MeSH headings : Biological Products / chemistry; Cheminformatics; Databases, Chemical; Machine Learning; Macrolides / chemistry; Models, Chemical; Quantitative Structure-Activity Relationship; Software

TL;DR: This study develops MacrolactoneDB, which integrates nearly 14,000 existing macrolactones and their bioactivity information from different public databases, and new molecular descriptors to better characterize macrolide structures, and shows that merging descriptors yields the best predictive power with Random Forest models. (via Semantic Scholar)