오태진 (선문대학교)

한빛사논문

조회474

선문대학교

CV File 237 kb

Brief. Bioinform., Nov 22 2023, 25 (1) bbad401 | https://doi.org/10.1093/bib/bbad401 Evidential deep learning for trustworthy prediction of enzyme commission number

So-Ra Han ^1,2, Mingyu Park ^2,3, Sai Kosaraju ⁴, JeungMin Lee ^2,3, Hyun Lee ^2,3,5, Jun Hyuck Lee ⁶, Tae-Jin Oh ^1,2,5,7, Mingon Kang⁴

¹Department of Life Science and Biochemical Engineering, Sun Moon University, Asan, Republic of Korea.

²Bio Big Data-based Chungnam Smart Clean Research Leader Training Program, SunMoon University, Asan, Republic of Korea.

³Division of Computer Science and Engineering, Sun Moon University, Asan, Republic of Korea.

⁴Department of Computer Science, University of Nevada, Las Vegas, NV, USA.

⁵Genome-based BioIT Convergence Institute, Asan, Republic of Korea.

⁶Research Unit of Cryogenic Novel Material, Korea Polar Research Institute, Incheon, Republic of Korea.

⁷Department of Pharmaceutical Engineering and Biotechnology, Sun Moon University, Asan, Republic of Korea.

So-Ra Han and Mingyu Park contributed equally to this work.

Corresponding authors : Tae-Jin Oh, Mingon Kang

Abstract

The rapid growth of uncharacterized enzymes and their functional diversity urge accurate and trustworthy computational functional annotation tools. However, current state-of-the-art models lack trustworthiness on the prediction of the multilabel classification problem with thousands of classes. Here, we demonstrate that a novel evidential deep learning model (named ECPICK) makes trustworthy predictions of enzyme commission (EC) numbers with data-driven domain-relevant evidence, which results in significantly enhanced predictive power and the capability to discover potential new motif sites. ECPICK learns complex sequential patterns of amino acids and their hierarchical structures from 20 million enzyme data. ECPICK identifies significant amino acids that contribute to the prediction without multiple sequence alignment. Our intensive assessment showed not only outstanding enhancement of predictive performance on the largest databases of Uniprot, Protein Data Bank (PDB) and Kyoto Encyclopedia of Genes and Genomes (KEGG), but also a capability to discover new motif sites in microorganisms. ECPICK is a reliable EC number prediction tool to identify protein functions of an increasing number of uncharacterized enzymes.

논문정보

형식Research article
게재일2023년 11월 (BRIC 등록일 2023-11-24)
연구진국내(교신)+국외 연구진
분야 바이오·의료융합 > 바이오·의료융합 기타

댓글 작성 로그인

CV 열람하기

연락처 보기