MOFGPT: Generative Design of Metal-Organic Frameworks using Language Models

TL;DR

This paper introduces MOFGPT, a novel framework combining language models and reinforcement learning to generate and optimize Metal-Organic Frameworks with specific properties efficiently, addressing the challenges of traditional computational methods.

Contribution

It presents a new transformer-based generative model, MOFGPT, with a chemically-informed string representation and reinforcement learning for property-guided MOF design.

Findings

Successfully generated MOFs with targeted properties.

Demonstrated scalable and valid MOF structures.

Accelerated inverse design process for MOFs.

Abstract

The discovery of Metal-Organic Frameworks (MOFs) with application-specific properties remains a central challenge in materials chemistry, owing to the immense size and complexity of their structural design space. Conventional computational screening techniques such as molecular simulations and density functional theory (DFT), while accurate, are computationally prohibitive at scale. Machine learning offers an exciting alternative by leveraging data-driven approaches to accelerate materials discovery. The complexity of MOFs, with their extended periodic structures and diverse topologies, creates both opportunities and challenges for generative modeling approaches. To address these challenges, we present a reinforcement learning-enhanced, transformer-based framework for the de novo design of MOFs. Central to our approach is MOFid, a chemically-informed string representation encoding both connectivity and topology, enabling scalable generative modeling. Our pipeline comprises three components: (1) a generative GPT model trained on MOFid sequences, (2) MOFormer, a transformer-based property predictor, and (3) a reinforcement learning (RL) module that optimizes generated candidates via property-guided reward functions. By integrating property feedback into sequence generation, our method drives the model toward synthesizable, topologically valid MOFs with desired functional attributes. This work demonstrates the potential of large language models, when coupled with reinforcement learning, to accelerate inverse design in reticular chemistry and unlock new frontiers in computational MOF discovery.