Agentic AI enables cell segmentation-free cell-type inference and cell-type-guided cell segmentation in spatial transcriptomics
- 1Pusan National University
Abstract
Cell-type identification in spatial transcriptomics often relies on cell segmentation, which can introduce inaccuracies in cell boundaries and transcript assignment. Segmentation-free or cell-free methods have been developed to completely avoid cell segmentation, but inaccurate cell typing hinder accurate downstream analysis. Here, we introduce SSAF-T, a segmentation-free agentic framework that identifies cell types directly from spatial gene expression without predefined reference datasets. For the reference-free cell typing, SSAF-T incorporates CeLLMan, which employs expert-level agents for each organ to annotate cell types using a literature-grounded knowledge graph. We benchmark SSAF-T on both array-based and imaging-based spatial transcriptomics datasets in terms of accuracy, reproducibility, and scalability. We further show that SSAF-T provides an accurate cell segmentation based on the segmentation-free mapping, which ensure compatibility to existing downstream analysis ecosystem, and eventually enable quantitative analysis at single-cell level.
Related
- OncoSpot enables benchmarking of cancer spatial transcriptomics methods across tumor evolutionary modes
- Live Spatial Transcriptomics Enables Longitudinal Tissue Mapping
- MCseg: AI agent-guided workflow search for no-code cell segmentation and transcript attribution in spatial transcriptomics
- Unified cell segmentation for spatial transcriptomics via transcript reassignment
- ASTRA enables zero-shot super-resolution of spatial transcriptomics across capture geometries
BibTeX
@misc{jeong2026agentic,
title = {{Agentic AI enables cell segmentation-free cell-type inference and cell-type-guided cell segmentation in spatial transcriptomics}},
author = {Y. Jeong and H. Lee and D. Lee and H.-M. Kim and S.-H. Kim and S. Park and J. Bae and E. S. Cho and Y.-L. Choi and O. Kwon and J.-I. Kim and H. Lee and J. Park},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.05.764509},
url = {https://www.biorxiv.org/content/10.64898/2026.11.05.764509v1},
note = {CC BY-ND},
}
RIS
TY - UNPB
TI - Agentic AI enables cell segmentation-free cell-type inference and cell-type-guided cell segmentation in spatial transcriptomics
AU - Y. Jeong
AU - H. Lee
AU - D. Lee
AU - H.-M. Kim
AU - S.-H. Kim
AU - S. Park
AU - J. Bae
AU - E. S. Cho
AU - Y.-L. Choi
AU - O. Kwon
AU - J.-I. Kim
AU - H. Lee
AU - J. Park
PY - 2026
DA - 2026/11/05
PB - bioRxiv
DO - 10.64898/2026.11.05.764509
UR - https://www.biorxiv.org/content/10.64898/2026.11.05.764509v1
AB - Cell-type identification in spatial transcriptomics often relies on cell segmentation, which can introduce inaccuracies in cell boundaries and transcript assignment. Segmentation-free or cell-free methods have been developed to completely avoid cell segmentation, but inaccurate cell typing hinder accurate downstream analysis. Here, we introduce SSAF-T, a segmentation-free agentic framework that identifies cell types directly from spatial gene expression without predefined reference datasets. For the reference-free cell typing, SSAF-T incorporates CeLLMan, which employs expert-level agents for each organ to annotate cell types using a literature-grounded knowledge graph. We benchmark SSAF-T on both array-based and imaging-based spatial transcriptomics datasets in terms of accuracy, reproducibility, and scalability. We further show that SSAF-T provides an accurate cell segmentation based on the segmentation-free mapping, which ensure compatibility to existing downstream analysis ecosystem, and eventually enable quantitative analysis at single-cell level.
ER -