Tera-MIND: Tera-scale mouse brain simulation via spatial mRNA-guided diffusion

Area of Science:

• Neuroscience
• Computational Biology
• Bioinformatics

Background:

• 3D modeling of molecularly defined brain structures is essential for understanding brain function.
• Existing tera-scale volumetric brain atlases present computational challenges for detailed modeling.
• Spatially resolved transcriptomic data offers sub-cellular resolution but requires advanced computational tools.

Purpose of the Study:

• To propose Tera-MIND, a novel generative framework for simulating teravoxel-scale 3D mouse brains.
• To address computational challenges in modeling intricate brain structures within their native spatial context.
• To generate virtual brains with detailed cellular morphology and identify spatial molecular interactions.

Main Methods:

• Developed a patch-based and boundary-aware diffusion model for 3D brain simulation.
• Utilized spatial gene expression as conditional input for generating virtual brains.
• Employed 3D gene-gene self-attention to identify spatial molecular interactions within transcriptomic pathways.

Main Results:

• Successfully generated teravoxel-scale virtual mouse brains with comprehensive cellular detail.
• Identified spatial molecular interactions in key transcriptomic pathways, including glutamatergic and dopaminergic systems.
• Demonstrated translational applicability of Tera-MIND on human brain samples.

Conclusions:

• Tera-MIND provides an efficient generative framework for whole-organism simulation.
• The framework enables integrative applications in biomedical research by modeling complex brain structures.
• This approach facilitates a deeper understanding of brain function through detailed 3D molecular modeling.