Integration of Epigenetic Mechanisms into Non-Genotoxic Carcinogenicity Hazard Assessment: Focus on DNA Methylation and Histone Modifications

Epigenetics involves a series of mechanisms that entail histone and DNA covalent modifications and non-coding RNAs, and that collectively contribute to programing cell functions and differentiation. Epigenetic anomalies and DNA mutations are co-drivers of cellular dysfunctions, including carcinogenesis. Alterations of the epigenetic system occur in cancers whether the initial carcinogenic events are from genotoxic (GTxC) or non-genotoxic (NGTxC) carcinogens. NGTxC are not inherently DNA reactive, they do not have a unifying mode of action and as yet there are no regulatory test guidelines addressing mechanisms of NGTxC. To fil this gap, the Test Guideline Programme of the Organisation for Economic Cooperation and Development is developing a framework for an integrated approach for the testing and assessment (IATA) of NGTxC and is considering assays that address key events of cancer hallmarks. Here, with the intent of better understanding the applicability of epigenetic assays in chemical carcinogenicity assessment, we focus on DNA methylation and histone modifications and review: (1) epigenetic mechanisms contributing to carcinogenesis, (2) epigenetic mechanisms altered following exposure to arsenic, nickel, or phenobarbital in order to identify common carcinogen-specific mechanisms, (3) characteristics of a series of epigenetic assay types, and (4) epigenetic assay validation needs in the context of chemical hazard assessment. As a key component of numerous NGTxC mechanisms of action, epigenetic assays included in IATA assay combinations can contribute to improved chemical carcinogen identification for the better protection of public health.

Predicting Environmental Chemical Carcinogenicity using a Hybrid Machine-Learning Approach

Determining environmental chemical carcinogenicity is an urgent need as humans are increasingly exposed to these chemicals. In this study, we determined the carcinogenicity of wide variety real-life exposure chemicals in large scale. To determine chemical carcinogenicity, we have developed carcinogenicity prediction models based on the hybrid neural network (HNN) architecture. In the HNN model, we included new SMILES feature representation method, by modifying our previous 3D array representation of 1D SMILES simulated by the convolutional neural network (CNN). We used 653 molecular descriptors modeled by feed forward neural network (FFNN), and SMILES as chemical features to train the models. We have developed three types of machine learning models: binary classification models to predict chemical is a carcinogenic or non-carcinogenic, multiclass classification models to predict severity of the chemical carcinogenicity, and regression models to predict median toxic dose of the chemicals. Along with the hybrid neural network (HNN) model that we developed, Random Forest (RF), Bootstrap Aggregating (Bagging) and Adaptive Boosting (AdaBoost) methods were also used for binary and multiclass classification. Regression models were developed using HNN, RF, Support Vector Regressor (SVR), Gradient Boosting (GB), Kernel Ridge (KR), Decision Tree with AdaBoost (DT), KNeighbors (KN), and a consensus method. For binary classification, our HNN model predicted with an average accuracy of 74.33% and an average AUC of 0.806, for multiclass classification, the HNN model predicted with an average accuracy of 50.58% and an average micro-AUC of 0.68, and for regression model, the consensus method achieved R2 of 0.40. The predictive performance of our models based on a highly diverse chemicals is comparable to the literature reported models that included the similar and less diverse molecules. Our models can be used in identifying the potentially carcinogenic chemicals for a wide variety of chemical classes