Computational Models That Use a Quantitative Structure–Activity Relationship Approach Based on Deep Learning

In the toxicological testing of new small-molecule compounds, it is desirable to establish in silico test methods predict toxicity instead relying on animal testing. Since quantitative structure–activity relationships (QSARs) can biological activity from structural information for QSAR applications prediction have been studied a long time. However, recent years, remarkable predictive performance deep learning has attracted attention practical applications. this review, we summarize application constructing models, including discussion parameter optimization learning.