Protein binding affinity prediction under multiple substitutions applying eGNNs on Residue and Atomic graphs combined with Language model information: eGRAL
This work addresses the challenge of accurate in-silico prediction of protein binding affinity changes, which is crucial for biological modeling and re-engineering, but it appears incremental as it builds on existing deep learning and graph neural network approaches.
The paper tackles the problem of predicting binding affinity changes in protein-protein interactions under multiple amino acid substitutions by proposing eGRAL, an SE(3) equivariant graph neural network that combines residue, atomic, and language model features, achieving results on a simulated dataset of about 500,000 data points and experimental data.
Protein-protein interactions (PPIs) play a crucial role in numerous biological processes. Developing methods that predict binding affinity changes under substitution mutations is fundamental for modelling and re-engineering biological systems. Deep learning is increasingly recognized as a powerful tool capable of bridging the gap between in-silico predictions and in-vitro observations. With this contribution, we propose eGRAL, a novel SE(3) equivariant graph neural network (eGNN) architecture designed for predicting binding affinity changes from multiple amino acid substitutions in protein complexes. eGRAL leverages residue, atomic and evolutionary scales, thanks to features extracted from protein large language models. To address the limited availability of large-scale affinity assays with structural information, we generate a simulated dataset comprising approximately 500,000 data points. Our model is pre-trained on this dataset, then fine-tuned and tested on experimental data.