构建统一的全原子分子生成框架，提升结构生物学建模与药物设计效率。
PharMolixFM: All-Atom Foundation Models for Molecular Modeling and Generation
- 基于多模态生成技术，将分子任务统一为带先验的去噪过程。
- 蛋白-小分子对接预测准确率达83.9%，推理速度显著提升。
- 支持可扩展采样策略，适合药物发现与结构生物学研究者使用。
结构生物学依赖精确的三维生物分子结构来深化对生物功能、疾病机制及治疗手段的理解。尽管深度学习进展推动了全原子基础模型在分子建模与生成中的应用，现有方法因原子数据的多模态特性及训练与采样策略分析不足，面临泛化能力差的问题。为此，我们提出PharMolixFM，一个基于多模态生成技术的统一框架，用于构建全原子基础模型。该框架包含三种采用前沿多模态生成模型的变体。通过将分子任务形式化为带有任务特定先验的广义去噪过程，PharMolixFM在多种结构生物学应用中实现稳健性能。实验表明，PharMolixFM-Diff在蛋白-小分子对接任务中达到83.9%的预测准确率（给定结合口袋时RMSD < 2Å），且推理速度显著提升。此外，我们通过引入更多采样重复或步骤，探索了经验推理缩放规律。代码与模型已开源：https://github.com/PharMolix/OpenBioMed。
原文摘要 · Abstract (English)
Structural biology relies on accurate three-dimensional biomolecular structures to advance our understanding of biological functions, disease mechanisms, and therapeutics. While recent advances in deep learning have enabled the development of all-atom foundation models for molecular modeling and generation, existing approaches face challenges in generalization due to the multi-modal nature of atomic data and the lack of comprehensive analysis of training and sampling strategies. To address these limitations, we propose PharMolixFM, a unified framework for constructing all-atom foundation models based on multi-modal generative techniques. Our framework includes three variants using state-of-the-art multi-modal generative models. By formulating molecular tasks as a generalized denoising process with task-specific priors, PharMolixFM achieves robust performance across various structural biology applications. Experimental results demonstrate that PharMolixFM-Diff achieves competitive prediction accuracy in protein-small-molecule docking (83.9% vs. 90.2% RMSD < 2Å, given pocket) with significantly improved inference speed. Moreover, we explore the empirical inference scaling law by introducing more sampling repeats or steps. Our code and model are available at https://github.com/PharMolix/OpenBioMed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。