DualBind: A Dual-Loss Framework for Protein-Ligand Binding Affinity Prediction

TL;DR

DualBind is a novel framework combining supervised and unsupervised learning techniques to improve the accuracy and generalizability of protein-ligand binding affinity predictions, effectively utilizing both labeled and unlabeled data.

Contribution

It introduces a dual-loss framework that integrates MSE and DSM, addressing limitations of existing methods and enhancing affinity prediction accuracy.

Findings

Outperforms existing models in affinity prediction accuracy

Utilizes both labeled and unlabeled data effectively

Improves generalizability of binding affinity models

Abstract

Accurate prediction of protein-ligand binding affinities is crucial for drug development. Recent advances in machine learning show promising results on this task. However, these methods typically rely heavily on labeled data, which can be scarce or unreliable, or they rely on assumptions like Boltzmann-distributed data that may not hold true in practice. Here, we present DualBind, a novel framework that integrates supervised mean squared error (MSE) with unsupervised denoising score matching (DSM) to accurately learn the binding energy function. DualBind not only addresses the limitations of DSM-only models by providing more accurate absolute affinity predictions but also improves generalizability and reduces reliance on labeled data compared to MSE-only models. Our experimental results demonstrate that DualBind excels in predicting binding affinities and can effectively utilize both labeled and unlabeled data to enhance performance.