FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation

2024-03-29

arXiv.org

AI Summary

Molecular docking faces bottlenecks including low efficiency of traditional physics-based simulation, inaccurate binding pocket prediction by deep learning models, and limited conformational sampling quality. FABind+ addresses these challenges with an end-to-end optimized framework: (1) a novel fine-grained pocket prediction module that significantly improves binding site localization accuracy; (2) an enhanced geometry-aware docking module integrating joint protein–ligand representation and structure-aware attention mechanisms to boost conformational generation capability; and (3) a lightweight confidence-guided sampling strategy coupled with regression-based confidence calibration, achieving substantial quality gains without sacrificing inference speed. Evaluated on multiple standard benchmarks, FABind+ outperforms its predecessor FABind and achieves competitive state-of-the-art performance in both docking accuracy and inference efficiency. The source code is publicly available.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Molecular docking is a pivotal process in drug discovery. While traditional techniques rely on extensive sampling and simulation governed by physical principles, these methods are often slow and costly. The advent of deep learning-based approaches has shown significant promise, offering increases in both accuracy and efficiency. Building upon the foundational work of FABind, a model designed with a focus on speed and accuracy, we present FABind+, an enhanced iteration that largely boosts the performance of its predecessor. We identify pocket prediction as a critical bottleneck in molecular docking and propose a novel methodology that significantly refines pocket prediction, thereby streamlining the docking process. Furthermore, we introduce modifications to the docking module to enhance its pose generation capabilities. In an effort to bridge the gap with conventional sampling/generative methods, we incorporate a simple yet effective sampling technique coupled with a confidence model, requiring only minor adjustments to the regression framework of FABind. Experimental results and analysis reveal that FABind+ remarkably outperforms the original FABind, achieves competitive state-of-the-art performance, and delivers insightful modeling strategies. This demonstrates FABind+ represents a substantial step forward in molecular docking and drug discovery. Our code is in https://github.com/QizhiPei/FABind.

Problem

• Enhances molecular docking efficiency and accuracy.
• Improves pocket prediction in drug discovery.
• Advances pose generation in docking processes.

Innovation

• Enhanced pocket prediction methodology
• Improved pose generation capabilities
• Integrated sampling and confidence model