用早期融合让大模型理解蛋白质序列与结构，提升问答准确率。
Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure
- 将序列和结构信息统一编码，通过虚拟标记实现文本与蛋白信息早期融合。
- 在两个数据集上表现优于现有方法，零样本预测也展现强泛化能力。
- 适配性强，适合需要蛋白质功能问答的生物医学研究者使用。
蛋白质在生命体中具有重要意义，但其功能理解面临多模态信息整合不足、参数量大、分类方法灵活性差及蛋白质问答系统缺乏系统评估指标等挑战。为此，我们提出Prot2Chat框架。该框架改造ProteinMPNN，统一编码蛋白质序列与结构信息；采用大语言模型（LLM）将问题向量化，并设计蛋白-文本适配器，基于这些向量将蛋白信息压缩为虚拟标记，实现文本与蛋白信息的早期融合。最终由同一LLM读取虚拟标记与问题生成答案。为提高训练效率，冻结编码器并使用低秩适应（LoRA）技术微调LLM。在两个数据集上的实验表明，自动评估与专家评价均显示本模型性能优越，零样本预测结果凸显其泛化能力。模型与代码已公开于https://github.com/wangzc1233/Prot2Chat。联系人：[email protected] 或 [email protected]。
原文摘要 · Abstract (English)
Motivation: Proteins are of great significance in living organisms. However, understanding their functions encounters numerous challenges, such as insufficient integration of multimodal information, a large number of training parameters, limited flexibility of classification-based methods, and the lack of systematic evaluation metrics for protein Q&A systems. To tackle these issues, we propose the Prot2Chat framework. Results: We modified ProteinMPNN to encode protein sequence and structural information in a unified way. We used a large language model (LLM) to encode questions into vectors and developed a protein-text adapter to compress protein information into virtual tokens based on these vectors, achieving the early fusion of text and protein information. Finally, the same LLM reads the virtual tokens and the questions to generate answers. To optimize training efficiency, we froze the encoder and employed Low-Rank Adaptation (LoRA) techniques for the LLM. Experiments on two datasets show that both automated metrics and expert evaluations demonstrate the superior performance of our model, and zero-shot prediction results highlight its generalization ability. The models and codes are available at https://github.com/ wangzc1233/Prot2Chat. Contact: [email protected] or [email protected] Key words: Protein Q&A, Early-Fusion, LLM
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。