The paper introduces 3d-OT, a sophisticated deep-learning framework designed to analyze and integrate spatial multi-omics data from biological tissues. By utilizing a geometry-aware architecture called PointNet++, the tool effectively identifies complex spatial domains and aligns disparate tissue slices, even when they suffer from nonrigid deformations. This computational approach outperforms existing methods in capturing fine-grained anatomical details, such as the specific layers of the mouse brain cortex. Furthermore, the framework enables the creation of 3D spatiotemporal trajectories, offering researchers a more holistic view of embryonic development and cellular relationships. Ultimately, the source presents 3d-OT as a robust solution for deciphering the intricate molecular and structural complexity inherent in modern biological studies.

References:

• Dai B, Yi L, Wang P, et al. 3d-OT: a deep geometry-aware framework for heterogeneous slices alignment of spatial multi-omics[J]. Nature Methods, 2026: 1-12.