@inproceedings{ding-etal-2026-rad,
title = "{RAD}-{PROTEIN}: Multi-source Knowledge-enriched Retrieval-augmented Protein Structure Searching",
author = "Ding, Kexin and
Biester, Alison and
Vallat, Brinda and
Shao, Chenghua and
Piehl, Dennis W and
Won, Dongwook and
Segura, Joan and
Duarte, Jose M. and
Zhou, Mu and
Feng, Zukang and
Rose, Yana and
Burley, Stephen K. and
Metaxas, Dimitris N.",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1940/",
pages = "44147--44164",
ISBN = "979-8-89176-459-0",
abstract = "The Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB) provides open access to macromolecular structures and offers an extensive structural keyword search infrastructure. However, the current RCSB PDB APIs do not support natural-language semantic search. To overcome this challenge, we propose RAD-PROTEIN, a novel multi-source knowledge-enriched Retrieval-Augmented Protein structure search system that answers user natural-language queries by jointly leveraging heterogeneous structural literature and metadata. In addition, we introduce the first benchmark for text-based protein-structure search evaluation, comprising 454 expert-verified queries. RAD-PROTEIN substantially outperforms baselines, achieving up to +19.8{\%} Recall@1 and +16.1{\%} in MRR with hybrid retrieval and multi-source knowledge enrichment. Comprehensive ablation studies further confirm the robustness of our proposed approach. Finally, we develop an interpretable interface to return top-ranked structures with LLM-generated explanations, enabling efficient human verification and downstream scientific analysis. Code: https://github.com/Cassie07/RAD{\_}PROTEIN"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2026-rad">
<titleInfo>
<title>RAD-PROTEIN: Multi-source Knowledge-enriched Retrieval-augmented Protein Structure Searching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kexin</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alison</namePart>
<namePart type="family">Biester</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brinda</namePart>
<namePart type="family">Vallat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Piehl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongwook</namePart>
<namePart type="family">Won</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joan</namePart>
<namePart type="family">Segura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Duarte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zukang</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yana</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Burley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitris</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Metaxas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>The Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB) provides open access to macromolecular structures and offers an extensive structural keyword search infrastructure. However, the current RCSB PDB APIs do not support natural-language semantic search. To overcome this challenge, we propose RAD-PROTEIN, a novel multi-source knowledge-enriched Retrieval-Augmented Protein structure search system that answers user natural-language queries by jointly leveraging heterogeneous structural literature and metadata. In addition, we introduce the first benchmark for text-based protein-structure search evaluation, comprising 454 expert-verified queries. RAD-PROTEIN substantially outperforms baselines, achieving up to +19.8% Recall@1 and +16.1% in MRR with hybrid retrieval and multi-source knowledge enrichment. Comprehensive ablation studies further confirm the robustness of our proposed approach. Finally, we develop an interpretable interface to return top-ranked structures with LLM-generated explanations, enabling efficient human verification and downstream scientific analysis. Code: https://github.com/Cassie07/RAD_PROTEIN</abstract>
<identifier type="citekey">ding-etal-2026-rad</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1940/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>44147</start>
<end>44164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RAD-PROTEIN: Multi-source Knowledge-enriched Retrieval-augmented Protein Structure Searching
%A Ding, Kexin
%A Biester, Alison
%A Vallat, Brinda
%A Shao, Chenghua
%A Piehl, Dennis W.
%A Won, Dongwook
%A Segura, Joan
%A Duarte, Jose M.
%A Zhou, Mu
%A Feng, Zukang
%A Rose, Yana
%A Burley, Stephen K.
%A Metaxas, Dimitris N.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F ding-etal-2026-rad
%X The Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB) provides open access to macromolecular structures and offers an extensive structural keyword search infrastructure. However, the current RCSB PDB APIs do not support natural-language semantic search. To overcome this challenge, we propose RAD-PROTEIN, a novel multi-source knowledge-enriched Retrieval-Augmented Protein structure search system that answers user natural-language queries by jointly leveraging heterogeneous structural literature and metadata. In addition, we introduce the first benchmark for text-based protein-structure search evaluation, comprising 454 expert-verified queries. RAD-PROTEIN substantially outperforms baselines, achieving up to +19.8% Recall@1 and +16.1% in MRR with hybrid retrieval and multi-source knowledge enrichment. Comprehensive ablation studies further confirm the robustness of our proposed approach. Finally, we develop an interpretable interface to return top-ranked structures with LLM-generated explanations, enabling efficient human verification and downstream scientific analysis. Code: https://github.com/Cassie07/RAD_PROTEIN
%U https://aclanthology.org/2026.emnlp-main.1940/
%P 44147-44164
Markdown (Informal)
[RAD-PROTEIN: Multi-source Knowledge-enriched Retrieval-augmented Protein Structure Searching](https://aclanthology.org/2026.emnlp-main.1940/) (Ding et al., EMNLP 2026)
ACL
- Kexin Ding, Alison Biester, Brinda Vallat, Chenghua Shao, Dennis W Piehl, Dongwook Won, Joan Segura, Jose M. Duarte, Mu Zhou, Zukang Feng, Yana Rose, Stephen K. Burley, and Dimitris N. Metaxas. 2026. RAD-PROTEIN: Multi-source Knowledge-enriched Retrieval-augmented Protein Structure Searching. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 44147–44164, Budapest, Hungary. Association for Computational Linguistics.