BioLM-Score：基于语言先验的概率几何势用于蛋白质-配体评分
BioLM-Score: Language-Prior Conditioned Probabilistic Geometric Potentials for Protein-Ligand Scoring
AI总结：
BioLM-Score结合几何建模与表征学习，提供一种高效、可泛化且可解释的蛋白质-配体评分方法，提升药物发现效率。
摘要：
蛋白质-配体评分是基于结构的药物设计中的核心组成部分，支撑着分子对接、虚拟筛选和构象优化。传统的物理基能量函数往往计算成本高，限制了其在大规模筛选中的应用。相比之下，基于深度学习的评分模型虽然计算效率更高，但通常存在跨目标泛化能力有限和可解释性差的问题，限制了其实际应用。本文提出了BioLM-Score，一种简单但具有泛化能力的蛋白质-配体评分模型，结合了几何建模与表征学习。具体来说，它使用针对不同模态和结构感知的编码器对蛋白质和配体进行编码，每个编码器都增强有生物分子语言模型以丰富结构和化学表征。随后，这些表征通过混合密度网络整合，以预测多模态的原子间距离分布，从而推导出基于统计的似然评分。在CASF-2016基准测试中，BioLM-Score在对接、评分、排序和筛选任务中均实现了显著提升。此外，所提出的评分函数为指导对接协议和构象搜索提供了有效的优化目标。总之，BioLM-Score为现有的评分函数提供了一个原理上可行且实用的替代方案，结合了效率、泛化能力和可解释性，用于基于结构的药物发现。
英文摘要：
Protein-ligand scoring is a central component of structure-based drug design, underpinning molecular docking, virtual screening, and pose optimization. Conventional physics-based energy functions are often computationally expensive, limiting their utility in large-scale screening. In contrast, deep learning-based scoring models offer improved computational efficiency but frequently suffer from limited cross-target generalization and poor interpretability, which restrict their practical applicability. Here we present BioLM-Score, a simple yet generalizable protein-ligand scoring model that couples geometric modeling with representation learning. Specifically, it employs modality-specific and structure-aware encoders for proteins and ligands, each augmented with biomolecular language models to enrich structural and chemical representations. Subsequently, these representations are integrated through a mixture density network to predict multimodal interatomic distance distributions, from which statistically grounded likelihood-based scores are derived. Evaluations on the CASF-2016 benchmark demonstrate that BioLM-Score achieves significant improvements across docking, scoring, ranking, and screening tasks. Moreover, the proposed scoring function serves as an effective optimization objective for guiding docking protocols and conformational search. In summary, BioLM-Score provides a principled and practical alternative to existing scoring functions, combining efficiency, generalization, and interpretability for structure-based drug discovery.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
