Emerging AI Approaches for Cancer Spatial Omics

TL;DR

This paper reviews how emerging AI methods are advancing the analysis of spatial omics data in cancer research, highlighting new paradigms, challenges, and integration strategies for understanding tumor biology.

Contribution

It provides a comprehensive overview of novel AI approaches for spatial omics in cancer, emphasizing the development of interpretable models and integration with biological hypotheses.

Findings

Emerging paradigms include data-driven and mechanistic spatial AI.

Challenges involve data integration and model interpretability.

Integration of AI with hypothesis-driven research enhances insights.

Abstract

Technological breakthroughs in spatial omics and artificial intelligence (AI) have the potential to transform the understanding of cancer cells and the tumor microenvironment. Here we review the role of AI in spatial omics, discussing the current state-of-the-art and further needs to decipher cancer biology from large-scale spatial tissue data. An overarching challenge is the development of interpretable spatial AI models, an activity which demands not only improved data integration, but also new conceptual frameworks. We discuss emerging paradigms, in particular data-driven spatial AI, constraint-based spatial AI, and mechanistic spatial modeling, as well as the importance of integrating AI with hypothesis-driven strategies and model systems to realize the value of cancer spatial information.