語言模型會夢見分子結合嗎？在空間約束下評估大型語言模型

摘要

基於結構的藥物設計（SBDD）利用蛋白質標靶的3D結構，並常輔以其他空間約束條件，以生成候選結合分子。儘管擴散模型長期主導高品質3D分子生成領域，基於大型語言模型（LLM）的方法正迅速崛起，在口袋條件下的分子生成中展現出競爭力。然而，這類方法在物理與3D空間環境推理方面的潛力尚未被充分探索。在本研究中，我們系統性地分析當前通用LLM是否能夠處理複雜的3D約束條件，並與專業擴散模型等既有基準進行比較。我們考量基於蛋白質口袋的3D配體生成，同時納入源自配體與交互作用的空間約束，包含錨定片段、藥效團點以及必備的口袋-配體交互作用。為實現此評估，我們提出3D-Fit——一種標記高效的基準測試策略，用於評估LLM在多條件空間分子生成中的表現。我們的研究結果揭示了LLM在空間能力上的明確規律：雖然仍落後於最先進的方法，但展現出潛力，能同時處理多種空間約束條件，從而可擴展至異質性設定。

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.