@inproceedings{wei-etal-2025-identifying,
title = "Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models",
author = "Wei, Huanhuan and
Luo, Xiao and
Yu, Hongyi and
Liang, Jinping and
Yang, Luning and
Lin, Lixing and
Popa, Alexandra and
Yan, Xiting",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.455/",
doi = "10.18653/v1/2025.acl-long.455",
pages = "9275--9289",
ISBN = "979-8-89176-251-0",
abstract = "Spatial transcriptomic technologies enable measuring gene expression profile and spatial information of cells in tissues simultaneously. Clustering of captured cells/spots in the spatial transcriptomic data is crucial for understanding tissue niches and uncovering disease-related changes.Current methods to cluster spatial transcriptomic data encounter obstacles, including inefficiency in handling multi-replicate data, lack of prior knowledge incorporation, and producing uninterpretable cluster labels.We introduce a novel approach, LLMiniST, to identify spatial niche using a zero-shot large language models (LLMs) by transforming spatial transcriptomic data into spatial context prompts, leveraging gene expression of neighboring cells/spots, cell type composition, tissue information, and external knowledge. The model was further enhanced using a two-stage fine-tuning strategy for improved generalizability. We also develop a user-friendly annotation tool to accelerate the creation of well-annotated spatial dataset for fine-tuning.Comprehensive method performance evaluations showed that both zero-shot and fine-tunned LLMiniST had superior performance than current non-LLM methods in many circumstances. Notably, the two-stage fine-tuning strategy facilitated substantial cross-subject generalizability. The results demonstrate the feasibility of LLMs for tissue niche identification using spatial transcriptomic data and the potential of LLMs as a scalable solution to efficiently integrate minimal human guidance for improved performance in large-scale datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2025-identifying">
<titleInfo>
<title>Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huanhuan</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinping</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luning</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lixing</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Popa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiting</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Spatial transcriptomic technologies enable measuring gene expression profile and spatial information of cells in tissues simultaneously. Clustering of captured cells/spots in the spatial transcriptomic data is crucial for understanding tissue niches and uncovering disease-related changes.Current methods to cluster spatial transcriptomic data encounter obstacles, including inefficiency in handling multi-replicate data, lack of prior knowledge incorporation, and producing uninterpretable cluster labels.We introduce a novel approach, LLMiniST, to identify spatial niche using a zero-shot large language models (LLMs) by transforming spatial transcriptomic data into spatial context prompts, leveraging gene expression of neighboring cells/spots, cell type composition, tissue information, and external knowledge. The model was further enhanced using a two-stage fine-tuning strategy for improved generalizability. We also develop a user-friendly annotation tool to accelerate the creation of well-annotated spatial dataset for fine-tuning.Comprehensive method performance evaluations showed that both zero-shot and fine-tunned LLMiniST had superior performance than current non-LLM methods in many circumstances. Notably, the two-stage fine-tuning strategy facilitated substantial cross-subject generalizability. The results demonstrate the feasibility of LLMs for tissue niche identification using spatial transcriptomic data and the potential of LLMs as a scalable solution to efficiently integrate minimal human guidance for improved performance in large-scale datasets.</abstract>
<identifier type="citekey">wei-etal-2025-identifying</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.455</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.455/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>9275</start>
<end>9289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models
%A Wei, Huanhuan
%A Luo, Xiao
%A Yu, Hongyi
%A Liang, Jinping
%A Yang, Luning
%A Lin, Lixing
%A Popa, Alexandra
%A Yan, Xiting
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F wei-etal-2025-identifying
%X Spatial transcriptomic technologies enable measuring gene expression profile and spatial information of cells in tissues simultaneously. Clustering of captured cells/spots in the spatial transcriptomic data is crucial for understanding tissue niches and uncovering disease-related changes.Current methods to cluster spatial transcriptomic data encounter obstacles, including inefficiency in handling multi-replicate data, lack of prior knowledge incorporation, and producing uninterpretable cluster labels.We introduce a novel approach, LLMiniST, to identify spatial niche using a zero-shot large language models (LLMs) by transforming spatial transcriptomic data into spatial context prompts, leveraging gene expression of neighboring cells/spots, cell type composition, tissue information, and external knowledge. The model was further enhanced using a two-stage fine-tuning strategy for improved generalizability. We also develop a user-friendly annotation tool to accelerate the creation of well-annotated spatial dataset for fine-tuning.Comprehensive method performance evaluations showed that both zero-shot and fine-tunned LLMiniST had superior performance than current non-LLM methods in many circumstances. Notably, the two-stage fine-tuning strategy facilitated substantial cross-subject generalizability. The results demonstrate the feasibility of LLMs for tissue niche identification using spatial transcriptomic data and the potential of LLMs as a scalable solution to efficiently integrate minimal human guidance for improved performance in large-scale datasets.
%R 10.18653/v1/2025.acl-long.455
%U https://aclanthology.org/2025.acl-long.455/
%U https://doi.org/10.18653/v1/2025.acl-long.455
%P 9275-9289
Markdown (Informal)
[Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models](https://aclanthology.org/2025.acl-long.455/) (Wei et al., ACL 2025)
ACL
- Huanhuan Wei, Xiao Luo, Hongyi Yu, Jinping Liang, Luning Yang, Lixing Lin, Alexandra Popa, and Xiting Yan. 2025. Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9275–9289, Vienna, Austria. Association for Computational Linguistics.