Digital Modeling of Spatial Pathway Activity from Histology Reveals Tumor Microenvironment Heterogeneity
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908990531698688 |
|---|---|
| author | Liao, Ling Yang, Changhuei Artyomov, Maxim Watson, Mark Kepecs, Adam Zhou, Haowen Sergushichev, Alexey Cote, Richard |
| author_facet | Liao, Ling Yang, Changhuei Artyomov, Maxim Watson, Mark Kepecs, Adam Zhou, Haowen Sergushichev, Alexey Cote, Richard |
| contents | Spatial transcriptomics (ST) enables simultaneous mapping of tissue morphology and spatially resolved gene expression, offering unique opportunities to study tumor microenvironment heterogeneity. Here, we introduce a computational framework that predicts spatial pathway activity directly from hematoxylin-and-eosin-stained histology images at microscale resolution 55 and 100 um. Using image features derived from a computational pathology foundation model, we found that TGFb signaling was the most accurately predicted pathway across three independent breast and lung cancer ST datasets. In 87-88% of reliably predicted cases, the resulting spatial TGFb activity maps reflected the expected contrast between tumor and adjacent non-tumor regions, consistent with the known role of TGFb in regulating interactions within the tumor microenvironment. Notably, linear and nonlinear predictive models performed similarly, suggesting that image features may relate to pathway activity in a predominantly linear fashion or that nonlinear structure is small relative to measurement noise. These findings demonstrate that features extracted from routine histopathology may recover spatially coherent and biologically interpretable pathway patterns, offering a scalable strategy for integrating image-based inference with ST information in tumor microenvironment studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09003 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Digital Modeling of Spatial Pathway Activity from Histology Reveals Tumor Microenvironment Heterogeneity Liao, Ling Yang, Changhuei Artyomov, Maxim Watson, Mark Kepecs, Adam Zhou, Haowen Sergushichev, Alexey Cote, Richard Quantitative Methods Artificial Intelligence Spatial transcriptomics (ST) enables simultaneous mapping of tissue morphology and spatially resolved gene expression, offering unique opportunities to study tumor microenvironment heterogeneity. Here, we introduce a computational framework that predicts spatial pathway activity directly from hematoxylin-and-eosin-stained histology images at microscale resolution 55 and 100 um. Using image features derived from a computational pathology foundation model, we found that TGFb signaling was the most accurately predicted pathway across three independent breast and lung cancer ST datasets. In 87-88% of reliably predicted cases, the resulting spatial TGFb activity maps reflected the expected contrast between tumor and adjacent non-tumor regions, consistent with the known role of TGFb in regulating interactions within the tumor microenvironment. Notably, linear and nonlinear predictive models performed similarly, suggesting that image features may relate to pathway activity in a predominantly linear fashion or that nonlinear structure is small relative to measurement noise. These findings demonstrate that features extracted from routine histopathology may recover spatially coherent and biologically interpretable pathway patterns, offering a scalable strategy for integrating image-based inference with ST information in tumor microenvironment studies. |
| title | Digital Modeling of Spatial Pathway Activity from Histology Reveals Tumor Microenvironment Heterogeneity |
| topic | Quantitative Methods Artificial Intelligence |
| url | https://arxiv.org/abs/2512.09003 |