Host: The Japanese Society of Toxicology
Name : The 47th Annual Meeting of the Japanese Society of Toxicology
Date : 2020 -
The purpose of this study was to identify chemical and structural features associated with drug-induced liver injury (DILI) using in silico methods. The model drugs’ data were obtained from the US FDA’s Liver Toxicity Knowledge Base and literature. The 2D chemical descriptors were calculated with Dragon 7 software. In the decision tree analysis of 432 DILI and 220 no-DILI drugs, 64% and 71% of DILI and no-DILI drugs, respectively, were correctly classified by AMW. By individual analyses of each ATC class 1 group, highly accurate discriminant models were obtained for classes A, C, M and S.