Back to Table of contents

Primeur weekly 2019-07-15

Quantum computing

Quantum chemistry on quantum computers ...

Quantum computing: Forschungszentrum Jülich and Google announce research partnership ...

The best of both worlds: how to solve real problems on modern quantum computers ...

Rigetti Computing acquires QxBranch to expand full-stack capabilities ...

Focus on Europe

Pioneer satellites launched ...

Inauguration of the Minho Advanced Computing Centre - MACC - in Portugal ...

e-InfraCentral reports on successful EOSC community event in Tallinn ...

ISC High Performance announces David Keyes as 2020 Programme Chair ...

GCS Centres converge on Frankfurt for ISC19 ...

Gauss Centre for Supercomputing to open 22nd call for large-scale projects ...

Middleware

Argonne team breaks record for Globus Data Movement ...

Hardware

Verne Global joins NVIDIA DGX-Ready Data Center Programme as HPC & AI colocation partner ...

NSF funds Bridges-2 supercomputer at Pittsburgh Supercomputing Center ...

Mellanox Capital extends storage ecosystem with investments in CNEX Labs and Pliops ...

Ohio Supercomputer Center staff leading programmes at PEARC19 conference ...

Tachyum closes $25 million Series A round ...

Vantage Data Centers joins NVIDIA DGX-Ready Data Center Colocation Programme ...

World-class research centre opens in Palo Alto ...

Intel's Pohoiki Beach, a 64-chip neuromorphic system, delivers breakthrough results in research tests ...

Applications

SDSC's Comet supercomputer used to model graphene-water interaction ...

US Naval Research Laboratory 'connects the dots' for quantum networks ...

Deep learning-powered 'DeepEC' helps accurately understand enzyme functions ...

Targeting new treatments for concussions by transforming brain pathology ...

NERSC's Cori system reveals integral role of gluons in proton pressure distribution ...

CMU scientists use XSEDE-allocated resources to simulate improved battery components ...

AI Excellence in Europe: 50 million euro to bring world-class researchers together ...

The Cloud

IBM closes landmark acquisition of Red Hat for $34 billion and defines open, hybrid Cloud future ...

USFlash

Intel unveils new tools in its advanced chip packaging toolbox ...

Deep learning-powered 'DeepEC' helps accurately understand enzyme functions


Overall scheme of DeepEC. Credit: KAIST.
9 Jul 2019 Daejeon - 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 the Korea Advanced Institute of Science and Technology (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 4669 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 theProceedings of the National Academy of Sciencesof 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", stated Professor Kim.

Distinguished Professor Lee stated: "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 Programme 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.

Source: The Korea Advanced Institute of Science and Technology - KAIST

Back to Table of contents

Primeur weekly 2019-07-15

Quantum computing

Quantum chemistry on quantum computers ...

Quantum computing: Forschungszentrum Jülich and Google announce research partnership ...

The best of both worlds: how to solve real problems on modern quantum computers ...

Rigetti Computing acquires QxBranch to expand full-stack capabilities ...

Focus on Europe

Pioneer satellites launched ...

Inauguration of the Minho Advanced Computing Centre - MACC - in Portugal ...

e-InfraCentral reports on successful EOSC community event in Tallinn ...

ISC High Performance announces David Keyes as 2020 Programme Chair ...

GCS Centres converge on Frankfurt for ISC19 ...

Gauss Centre for Supercomputing to open 22nd call for large-scale projects ...

Middleware

Argonne team breaks record for Globus Data Movement ...

Hardware

Verne Global joins NVIDIA DGX-Ready Data Center Programme as HPC & AI colocation partner ...

NSF funds Bridges-2 supercomputer at Pittsburgh Supercomputing Center ...

Mellanox Capital extends storage ecosystem with investments in CNEX Labs and Pliops ...

Ohio Supercomputer Center staff leading programmes at PEARC19 conference ...

Tachyum closes $25 million Series A round ...

Vantage Data Centers joins NVIDIA DGX-Ready Data Center Colocation Programme ...

World-class research centre opens in Palo Alto ...

Intel's Pohoiki Beach, a 64-chip neuromorphic system, delivers breakthrough results in research tests ...

Applications

SDSC's Comet supercomputer used to model graphene-water interaction ...

US Naval Research Laboratory 'connects the dots' for quantum networks ...

Deep learning-powered 'DeepEC' helps accurately understand enzyme functions ...

Targeting new treatments for concussions by transforming brain pathology ...

NERSC's Cori system reveals integral role of gluons in proton pressure distribution ...

CMU scientists use XSEDE-allocated resources to simulate improved battery components ...

AI Excellence in Europe: 50 million euro to bring world-class researchers together ...

The Cloud

IBM closes landmark acquisition of Red Hat for $34 billion and defines open, hybrid Cloud future ...

USFlash

Intel unveils new tools in its advanced chip packaging toolbox ...