Machine Learning-based Biomarkers Identification and Validation from Toxicogenomics - Bridging to Regulatory Relevant Phenotypic Endpoints

Abstract

High-throughput in vitro assays and AOP-based approach is promising for the assessment of health and ecotoxicological risks from exposure to pollutants and their mixtures. However, one of the major challenges in realization and implementations of the Tox21 vision is the urgent need to establish quantitative link between in-vitro assay molecular endpoint and in-vivo phenotypic toxicity endpoint. Here, we demonstrated that, using time series toxicomics in-vitro assay along with machine learning-based feature selection (MRMR) and classification method (SVM), an “optimal” number of biomarkers with minimum redundancy can be identified for prediction of phenotypic endpoints with good accuracy. We included two case studies for in-vivo carcinogenicity and Ames genotoxicity prediction with 20 selected chemicals including model genotoxic chemicals and negative controls, respectively, using an in-vitro toxicogenomic assay that captures real-time proteomic response data of 38 GFP-fused proteins of S. cerevisiae strains covering biomarkers indicative of all known DNA damage and repair pathways in yeast. The results suggested that, employing the adverse outcome pathway (AOP) concept, molecular endpoints based on a relatively small number of properly selected biomarker-ensemble involved in the conserved DNA-damage and repair pathways among eukaryotes, were able to predict both in-vivo carcinogenicity in rats and Ames genotoxicity endpoints. The specific biomarkers identified are different for the two different phenotypic genotoxicity assays. The top-ranked five biomarkers for the in-vivo carcinogenicity prediction mainly focused on double strand break repair and DNA recombination, whereas the selected top-ranked biomarkers for Ames genotoxicity prediction are associated with base- and nucleotide-excision repair. Current toxicomics approach still mostly rely on large number of redundant markers without pre-selection or ranking, therefore, selection of relevant biomarkers with minimal redundancy would reduce the number of markers to be monitored and reduce the cost, time, and complexity of the toxicity screening and risk monitoring. The method developed in this study will help to fill in the knowledge gap in phenotypic anchoring and predictive toxicology, and contribute to the progress in the implementation of tox 21 vision for environmental and health applications.TOC Art