Exploring genetic influences on adverse outcome pathways using heuristic simulation and graph data science

• Published in: Computational toxicology 2023-02, Vol.25, p.100261, Article 100261
• Main Authors: Romano, Joseph D., Mei, Liang, Senn, Jonathan, Moore, Jason H., Mortensen, Holly M.
• Format: Article
• Language: English
• Subjects: Adverse outcome pathway; Graph data science; Liver cancer, genetic programming
• ISSN: 2468-1113; 2468-1113
• DOI: 10.1016/j.comtox.2023.100261

•AI methods can be leveraged to uncover patterns of genetic regulation in AOPs using observational data.•The AOP framework and AI methods can be implemented to gain novel insights into toxicity-mediated mechanisms and outcomes.•This is the first study into how GP can be used to understand the genetic mechanisms underlying toxicity-mediated disease.•The simultaneous association observed for variants in the AHR and ABCB11 genes indicates increased risk for liver cancer.•Our socioeconomic deprivation approach provides a tool for improving social justice in environmental health studies. Adverse outcome pathways provide a powerful tool for understanding the biological signaling cascades that lead to disease outcomes following toxicity. The framework outlines downstream responses known as key events, culminating in a clinically significant adverse outcome as a final result of the toxic exposure. Here we use the AOP framework combined with artificial intelligence methods to gain novel insights into genetic mechanisms that underlie toxicity-mediated adverse health outcomes. Specifically, we focus on liver cancer as a case study with diverse underlying mechanisms that are clinically significant. Our approach uses two complementary AI techniques: Generative modeling via automated machine learning and genetic algorithms, and graph machine learning. We used data from the US Environmental Protection Agency’s Adverse Outcome Pathway Database (AOP-DB; aopdb.epa.gov) and the UK Biobank’s genetic data repository. We use the AOP-DB to extract disease-specific AOPs and build graph neural networks used in our final analyses. We use the UK Biobank to retrieve real-world genotype and phenotype data, where genotypes are based on single nucleotide polymorphism data extracted from the AOP-DB, and phenotypes are case/control cohorts for the disease of interest (liver cancer) corresponding to those adverse outcome pathways. We also use propensity score matching to appropriately sample based on important covariates (demographics, comorbidities, and social deprivation indices) and to balance the case and control populations in our machine language training/testing datasets. Finally, we describe a novel putative risk factor for LC that depends on genetic variation in both the aryl-hydrocarbon receptor (AHR) and ATP binding cassette subfamily B member 11 (ABCB11) genes.