You are here:
A Machine Learning Model to Estimate Toxicokinetic Half-Lives of PFAS in Multiple Species
Citation:
Wambaugh, J. A Machine Learning Model to Estimate Toxicokinetic Half-Lives of PFAS in Multiple Species. Federal-State Toxicology Risk Analysis Committee, Virtual, NC, April 20, 2023. https://doi.org/10.23645/epacomptox.22589062
Impact/Purpose:
A PowerPoint slide presentation has been prepared by John Wambaugh in response to an invitation from the Federal-State Toxicology Risk Analysis Committee (FSTRAC). The goal of FSTRAC is to strengthen relationships and cooperation among EPA, states, and tribes through the exchange of technical information primarily regarding water-related human health and risk assessment and also share information on ecological effects related to water quality criteria. Please refer to EPA’s FSTRAC website for additional information (https://www.epa.gov/water-research/federal-state-toxicology-risk-analysis-committee-fstrac). The presentation is entitled “A Machine Learning Model to Estimate Toxicokinetic Half-Lives of PFAS in Multiple Species”. The presentation covers the Dawson et al. (2023) model that was recently cleared and published by ORD (https://doi.org/10.3390/toxics11020098).
Description:
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 (t½) have been observed in some cases. Knowledge of chemical-specific t½ 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 t½ 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 t½ (Bin 1: <12 h; Bin 2: <1 week; Bin 3: <2 months; Bin 4: >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 t½ was predicted using the bin medians: 4.9 h, 2.2 days, 33 days, and 3.3 years. For human t½, 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.
URLs/Downloads:
DOI: A Machine Learning Model to Estimate Toxicokinetic Half-Lives of PFAS in Multiple Species
WAMBAUGH-PFAS-HALFLIFE-MODEL-V3.PDF (PDF, NA pp, 1828.566 KB, about PDF)