语言模型会梦见分子结合吗？在空间约束下对LLMs进行基准测试

摘要

基于结构的药物设计（SBDD）利用蛋白质靶标的三维结构（通常辅以其他空间约束）来生成候选结合分子。尽管扩散模型作为高质量三维分子生成的主流范式占据主导地位，但基于大语言模型（LLM）的方法正快速涌现于分子设计领域，并在以口袋为条件的分子生成中展现出具有竞争力的性能。然而，这些模型在物理推理与三维空间环境理解方面的能力尚未得到充分探索。本研究系统分析了当前通用LLM在处理复杂三维约束时的表现，并将其与已建立的标准方法（如专用扩散模型）进行比较。我们聚焦于以蛋白质口袋为条件的三维配体生成任务，同时结合由配体与相互作用导出的空间约束条件，包括锚定片段、药效团点及必备的口袋-配体相互作用。为支撑该评估，我们提出3D-Fit——一种用于评估LLM在多条件空间分子生成中性能的令牌高效基准测试策略。研究结果揭示了LLM空间能力的明确模式：尽管其表现仍落后于最先进的方法，但展现出令人期待的前景，能够同时处理多个空间约束，从而支持扩展到异构设置。

English

Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial constraints, to generate candidate binding molecules. While diffusion models have dominated as a leading paradigm for high-quality 3D molecule generation, LLM-based methods are rapidly emerging in molecular design and have shown competitive performance in pocket-conditioned molecular generation. However, their ability to reason about physics and 3D spatial environments is largely underexplored. In this work, we systematically analyze whether current general-purpose LLMs are capable of navigating complex 3D constraints compared to established baselines such as specialized diffusion models. We consider 3D ligand generation conditioned on protein pockets together with ligand- and interaction-derived spatial constraints, including anchor fragments, pharmacophore points, and mandatory pocket-ligand interactions. To enable this evaluation, we introduce 3D-Fit - a token-efficient benchmarking strategy for assessing LLM performance on multi-conditioned spatial molecule generation. Our findings reveal a clear pattern in LLM spatial capabilities: while they still lag behind state-of-the-art approaches, they are promising and can handle multiple spatial constraints simultaneously, enabling scaling to heterogeneous setups.