Co-evolution-based Metal-binding Residue Prediction with Graph Neural Networks
This addresses a problem in computational structural biology for researchers studying protein-metal interactions, representing an incremental improvement by integrating co-evolutionary insights with advanced machine learning.
The paper tackled the challenge of predicting metal-binding sites and metal types in proteins by introducing MBGNN, a graph neural network that uses the entire co-evolved residue network, resulting in outperforming existing co-evolution-based methods and being competitive against sequence-based methods on a public dataset.
In computational structural biology, predicting metal-binding sites and their corresponding metal types is challenging due to the complexity of protein structures and interactions. Conventional sequence- and structure-based prediction approaches cannot capture the complex evolutionary relationships driving these interactions to facilitate understanding, while recent co-evolution-based approaches do not fully consider the entire structure of the co-evolved residue network. In this paper, we introduce MBGNN (Metal-Binding Graph Neural Network) that utilizes the entire co-evolved residue network and effectively captures the complex dependencies within protein structures via graph neural networks to enhance the prediction of co-evolved metal-binding residues and their associated metal types. Experimental results on a public dataset show that MBGNN outperforms existing co-evolution-based metal-binding prediction methods, and it is also competitive against recent sequence-based methods, showing the potential of integrating co-evolutionary insights with advanced machine learning to deepen our understanding of protein-metal interactions. The MBGNN code is publicly available at https://github.com/SRastegari/MBGNN.