Learning Context-aware Structural Representations to Predict Antigen and Antibody Binding Interfaces

Abstract

Understanding how antibodies specifically interact with their antigens can enable better drug and vaccine design, as well as provide insights into natural immunity. Experimental structural characterization can detail the \"ground truth\" of antibody-antigen interactions, but computational methods are required to efficiently scale to large-scale studies. In order to increase prediction accuracy as well as to provide a means to gain new biological insights into these interactions, we have developed a unified deep learning-based framework to predict binding interfaces on both antibodies and antigens. The framework leverages three key aspects of antibody-antigen interactions in order to learn predictive structural representations: (1) since interfaces are formed from multiple residues in spatial proximity, we employ graph convolutions to aggregate properties across local regions in a protein; (2) since interactions are specific between antibody-antigen pairs, we employ an attention layer to explicitly encode the context of the partner; (3) since more data is available for general protein-protein interactions, we employ transfer learning to leverage this data as a prior for the specific case of antibody-antigen interactions. We show that this single framework achieves state-of-the-art performance at predicting binding interfaces on both antibodies and antigens, and that each of its three aspects drives additional improvement in the performance. We further show that the attention layer not only improves performance, but also provides a biologically interpretable perspective into the mode of interaction.