Building-Block Aware Generative Modeling for 3D Crystals of Metal Organic Frameworks
This work addresses the problem of exploring the vast design space of MOFs for materials science researchers, offering a practical generative approach that expands accessible chemical space, though it builds incrementally on existing diffusion models by incorporating building-block awareness.
The paper tackled the challenge of generating diverse and valid 3D metal-organic frameworks (MOFs) by introducing BBA MOF Diffusion, an SE(3)-equivariant diffusion model that samples MOFs with up to 1000 atoms per unit cell, achieving geometric validity and novelty, and successfully synthesizing a predicted MOF confirmed by experimental analysis.
Metal-organic frameworks (MOFs) marry inorganic nodes, organic edges, and topological nets into programmable porous crystals, yet their astronomical design space defies brute-force synthesis. Generative modeling holds ultimate promise, but existing models either recycle known building blocks or are restricted to small unit cells. We introduce Building-Block-Aware MOF Diffusion (BBA MOF Diffusion), an SE(3)-equivariant diffusion model that learns 3D all-atom representations of individual building blocks, encoding crystallographic topological nets explicitly. Trained on the CoRE-MOF database, BBA MOF Diffusion readily samples MOFs with unit cells containing 1000 atoms with great geometric validity, novelty, and diversity mirroring experimental databases. Its native building-block representation produces unprecedented metal nodes and organic edges, expanding accessible chemical space by orders of magnitude. One high-scoring [Zn(1,4-TDC)(EtOH)2] MOF predicted by the model was synthesized, where powder X-ray diffraction, thermogravimetric analysis, and N2 sorption confirm its structural fidelity. BBA-Diff thus furnishes a practical pathway to synthesizable and high-performing MOFs.