Metabolomic Pathways to Osteoporosis in Middle-Aged Women: A Genome-Metabolome-Wide Mendelian Randomization Study

Abstract

The metabolic state of the body can be a major determinant of bone health. We used a Mendelian randomization approach to identify metabolites causally associated with bone mass to better understand the biological mechanisms of osteoporosis. We tested bone phenotypes (femoral neck, total hip, and lumbar spine bone mineral density [BMD]) for association with 280 fasting blood metabolites in 6055 women from TwinsUK cohort with genomewide genotyping scans. Causal associations between metabolites and bone phenotypes were further assessed in a bidirectional Mendelian randomization study using genetic markers/scores as instrumental variables. Significant associations were replicated in 624 participants from the Hong Kong Osteoporosis Study (HKOS). Fifteen metabolites showed direct associations with bone phenotypes after adjusting for covariates and multiple testing. Using genetic instruments, four of these metabolites were found to be causally associated with hip or spine BMD. These included androsterone sulfate, epiandrosterone sulfate, 5alpha-androstan-3beta17beta-diol disulfate (encoded by CYP3A5), and 4-androsten-3beta17beta-diol disulfate (encoded by SULT2A1). In the HKOS population, all four metabolites showed significant associations with hip and spine BMD in the expected directions. No causal reverse association between BMD and any of the metabolites were found. In the first metabolome-genomewide Mendelian randomization study of human bone mineral density, we identified four novel biomarkers causally associated with BMD. Our findings reveal novel biological pathways involved in the pathogenesis of osteoporosis. © 2017 American Society for Bone and Mineral Research.

Keywords: BONE MINERAL DENSITY; GENOMEWIDE ASSOCIATION STUDIES; INSTRUMENTAL VARIABLES ANALYSIS; MENDELIAN RANDOMIZATION; METABOLOMICS; OSTEOPOROSIS.

Figure 1

Flow chart of the study.

Figure 2

Scatter plot of observed versus predicted total hip bone mineral density (BMD) values based on orthogonally filtered partial least square (O‐PLS) model with 280 metabolites among 4937 participants. *RMSEe = root mean square error of the estimation (the fit) for training sample; RMSEcv = root mean square error for cross‐validation sample.