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

TL;DR

This paper presents an AI-powered Help Desk system for protein structure depositors, utilizing retrieval-augmented generation with GPT-4.1-mini to improve efficiency and response quality.

Contribution

It introduces a novel retrieval-augmented generation system tailored for biocuration support, integrating advanced document processing and filtering techniques.

Findings

System provides citation-backed, streaming responses 24/7.

Deployed on Kubernetes for reliable, continuous operation.

Handles approximately 19,000 depositor messages annually.

Abstract

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.