Unsupervised representation learning improves genomic discovery and risk prediction for respiratory and circulatory functions and diseases

High-dimensional clinical data are becoming more accessible in biobank-scale datasets. However, effectively utilizing high-dimensional clinical data for genetic discovery remains challenging. Here we introduce a general deep learning-based framework, REpresentation learning for Genetic discovery on Low-dimensional Embeddings (REGLE), for discovering associations between genetic variants and high-dimensional clinical data. REGLE uses convolutional variational autoencoders to compute a non-linear, low-dimensional, disentangled embedding of the data with highly heritable individual components. REGLE can incorporate expert-defined or clinical features and provides a framework to create accurate disease-specific polygenic risk scores (PRS) in datasets which have minimal expert phenotyping. We apply REGLE to both respiratory and circulatory systems: spirograms which measure lung function and photoplethysmograms (PPG) which measure blood volume changes. Genome-wide association studies on REGLE embeddings identify more genome-wide significant loci than existing methods and replicate known loci for both spirograms and PPG, demonstrating the generality of the framework. Furthermore, these embeddings are associated with overall survival. Finally, we construct a set of PRSs that improve predictive performance of asthma, chronic obstructive pulmonary disease, hypertension, and systolic blood pressure in multiple biobanks. Thus, REGLE embeddings can quantify clinically relevant features that are not currently captured in a standardized or automated way. ### Competing Interest Statement T.Y., J.C., B.B., Z.R.M., J.B., H.Y., Y.Z., A.C., C.Y.M., and F.H. are current or former employees of Google or Verily Life Sciences and own Alphabet stock as part of the standard compensation package. ### Funding Statement T.Y., J.C., B.B., Z.R.M., J.B., H.Y., Y.Z., A.C., C.Y.M., and F.H. are current or former employees of Google or Verily Life Sciences and received salary, bonus, and stock awards as part of the standard compensation package. B.D.H. was supported by NIH R01 HL162813, U01 HL089856, R01 HL155749, and a Research Grant from the Alpha-1 Foundation. M.H.C. was supported by NHLBI R01HL153248, R01HL149861, and R01HL147148. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Advarra IRB (Columbia, MD) waived ethical approval for this work involving de-identified medical imagery and metadata under 45 CFR 46. Work related to genomics data were additionally reviewed by the respective data sources: UK Biobank, COPDGene, eMERGE III, EPIC Norfolk, and Indiana Biobank. This research has been conducted using the UK Biobank Resource under Application Number 65275. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Datasets used in this study (UK Biobank, COPDGene, eMERGE III, EPIC Norfolk, and Indiana Biobank) are available to qualified researchers via applying access to each dataset maintainers. All results derived from UK Biobank by this study will be returned to UK Biobank and will be made available by UK Biobank maintainers. Open-source code used for this study is available on GitHub at https://github.com/Google-Health/genomics-research under "regle" directory. GWAS summary statistics are freely available on Google Cloud Storage at https://console.cloud.google.com/storage/browser/brain-genomics-public/research/regle