McKenzie Maddison, Irac Sergio Erdel, Chen Zhian, Moradi Afshin, Jenner Adrianne, Nguyen Quan, Rashidieh Behnam
QIMR Berghofer Medical Research Institute, Brisbane, QLD, Australia; Faculty of Science, The Queensland University of Technology, Brisbane, QLD, Australia.
Mater Research, The University of Queensland, Translational Research Institute, Brisbane, QLD, Australia.
Semin Cancer Biol. 2026 Feb;119:65-82. doi: 10.1016/j.semcancer.2026.01.002. Epub 2026 Jan 9.
The integration of multi-omics data, including genomics, transcriptomics, proteomics, epigenomics, and metabolomics, coupled with histological spatial data has transformed biomedical research, offering unprecedented insights into cellular functions and disease mechanisms. However, the sheer volume and complexity of these datasets present a significant challenge in terms of interpretation and clinical translation. Artificial intelligence (AI) and machine learning (ML) are transforming data analysis, enabling the extraction of meaningful patterns from high-dimensional datasets and facilitating the development of predictive models. This shift is particularly transformative in cancer research, where understanding the tumor microenvironment (TME) and its spatial dynamics is crucial for improving therapeutic outcomes. This review explores recent advancements in spatial omics (SO) including spatial transcriptomics (ST) and spatial proteomics (SP), and AI-driven computational models, focusing on their applications in oncology. We discuss key methodologies, including spatial barcoding, in situ sequencing, and digital spatial profiling, and highlight major platforms. AI-powered tools, including deep learning models and spatial graph-based analyses, enhance data interpretation, allowing for robust predictive modeling, biomarker discovery, and personalized therapeutic strategies. Despite their transformative potential, ST and AI-driven approaches face challenges, including high-dimensional data complexity, computational constraints, and standardization of analytical pipelines. Addressing these challenges requires advanced mathematical frameworks such as spatial graph theory, topological data analysis, and agent-based modeling, which refine data integration and improve biological insights. Future research should focus on enhancing spatial resolution, cross-platform data harmonization, and AI-driven predictive models to advance precision oncology. By integrating ST, SP, and AI, researchers can develop dynamic, patient-specific treatment strategies, ultimately improving clinical outcomes and deepening our understanding of cancer progression and immune system interactions.
