Predicting the effects of drugs and unveiling their mechanisms of action using an interpretable pharmacodynamic mechanism knowledge graph (IPM-KG).

Background: Multiple studies have aimed to consolidate drug-related data and predict drug effects. However, most of these studies have focused on integrating diverse data through correlation rather than representing them based on the pharmacodynamic mechanism of action (MOA). It is thus crucial to obtain interpretability to validate prediction results. In this study, we propose a novel framework to construct knowledge graphs that represent pharmacodynamic MOA, predict drug effects, and derive conceivable mechanistic pathways.

Methods And Results: We constructed an interpretable pharmacodynamic mechanism knowledge graph (IPM-KG) by integrating various existing databases and combining them with the approach of this study to automatically fill in the missing data. This yielded a knowledge graph comprising 1455 drugs and 2547 diseases. Additionally, a graph neural network (GNN)-based approach was used to predict therapeutic medication and indication, which outperformed previous approaches that relied on correlation-based knowledge graphs lacking pharmacodynamic MOA representations. Furthermore, we proposed and assessed a method to interpret pharmacodynamic MOA using gene perturbation data. This feasibility study demonstrated the successful derivation of an accurate mechanism in approximately 50 % of cases. Additionally, it facilitated the identification of candidate drugs, which are currently unapproved but exhibit potential for drug repositioning, and their mechanisms of action.

Conclusions: This framework not only enables the derivation of highly accurate "drug-indication" predictions but also offers a basic mechanistic understanding, thereby facilitating future drug repositioning efforts.