HExpPredict: In Vivo Exposure Prediction of Human Blood Exposome Using a Random Forest Model and Its Application in Chemical Risk Prioritization

BACKGROUND: Due to many substances in the human exposome, there is a dearth of exposure and toxicity information available to assess potential health risks. Quantification of all trace organics in the biological fluids seems impossible and costly, regardless of the high individual exposure variability. We hypothesized that the blood concentration ([Formula: see text]) of organic pollutants could be predicted via their exposure and chemical properties. Developing a prediction model on the annotation of chemicals in human blood can provide new insight into the distribution and extent of exposures to a wide range of chemicals in humans. OBJECTIVES: Our objective was to develop a machine learning (ML) model to predict blood concentrations ([Formula: see text]) of chemicals and prioritize chemicals of health concern. METHODS: We curated the [Formula: see text] of compounds mostly measured at population levels and developed an ML model for chemical [Formula: see text] predictions by considering chemical daily exposure (DE) and exposure pathway indicators ([Formula: see text]), half-lives ([Formula: see text]), and volume of distribution ([Formula: see text]). Three ML models, including random forest (RF), artificial neural network (ANN) and support vector regression (SVR) were compared. The toxicity potential or prioritization of each chemical was represented as a bioanalytical equivalency (BEQ) and its percentage (BEQ%) estimated based on the predicted [Formula: see text] and ToxCast bioactivity data. We also retrieved the top 25 most active chemicals in each assay to further observe changes in the BEQ% after the exclusion of the drugs and endogenous substances. RESULTS: We curated the [Formula: see text] of 216 compounds primarily measured at population levels. RF outperformed the ANN and SVF models with the root mean square error (RMSE) of 1.66 and [Formula: see text] , the mean absolute error (MAE) values of 1.28 and [Formula: see text] , the mean absolute percentage error (MAPE) of 0.29 and 0.23, and [Formula: see text] of 0.80 and 0.72 across test and testing sets. Subsequently, the human [Formula: see text] of 7,858 ToxCast chemicals were successfully predicted, ranging from [Formula: see text] to [Formula: see text]. The predicted [Formula: see text] were then combined with ToxCast in vitro bioassays to prioritize the ToxCast chemicals across 12 in vitro assays with important toxicological end points. It is interesting that we found the most active compounds to be food additives and pesticides rather than widely monitored environmental pollutants. DISCUSSION: We have shown that the accurate prediction of “internal exposure” from “external exposure” is possible, and this result can be quite useful in the risk prioritization. https://doi.org/10.1289/EHP11305