Integrating edge features and complementary attention mechanism for drug response prediction

Predicting drug response in cancer cell lines is a vital field in precision medicine, supporting personalized treatment planning, optimizing drug selection, and enhancing the accuracy and effectiveness of cancer therapies. Although graph neural network-based models for drug response prediction have made significant progress in performance, they often focus solely on learning node embeddings while overlooking adjacency relationships between cell lines, limiting the model’s ability to capture inter-cell line adjacency information. To address this limitation, we propose a novel model that constructs edge features by measuring similarity between cell lines and their k-nearest neighbors, integrating these edge features with a node-edge complementary attention mechanism. This approach enables the model to dynamically incorporate node and edge information, achieving complementary and collaborative feature learning. Such a design substantially improves the accuracy and biological interpretability of drug response prediction. Furthermore, to enhance the independence and complementarity of node and edge features, we introduce a complementary loss mechanism in the model and design a topology updating module that performs dynamic feature updates via neighborhood aggregation, effectively capturing and utilizing multi-omics data. We conduct comprehensive experiments on the Genomics of Drug Sensitivity in Cancer and the Cancer Cell Line Encyclopedia, which contains various diseases such as esophageal carcinoma, stomach adenocarcinoma, colon adenocarcinoma and rectal adenocarcinoma, the results demonstrate that our model outperforms current state-of-the-art methods in cancer drug response prediction.