@inproceedings{xiao-etal-2026-stella,
title = "{STELLA}: A Multimodal {LLM} for Protein Functional Annotation via Unified Sequence-Structure Encoding",
author = "Xiao, Hongwang and
Lin, Wenjun and
Chen, Xi and
Wang, Hui and
Chen, Kai and
Li, Jiashan and
Sun, Yuancheng and
Dai, Sicheng and
Wu, Boya and
Ye, Qiwei",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1254/",
pages = "25030--25049",
ISBN = "979-8-89176-395-1",
abstract = "Understanding the intricate interplay among sequence, structure, and function remains a fundamental challenge in proteomics. The sequence-structure-function paradigm posits that biological roles are governed by the tertiary geometric conformations encoded within primary sequences; consequently, integrating these multi-modal descriptors is imperative for accurate functional annotation. While protein language models (pLMs) have achieved significant progress via representation learning on massive sequence data, they often lack the capacity to incorporate high-resolution structural information and the rich textual context that characterizes protein roles. In this work, we present STELLA, a multimodal LLM that synergistically aligns bimodal (sequence-structure) representations with the textual modality to advance protein functional annotation. By leveraging ESM3 for unified bimodal encoding and Llama-3.1-8B-Instruct for natural language modeling, STELLA achieves state-of-the-art performance in two critical tasks: Functional Description Prediction and Enzyme-catalyzed Reaction Prediction. This study demonstrates that multimodal LLMs represent a paradigm shift beyond pure pLMs, offering a new frontier for protein biology and biomedical discovery. The codes can be accessed via https://github.com/ocx-lab/STELLA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2026-stella">
<titleInfo>
<title>STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongwang</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjun</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiashan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuancheng</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sicheng</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boya</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiwei</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Understanding the intricate interplay among sequence, structure, and function remains a fundamental challenge in proteomics. The sequence-structure-function paradigm posits that biological roles are governed by the tertiary geometric conformations encoded within primary sequences; consequently, integrating these multi-modal descriptors is imperative for accurate functional annotation. While protein language models (pLMs) have achieved significant progress via representation learning on massive sequence data, they often lack the capacity to incorporate high-resolution structural information and the rich textual context that characterizes protein roles. In this work, we present STELLA, a multimodal LLM that synergistically aligns bimodal (sequence-structure) representations with the textual modality to advance protein functional annotation. By leveraging ESM3 for unified bimodal encoding and Llama-3.1-8B-Instruct for natural language modeling, STELLA achieves state-of-the-art performance in two critical tasks: Functional Description Prediction and Enzyme-catalyzed Reaction Prediction. This study demonstrates that multimodal LLMs represent a paradigm shift beyond pure pLMs, offering a new frontier for protein biology and biomedical discovery. The codes can be accessed via https://github.com/ocx-lab/STELLA.</abstract>
<identifier type="citekey">xiao-etal-2026-stella</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1254/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>25030</start>
<end>25049</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding
%A Xiao, Hongwang
%A Lin, Wenjun
%A Chen, Xi
%A Wang, Hui
%A Chen, Kai
%A Li, Jiashan
%A Sun, Yuancheng
%A Dai, Sicheng
%A Wu, Boya
%A Ye, Qiwei
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F xiao-etal-2026-stella
%X Understanding the intricate interplay among sequence, structure, and function remains a fundamental challenge in proteomics. The sequence-structure-function paradigm posits that biological roles are governed by the tertiary geometric conformations encoded within primary sequences; consequently, integrating these multi-modal descriptors is imperative for accurate functional annotation. While protein language models (pLMs) have achieved significant progress via representation learning on massive sequence data, they often lack the capacity to incorporate high-resolution structural information and the rich textual context that characterizes protein roles. In this work, we present STELLA, a multimodal LLM that synergistically aligns bimodal (sequence-structure) representations with the textual modality to advance protein functional annotation. By leveraging ESM3 for unified bimodal encoding and Llama-3.1-8B-Instruct for natural language modeling, STELLA achieves state-of-the-art performance in two critical tasks: Functional Description Prediction and Enzyme-catalyzed Reaction Prediction. This study demonstrates that multimodal LLMs represent a paradigm shift beyond pure pLMs, offering a new frontier for protein biology and biomedical discovery. The codes can be accessed via https://github.com/ocx-lab/STELLA.
%U https://aclanthology.org/2026.findings-acl.1254/
%P 25030-25049
Markdown (Informal)
[STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding](https://aclanthology.org/2026.findings-acl.1254/) (Xiao et al., Findings 2026)
ACL
- Hongwang Xiao, Wenjun Lin, Xi Chen, Hui Wang, Kai Chen, Jiashan Li, Yuancheng Sun, Sicheng Dai, Boya Wu, and Qiwei Ye. 2026. STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding. In Findings of the Association for Computational Linguistics: ACL 2026, pages 25030–25049, San Diego, California, United States. Association for Computational Linguistics.