SPIN: SE(3)-Invariant Physics Informed Network for Binding Affinity Prediction

TL;DR

SPIN is a novel SE(3)-invariant physics-informed neural network that improves protein-ligand binding affinity prediction by incorporating geometric and physicochemical biases, leading to better generalization and practical drug discovery applications.

Contribution

The paper introduces SPIN, a physics-informed neural network that integrates geometric and physicochemical biases to enhance binding affinity prediction accuracy and generalization.

Findings

Outperforms existing models on CASF-2016 and CSAR HiQ benchmarks.

Demonstrates effectiveness in virtual screening tasks.

Validated through interpretability and reliability assessments.

Abstract

Accurate prediction of protein-ligand binding affinity is crucial for rapid and efficient drug development. Recently, the importance of predicting binding affinity has led to increased attention on research that models the three-dimensional structure of protein-ligand complexes using graph neural networks to predict binding affinity. However, traditional methods often fail to accurately model the complex's spatial information or rely solely on geometric features, neglecting the principles of protein-ligand binding. This can lead to overfitting, resulting in models that perform poorly on independent datasets and ultimately reducing their usefulness in real drug development. To address this issue, we propose SPIN, a model designed to achieve superior generalization by incorporating various inductive biases applicable to this task, beyond merely training on empirical data from datasets. For prediction, we defined two types of inductive biases: a geometric perspective that maintains consistent binding affinity predictions regardless of the complexs rotations and translations, and a physicochemical perspective that necessitates minimal binding free energy along their reaction coordinate for effective protein-ligand binding. These prior knowledge inputs enable the SPIN to outperform comparative models in benchmark sets such as CASF-2016 and CSAR HiQ. Furthermore, we demonstrated the practicality of our model through virtual screening experiments and validated the reliability and potential of our proposed model based on experiments assessing its interpretability.