A metabolomic investigation of serum perfluorooctane sulfonate and perfluorooctanoate

Abstract

Background: Exposures to perfluorooctane sulfonate (PFOS) and perfluorooctanoate (PFOA), environmentally persistent chemicals detectable in the blood of most Americans, have been associated with several health outcomes. To offer insight into their possible biologic effects, we evaluated the metabolomic correlates of circulating PFOS and PFOA among 3,647 participants in eight nested case-control serum metabolomic profiling studies from the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial.

Methods: Metabolomic profiling was conducted by Metabolon Inc., using ultra high-performance liquid chromatography/tandem accurate mass spectrometry. We conducted study-specific multivariable linear regression analyses estimating the associations of metabolite levels with levels of PFOS or PFOA. For metabolites measured in at least 3 of 8 nested case-control studies, random effects meta-analysis was used to summarize study-specific results (1,038 metabolites in PFOS analyses and 1,100 in PFOA analyses).

Results: The meta-analysis identified 51 and 38 metabolites associated with PFOS and PFOA, respectively, at a Bonferroni-corrected significance level (4.8x10^-5 and 4.6x10^-5, respectively). For both PFOS and PFOA, the most common types of associated metabolites were lipids (sphingolipids, fatty acid metabolites) and xenobiotics (xanthine metabolites, chemicals). Positive associations were commonly observed with lipid metabolites sphingomyelin (d18:1/18:0) (P = 2.0x10^-10 and 2.0x10^-8, respectively), 3-carboxy-4-methyl-5-pentyl-2-furanpropionate (P = 2.7x10^-15, 1.1x10^-17), and lignoceroylcarnitine (C24) (P = 2.6x10^-8, 6.2x10^-6). The strongest positive associations were observed for chemicals 3,5-dichloro-2,6-dihydroxybenzoic acid (P = 3.0x10^-112 and 6.8x10^-13, respectively) and 3-bromo-5-chloro-2,6-dihydroxybenzoic acid (P = 1.6x10^-14, 2.3x10^-6). Other metabolites positively associated with PFOS included D-glucose (carbohydrate), carotene diol (vitamin A metabolism), and L-alpha-aminobutyric acid (glutathione metabolism), while uric acid (purine metabolite) was positively associated with PFOA. PFOS associations were consistent even after adjusting for PFOA as a covariate, while PFOA associations were greatly attenuated with PFOS adjustment.

Conclusions: In this large metabolomic study, we observed robust positive associations with PFOS for several molecules. Further investigation of these metabolites may offer insight into PFOS-related biologic effects.

Keywords: Metabolomics; Per- and polyfluoroalkyl substances; Perfluorooctane sulfonate; Perfluorooctanoate.

Figure 1.

Scatter plots of serum PFAS measured at Metabolon and CDC. Spearman correlations are 0.77 for n-PFOA and 0.74 for n-PFOS. PFAS, per- and polyfluoroalkyl substances; PFOA, perfluorooctanoate; PFOS, perfluorooctane sulfonate; CDC, Centers for Disease Control and Prevention Serum PFOA and PFOS are for the linear isomer. All measurements were log-transformed.