Learning Interpretable Tumor Microenvironment Representations by Fitting Pan-Cancer Cell State-Niche Correlation
Abstract
In the tumor microenvironment, a cell's state is influenced by cell-cell interactions (CCIs) with neighboring cells in its niches. Identifying dysregulated CCIs that are associated with pathogenic processes pinpoints targets for drug discovery. Imaging-based spatial transcriptomics and single-cell RNA sequencing provide, respectively, single-cell spatial information and transcriptome-wide measurements needed to study CCIs, but neither modality provides both. Existing spatial transcriptomics foundation models also cannot effectively learn from spatially resolved single-cell data with full-transcriptome coverage, explicitly infer the CCI mechanisms driving cell state-niche associations, or be interpretable enough to support direct biological interpretations. Here, we present GITIII-scale, a hierarchical, interpretable pan-cancer spatial transcriptomics foundation model for TME representation learning that investigates cell state-niche associations and their underlying ligand-receptor (LR) signaling pathways. GITIII-scale uses transformers to model interactions between pairs of cells at defined spatial distances, an interpretable single-layer graph transformer without a feed-forward network to decompose how each gene in a receiver cell is influenced by each neighboring sender cell, and a graph transformer to generate cellular-neighborhood embeddings. Trained on our assembled pan-cancer database of specimen-matched scRNA-seq and imaging-based spatial transcriptomics datasets, GITIII-scale generated TME embeddings that recovered niche-associated state changes more accurately than existing spatial transcriptomics foundation models in cancer types unseen during training. A case study of an unseen breast cancer dataset further demonstrated the model's interpretability by identifying potentially drug-targetable LR pathways associated with endothelial overgrowth and tumorigenesis.
Related
- FloREN: Decoding Immune Regulatory Networks through Interpretable Graph Transformer Patient Representations
- Between patterns and predictions: Interpretable latent EEG representations for clinical insights.
- Interpretable Machine Learning Links Group-Specific Plasma Proteomics to Regional Structural Neuroimaging in Alzheimer's Disease
- BiomECG: Learning Transferable ECG Representations from Small Cohorts
- Intrinsic dimensionality of deep learning representations reveals cell death-associated heterogeneity in Parkinsons disease iPSC-derived neurons
BibTeX
@misc{xiao2026learning,
title = {{Learning Interpretable Tumor Microenvironment Representations by Fitting Pan-Cancer Cell State-Niche Correlation}},
author = {Xiao Xiao and Jiashu He and Shiyang Zhang and Marissa Mao},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.26208},
eprint = {2608.26208},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.26208},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning Interpretable Tumor Microenvironment Representations by Fitting Pan-Cancer Cell State-Niche Correlation
AU - Xiao Xiao
AU - Jiashu He
AU - Shiyang Zhang
AU - Marissa Mao
PY - 2026
DA - 2026/09/26
PB - arXiv
DO - 10.48550/arxiv.2608.26208
UR - https://arxiv.org/abs/2608.26208
AB - In the tumor microenvironment, a cell's state is influenced by cell-cell interactions (CCIs) with neighboring cells in its niches. Identifying dysregulated CCIs that are associated with pathogenic processes pinpoints targets for drug discovery. Imaging-based spatial transcriptomics and single-cell RNA sequencing provide, respectively, single-cell spatial information and transcriptome-wide measurements needed to study CCIs, but neither modality provides both. Existing spatial transcriptomics foundation models also cannot effectively learn from spatially resolved single-cell data with full-transcriptome coverage, explicitly infer the CCI mechanisms driving cell state-niche associations, or be interpretable enough to support direct biological interpretations. Here, we present GITIII-scale, a hierarchical, interpretable pan-cancer spatial transcriptomics foundation model for TME representation learning that investigates cell state-niche associations and their underlying ligand-receptor (LR) signaling pathways. GITIII-scale uses transformers to model interactions between pairs of cells at defined spatial distances, an interpretable single-layer graph transformer without a feed-forward network to decompose how each gene in a receiver cell is influenced by each neighboring sender cell, and a graph transformer to generate cellular-neighborhood embeddings. Trained on our assembled pan-cancer database of specimen-matched scRNA-seq and imaging-based spatial transcriptomics datasets, GITIII-scale generated TME embeddings that recovered niche-associated state changes more accurately than existing spatial transcriptomics foundation models in cancer types unseen during training. A case study of an unseen breast cancer dataset further demonstrated the model's interpretability by identifying potentially drug-targetable LR pathways associated with endothelial overgrowth and tumorigenesis.
ER -