arXiv 2604.228002026-04-13cs.IRcs.AIcs.CLq-bio.QM

RCSB PDB AI Help Desk：基于检索增强生成的蛋白质结构沉积支持

RCSB PDB AI Help Desk: retrieval-augmented generation for protein structure deposition support

RCSB Protein Data Bank, Rutgers, The State University of New Jersey（RCSB蛋白质数据银行，新泽西州立大学拉特格斯分校）；RCSB Protein Data Bank, San Diego Supercomputer Center, University of California San Diego（RCSB蛋白质数据银行，圣地亚哥超级计算机中心，加州大学圣地亚哥分校）

Vivek Reddy Chithari, Jasmine Y. Young, Irina Persikova, Yuhe Liang, Gregg V. Crichlow, Justin W. Flatt, Sutapa Ghosh, Brian P. Hudson, Ezra Peisach, Monica Sek… 展开作者

Vivek Reddy Chithari, Jasmine Y. Young, Irina Persikova, Yuhe Liang, Gregg V. Crichlow, Justin W. Flatt, Sutapa Ghosh, Brian P. Hudson, Ezra Peisach, Monica Sekharan, Chenghua Shao, Stephen K. Burley

备注：: 13 pages, 0 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出基于检索增强生成的AI帮助台系统，用于支持蛋白质结构沉积的验证与生物整理，通过RAG技术提升帮助台效率，实现全天候的存款人支持。

摘要：

动机：结构生物学家已向蛋白质数据银行（PDB）贡献了超过245,000个实验确定的生物大分子三维结构。 incoming数据由约20名专家生物整理员进行验证和生物整理。 RCSB PDB生物整理员处理超过全球40%的沉积物面临维持高效帮助台操作的挑战，2025年约有19,000条消息来自存款人。结果：我们开发了一个基于LangChain的AI帮助台，采用基于pgvector存储（PostgreSQL）和GPT-4.1-mini的检索增强生成（RAG）技术。系统采用pymupdf4llm进行保留Markdown的PDF提取，双阶段文档分块，最大边际相关性检索，一个主题过滤栏过滤无关查询，以及一个专门的系统提示以防止暴露内部术语。双LLM架构使用不同的模型配置进行问题浓缩和响应生成。部署在Kubernetes上，使用PostgreSQL（pgvector），提供全天候存款人支持，具有引用支持的流式响应。可用性和实现：免费提供于https://rcsb-deposit-help.rcsb.org。

英文摘要：

Motivation: Structural Biologists have contributed more than 245,000 experimentally determined three-dimensional structures of biological macromolecules to the Protein Data Bank (PDB). Incoming data are validated and biocurated by ~20 expert biocurators across the wwPDB. RCSB PDB biocurators who process more than 40% of global depositions face increasing challenges in maintaining efficient Help Desk operations, with approximately 19,000 messages in approximately 8,000 entries received from depositors in 2025. Results: We developed an AI-powered Help Desk using Retrieval-Augmented Generation (RAG) built on LangChain with a pgvector store (PostgreSQL) and GPT-4.1-mini. The system employs pymupdf4llm for Markdown-preserving PDF extraction, two-stage document chunking, Maximal Marginal Relevance retrieval, a topical guardrail that filters off-topic queries, and a specialized system prompt that prevents exposure of internal terminology. A dual-LLM architecture uses separate model configurations for question condensing and response generation. Deployed in production on Kubernetes with PostgreSQL (pgvector), it provides around-the-clock depositor assistance with citation-backed, streaming responses. Availability and implementation: Freely available at https://rcsb-deposit-help.rcsb.org.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。