An Integrated AIVIVE-PBPK-QIVIVE Framework with HTTK Validation for Probabilistic Risk Assessment of Neodymium...

Area of Science:

• Computational Toxicology and Risk Assessment
• Environmental Health and Exposure Science
• Pharmacokinetics and Toxicokinetics

Background:

• Rare earth elements (REEs) are vital for industries but pose increasing health risks due to environmental release.
• Neodymium nitrate (Nd(NO3)3), a representative REE compound, lacks comprehensive toxicological data for risk assessment.
• Existing toxicological models struggle with metals exhibiting nonlinear pharmacokinetic behavior.

Purpose of the Study:

• To develop and validate an integrated computational toxicology framework for mechanism-based risk assessment of neodymium nitrate.
• To address data gaps in REE toxicology, particularly for compounds with nonlinear kinetics.
• To reduce reliance on animal testing through advanced in vitro to in vivo extrapolation methods.

Main Methods:

• Developed an integrated framework combining artificial intelligence-enhanced in vitro to in vivo extrapolation (AIVIVE), physiologically based pharmacokinetic (PBPK) modeling, quantitative in vitro to in vivo extrapolation (QIVIVE), and high-throughput toxicokinetic (HTTK) validation.
• Employed a closed-loop 'model-informed experimental design' using conditional generative adversarial networks (cGANs) for pathway prediction and experimental calibration of key toxicokinetic parameters.
• Utilized Monte Carlo simulation and Sobol sensitivity analysis to quantify uncertainty in human equivalent dose (HED) predictions.

Main Results:

• AIVIVE accurately predicted transcriptomic responses (cosine similarity = 0.9986) and identified key toxicity pathways (p53, apoptosis, ferroptosis) with >85% accuracy.
• Experimental calibration revealed significant nonlinearity in plasma unbound fraction (fu) and cellular partition coefficients (K), which HTTK models underestimated.
• The integrated framework predicted a median HED of 0.032 mg/kg/day, with an 18% probability of exceeding the high-risk threshold; sensitivity analysis highlighted fu as the dominant uncertainty source.
• Probabilistic risk assessment indicated a high safety margin for the general population but concerns for mining area residents.

Conclusions:

• The developed integrated computational toxicology framework effectively assesses risks of metals with nonlinear kinetics, like neodymium nitrate.
• The framework reduces reliance on animal testing and provides a robust approach for regulatory decision-making.
• An occupational exposure limit of 0.05 mg/m³ for neodymium nitrate is proposed based on the risk assessment.