Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.01918 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909633259503616 |
|---|---|
| author | Chen, Chi-Jane Chen, Yuhang Yun, Sukwon Stanley, Natalie Chen, Tianlong |
| author_facet | Chen, Chi-Jane Chen, Yuhang Yun, Sukwon Stanley, Natalie Chen, Tianlong |
| contents | Image mass cytometry (IMC) enables high-dimensional spatial profiling by combining mass cytometry's analytical power with spatial distributions of cell phenotypes. Recent studies leverage large language models (LLMs) to extract cell states by translating gene or protein expression into biological context. However, existing single-cell LLMs face two major challenges: (1) Integration of spatial information: they struggle to generalize spatial coordinates and effectively encode spatial context as text, and (2) Treating each cell independently: they overlook cell-cell interactions, limiting their ability to capture biological relationships. To address these limitations, we propose Spatial2Sentence, a novel framework that integrates single-cell expression and spatial information into natural language using a multi-sentence approach. Spatial2Sentence constructs expression similarity and distance matrices, pairing spatially adjacent and expressionally similar cells as positive pairs while using distant and dissimilar cells as negatives. These multi-sentence representations enable LLMs to learn cellular interactions in both expression and spatial contexts. Equipped with multi-task learning, Spatial2Sentence outperforms existing single-cell LLMs on preprocessed IMC datasets, improving cell-type classification by 5.98% and clinical status prediction by 4.18% on the diabetes dataset while enhancing interpretability. The source code can be found here: https://github.com/UNITES-Lab/Spatial2Sentence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01918 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spatial Coordinates as a Cell Language: A Multi-Sentence Framework for Imaging Mass Cytometry Analysis Chen, Chi-Jane Chen, Yuhang Yun, Sukwon Stanley, Natalie Chen, Tianlong Computation and Language Image mass cytometry (IMC) enables high-dimensional spatial profiling by combining mass cytometry's analytical power with spatial distributions of cell phenotypes. Recent studies leverage large language models (LLMs) to extract cell states by translating gene or protein expression into biological context. However, existing single-cell LLMs face two major challenges: (1) Integration of spatial information: they struggle to generalize spatial coordinates and effectively encode spatial context as text, and (2) Treating each cell independently: they overlook cell-cell interactions, limiting their ability to capture biological relationships. To address these limitations, we propose Spatial2Sentence, a novel framework that integrates single-cell expression and spatial information into natural language using a multi-sentence approach. Spatial2Sentence constructs expression similarity and distance matrices, pairing spatially adjacent and expressionally similar cells as positive pairs while using distant and dissimilar cells as negatives. These multi-sentence representations enable LLMs to learn cellular interactions in both expression and spatial contexts. Equipped with multi-task learning, Spatial2Sentence outperforms existing single-cell LLMs on preprocessed IMC datasets, improving cell-type classification by 5.98% and clinical status prediction by 4.18% on the diabetes dataset while enhancing interpretability. The source code can be found here: https://github.com/UNITES-Lab/Spatial2Sentence. |
| title | Spatial Coordinates as a Cell Language: A Multi-Sentence Framework for Imaging Mass Cytometry Analysis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.01918 |