(Q)SAR Approaches to Predict the Extent of Nitrosation in Pharmaceutical Compounds.

ABSTRACT: Since their discovery as impurities in numerous pharmaceuticals beginning in 2018, there has been a strong push to predict and prevent the formation of mutagenic nitrosamines. Several experimental methods, particularly the Nitrosation Assay Procedure, have been developed to predict a molecule's susceptibility to nitrosation. Here, we have compiled the results of hundreds of these experiments from the literature to construct two structure-activity relationship models: a statistical model and an expert rule-based model. The statistical model has been built with graph neural networks and was trained on a dataset of 207 nitrogen-containing molecules. This model makes a binary call for each nitrogen center, predicting if it is likely to be nitrosated or not. Conversely, the rule-based model lab

SUBMITTER: Reiss K 

PROVIDER: S-EPMC11921035 | biostudies-literature | 2025 Mar

REPOSITORIES: biostudies-literature