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

Holistic 3D modeling of molecularly defined brain structures is crucial for understanding complex brain functions. Using emerging tissue profiling technologies, researchers charted comprehensive atlases of mammalian brain with sub-cellular resolution and spatially resolved transcriptomic data. However, these tera-scale volumetric atlases pose computational challenges for modeling intricate brain structures within the native spatial context. We propose $\mathbf{\text{Tera-MIND}}$, a novel generative framework capable of simulating $\mathbf{\text{Tera}}$-scale $\mathbf{\text{M}}$ouse bra$\mathbf{\text{IN}}$s in 3D using a patch-based and boundary-aware $\mathbf{\text{D}}$iffusion model. Taking spatial gene expression as conditional input, we generate virtual mouse brains with comprehensive cellular morphological detail at teravoxel scale. Through the lens of 3D $\mathit{\text{gene}}$-$\mathit{\text{gene}}$ self-attention, we identify spatial molecular interactions for key transcriptomic pathways, including glutamatergic and dopaminergic neuronal systems. Lastly, we showcase the translational applicability of Tera-MIND on previously unseen human brain samples. Tera-MIND offers an efficient generative modeling of whole virtual organisms, paving the way for integrative applications in biomedical research. Project website: https://musikisomorphie.github.io/Tera-MIND.html