发表机构
Shanghai Jiao Tong University; School of Computer Science; Centre for Cognitive Machines and Computational Health (CMaCH)（上海交通大学; 计算机科学学院; 认知机器与计算健康中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出PepLLM框架，整合ESM与LLaMA，生成蛋白质-肽结合界面的多属性结构化注释，为可解释的蛋白质-肽界面分析建立新任务与建模范式。
AI 中文摘要
蛋白质-肽相互作用是细胞调控和肽类药物发现的核心，但现有计算方法主要聚焦于相互作用分类、结合位点预测或肽结合剂生成，这些形式对决定肽如何结合蛋白质的物理化学机制提供的见解有限。本研究引入PepLLM，这是一个用于结构化蛋白质-肽界面理解的指令微调框架。给定蛋白质-肽序列，PepLLM会生成机器可读的JSON注释，描述多种界面属性，包括肽埋藏状态、氢键密度、盐桥存在情况、热点残基、疏水性和静电互补性。为支持该任务，研究人员整合结构界面分析、溶剂可及表面积计算、疏水性埋藏估计、静电势计算以及冗余感知数据划分，构建了新的蛋白质-肽界面数据集。PepLLM通过非线性模态适配器连接预训练的ESM编码器与LLaMA解码器，经适配的ESM残基嵌入通过占位符标记替换作为连续软标记注入LLaMA提示中，使解码器能在指令微调下生成结构化界面注释。通过从单标签预测转向多属性和机制感知生成，PepLLM为可解释的蛋白质-肽界面分析建立了新任务和建模范式。
英文摘要
Protein-peptide interactions are central to cellular regulation and peptide-based drug discovery, yet existing computational methods mainly focus on interaction classification, binding-site prediction, or peptide binder generation. These formulations provide limited insight into the physicochemical mechanisms that determine how a peptide binds to a protein. In this work, we introduce \textbf{PepLLM}, an instruction-tuned framework for structured protein-peptide interface understanding. Given protein-peptide sequences, PepLLM generates a machine-readable JSON annotation describing multiple interface properties, including peptide burial state, hydrogen-bond density, salt-bridge presence, hotspot residues, hydrophobicity, and electrostatic complementarity. To support this task, we construct a new protein-peptide interface dataset by integrating structural interface analysis, solvent-accessible surface area computation, hydrophobic burial estimation, electrostatic potential calculation, and redundancy-aware data splitting. PepLLM connects a pretrained ESM encoder with a LLaMA decoder through a nonlinear modality adapter. The adapted ESM residue embeddings are injected into the LLaMA prompt as continuous soft tokens via placeholder-token replacement, enabling the decoder to generate structured interface annotations under instruction tuning. By moving beyond single-label prediction toward multi-property and mechanism-aware generation, PepLLM establishes a new task and modeling paradigm for interpretable protein-peptide interface analysis.
