Tri-graph Information Propagation for Polypharmacy Side Effect Prediction
This addresses the problem of predicting side effects from drug combinations for healthcare applications, offering a more efficient and accurate solution.
The paper tackles polypharmacy side effect prediction by proposing a Tri-graph Information Propagation model that operates on three subgraphs, improving accuracy by over 7%, time efficiency by 83 times, and space efficiency by 3 times compared to prior methods.
The use of drug combinations often leads to polypharmacy side effects (POSE). A recent method formulates POSE prediction as a link prediction problem on a graph of drugs and proteins, and solves it with Graph Convolutional Networks (GCNs). However, due to the complex relationships in POSE, this method has high computational cost and memory demand. This paper proposes a flexible Tri-graph Information Propagation (TIP) model that operates on three subgraphs to learn representations progressively by propagation from protein-protein graph to drug-drug graph via protein-drug graph. Experiments show that TIP improves accuracy by 7%+, time efficiency by 83$\times$, and space efficiency by 3$\times$.