AI Agent 自动识别药物可靶向蛋白位点，兼顾生物可及性与药物类型适配。
Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
- 基于多模态证据的智能代理，自动推荐可靶向区域。
- 输出排序位点列表、风险提示和可追溯决策日志。
- 适合新药研发中筛选膜蛋白靶点，尤其关注可及性与修饰影响。
选择在蛋白上干预的位置（即可靶向位点）常比选择结合物更模糊且易失败，尤其是膜蛋白，其可及性、拓扑结构及翻译后修饰（PTMs）限制了可行区域。我们提出 Site4Drug，一个模态感知的位点发现智能体，可输出带显式约束、证据摘要、风险标记和可追溯决策日志的可靶向区域排名列表。该模型无需用户预先指定药物模态，能从同一套证据中同时推断出合适结合模态（如抗体/肽类或小分子），证据包括拓扑结构、疏水性、PTM倾向、二硫键、结构域上下文及序列特征。关键的是，这些证据在所有模态下保持一致应用，避免选出化学上可行但生物学上被遮蔽的位点，包括小分子口袋发现任务。
原文摘要 · Abstract (English)
Selecting where to intervene on a protein (i.e., choosing a targetable site) is often a more ambiguous and failure-prone bottleneck than selecting what binds, especially for membrane proteins where accessibility, topology, and post-translational modifications (PTMs) constrain actionable regions. We present Site4Drug, a modality-aware site-finding agent that outputs a ranked list of targetable regions with explicit constraints, evidence summaries, risk flags, and a traceable decision log. Rather than requiring users to specify the drug modality upfront, Site4Drug can recommend a binding modality (e.g., antibody/peptide-like vs small-molecule) from the same evidence used for site discovery, including topology, hydropathy, PTM propensity, disulfides, domain context, and sequence. Importantly, this evidence is applied consistently across modalities, including small-molecule pocket discovery, to avoid selecting chemically plausible but biologically occluded sites.
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。