A Machine Learning Model to Estimate Toxicokinetic Half-Lives of Per- and Polyfluoro-Alkyl Substances (PFAS) in Multiple Species

Per- and polyfluoroalkyl substances (PFAS) are a diverse group of man-made chemicals that are commonly found in body tissues. The toxicokinetics of most PFAS are currently uncharacterized, but long half-lives (t(1/2)) have been observed in some cases. Knowledge of chemical-specific t(1/2) is necessary for exposure reconstruction and extrapolation from toxicological studies. We used an ensemble machine learning method, random forest, to model the existing in vivo measured t(1/2) across four species (human, monkey, rat, mouse) and eleven PFAS. Mechanistically motivated descriptors were examined, including two types of surrogates for renal transporters: (1) physiological descriptors, including kidney geometry, for renal transporter expression and (2) structural similarity of defluorinated PFAS to endogenous chemicals for transporter affinity. We developed a classification model for t(1/2) (Bin 1: 2 months). The model had an accuracy of 86.1% in contrast to 32.2% for a y-randomized null model. A total of 3890 compounds were within domain of the model, and t(1/2) was predicted using the bin medians: 4.9 h, 2.2 days, 33 days, and 3.3 years. For human t(1/2), 56% of PFAS were classified in Bin 4, 7% were classified in Bin 3, and 37% were classified in Bin 2. This model synthesizes the limited available data to allow tentative extrapolation and prioritization.

Automated summary

In this study, a random forest method was used to model the t(1/2) of PFAS across four species and eleven compounds. A classification model for t(1/2) was developed, and the t(1/2) of 3890 compounds was predicted. This model provides a basis for tentative extrapolation and prioritization.