EGMOF: Efficient Generation of Metal-Organic Frameworks Using a Hybrid Diffusion-Transformer Architecture

TL;DR

EGMOF introduces a modular hybrid diffusion-transformer framework for efficient, data-minimal inverse design of metal-organic frameworks, achieving high validity and property accuracy across diverse datasets.

Contribution

The paper presents a novel, modular diffusion-transformer approach that enables inverse MOF design with minimal retraining and high accuracy in small-data regimes.

Findings

EGMOF achieved over 94% validity and 91% hit rate on a hydrogen uptake dataset.

The model outperformed existing methods with up to 39% higher validity and 29% higher hit rate.

EGMOF successfully performed conditional generation across 29 diverse property datasets.

Abstract

Designing materials with targeted properties remains challenging due to the vastness of chemical space and the scarcity of property-labeled data. While recent advances in generative models offer a promising way for inverse design, most approaches require large datasets and must be retrained for every new target property. Here, we introduce the EGMOF (Efficient Generation of MOFs), a hybrid diffusion-transformer framework that overcomes these limitations through a modular, descriptor-mediated workflow. EGMOF decomposes inverse design into two steps: (1) a one-dimensional diffusion model (Prop2Desc) that maps desired properties to chemically meaningful descriptors followed by (2) a transformer model (Desc2MOF) that generates structures from these descriptors. This modular hybrid design enables minimal retraining and maintains high accuracy even under small-data conditions. On a hydrogen uptake dataset, EGMOF achieved over 94% validity and 91% hit rate, representing significant improvements of up to 39% in validity and 29% in hit rate compared to existing methods, while remaining effective with only 1,000 training samples. Moreover, our model successfully performed conditional generation across 29 diverse property datasets, including CoREMOF, QMOF, and text-mined experimental datasets, whereas previous models have not. This work presents a data-efficient, generalizable approach to the inverse design of diverse MOFs and highlights the potential of modular inverse design workflows for broader materials discovery.