Receive KAIST news by email!
Type your e-mail address here.
by recently order
by view order
Deep Learning-Powered 'DeepEC' Helps Accurately Understand Enzyme Functions
(Figure: Overall scheme of DeepEC) A deep learning-powered computational framework, ‘DeepEC,’ will allow the high-quality and high-throughput prediction of enzyme commission numbers, which is essential for the accurate understanding of enzyme functions. A team of Dr. Jae Yong Ryu, Professor Hyun Uk Kim, and Distinguished Professor Sang Yup Lee at KAIST reported the computational framework powered by deep learning that predicts enzyme commission (EC) numbers with high precision in a high-throughput manner. DeepEC takes a protein sequence as an input and accurately predicts EC numbers as an output. Enzymes are proteins that catalyze biochemical reactions and EC numbers consisting of four level numbers (i.e., a.b.c.d) indicate biochemical reactions. Thus, the identification of EC numbers is critical for accurately understanding enzyme functions and metabolism. EC numbers are usually given to a protein sequence encoding an enzyme during a genome annotation procedure. Because of the importance of EC numbers, several EC number prediction tools have been developed, but they have room for further improvement with respect to computation time, precision, coverage, and the total size of the files needed for the EC number prediction. DeepEC uses three convolutional neural networks (CNNs) as a major engine for the prediction of EC numbers, and also implements homology analysis for EC numbers if the three CNNs do not produce reliable EC numbers for a given protein sequence. DeepEC was developed by using a gold standard dataset covering 1,388,606 protein sequences and 4,669 EC numbers. In particular, benchmarking studies of DeepEC and five other representative EC number prediction tools showed that DeepEC made the most precise and fastest predictions for EC numbers. DeepEC also required the smallest disk space for implementation, which makes it an ideal third-party software component. Furthermore, DeepEC was the most sensitive in detecting enzymatic function loss as a result of mutations in domains/binding site residue of protein sequences; in this comparative analysis, all the domains or binding site residue were substituted with L-alanine residue in order to remove the protein function, which is known as the L-alanine scanning method. This study was published online in the Proceedings of the National Academy of Sciences of the United States of America (PNAS) on June 20, 2019, entitled “Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers.” “DeepEC can be used as an independent tool and also as a third-party software component in combination with other computational platforms that examine metabolic reactions. DeepEC is freely available online,” said Professor Kim. Distinguished Professor Lee said, “With DeepEC, it has become possible to process ever-increasing volumes of protein sequence data more efficiently and more accurately.” This work was supported by the Technology Development Program to Solve Climate Changes on Systems Metabolic Engineering for Biorefineries from the Ministry of Science and ICT through the National Research Foundation of Korea. This work was also funded by the Bio & Medical Technology Development Program of the National Research Foundation of Korea funded by the Korean government, the Ministry of Science and ICT. Profile: -Professor Hyun Uk Kim (firstname.lastname@example.org) https://sites.google.com/view/ehukim Department of Chemical and Biomolecular Engineering -Distinguished Professor Sang Yup Lee (email@example.com) Department of Chemical and Biomolecular Engineering http://mbel.kaist.ac.kr
New drug targeting method for microbial pathogens developed using in silico cell
A ripple effect is expected on the new antibacterial discovery using “in silico” cells Featured as a journal cover paper of Molecular BioSystems A research team of Distinguished Professor Sang Yup Lee at KAIST recently constructed an in silico cell of a microbial pathogen that is resistant to antibiotics and developed a new drug targeting method that could effectively disrupt the pathogen"s growth using the in silico cell. Hyun Uk Kim, a graduate research assistant at the Department of Chemical and Biomolecular Engineering, KAIST, conducted this study as a part of his thesis research, and the study was featured as a journal cover paper in the February issue of Molecular BioSystems this year, published by The Royal Society of Chemistry based in Europe. It was relatively easy to treat infectious microbes using antibiotics in the past. However, the overdose of antibiotics has caused pathogens to increase their resistance to various antibiotics, and it has become more difficult to cure infectious diseases these days. A representative microbial pathogen is Acinetobacter baumannaii. Originally isolated from soils and water, this microorganism did not have resistance to antibiotics, and hence it was easy to eradicate them if infected. However, within a decade, this miroorganism has transformed into a dreadful super-bacterium resistant to antibiotics and caused many casualties among the U.S. and French soldiers who were injured from the recent Iraqi war and infected with Acinetobacter baumannaii. Professor Lee’s group constructed an in silico cell of this A. baumannii by computationally collecting, integrating, and analyzing the biological information of the bacterium, scattered over various databases and literatures, in order to study this organism"s genomic features and system-wide metabolic characteristics. Furthermore, they employed this in silico cell for integrative approaches, including several network analysis and analysis of essential reactions and metabolites, to predict drug targets that effectively disrupt the pathogen"s growth. Final drug targets are the ones that selectively kill pathogens without harming human body. Here, essential reactions refer to enzymatic reactions required for normal metabolic functioning in organisms, while essential metabolites indicate chemical compounds required in the metabolism for proper functioning, and their removal brings about the effect of simultaneously disrupting their associated enzymes that interact with them. This study attempted to predict highly reliable drug targets by systematically scanning biological components, including metabolic genes, enzymatic reactions, that constitute an in silico cell in a short period of time. This research achievement is highly regarded as it, for the first time, systematically scanned essential metabolites for the effective drug targets using the concept of systems biology, and paved the way for a new antibacterial discovery. This study is also expected to contribute to elucidating the infectious mechanism caused by pathogens. "Although tons of genomic information is poured in at this moment, application research that efficiently converts this preliminary information into actually useful information is still lagged behind. In this regard, this study is meaningful in that medically useful information is generated from the genomic information of Acinetobacter baumannii," says Professor Lee. "In particular, development of this organism"s in silico cell allows generation of new knowledge regarding essential genes and enzymatic reactions under specific conditions," he added. This study was supported by the Korean Systems Biology Project of the Ministry of Education, Science and Technology, and the patent for the development of in silico cells of microbial pathogens and drug targeting methods has been filed. [Picture 1 Cells in silico] [Picture 2 A process of generating drug targets without harming human body while effectively disrupting the growth of a pathogen, after predicting metabolites from in silico cells]
마지막 페이지 1
KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
Copyright(C) 2020, Korea Advanced Institute of Science and Technology,
All Rights Reserved.