A joint research team has developed DeepECtransformer, an AI that can predict enzyme functions from protein sequences. The joint research team discovered previously unknown enzymes using the AI.

Enzymes are proteins that catalyze biological reactions. Identifying the function of each enzyme is essential to understanding the various chemical reactions that exist in living organisms and the metabolic characteristics of those organisms. While Escherichia coli is one of the most studied organisms, the function of 30% of the proteins that make up E. coli has not yet been revealed. For this, a newly developed artificial intelligence (AI) model was used to discover 464 enzymes from the unknown proteins.

A joint research team comprised of Gi Bae Kim, Ji Yeon Kim, Dr. Jong An Lee and Distinguished Professor Sang Yup Lee of the Department of Chemical and Biomolecular Engineering at KAIST, and Dr. Charles J. Norsigian and Professor Bernhard O. Palsson of the Department of Bioengineering at UCSD have developed DeepECtransformer, an AI that can predict the enzyme functions from the protein sequence. The team has established a prediction system by utilizing the AI to quickly and accurately identify the Enzyme Commission (EC) number. EC number is an enzyme function classification system designed by the International Union of Biochemistry and Molecular Biology, and to understand the metabolic characteristics of various organisms, it is necessary to develop a technology that can quickly analyze enzymes and EC numbers of the enzymes present in the genome. Various methodologies based on deep learning have been developed to analyze the features of biological sequences, including protein function prediction. However, most have a problem of a black box, where the inference process of AI cannot be interpreted. Various prediction systems that utilize AI for enzyme function prediction have also been reported but they do not solve the black box problem, nor can they interpret the reasoning process at a fine-grained level (e.g., the level of amino acid residues in the enzyme sequence).

The joint team further analyzed the transformer architecture to understand the inference process of DeepECtransformer, and found that in the inference process, the AI utilizes information on catalytic active sites and/or the cofactor binding sites, which are important for enzyme function. By analyzing the black box of DeepECtransformer, it was confirmed that the AI was able to identify the features that are important for enzyme function on its own during the learning process.