Publications by authors named "Xin-Man Hu"
Cytochrome P450 (P450)-mediated bioactivation, which can lead to the hepatotoxicity through the formation of reactive metabolites (RMs), has been regarded as the major problem of drug failures. Herein, we purposed to establish machine learning models to predict the bioactivation of P450. On the basis of the literature-derived bioactivation dataset, models for Benzene ring, Nitrogen heterocycle and Sulfur heterocycle were developed with machine learning methods, i.
View Article and Find Full Text PDFArticle Synopsis
- UDP-glucuronosyltransferase 1A1 (UGT1A1) is crucial for detoxifying various substances, making its metabolic profile important for avoiding drug interactions.
- The study developed machine learning models to predict the metabolism of UGT1A1 substrates, using eight methods, with Random Forest, Random Subspace, and J48 performing the best.
- The models showed high accuracy with AUC values between 0.901 and 0.997 and successfully predicted new metabolites, providing a solid strategy for enhancing drug metabolism and minimizing clinical drug-drug interactions.