 2009 10 191 201 10.2217/14622416.10.2.191 19207020 PMC2695132 · DOI
- [10]Locke AE Genetic studies of body mass index yield new insights for obesity biology Nature 2015 518 197 206 10.1038/nature14177 25673413 PMC4382211 · DOI · Paper page
- [11]Wood AR Defining the role of common variation in the genomic and biological architecture of adult human height Nature genetics 2014 46 1173 1186 10.1038/ng.3097 25282103 PMC4250049 · DOI · Paper page
- [12]Chen CY Han J Hunter DJ Kraft P Price AL Explicit Modeling of Ancestry Improves Polygenic Risk Scores and BLUP Prediction Genet Epidemiol 2015 39 427 438 10.1002/gepi.21906 25995153 PMC4734143 · DOI
- [13]Yang J Lee SH Goddard ME Visscher PM GCTA: a tool for genome-wide complex trait analysis Am J Hum Genet 2011 88 76 82 10.1016/j.ajhg.2010.11.011 21167468 PMC3014363 · DOI · Paper page
- [14]Morris AP Large-scale association analysis provides insights into the genetic architecture and pathophysiology of type 2 diabetes Nature genetics 2012 44 981 990 10.1038/ng.2383 22885922 PMC3442244 · DOI · Paper page
- [16]Friedman J Hastie T Tibshirani R Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors) The Annals of Statistics 2000 28 337 407 10.1214/aos/1016218223 · DOI · Paper page
- [17]Speliotes EK Association analyses of 249,796 individuals reveal 18 new loci associated with body mass index Nature genetics 2010 42 937 948 10.1038/ng.686 20935630 PMC3014648 · DOI · Paper page
- [18]Sudlow C UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age PLoS Med 2015 12 e1001779 10.1371/journal.pmed.1001779 25826379 PMC4380465 · DOI · Paper page
- [20]Lango Allen H Hundreds of variants clustered in genomic loci and biological pathways affect human height Nature 2010 467 832 838 10.1038/nature09410 20881960 PMC2955183 · DOI · Paper page
- [21]Purcell S PLINK: a tool set for whole-genome association and population-based linkage analyses Am J Hum Genet 2007 81 559 575 10.1086/519795 17701901 PMC1950838 · DOI · Paper page
Cited by
Sorted by citations
Applications of machine learning in drug discovery and development
Vamathevan, J., Clark, D., Czodrowski, P., Dunham, I., Ferran, E., Lee, G., Li, B., Madabhushi, A., Shah, P., Spitzer, M., et al. (2019) · Nature Reviews Drug Discovery · doi:10.1038/s41573-019-0024-5 · Cited by 3,228 · see citing works
Clinical use of current polygenic risk scores may exacerbate health disparities
Martin, A. R., Kanai, M., Kamatani, Y., Okada, Y., Neale, B. M., & Daly, M. J. (2019) · Nature Genetics · doi:10.1038/s41588-019-0379-x · Cited by 2,831 · see citing works
Analysis of polygenic risk score usage and performance in diverse human populations
Duncan, L., Shen, H., Gelaye, B., Meijsen, J., Ressler, K., Feldman, M., Peterson, R., & Domingue, B. (2019) · Nature Communications · doi:10.1038/s41467-019-11112-0 · Cited by 1,038 · see citing works
Nicholls, H. L., John, C. R., Watson, D. S., Munroe, P. B., Barnes, M. R., & Cabrera, C. P. (2020) · Frontiers in Genetics · doi:10.3389/fgene.2020.00350 · Cited by 155 · see citing works
Current clinical use of polygenic scores will risk exacerbating health disparities
Martin, A. R., Kanai, M., Kamatani, Y., Okada, Y., Neale, B. M., & Daly, M. J. (2018) · doi:10.1101/441261 · Cited by 2,813 · see citing works
- Authors
- Paré, G., Mao, S., & Deng, W. Q.
- Affiliations
- Population Health Research Institute (CA)
- University of Toronto (CA)
- Corresponding author
- Paré, Guillaume
- Venue
- Scientific Reports
- Published
- 2017-10-04
- Volume
- 7
- Issue
- 1
- Pages
- 12665-12665
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC5627249
- OpenAlex
- W2759066107
- Cited by
- 85
- References
- 3
- Citations by year
- 2026: 2 · 2025: 7 · 2024: 7 · 2023: 10 · 2022: 12 · 2021: 14 · 2020: 16 · 2019: 10 · 2018: 7
- FWCI
- 5.99
- Type
- journal article
- Language
- en
- Update notices
- correction (2019-11-20)
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nd)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Cisco Systems
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic Associations and Epidemiology
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic and phenotypic traits in livestock
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetics and Physical Performance
- Keywords
- polygenic risk score, polygenic traits, gradient boosting regression tree, height prediction, body mass index, type 2 diabetes prediction, complex traits
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
