@inproceedings{ibtehaz-kihara-2026-protein,
title = "Protein-{STORY}: Semantic Text-Oriented Representation Yields biologically meaningful Protein embeddings",
author = "Ibtehaz, Nabil and
Kihara, Daisuke",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-short.73/",
pages = "883--897",
ISBN = "979-8-89176-391-3",
abstract = "Unsupervised representation learning using masked language modeling on the language of life has transformed protein research, enabling the analysis of a protein universe that is expanding at an exponential pace. However, most current models rely solely on sequence data, overlooking decades of expert-curated biological knowledge stored in natural language. While recent multimodal and knowledge-graph-based approaches attempt to bridge this gap, they often rely on shallow functional labels that lack the contextual depth of full textual narratives. We present Protein-STORY, a general pipeline that synthesizes protein embeddings from diverse, multi-source text descriptions. At the core of our approach is a novel network architecture designed for the semantic compression of multi document embeddings, which integrates high-fidelity functional and structural insights into a unified representation. Our experiments demonstrate that Protein-STORY produces biologically meaningful embeddings ($r \approx 0.75$) that outperform existing models on diverse downstream tasks (+2 pts F1 in function prediction). Furthermore, by projecting the story of a protein into a natural language semantic space, our model enables effective zero-shot text-prompted protein search."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ibtehaz-kihara-2026-protein">
<titleInfo>
<title>Protein-STORY: Semantic Text-Oriented Representation Yields biologically meaningful Protein embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nabil</namePart>
<namePart type="family">Ibtehaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Kihara</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</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">979-8-89176-391-3</identifier>
</relatedItem>
<abstract>Unsupervised representation learning using masked language modeling on the language of life has transformed protein research, enabling the analysis of a protein universe that is expanding at an exponential pace. However, most current models rely solely on sequence data, overlooking decades of expert-curated biological knowledge stored in natural language. While recent multimodal and knowledge-graph-based approaches attempt to bridge this gap, they often rely on shallow functional labels that lack the contextual depth of full textual narratives. We present Protein-STORY, a general pipeline that synthesizes protein embeddings from diverse, multi-source text descriptions. At the core of our approach is a novel network architecture designed for the semantic compression of multi document embeddings, which integrates high-fidelity functional and structural insights into a unified representation. Our experiments demonstrate that Protein-STORY produces biologically meaningful embeddings (r \approx 0.75) that outperform existing models on diverse downstream tasks (+2 pts F1 in function prediction). Furthermore, by projecting the story of a protein into a natural language semantic space, our model enables effective zero-shot text-prompted protein search.</abstract>
<identifier type="citekey">ibtehaz-kihara-2026-protein</identifier>
<location>
<url>https://aclanthology.org/2026.acl-short.73/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>883</start>
<end>897</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Protein-STORY: Semantic Text-Oriented Representation Yields biologically meaningful Protein embeddings
%A Ibtehaz, Nabil
%A Kihara, Daisuke
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-391-3
%F ibtehaz-kihara-2026-protein
%X Unsupervised representation learning using masked language modeling on the language of life has transformed protein research, enabling the analysis of a protein universe that is expanding at an exponential pace. However, most current models rely solely on sequence data, overlooking decades of expert-curated biological knowledge stored in natural language. While recent multimodal and knowledge-graph-based approaches attempt to bridge this gap, they often rely on shallow functional labels that lack the contextual depth of full textual narratives. We present Protein-STORY, a general pipeline that synthesizes protein embeddings from diverse, multi-source text descriptions. At the core of our approach is a novel network architecture designed for the semantic compression of multi document embeddings, which integrates high-fidelity functional and structural insights into a unified representation. Our experiments demonstrate that Protein-STORY produces biologically meaningful embeddings (r \approx 0.75) that outperform existing models on diverse downstream tasks (+2 pts F1 in function prediction). Furthermore, by projecting the story of a protein into a natural language semantic space, our model enables effective zero-shot text-prompted protein search.
%U https://aclanthology.org/2026.acl-short.73/
%P 883-897
Markdown (Informal)
[Protein-STORY: Semantic Text-Oriented Representation Yields biologically meaningful Protein embeddings](https://aclanthology.org/2026.acl-short.73/) (Ibtehaz & Kihara, ACL 2026)
ACL