Bayesian Stacking of Quantitative Adverse Outcome Pathways Isolates Primary Drivers of Liver Steatosis
- 1Department of Pesticides Safety, German Federal Institute for Risk Assessment (BfR), Max- Dohrn-Str. 8-10, 10589 Berlin, Germany
Abstract
The quantification of adverse outcome pathways (qAOPs) involving multiple converging pathways remains a fundamental challenge in toxicology. This difficulty is worsened by small in vitro datasets with missing values and heteroscedasticity, which limit the estimation of non-linear response functions and the robust estimation of uncertainty. To overcome these limitations, we developed a framework for estimating a Bayesian qAOP Ensemble (Bayesian qAOPE) that combines heteroscedastic dose-response functions with continuous splines and linear models. By combining multiple converging non-linear pathways through Bayesian stacking, the most meaningful pathways are identified, and strongly correlated responses are naturally accounted for. Applying our approach to a hepatic steatosis dataset, we demonstrate by exact Bayesian leave-one-out cross-validation that our framework yields an exceptional predictive performance suitable for the derivation of a probabilistically weighted Benchmark Dose (BMD). Our framework is highly adaptable and provides a chemical-agnostic, mathematically founded blueprint for integrating multiple converging pathways in a Bayesian network.
Related
- Ultrasound Normalized Weighted Cumulative Residual Entropy Imaging: A New Quantitative Ultrasound Method for Characterizing Hepatic Steatosis.
- Temporal Trends in Lung Cancer and Histological Subtype Incidence and Bayesian Projections to 2030 in China: Population-Based Quantitative Study.
- Hepatic Nnmt Deficiency Alleviates Thiamethoxam-Induced Hepatic Steatosis Via AMPK Activation
- The CYB5R3–mARC1 Redox Axis in Metabolic Dysfunction-associated Steatotic Liver Disease: Mechanistic Basis and Therapeutic Prospects across the Steatosis–Cirrhosis–Hepatocellular Carcinoma Spectrum
- Hepatoprotective Formula 919 ameliorates hepatic steatosis and metabolic disturbance in NAFLD with involvement of AMPK signaling
BibTeX
@misc{steinbach2026bayesian,
title = {{Bayesian Stacking of Quantitative Adverse Outcome Pathways Isolates Primary Drivers of Liver Steatosis}},
author = {A. M. Steinbach and P. Marx-Stoelting and C. T. Willenbockel},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.20.760409},
url = {https://www.biorxiv.org/content/10.64898/2026.10.20.760409v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Bayesian Stacking of Quantitative Adverse Outcome Pathways Isolates Primary Drivers of Liver Steatosis
AU - A. M. Steinbach
AU - P. Marx-Stoelting
AU - C. T. Willenbockel
PY - 2026
DA - 2026/10/20
PB - bioRxiv
DO - 10.64898/2026.10.20.760409
UR - https://www.biorxiv.org/content/10.64898/2026.10.20.760409v1
AB - The quantification of adverse outcome pathways (qAOPs) involving multiple converging pathways remains a fundamental challenge in toxicology. This difficulty is worsened by small in vitro datasets with missing values and heteroscedasticity, which limit the estimation of non-linear response functions and the robust estimation of uncertainty. To overcome these limitations, we developed a framework for estimating a Bayesian qAOP Ensemble (Bayesian qAOPE) that combines heteroscedastic dose-response functions with continuous splines and linear models. By combining multiple converging non-linear pathways through Bayesian stacking, the most meaningful pathways are identified, and strongly correlated responses are naturally accounted for. Applying our approach to a hepatic steatosis dataset, we demonstrate by exact Bayesian leave-one-out cross-validation that our framework yields an exceptional predictive performance suitable for the derivation of a probabilistically weighted Benchmark Dose (BMD). Our framework is highly adaptable and provides a chemical-agnostic, mathematically founded blueprint for integrating multiple converging pathways in a Bayesian network.
ER -