Abstract 2417: N-Orbit: An interpretable, distance-based framework for comparison of tumor microenvironments and beyond
Abstract The tumor microenvironment (TME) plays a major role in cancer progression and treatment resistance. Advances in single-cell resolution spatial omics technologies have facilitated the exploration of the TME and its role in these processes. Recent developments in quantitative methods for tissue cellular neighborhood (TCN) detection have provided further insights into the organization of spatial heterogeneity within individual tissue samples. Yet a theoretical framework for modeling and comparing tissue architecture across time points and clinical subtypes remains lacking. We introduce, N-Orbit, a mathematical model that captures both cell type composition and spatial relationships within tissue cellular neighborhoods, encoding this information in a vector format for computationally efficient distance metric calculations. We benchmark our N-Orbit-based neighborhood distance metric on spatial omics datasets with manually annotated ground truth anatomical regions and on patient datasets with corresponding clinical variables. We also demonstrate that N-Orbit neighborhood distances recapitulate transitions across treatment phases and can be used to identify resistance-enriched neighborhood clusters in triple-negative breast cancer. Additionally, N-Orbit enhances model interpretability by allowing these neighborhood clusters to be traced back to enriched cell-cell interactions. N-Orbit holds significant potential for deepening our understanding of how TMEs, as well as tissue microenvironments more broadly, evolve across treatment timelines and clinical subtypes. Citation Format: Barbara Xiong, Yuxuan Hu, Kai Tan. N-Orbit: An interpretable, distance-based framework for comparison of tumor microenvironments and beyond [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 2417.
Authors
- Kai Tan (ORCID: https://orcid.org/0000-0002-9104-5567)
- Barbara Xiong (ORCID: https://orcid.org/0000-0002-5202-1095)
- Yuxuan Hu (ORCID: https://orcid.org/0000-0002-8830-6893)
Institutions
- University of Pennsylvania (US)
Publication Details
- Journal
- Cancer Research
- Published
- 2025-04-21
- DOI
- https://doi.org/10.1158/1538-7445.am2025-2417
- Primary Topic
- Nanoplatforms for cancer theranostics
- Type
- article
- Field-Weighted Citation Impact
- 0.00