DDMut-PPI Predicting effects of mutations on protein-protein interactions using graph-based deep learning
Yunzhuo Zhou, YooChan Myung, Carlos H.M. Rodrigues & David B. Ascher
Abstract: Protein-protein interactions (PPIs) play a vital role in cellular functions and are essential in the context of therapeutic development and understanding disease mechanism. However, current predictive tools often struggle to balance efficiency and precision in predicting the effects of mutations on these complex interactions. To overcome this limitation, we present DDMut-PPI, a deep learning model that efficiently and accurately predicts the changes in PPI binding free energy upon single and multiple point mutations. Building upon the robust siamese network architecture with graph-based signatures from our prior work, DDMut, the DDMut-PPI model was further augmented with a graph convolutional network operated on the protein interaction interface. We employed the ProtT5 protein language model to provide residue-specific embeddings as node features, and a variety of molecular interactions serve as edge features. By integrating evolutionary context with spatial information, this framework enables DDMut-PPI to achieve a robust Pearson correlation of up to 0.75 (RMSE: 1.33 kcal/mol) in our evaluations, outperforming most existing methods. Importantly, the model demonstrated consistent performance across mutations that increase or decrease binding affinity. DDMut-PPI offers a significant advancement in the field and will serve as a valuable tool for researchers probing the complexities of protein interactions.