Vivek Reddy Chithari

Through the RCSB.org research-focused web portal, many millions of users access rigorously validated, expertly biocurated, 3D biostructure information stored in the Protein Data Bank (PDB) archive alongside predicted Computed Structure Models (CSMs) from AlphaFold DB and ModelArchive. Specialized tools and related resources, from 3D visualization to protein annotations, allow deep exploration of this rich trove of data. The recently updated RCSB.org Advanced Search interface provides a more intuitive experience with enhanced support for 3D structure exploration. The 3D Similarity Search option is powered by a new AI-based system that is more accurate and scalable to much larger collections of structures. Additional capabilities are provided through web-based APIs and a Python API wrapper package that enable researchers to easily interact with RCSB PDB programmatic services for individually tailored analyses. These resources, together with a statistics tool, training and documentation, and the upcoming wwPDB ID and archive transition, are described.

Motivation: Structural biologists have contributed more than 260 000 experimentally determined three-dimensional structures of biological macromolecules to the Protein Data Bank. Incoming depositions are validated and biocurated by approximately 20 expert biocurators at the collaborating data centers worldwide. Biocurators at the Research Collaboratory for Structural Bioinformatics Protein Data Bank, who process more than 40% of global depositions, face growing difficulty sustaining efficient Help Desk operations, having received roughly 19 000 depositor messages across some 8000 entries in 2025. Results: We developed an artificial intelligence Help Desk assistant built on retrieval-augmented generation. Source documents are converted to Markdown with layout preserved, divided by a two-stage chunking procedure, embedded, and stored in a relational vector database. At query time, maximal marginal relevance retrieval selects diverse supporting passages, a topical guardrail filters out-of-scope questions, and a purpose-built system prompt prevents disclosure of internal curation terminology. Separate language model configurations handle question condensing and answer generation. The service runs in production on a container orchestration platform, providing around-the-clock depositor assistance with streaming, citation-backed responses. Availability and implementation: Freely available at https://rcsb-deposit-help.rcsb.org. Source code: https://github.com/rcsb/rcsb-pdb-helpdesk (archived at Zenodo: https://doi.org/10.5281/zenodo.19560785).