Using chemical structure information to develop predictive models for in vitro toxicokinetic parameters to inform high-throughput risk-assessment

Publication: Computational Toxicology
Software: ADMET Predictor®


The toxicokinetic (TK) parameters fraction of the chemical unbound to plasma proteins and metabolic clearance are critical for relating exposure and internal dose when building in vitro-based risk assessment models. However, experimental toxicokinetic studies have only been carried out on limited chemicals of environmental interest (~1000 chemicals with TK data relative to tens of thousands of chemicals of interest). This work evaluated the utility of chemical structure information to predict TK parameters in silico; development of cluster-based read-across and quantitative structure–activity relationship models of fraction unbound or fub (regression) and intrinsic clearance or Clint (classification and regression) using a dataset of 1487 chemicals; utilization of predicted TK parameters to estimate uncertainty in steady-state plasma concentration (Css); and subsequent in vitroin vivo extrapolation analyses to derive bioactivity-exposure ratio (BER) plot to compare human oral equivalent doses and exposure predictions using androgen and estrogen receptor activity data for 233 chemicals as an example dataset. The results demonstrate that fub is structurally more predictable than Clint. The model with the highest observed performance for fub had an external test set RMSE/σ = 0.61 and R2 = 0.57, for Clint classification had an external test set accuracy = 73.2%, and for intrinsic clearance regression had an external test set RMSE/σ = 0.92 and R2 = 0.16. This relatively low performance is in part due to the large uncertainty in the underlying Clint data. We show that Css is relatively insensitive to uncertainty in Clint. The models were benchmarked against the ADMET Predictor software. Finally, the BER analysis allowed identification of 14 out of 136 chemicals for further risk assessment demonstrating the utility of these models in aiding risk-based chemical prioritization.

By PrachiPradeep, Grace Patlewicz, Robert Pearce, John Wambaugh, Barbara Wetmore, Richard Judson