1
0The paper is a comprehensive academic review exploring the integration of machine learning and deep learning within the field of spatial omics. It highlights how computational models analyze high-dimensional molecular data while accounting for tissue architecture and spatial relationships. The authors compare classical algorithms, useful for interpretable baselines, with modern architectures like graph neural networks and transformers that excel at multi-omics integration. To assist researchers, the article proposes a decision framework that maps specific biological objectives and data types to the most effective computational strategies. Furthermore, the source examines emerging frontiers, such as quantum-inspired computing and satellite-mapping analogies, to address persistent challenges in scalability and clinical translation.
References:
Zirem Y, Fournier I, Salzet M. Toward next-generation machine learning and deep learning for spatial omics[J]. Briefings in Bioinformatics, 2026, 27(2): bbag131.
