Parham Haddadi

Aug 29, 2024 | biorxiv.org | Ayan Chatterjee |Babak Ravandi |Parham Haddadi |Naomi H. Philip

AbstractUnraveling the human interactome to uncover disease-specific patterns and discover drug targets hinges on accurate protein-protein interaction (PPI) predictions. However, challenges persist in machine learning (ML) models due to a scarcity of quality hard negative samples, shortcut learning, and limited generalizability to novel proteins.