New AI model transforms understanding of metal-organic frameworks

A computer server transformed by MOFs
Credit: Kevin Jablonka (EPFL)
Creative Commons CC BY-SA 4.0 license

How does an iPhone predict the next word you’re going to type in your messages? The technology behind this, and also at the core of many AI applications, is called a transformer; a deep-learning algorithm that detects patterns in datasets.

Now, researchers at EPFL and KAIST have created a transformer for Metal-Organic Frameworks (MOFs), a class of porous crystalline materials. By combining organic linkers with metal nodes, chemists can synthesize millions of different materials with potential applications in energy storage and gas separation.

The “MOFtransformer” is designed to be the ChatGPT for researchers that study MOFs. It’s architecture is based on an AI called Google Brain that can process natural language and forms the core of popular language models such as GPT-3, the predecessor to ChatGPT. The central idea behind these models is that they are pre-trained on a large amount of text, so when we start typing on an iPhone, for example, models like this “know” and autocomplete the most likely next word.

“We wanted to explore this idea for MOFs, but instead of giving a word suggestion, we wanted to have it suggest a property,” says Professor Berend Smit, who led the EPFL side of the project. “We pre-trained the MOFTransformer with a million hypothetical MOFs to learn their essential characteristics, which we represented as a sentence. The model was then trained to complete these sentences to give the MOF’s correct characteristics.”

The researchers then fine-tuned the MOFTransformer for tasks related to hydrogen storage, such as the storage capacity of hydrogen, its diffusion coefficient, and the band gap of the MOF (an “energy barrier” that determines how easily electrons can move through a material).

The approach showed that the MOFTransformer could get results using far fewer data compared to conventional machine-learning methods, which require much more data. “Because of the pre-training, the MOFTtransformer knows already many of the general properties of MOFs; and because of this knowledge, we need less data to train for another property,” says Smit. Moreover, the same model could be used for all properties, while in conventional machine learning, a separate model must be developed for each application.

The MOFTransformer is a game-changer for the study of MOFs, providing faster results with less data and a more comprehensive understanding of the material. The researchers hope that the MOFTransformer will pave the way for the development of new MOFs with improved properties for hydrogen storage and other applications.

Reference

Yeonghun Kang, Hyunsoo Park, Berend Smit, Jihan Kim. MOFTransformer: A multi-modal pre-training transformer for universal transfer learning in metal-organic frameworks. Nature Machine Intelligence 13 March 2023. DOI: 10.1038/s42256-023-00628-2

Media Contact

Nik Papageorgiou
Ecole Polytechnique Fédérale de Lausanne
n.papageorgiou@epfl.ch
Office: 41-216-932-105

Expert Contact

Berend Smit
EPFL
berend.smit@epfl.ch
Office: +41 21 693 00 79
 @EPFL_en

www.epfl.ch

Media Contact

Nik Papageorgiou
Ecole Polytechnique Fédérale de Lausanne

All latest news from the category: Information Technology

Here you can find a summary of innovations in the fields of information and data processing and up-to-date developments on IT equipment and hardware.

This area covers topics such as IT services, IT architectures, IT management and telecommunications.

Back to home

Comments (0)

Write a comment

Newest articles

When the music changes, so does the dance

Controlling cooperative electronic states in Kagome metals. Playing a different sound track is, physically speaking, only a minute change of the vibration spectrum, yet its impact on a dance floor…

EcoFABs could lead to better bioenergy crops

Fabricated ecosystems created at Berkeley Lab will expedite microbiome research, and help underrepresented students in the classroom. A greater understanding of how plants and microbes work together to store vast…

Rice lab finds better way to handle hard-to-recycle material

Process transforms glass fiber-reinforced plastic into silicon carbide. Glass fiber-reinforced plastic (GFRP), a strong and durable composite material, is widely used in everything from aircraft parts to windmill blades. Yet…

Partners & Sponsors