AtomGPT: Atomistic Generative Pre-trained Transformer for Forward and Inverse Materials Design

Published

June 27, 2024

Author(s)

Kamal Choudhary

Abstract

Large language models (LLMs) such as generative pretrained transformers (GPTs) have shown potential for various commercial applications, but their applicability for materials design remains underexplored. In this article, we introduce AtomGPT, a model specifically developed for materials design based on transformer architectures, to demonstrate the capability for both atomistic property prediction and structure generation. We show that a combination of chemical and structural text descriptions can efficiently predict material properties with accuracy comparable to graph neural network models, including formation energies, electronic bandgaps from two different methods and superconducting transition temperatures. Furthermore, we demonstrate that AtomGPT can generate atomic structures for tasks such as designing new superconductors, with the predictions validated through density functional theory calculations. This work paves the way for leveraging LLMs in forward and inverse materials design, offering an efficient approach to the discovery and optimization of materials.

Citation

Journal of Physical Chemistry Letters

Pub Type

Journals

Download Paper

https://doi.org/10.1021/acs.jpclett.4c01126

Local Download

Citation

Choudhary, K. (2024), AtomGPT: Atomistic Generative Pre-trained Transformer for Forward and Inverse Materials Design, Journal of Physical Chemistry Letters, [online], https://doi.org/10.1021/acs.jpclett.4c01126, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=957872 (Accessed April 26, 2026)

Additional citation formats