ToxBench: A Binding Affinity Prediction Benchmark with AB-FEP-Calculated Labels for Human Estrogen Receptor Alpha

2025-07-11

AI Summary

Protein–ligand binding affinity prediction faces a dual bottleneck: high-accuracy physical methods (e.g., alchemical free-energy perturbation, AB-FEP) incur prohibitive computational cost, while machine learning (ML) models are limited by scarcity of high-quality experimental or computed labels. To address this, we introduce ToxBench—the first large-scale, AB-FEP–derived benchmark dataset specifically for human estrogen receptor α (ERα), comprising 8,770 protein–ligand complexes and employing ligand-wise non-overlapping splits to ensure rigorous generalization evaluation. We further propose DualBind, a novel ML framework integrating structural inputs with physics-informed consistency constraints via a dual-loss objective. On ToxBench, DualBind achieves a root-mean-square error (RMSE) of 1.75 kcal/mol—matching AB-FEP accuracy at negligible computational cost. This work establishes a new paradigm for high-throughput, accurate binding affinity prediction in toxicity assessment and drug discovery.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Human-in-the-loop Machine Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Protein-ligand binding affinity prediction is essential for drug discovery and toxicity assessment. While machine learning (ML) promises fast and accurate predictions, its progress is constrained by the availability of reliable data. In contrast, physics-based methods such as absolute binding free energy perturbation (AB-FEP) deliver high accuracy but are computationally prohibitive for high-throughput applications. To bridge this gap, we introduce ToxBench, the first large-scale AB-FEP dataset designed for ML development and focused on a single pharmaceutically critical target, Human Estrogen Receptor Alpha (ER$α$). ToxBench contains 8,770 ER$α$-ligand complex structures with binding free energies computed via AB-FEP with a subset validated against experimental affinities at 1.75 kcal/mol RMSE, along with non-overlapping ligand splits to assess model generalizability. Using ToxBench, we further benchmark state-of-the-art ML methods, and notably, our proposed DualBind model, which employs a dual-loss framework to effectively learn the binding energy function. The benchmark results demonstrate the superior performance of DualBind and the potential of ML to approximate AB-FEP at a fraction of the computational cost.

Problem

• Bridging ML and physics-based binding affinity prediction gaps
• Providing reliable AB-FEP data for Human ERα target
• Assessing ML model generalizability with non-overlapping ligands

Innovation

• Large-scale AB-FEP dataset for ML development
• DualBind model with dual-loss framework
• Benchmarking ML methods for binding affinity