发表机构
City University of Hong Kong; The University of Hong Kong; Stanford University（香港城市大学; 香港大学; 斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出基于流匹配的语言知情跨模态框架LiFT，通过“感知-演化-组装”智能体和自条件解耦路由器实现趋势引导的3D分子生成，在Cross-Docked2020数据集上验证了其分布匹配、药物化学指标及结构有效性的优势。
AI 中文摘要
基于结构的药物设计（SBDD）需要配体同时满足三维靶点亲和力和一维化学有效性。现有的可控生成方法通常依赖特定任务的微调或外部施加的采样时引导，增加了成本，且可能与不断变化的三维几何约束相冲突。我们提出LiFT，这是一个基于流匹配的语言知情跨模态框架，用于从头设计和骨架跳跃的趋势引导3D分子生成。LiFT使用“感知-演化-组装”智能体生成目标感知的SMILES作为中间化学条件，预训练的化学基础模型从中提取连续语义先验。这些先验通过轻量级语义投影器整合到几何生成中，该投影器带有零初始化自适应归一化，用于稳定的跨模态条件设置。我们进一步引入自条件解耦路由器（SCDR），它在常微分方程（ODE）积分期间根据中间结构状态调制速度场。在Cross-Docked2020上的实验表明，LiFT在无需额外生成器微调的任务引导设置下，实现了有竞争力的分布匹配，同时改进了药物化学指标并保持了有竞争力的结构有效性。我们的结果表明，源自语言的化学先验为3D分子生成提供了有效的趋势级引导。代码和发布的工件可在此https URL获取。
英文摘要
Structure-based drug design (SBDD) requires ligands that satisfy both 3D target affinity and 1D chemical validity. Existing controllable generation methods often rely on task-specific fine-tuning or externally imposed sampling-time guidance, adding cost and potentially conflicting with evolving 3D geometric constraints. We propose LiFT, a language-informed cross-modal framework built on Flow Matching for trend-guided 3D molecular generation across both de novo design and scaffold hopping. LiFT uses a "Sense-Evolve-Assemble" agent to generate target-aware SMILES as intermediate chemical conditions, from which a pre-trained chemical foundation model extracts continuous semantic priors. These priors are integrated into geometric generation through a lightweight semantic projector with zero-initialized adaptive normalization for stable cross-modal conditioning. We further introduce a Self-Conditioned Decoupled Router (SCDR), which modulates the velocity field according to intermediate structural states during ODE integration. Experiments on Cross-Docked2020 show that LiFT achieves competitive distribution matching while improving medicinal chemistry metrics and maintaining competitive structural validity under task-steering settings without additional generator fine-tuning. Our results suggest that language-derived chemical priors provide effective trend-level guidance for 3D molecular generation. Code and released artifacts are available at https://github.com/kasurl/LiFT.
CommentsAccepted at Findings of EMNLP 2026
