AnchorPose for Geometry-Aware MOF Assembly through Meso-Grained Pose Generation

2026-10-05

AI Summary

This study addresses the anisotropy of rotational error space and geometric dependencies in metal-organic framework (MOF) assembly by proposing the AnchorPose framework. This method leverages Bayesian flow networks to generate representative anchor atom coordinates, incorporating geometric constraints into a mid-grained representation that bridges point-level predictions with block-level constraints while circumventing full-atom parameterization. Subsequently, complete building block poses are recovered through rigid alignment. Evaluated on MOF benchmarks, AnchorPose significantly outperforms existing block-level and all-atom baselines in single-candidate matching accuracy, achieving efficient and geometry-aware pose generation.

Abstract

Predicting metal-organic framework (MOF) structures from given building blocks requires recovering their positions and orientations in a periodic crystal. The spatial effects of rotation errors are geometry-dependent and anisotropic. The same angular error can produce different atomic displacements depending on block size, shape, and rotation axis. Angular error alone, without reference to the specific block geometry, therefore cannot fully describe the spatial consequences of a pose error. We introduce AnchorPose, a meso-grained pose generation framework that incorporates this geometric dependence into its generative representation. It represents each block through a small set of representative atoms, combines their local geometry with the current spatial state, and generates their coordinates with Bayesian Flow Networks. Known atom correspondences enable rigid alignment to recover complete building-block poses and return geometrically consistent points to the generation process. This design connects point-level spatial prediction with block-level structural constraints. Geometry participates in the pose state and its prediction, while rigid reconstruction preserves intra-block structure without treating all atomic coordinates as assembly variables. On the MOF benchmark, AnchorPose improves single-candidate match rates over the compared block-level and all-atom baselines.

Problem

• Metal-Organic Frameworks
• Pose Prediction
• Geometry-Aware Assembly
• Rotation Error
• Crystal Structure

Innovation

• Meso-Grained Pose Generation
• Bayesian Flow Networks
• Metal-Organic Frameworks
• Rigid Alignment
• Geometry-Aware Representation