KAIST

< (From left) Professor Sang Yup Lee of the Department of Chemical and Biomolecular Engineering (top), Hongkeun Ji, PhD candidate of the Department of Chemical and Biomolecular Engineering (top), Ha Rim Kim, PhD candidate of the Department of Chemical and Biomolecular Engineering, and Dr. Gi Bae Kim of the BioProcess Engineering Research Center >

Enzymes are proteins that catalyze biochemical reactions within cells and play a pivotal role in metabolic processes. Accordingly, identifying the functions of novel enzymes is a critical task in the construction of microbial cell factories.

A KAIST research team has leveraged artificial intelligence (AI) to design novel enzymes that do not exist in nature, significantly accelerating microbial cell factory development and boosting the potential for next-generation biotechnological applications such as drug development and biofuel production.

KAIST (represented by President Kwang-Hyung Lee) announced on the 21st of April that Distinguished Professor Sang Yup Lee and his team from the Department of Chemical and Biomolecular Engineering have published a review titled “Enzyme Functional Classification Using Artificial Intelligence,” which outlines the advancement of AI-based enzyme function prediction technologies and analyzes how AI has contributed to the discovery and design of new enzymes.

Professor Lee’s team systematically reviewed the development of enzyme function prediction technologies utilizing machine learning and deep learning, offering a comprehensive analysis.

From sequence similarity-based prediction methods to the integration of convolutional neural networks (CNNs), recurrent neural networks (RNNs), graph neural networks (GNNs), and transformer-based large language models, the paper covers a broad range of AI applications. It analyzes how these technologies extract meaningful information from protein sequences and enhance prediction accuracy.

In particular, enzyme function prediction using deep learning goes beyond simple sequence similarity analysis. By automatically extracting structural and evolutionary features embedded in amino acid sequences, deep learning enables more precise predictions of catalytic functions.

This highlights the unique advantages of AI models compared to traditional bioinformatics approaches.

Moreover, the review suggests that the advancement of generative AI will move future research beyond predicting existing functions to generating entirely new enzymes with functions not found in nature. This shift is expected to profoundly impact the trajectory of biotechnology and synthetic biology.

< Figure 1. Extraction of enzyme characteristics and function prediction using various deep learning structures >

Ha Rim Kim, a Ph.D. candidate and co-first author from the Department of Chemical and Biomolecular Engineering, stated, “AI-based enzyme function prediction and enzyme design are highly important across various fields including metabolic engineering, synthetic biology, and healthcare.” 

Distinguished Professor Sang Yup Lee added, “AI-powered enzyme function prediction shows the potential to solve diverse biological problems and will significantly contribute to accelerating research across the entire field.”

The review was published on March 28 in Trends in Biotechnology, a leading biotechnology journal issued by Cell Press.

 ※ Title: Enzyme Functional Classification Using Artificial Intelligence

 ※DOI: https://doi.org/10.1016/j.tibtech.2025.03.003

 ※ Author Information: Ha Rim Kim (KAIST, Co-first author), Hongkeun Ji (KAIST, Co-first author), Gi Bae Kim (KAIST, Third author), Sang Yup Lee (KAIST, Corresponding author) 

This research was supported by the Ministry of Science and ICT under the project Development of Core Technologies for Advanced Synthetic Biology to Lead the Bio-Manufacturing Industry (aimed at replacing petroleum-based chemicals), and also by joint support from the Ministry of Science and ICT and the Ministry of Health and Welfare for the project Development of Novel Antibiotic Structures Using Deep Learning-Based Synthetic Biology.