Risk stratification is critical for the early identification of high-risk individuals and disease prevention. Here we explored the potential of nuclear magnetic resonance (NMR) spectroscopy-derived metabolomic profiles to inform on multidisease risk beyond conventional clinical predictors for the onset of 24 common conditions, including metabolic, vascular, respiratory, musculoskeletal and neurological diseases and cancers. Specifically, we trained a neural network to learn disease-specific metabolomic states from 168 circulating metabolic markers measured in 117,981 participants with ~1.4 million person-years of follow-up from the UK Biobank and validated the model in four independent cohorts. We found metabolomic states to be associated with incident event rates in all the investigated conditions, except breast cancer. For 10-year outcome prediction for 15 endpoints, with and without established metabolic contribution, a combination of age and sex and the metabolomic state equaled or outperformed established predictors. Moreover, metabolomic state added predictive information over comprehensive clinical variables for eight common diseases, including type 2 diabetes, dementia and heart failure. Decision curve analyses showed that predictive improvements translated into clinical utility for a wide range of potential decision thresholds. Taken together, our study demonstrates both the potential and limitations of NMR-derived metabolomic profiles as a multidisease assay to inform on the risk of many common diseases simultaneously.

Motivation: 1H-NMR metabolomics is rapidly becoming a standard resource in large epidemiological studies to acquire metabolic profiles in large numbers of samples in a relatively low-priced and standardized manner. Concomitantly, metabolomics-based models are increasingly developed that capture disease risk or clinical risk factors. These developments raise the need for user-friendly toolbox to inspect new 1H-NMR metabolomics data and project a wide array of previously established risk models. Results: We present MiMIR (Metabolomics-based Models for Imputing Risk), a graphical user interface that provides an intuitive framework for ad hoc statistical analysis of Nightingale Health's 1H-NMR metabolomics data and allows for the projection and calibration of 24 pre-trained metabolomics-based models, without any pre-required programming knowledge.

Population-scale expression profiling studies can provide valuable insights into biological and disease-underlying mechanisms. The availability of phenotypic traits is essential for studying clinical effects. Therefore, missing, incomplete, or inaccurate phenotypic information can make analyses challenging and prevent RNA-seq or other omics data to be reused. A possible solution are predictors that infer clinical or behavioral phenotypic traits from molecular data. While such predictors have been developed based on different omics data types and are being applied in various studies, metabolomics-based surrogates are less commonly used than predictors based on DNA methylation profiles.In this study, we inferred 17 traits, including diabetes status and exposure to lipid medication, using previously trained metabolomic predictors. We evaluated whether these metabolomic surrogates can be used as an alternative to reported information for studying the respective phenotypes using expression profiling data of four population cohorts. For the majority of the 17 traits, the metabolomic surrogates performed similarly to the reported phenotypes in terms of effect sizes, number of significant associations, replication rates, and significantly enriched pathways.The application of metabolomics-derived surrogate outcomes opens new possibilities for reuse of multi-omics data sets. In studies where availability of clinical metadata is limited, missing or incomplete information can be complemented by these surrogates, thereby increasing the size of available data sets. Additionally, the availability of such surrogates could be used to correct for potential biological confounding. In the future, it would be interesting to further investigate the use of molecular predictors across different omics types and cohorts.

Background: Missing or incomplete phenotypic information can severely deteriorate the statistical power in epidemiological studies. High-throughput quantification of small-molecules in bio-samples, i.e. ‘metabolomics’, is steadily gaining popularity, as it is highly informative for various phenotypical characteristics. Here we aim to leverage metabolomics to impute missing data in clinical variables routinely assessed in large epidemiological and clinical studies. Methods: To this end, we have employed ∼26,000 ¹H-NMR metabolomics samples from 28 Dutch cohorts collected within the BBMRI-NL consortium, to create 19 metabolomics-based predictors for clinical variables, including diabetes status (AUC_{5-Fold CV} = 0·94) and lipid medication usage (AUC_{5-Fold CV} = 0·90). Findings: Subsequent application in independent cohorts confirmed that our metabolomics-based predictors can indeed be used to impute a wide array of missing clinical variables from a single metabolomics data resource. In addition, application highlighted the potential use of our predictors to explore the effects of totally unobserved confounders in omics association studies. Finally, we show that our predictors can be used to explore risk factor profiles contributing to mortality in older participants. Interpretation: To conclude, we provide ¹H-NMR metabolomics-based models to impute clinical variables routinely assessed in epidemiological studies and illustrate their merit in scenarios when phenotypic variables are partially incomplete or totally unobserved. Funding: BBMRI-NL, X-omics, VOILA, Medical Delta and the Dutch Research Council (NWO-VENI).