Wen-Li Gu

MolADR: Multi-Scale Complementary Learning of Dual-Granularity Molecules and Knowledge Graphs for ADR Prediction in Drug Combinations.

MolADR is proposed, a multiscale complementary learning framework that integrates GNN-based KG learning with dual-granularity molecular cross-attention modeling to combine macro-level biomedical associations with microlevel molecular interaction cues, suggesting its ability to highlight chemically plausible atoms and f...