The prediction and optimization of pharmacokinetic properties are essential in lead optimization. Traditional strategies mainly depend on the empirical chemical rules from medicinal chemists. However, with the rising amount of data, it is getting more difficult to manually extract useful medicinal chemistry knowledge. To this end, we introduced IDL-PPBopt, a computational strategy for predicting and optimizing the plasma protein binding (PPB) property based on an interpretable deep learning method. At first, a curated PPB data set was used to construct an interpretable deep learning model, which showed excellent predictive performance with a root mean squared error of 0.112 for the entire test set. Then, we designed a detection protocol based on the model and Wilcoxon test to identify the PPB-related substructures (named privileged substructures, PSubs) for each molecule. In total, 22 general privileged substructures (GPSubs) were identified, which shared some common features such as nitrogen-containing groups, diamines with two carbon units, and azetidine. Furthermore, a series of second-level chemical rules for each GPSub were derived through a statistical test and then summarized into substructure pairs. We demonstrated that these substructure pairs were equally applicable outside the training set and accordingly customized the structural modification schemes for each GPSub, which provided alternatives for the optimization of the PPB property. Therefore, IDL-PPBopt provides a promising scheme for the prediction and optimization of the PPB property and would be helpful for lead optimization of other pharmacokinetic properties.

Identification of drug–pathway associations plays an important role in pathway-based drug repurposing. However, it is time-consuming and costly to uncover new drug–pathway associations experimentally. The drug-induced transcriptomics data provide a global view of cellular pathways and tell how these pathways change under different treatments. These data enable computational approaches for large-scale prediction of drug–pathway associations. Here we introduced DPNetinfer, a novel computational method to predict potential drug–pathway associations based on substructure–drug–pathway networks via network-based approaches. The results demonstrated that DPNetinfer performed well in a pan-cancer network with an AUC (area under curve) = 0.9358. Meanwhile, DPNetinfer was shown to have a good capability of generalization on two external validation sets (AUC = 0.8519 and 0.7494, respectively). As a case study, DPNetinfer was used in pathway-based drug repurposing for cancer therapy. Unexpected anticancer activities of some nononcology drugs were then identified on the PI3K-Akt pathway. Considering tumor heterogeneity, seven primary site-based models were constructed by DPNetinfer in different drug–pathway networks. In a word, DPNetinfer provides a powerful tool for large-scale prediction of drug–pathway associations in pathway-based drug repurposing. A web tool for DPNetinfer is freely available at .