Uncertainty-Informed Deep Transfer Learning of Perfluoroalkyl and Polyfluoroalkyl Substance Toxicity.

Perfluoroalkyl and polyfluoroalkyl substances (PFAS) pose a significant hazard because of their widespread industrial uses, environmental persistence, and bioaccumulation. A growing, increasingly diverse inventory of PFAS, including 8163 chemicals, has recently been updated by the U.S. Environmental Protection Agency. However, with the exception of a handful of well-studied examples, little is known about their human toxicity potential because of the substantial resources required for in vivo toxicity experiments. We tackle the problem of expensive in vivo experiments by evaluating multiple machine learning (ML) methods, including random forests, deep neural networks (DNN), graph convolutional networks, and Gaussian processes, for predicting acute toxicity (e.g., median lethal dose, or LD50) of PFAS compounds. To address the scarcity of toxicity information for PFAS, publicly available datasets of oral rat LD50 for all organic compounds are aggregated and used to develop state-of-the-art ML source models for transfer learning. A total of 519 fluorinated compounds containing two or more C-F bonds with known toxicity are used for knowledge transfer to ensembles of the best-performing source model, DNN, to generate the target models for the PFAS domain with access to uncertainty. This study predicts toxicity for PFAS with a defined chemical structure. To further inform prediction confidence, the transfer-learned model is embedded within a SelectiveNet architecture, where the model is allowed to identify regions of prediction with greater confidence and abstain from those with high uncertainty using a calibrated cutoff rate.

An approach for assessing human exposures to chemical mixtures in the environment.

Humans are exposed daily to multiple chemicals, including incidental exposures to complex chemical mixtures released into the environment and to combinations of chemicals that already co-exist in the environment because of previous releases from various sources. Exposures to chemical mixtures can occur through multiple pathways and across multiple routes. In this paper, we propose an iterative approach for assessing exposures to environmental chemical mixtures; it is similar to single-chemical approaches. Our approach encompasses two elements of the Risk Assessment Paradigm: Problem Formulation and Exposure Assessment. Multiple phases of the assessment occur in each element of the paradigm. During Problem Formulation, analysts identify and characterize the source(s) of the chemical mixture, ensure that dose-response and exposure assessment measures are concordant, and develop a preliminary evaluation of the mixture's fate. During Exposure Assessment, analysts evaluate the fate of the chemicals comprising the mixture using appropriate models and measurement data, characterize the exposure scenario, and estimate human exposure to the mixture. We also describe the utility of grouping the chemicals to be analyzed based on both physical-chemical properties and an understanding of environmental fate. In the article, we also highlight the need for understanding of changes in the mixture composition in the environment due to differential transport, differential degradation, and differential partitioning to other media. The Results section describes the application of the method to various chemical mixtures, highlighting issues associated with assessing exposures to chemical mixtures in the environment.