Spatial omics in the AI era: Technologies, algorithmic ecosystems, biological applications, and large model...

Area of Science:

• Life Sciences
• Molecular Biology
• Bioinformatics

Background:

• Conventional omics lack spatial context, limiting understanding of microenvironments.
• Spatial omics technologies provide molecular-level resolution within their native tissue context.
• Interdisciplinary research faces challenges in platform selection, algorithm choice, and understanding technical principles.

Purpose of the Study:

• To systematically review spatial omics technology platforms and analytical algorithms.
• To compare the advantages and disadvantages of different spatial omics approaches for specific tasks.
• To outline emerging research directions, including large model integration in spatial omics.

Main Methods:

• Systematic literature review of spatial omics technologies and analytical methods.
• Comparative analysis of platform capabilities, algorithmic approaches, and research workflows.
• Case study presentation of spatial omics applications across various biological fields.

Main Results:

• Detailed explanation of diverse spatial omics technical principles and platforms.
• Comparison of analytical algorithms, highlighting strengths and weaknesses for different applications.
• Identification of key challenges and emerging trends, including AI/large model integration.

Conclusions:

• Spatial omics is crucial for addressing spatially resolved biological questions.
• A comprehensive understanding of platforms and algorithms is essential for effective study design.
• Future directions emphasize technological integration and advanced computational approaches for deeper biological insights.