A machine learning-driven approach for prioritizing food contact chemicals of carcinogenic concern based on complementary in silico methods. (February 2022)

• Record Type: Journal Article
• Authors: Wang, Chia-Chi; Liang, Yu-Chih; Wang, Shan-Shan; Lin, Pinpin; Tung, Chun-Wei
• Is Part Of: Food and chemical toxicology. Volume 160(2022)
• Publication Date: 2022-02
• Subjects: Machine learning -- Weight-of-evidence -- Food contact chemical -- Toxicogenomics -- Quantitative structure-activity relationship -- Structural alert; Toxicology -- Periodicals; Food poisoning -- Periodicals; Food Poisoning -- Periodicals; Toxicology -- Periodicals; Toxicologie -- Périodiques; Intoxications alimentaires -- Périodiques; Food poisoning; Toxicology; Periodicals; Electronic journals; 615.9
• DOI: 10.1016/j.fct.2021.112802
• Languages: English
• ISSNs: 0278-6915

Abstract

Abstract: Carcinogenicity is one of the most critical endpoints for the risk assessment of food contact chemicals (FCCs). However, the carcinogenicity of FCCs remains insufficiently investigated. To fill the data gap, the application of standard experimental methods for identifying chemicals of carcinogenic concerns from a large set of FCCs is impractical due to their resource-intensive nature. In contrast, computational methods provide an efficient way to quickly screen chemicals with carcinogenic potential for subsequent experimental validation. Since every model was developed based on a limited number of training samples, the use of single models for carcinogenicity assessment may not cover the complex mechanisms of carcinogenesis. This study proposed a novel machine learning-based weight-of-evidence (WoE) model for prioritizing chemical carcinogenesis. The WoE model can nonlinearly integrate complementary computational methods of structural alerts, quantitative structure-activity relationship models and in silico toxicogenomics models into a WoE-score. Compared to the best single method, the WoE model gained 8% and 19.7% improvement in the area under the receiver operating characteristic curve (AUC) value and chemical coverage, respectively. The prioritization of 1623 FCCs concludes 44 chemicals of high carcinogenic concern. The machine learning-based WoE approach provides a fast and comprehensive way for prioritizing chemicals of carcinogenic concern. Highlights: Complementary methods are integrated for prioritizing chemical carcinogenesis. Individual models are not sufficient to address complex carcinogenic mechanism. Food contact chemicals of carcinogenic concern have been identified. The machine learning-based framework is potentially useful for other toxicities.