Significant Sparse Polygenic Risk Scores across 813 traits in UK Biobank

Tanigawa, Yosuke; Qian, Junyang; Venkataraman, Guhan Ram; Justesen, Johanne Marie; Li, Ruilin; Tibshirani, Robert; Hastie, Trevor; Rivas, Manuel A.

doi:10.1101/2021.09.02.21262942

Cited by 13 publications

(23 citation statements)

References 75 publications

(144 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average AUC between these models was 0.70. The small number of variables used by our models (125 for T2D and 666 for hypertension), makes them comparable to those reported by Tanigawa et al [44] who also used the BASIL algorithm. Likewise, the number of individuals whose data was used to train the models is modest in comparison to large academic and clinical databases.…”

Section: Genome-wide Association Results For Diabetes Type 2 and Hype...supporting

confidence: 79%

“…The European Bioinformatics Institute (EBI) has launched a PRS catalog database, allowing for reproducibility and standardization of reporting of PRS models [33]. As of Feb 16, 2022, the catalog includes 35 models related to the T2D from 15 peer reviewed publications [34][35][36][37][38][39][40][41][42][43][44][45][46], and six models related to hypertension across 3 publications [39,44,46]. However, these models mostly include single ancestry participants (typically European) which may not generalize across other ancestral groups.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Validating and automating learning of cardiometabolic polygenic risk scores from direct-to-consumer genetic and phenotypic data: implications for scaling precision health research

Pineda

Vernekar

Grau³

et al. 2022

Preprint

View full text Add to dashboard Cite

IntroductionA major challenge to enabling precision health at a global scale is the bias between those who enroll in state sponsored genomic research and those suffering from chronic disease. More than 30 million people have been genotyped by direct-to-consumer (DTC) companies such as 23andMe, Ancestry DNA, and MyHeritage, providing a potential mechanism for democratizing access to medical interventions and thus catalyzing improvements in patient outcomes as the cost of data acquisition drops. However, much of these data are sequestered in the initial provider network, without the ability for the scientific community to either access or validate. Here, we present a novel geno-pheno platform that integrates heterogeneous data sources and applies learnings to common chronic disease conditions including Type 2 diabetes (T2D) and hypertension.MethodsWe collected genotyped data from a novel DTC platform where participants upload their genotype data files, and were invited to answer general health questionnaires regarding cardiometabolic traits over a period of 6 months. Quality control, imputation and genome-wide association studies were performed on this dataset, and polygenic risk scores were built in a case-control setting using the BASIL algorithm.ResultsWe collected data on N=4,550 (389 cases / 4,161 controls) who reported being affected or previously affected for T2D; and N=4,528 (1,027 cases / 3,501 controls) for hypertension. We identified 164 out of 272 variants showing identical effect direction to previously reported genome-significant findings in Europeans. Performance metric of the PRS models was AUC=0.68, which is comparable to previously published PRS models obtained with larger datasets including clinical biomarkers.DiscussionDTC platforms have the potential of inverting research models of genome sequencing and phenotypic data acquisition. Quality control (QC) mechanisms proved to successfully enable traditional GWAS and PRS analyses. The direct participation of individuals has shown the potential to generate rich datasets enabling the creation of PRS cardiometabolic models. More importantly, federated learning of PRS from reuse of DTC data provides a mechanism for scaling precision health care delivery beyond the small number of countries who can afford to finance these efforts directly.ConclusionsThe genetics of T2D and hypertension have been studied extensively in controlled datasets, and various polygenic risk scores (PRS) have been developed. We developed predictive tools for both phenotypes trained with heterogeneous genotypic and phenotypic data generated outside of the clinical environment and show that our methods can recapitulate prior findings with fidelity. From these observations, we conclude that it is possible to leverage DTC genetic repositories to identify individuals at risk of debilitating diseases based on their unique genetic landscape so that informed, timely clinical interventions can be incorporated.

show abstract

Section: Genome-wide Association Results For Diabetes Type 2 and Hype...supporting

confidence: 79%

Section: Introductionmentioning

confidence: 99%

Validating and automating learning of cardiometabolic polygenic risk scores from direct-to-consumer genetic and phenotypic data: implications for scaling precision health research

Pineda

Vernekar

Grau³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…As expected, due to a small sample size and the likely small effects of SNPs on phenotypes, the PRS developed using the UCLA cohort did not add substan-tial predictive power over the baseline features. Studies leveraging biobanks with sample sizes several magnitudes larger than the cohort at UCLA however, have shown non-zero heritability for a variety of phenotypes [1, 51–53]. Therefore, we sought to compare the MRS and PRS generated with the UCLA data to a polygenic risk score created using the UKBiobank data [54].…”

Section: Resultsmentioning

confidence: 99%

Section: Imputation Using Baseline Medical Featuresmentioning

confidence: 99%

“…Imputing external polygenic risk scores into the ATLAS cohort We compared our in-house built risk scores to risk scores learned in the UKBiobank dataset [51,53]. In both [51,53] the authors construct their PRS using penalized regression akin to as we have done in our analyses. Notably, using penalized regression on individual-level genotypes allows one to automatically, optimally control for shrinkage and variable selection at the step of model generation [41,76].…”

Section: Imputation Using Baseline Medical Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Methylation risk scores are associated with a collection of phenotypes within electronic health record systems

Thompson

Hill

Rokocz

et al. 2022

Preprint

View full text Add to dashboard Cite

Inference of clinical phenotypes is a fundamental task in precision medicine, and has therefore been heavily investigated in recent years in the context of electronic health records (EHR) using a large arsenal of machine learning techniques, as well as in the context of genetics using polygenic risk scores (PRS). In this work, we considered the epigenetic analog of PRS, methylation risk scores (MRS), a linear combination of methylation states. Since methylation states are influenced by both environmental and genetic factors, we hypothesized that MRS would complement PRS and EHR-based machine-learning methods, improving overall prediction accuracy. To evaluate this hypothesis, we performed the largest assessment of methylation risk scores in clinical datasets to be conducted to date. We measured methylation across a large cohort (n=831) of diverse samples in the UCLA Health biobank, for which both genetic and complete EHR data are available. We constructed MRS for 607 phenotypes spanning diagnoses, clinical lab tests, and medication prescriptions. When added to a baseline set of predictive features, MRS significantly improved the imputation of 139 outcomes, whereas the PRS improved only 22 (median improvement for methylation 10.74%, 141.52%, and 15.46% in medications, labs and diagnosis codes, respectively, whereas genotypes only improved the labs at a median increase of 18.42%). We added significant MRS to state-of-the-art EHR imputation methods that leverage the entire set of medical records, and found that including MRS as a medical feature in the algorithm significantly improves EHR imputation in 37% of lab tests examined (median R2 increase 47.6%). Finally, we replicated several MRS in multiple external studies of methylation (minimum p-value of 2.72 × 10-7) and replicated 22 of 30 tested MRS internally in two separate cohorts of different ethnicity. In summary, our work provides a comprehensive evaluation of MRS in comparison to PRS and EHR imputation on the largest dataset consisting of methylation, genotype, and EHR data. Our publicly available results and weights show promise for methylation risk scores as clinical and scientific tools.

show abstract

Statistical learning for sparser fine‐mapped polygenic models: The prediction of LDL‐cholesterol

Maj

Staerk

Borisov

et al. 2022

Genetic Epidemiology

View full text Add to dashboard Cite

Polygenic risk scores quantify the individual genetic predisposition regarding a particular trait. We propose and illustrate the application of existing statistical learning methods to derive sparser models for genome-wide data with a polygenic signal. Our approach is based on three consecutive steps. First, potentially informative loci are identified by a marginal screening approach. Then, fine-mapping is independently applied for blocks of variants in linkage disequilibrium, where informative variants are retrieved by using variable selection methods including boosting with probing and stochastic searches with the Adaptive Subspace method. Finally, joint prediction models with the selected variants are derived using statistical boosting. In contrast to alternative approaches relying on univariate summary statistics from genome-wide association studies, our three-step approach enables to select and fit multivariable regression models on large-scale genotype data. Based on UK Biobank data, we develop prediction models for LDL-cholesterol as a continuous trait. Additionally, we consider a recent scalable algorithm for the Lasso. Results show that statistical learning approaches based on fine-mapping of genetic signals result in a competitive prediction performance compared to classical polygenic risk approaches, while yielding sparser risk models that tend to be more robust regarding deviations from the target population.

show abstract

Significant Sparse Polygenic Risk Scores across 813 traits in UK Biobank

Cited by 13 publications

References 75 publications

Validating and automating learning of cardiometabolic polygenic risk scores from direct-to-consumer genetic and phenotypic data: implications for scaling precision health research

Validating and automating learning of cardiometabolic polygenic risk scores from direct-to-consumer genetic and phenotypic data: implications for scaling precision health research

Methylation risk scores are associated with a collection of phenotypes within electronic health record systems

Statistical learning for sparser fine‐mapped polygenic models: The prediction of LDL‐cholesterol

Contact Info

Product

Resources

About