Systems
-
Emeritus Professor Jae-Kyu Lee Wins the AIS LEO Award
Emeritus Professor Jae-Kyu Lee has won the Association for Information Systems LEO Award 2020. Professor Lee, the first Korean to receive the LEO Award, was recognized for his research and development in preventative cyber security, which is a major part of the efforts he leads to realize what Professor Lee has named "Bright Internet."
Established in 1999, this award was named after the world’s first business application of computing, the Lyons Electronic Office and recognizes outstanding individuals in the field of information systems. The LEO Award recognized four winners including Professor Lee this year.
He has been professor and HHI Chair Professor at KAIST from 1985 to 2016 since he has received his Ph.D. in information and operations management from the Wharton School, University of Pennsylvania. He served as the Dean of College of Business and supervised around 30 doctoral students. He is currently the Distinguished Professor of School of Management at Xi’an Jiaotong University.
His research mainly focused on the creation of Bright Internet for preventive cybersecurity, improving relevance of research from Axiomatic Theories, and development of AI for electronic commerce and managerial decision support.
He is a fellow and was the president of the Association for Information Systems, and co-chaired the International Conference on Information Systems in 2017. He was the founder of Principles for the Bright Internet and established the Bright Internet Research Center at KAIST and Xi’an Jiatong University. He also established the Bright Internet Global Summit since ICIS 2017 in Seoul, and organized the Bright Internet Project Consortium in 2019 as a combined effort of academia-industry partnership. (www.brightinternet.org.)
He was a charter member of the Pacific Asia Conference in Information Systems, and served as conference chair. He was the founder editor-in-chief of the journal, Electronic Commerce Research and Applications (Elsevier), and was the founding chair of the International Conference on Electronic Commerce. In Korea, her served as president of Korea Society of Management Information Systems and Korea Society of Intelligent Information Systems.
"I am honored to be designated the first Korean winner of the honorable LEO Award," Lee said. "Based on my life-long efforts for developments in the field, I will continue to contribute to the research and development of information media systems."
2020.12.16 View 5398 -
E. coli Engineered to Grow on CO₂ and Formic Acid as Sole Carbon Sources
- An E. coli strain that can grow to a relatively high cell density solely on CO₂ and formic acid was developed by employing metabolic engineering. -
Most biorefinery processes have relied on the use of biomass as a raw material for the production of chemicals and materials. Even though the use of CO₂ as a carbon source in biorefineries is desirable, it has not been possible to make common microbial strains such as E. coli grow on CO₂.
Now, a metabolic engineering research group at KAIST has developed a strategy to grow an E. coli strain to higher cell density solely on CO₂ and formic acid. Formic acid is a one carbon carboxylic acid, and can be easily produced from CO₂ using a variety of methods. Since it is easier to store and transport than CO₂, formic acid can be considered a good liquid-form alternative of CO₂.
With support from the C1 Gas Refinery R&D Center and the Ministry of Science and ICT, a research team led by Distinguished Professor Sang Yup Lee stepped up their work to develop an engineered E. coli strain capable of growing up to 11-fold higher cell density than those previously reported, using CO₂ and formic acid as sole carbon sources. This work was published in Nature Microbiology on September 28.
Despite the recent reports by several research groups on the development of E. coli strains capable of growing on CO₂ and formic acid, the maximum cell growth remained too low (optical density of around 1) and thus the production of chemicals from CO₂ and formic acid has been far from realized.
The team previously reported the reconstruction of the tetrahydrofolate cycle and reverse glycine cleavage pathway to construct an engineered E. coli strain that can sustain growth on CO₂ and formic acid. To further enhance the growth, the research team introduced the previously designed synthetic CO₂ and formic acid assimilation pathway, and two formate dehydrogenases.
Metabolic fluxes were also fine-tuned, the gluconeogenic flux enhanced, and the levels of cytochrome bo3 and bd-I ubiquinol oxidase for ATP generation were optimized. This engineered E. coli strain was able to grow to a relatively high OD600 of 7~11, showing promise as a platform strain growing solely on CO₂ and formic acid.
Professor Lee said, “We engineered E. coli that can grow to a higher cell density only using CO₂ and formic acid. We think that this is an important step forward, but this is not the end. The engineered strain we developed still needs further engineering so that it can grow faster to a much higher density.”
Professor Lee’s team is continuing to develop such a strain. “In the future, we would be delighted to see the production of chemicals from an engineered E. coli strain using CO₂ and formic acid as sole carbon sources,” he added.
-Profile:Distinguished Professor Sang Yup Leehttp://mbel.kaist.ac.krDepartment of Chemical and Biomolecular EngineeringKAIST
2020.09.29 View 9560 -
Before Eyes Open, They Get Ready to See
- Spontaneous retinal waves can generate long-range horizontal connectivity in visual cortex. -
A KAIST research team’s computational simulations demonstrated that the waves of spontaneous neural activity in the retinas of still-closed eyes in mammals develop long-range horizontal connections in the visual cortex during early developmental stages.
This new finding featured in the August 19 edition of Journal of Neuroscience as a cover article has resolved a long-standing puzzle for understanding visual neuroscience regarding the early organization of functional architectures in the mammalian visual cortex before eye-opening, especially the long-range horizontal connectivity known as “feature-specific” circuitry.
To prepare the animal to see when its eyes open, neural circuits in the brain’s visual system must begin developing earlier. However, the proper development of many brain regions involved in vision generally requires sensory input through the eyes.
In the primary visual cortex of the higher mammalian taxa, cortical neurons of similar functional tuning to a visual feature are linked together by long-range horizontal circuits that play a crucial role in visual information processing.
Surprisingly, these long-range horizontal connections in the primary visual cortex of higher mammals emerge before the onset of sensory experience, and the mechanism underlying this phenomenon has remained elusive.
To investigate this mechanism, a group of researchers led by Professor Se-Bum Paik from the Department of Bio and Brain Engineering at KAIST implemented computational simulations of early visual pathways using data obtained from the retinal circuits in young animals before eye-opening, including cats, monkeys, and mice.
From these simulations, the researchers found that spontaneous waves propagating in ON and OFF retinal mosaics can initialize the wiring of long-range horizontal connections by selectively co-activating cortical neurons of similar functional tuning, whereas equivalent random activities cannot induce such organizations.
The simulations also showed that emerged long-range horizontal connections can induce the patterned cortical activities, matching the topography of underlying functional maps even in salt-and-pepper type organizations observed in rodents. This result implies that the model developed by Professor Paik and his group can provide a universal principle for the developmental mechanism of long-range horizontal connections in both higher mammals as well as rodents.
Professor Paik said, “Our model provides a deeper understanding of how the functional architectures in the visual cortex can originate from the spatial organization of the periphery, without sensory experience during early developmental periods.”
He continued, “We believe that our findings will be of great interest to scientists working in a wide range of fields such as neuroscience, vision science, and developmental biology.”
This work was supported by the National Research Foundation of Korea (NRF). Undergraduate student Jinwoo Kim participated in this research project and presented the findings as the lead author as part of the Undergraduate Research Participation (URP) Program at KAIST.
Figures and image credit: Professor Se-Bum Paik, KAIST
Image usage restrictions: News organizations may use or redistribute these figures and image, with proper attribution, as part of news coverage of this paper only.
Publication:
Jinwoo Kim, Min Song, and Se-Bum Paik. (2020). Spontaneous retinal waves generate long-range horizontal connectivity in visual cortex. Journal of Neuroscience, Available online athttps://www.jneurosci.org/content/early/2020/07/17/JNEUROSCI.0649-20.2020
Profile: Se-Bum Paik
Assistant Professor
sbpaik@kaist.ac.kr
http://vs.kaist.ac.kr/
VSNN Laboratory
Department of Bio and Brain Engineering
Program of Brain and Cognitive Engineering
http://kaist.ac.kr
Korea Advanced Institute of Science and Technology (KAIST) Daejeon, Republic of Korea
Profile: Jinwoo Kim
Undergraduate Student
bugkjw@kaist.ac.kr
Department of Bio and Brain Engineering, KAIST
Profile: Min Song
Ph.D. Candidate
night@kaist.ac.kr
Program of Brain and Cognitive Engineering, KAIST
(END)
2020.08.25 View 10347 -
Researchers Present a Microbial Strain Capable of Massive Succinic Acid Production
A research team led by Distinguished Professor Sang Yup Lee reported the production of a microbial strain capable of the massive production of succinic acid with the highest production efficiency to date. This strategy of integrating systems metabolic engineering with enzyme engineering will be useful for the production of industrially competitive bio-based chemicals. Their strategy was described in Nature Communications on April 23.
The bio-based production of industrial chemicals from renewable non-food biomass has become increasingly important as a sustainable substitute for conventional petroleum-based production processes relying on fossil resources. Here, systems metabolic engineering, which is the key component for biorefinery technology, is utilized to effectively engineer the complex metabolic pathways of microorganisms to enable the efficient production of industrial chemicals.
Succinic acid, a four-carbon dicarboxylic acid, is one of the most promising platform chemicals serving as a precursor for industrially important chemicals. Among microorganisms producing succinic acid, Mannheimia succiniciproducens has been proven to be one of the best strains for succinic acid production.
The research team has developed a bio-based succinic acid production technology using the M. succiniciproducens strain isolated from the rumen of Korean cow for over 20 years and succeeded in developing a strain capable of producing succinic acid with the highest production efficiency.
They carried out systems metabolic engineering to optimize the succinic acid production pathway of the M. succiniciproducens strain by determining the crystal structure of key enzymes important for succinic acid production and performing protein engineering to develop enzymes with better catalytic performance.
As a result, 134 g per liter of succinic acid was produced from the fermentation of an engineered strain using glucose, glycerol, and carbon dioxide. They were able to achieve 21 g per liter per hour of succinic acid production, which is one of the key factors determining the economic feasibility of the overall production process. This is the world’s best succinic acid production efficiency reported to date. Previous production methods averaged 1~3 g per liter per hour.
Distinguished professor Sang Yup Lee explained that his team’s work will significantly contribute to transforming the current petrochemical-based industry into an eco-friendly bio-based one.
“Our research on the highly efficient bio-based production of succinic acid from renewable non-food resources and carbon dioxide has provided a basis for reducing our strong dependence on fossil resources, which is the main cause of the environmental crisis,” Professor Lee said.
This work was supported by the Technology Development Program to Solve Climate Changes via Systems Metabolic Engineering for Biorefineries and the C1 Gas Refinery Program from the Ministry of Science and ICT through the National Research Foundation of Korea.
2020.05.06 View 8107 -
Professor Minsoo Rhu Recognized as Facebook Research Scholar
Professor Minsoo Rhu from the School of Electrical Engineering was selected as the recipient of the Systems for Machine Learning Research Awards presented by Facebook.
Facebook launched the award last year with the goal of funding impactful solutions in the areas of developer tookits, compilers and code generation, system architecture, memory technologies, and machine learning accelerator support.
A total of 167 scholars from 100 universities representing 26 countries submitted research proposals, and Facebook selected final 10 scholars. Professor Rhu made the list with his research topic ‘A Near-Memory Processing Architecture for Training Recommendation Systems.’ He will receive 5,000 USD in research funds at the award ceremony which will take place during this year’s AI Systems Faculty Summit at the Facebook headquarters in Menlo Park, California.
Professor Rhu’s submission was based on research on ‘Memory-Centric Deep Learning System Architecture’ that he carried out for three years under the auspices of Samsung Science and Technology Foundation from 2017. It was an academic-industrial cooperation research project in which leading domestic companies like Samsung Electronics and SK Hynix collaborated to make a foray into the global memory-centric smart system semiconductor market.
Professor Rhu who joined KAIST in 2018 has led various systems research projects to accelerate the AI computing technology while working at NVIDIA headquarters from 2014.
(END)
2020.02.21 View 7940 -
What Fuels a “Domino Effect” in Cancer Drug Resistance?
KAIST researchers have identified mechanisms that relay prior acquired resistance to the first-line chemotherapy to the second-line targeted therapy, fueling a “domino effect” in cancer drug resistance. Their study featured in the February 7 edition of Science Advances suggests a new strategy for improving the second-line setting of cancer treatment for patients who showed resistance to anti-cancer drugs.
Resistance to cancer drugs is often managed in the clinic by chemotherapy and targeted therapy. Unlike chemotherapy that works by repressing fast-proliferating cells, targeted therapy blocks a single oncogenic pathway to halt tumor growth. In many cases, targeted therapy is engaged as a maintenance therapy or employed in the second-line after front-line chemotherapy.
A team of researchers led by Professor Yoosik Kim from the Department of Chemical and Biomolecular Engineering and the KAIST Institute for Health Science and Technology (KIHST) has discovered an unexpected resistance signature that occurs between chemotherapy and targeted therapy. The team further identified a set of integrated mechanisms that promotes this kind of sequential therapy resistance.
“There have been multiple clinical accounts reflecting that targeted therapies tend to be least successful in patients who have exhausted all standard treatments,” said the first author of the paper Mark Borris D. Aldonza. He continued, “These accounts ignited our hypothesis that failed responses to some chemotherapies might speed up the evolution of resistance to other drugs, particularly those with specific targets.”
Aldonza and his colleagues extracted large amounts of drug-resistance information from the open-source database the Genomics of Drug Sensitivity in Cancer (GDSC), which contains thousands of drug response data entries from various human cancer cell lines. Their big data analysis revealed that cancer cell lines resistant to chemotherapies classified as anti-mitotic drugs (AMDs), toxins that inhibit overacting cell division, are also resistant to a class of targeted therapies called epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKIs).
In all of the cancer types analyzed, more than 84 percent of those resistant to AMDs, representatively ‘paclitaxel’, were also resistant to at least nine EGFR-TKIs. In lung, pancreatic, and breast cancers where paclitaxel is often used as a first-line, standard-of-care regimen, greater than 92 percent showed resistance to EGFR-TKIs. Professor Kim said, “It is surprising to see that such collateral resistance can occur specifically between two chemically different classes of drugs.”
To figure out how failed responses to paclitaxel leads to resistance to EGFR-TKIs, the team validated co-resistance signatures that they found in the database by generating and analyzing a subset of slow-doubling, paclitaxel-resistant cancer models called ‘persisters’.
The results demonstrated that paclitaxel-resistant cancers remodel their stress response by first becoming more stem cell-like, evolving the ability to self-renew to adapt to more stressful conditions like drug exposures. More surprisingly, when the researchers characterized the metabolic state of the cells, EGFR-TKI persisters derived from paclitaxel-resistant cancer cells showed high dependencies to energy-producing processes such as glycolysis and glutaminolysis.
“We found that, without an energy stimulus like glucose, these cells transform to becoming more senescent, a characteristic of cells that have arrested cell division. However, this senescence is controlled by stem cell factors, which the paclitaxel-resistant cancers use to escape from this arrested state given a favorable condition to re-grow,” said Aldonza.
Professor Kim explained, “Before this research, there was no reason to expect that acquiring the cancer stem cell phenotype that dramatically leads to a cascade of changes in cellular states affecting metabolism and cell death is linked with drug-specific sequential resistance between two classes of therapies.”
He added, “The expansion of our work to other working models of drug resistance in a much more clinically-relevant setting, perhaps in clinical trials, will take on increasing importance, as sequential treatment strategies will continue to be adapted to various forms of anti-cancer therapy regimens.”
This study was supported by the Basic Science Research Program of the National Research Foundation of Korea (NRF-2016R1C1B2009886), and the KAIST Future Systems Healthcare Project (KAISTHEALTHCARE42) funded by the Korean Ministry of Science and ICT (MSIT). Undergraduate student Aldonza participated in this research project and presented the findings as the lead author as part of the Undergraduate Research Participation (URP) Program at KAIST.
< Figure 1. Schematic overview of the study. >
< Figure 2. Big data analysis revealing co-resistance signatures between classes of anti-cancer drugs. >
Publication:
Aldonza et al. (2020) Prior acquired resistance to paclitaxel relays diverse EGFR-targeted therapy persistence mechanisms. Science Advances, Vol. 6, No. 6, eaav7416. Available online at http://dx.doi.org/10.1126/sciadv.aav7416
Profile: Prof. Yoosik Kim, MA, PhD
ysyoosik@kaist.ac.kr
https://qcbio.kaist.ac.kr/
Assistant Professor
Bio Network Analysis Laboratory
Department of Chemical and Biomolecular Engineering
Korea Advanced Institute of Science and Technology (KAIST)
http://kaist.ac.kr
Daejeon, Republic of Korea
Profile: Mark Borris D. Aldonza
borris@kaist.ac.kr
Undergraduate Student
Department of Biological Sciences
Korea Advanced Institute of Science and Technology (KAIST)
http://kaist.ac.kr
Daejeon, Republic of Korea
(END)
2020.02.10 View 11678 -
Professor Junil Choi Receives Stephen O. Rice Prize
< Professor Junil Choi (second from the left) >
Professor Junil Choi from the School of Electrical Engineering received the Stephen O. Rice Prize at the Global Communications Conference (GLOBECOM) hosted by the Institute of Electrical and Electronics Engineers (IEEE) in Hawaii on December 10, 2019.
The Stephen O. Rice Prize is awarded to only one paper of exceptional merit every year. The IEEE Communications Society evaluates all papers published in the IEEE Transactions on Communications journal within the last three years, and marks each paper by aggregating its scores on originality, the number of citations, impact, and peer evaluation.
Professor Choi won the prize for his research on one-bit analog-to-digital converters (ADCs) for multiuser massive multiple-input and multiple-output (MIMO) antenna systems published in 2016. In his paper, Professor Choi proposed a technology that can drastically reduce the power consumption of the multiuser massive MIMO antenna systems, which are the core technology for 5G and future wireless communication. Professor Choi’s paper has been cited more than 230 times in various academic journals and conference papers since its publication, and multiple follow-up studies are actively ongoing.
In 2015, Professor Choi received the IEEE Signal Processing Society Best Paper Award, an award equals to the Stephen O. Rice Prize. He was also selected as the winner of the 15th Haedong Young Engineering Researcher Award presented by the Korean Institute of Communications and Information Sciences (KICS) on December 6, 2019 for his outstanding academic achievements, including 34 international journal publications and 26 US patent registrations.
(END)
2019.12.23 View 9074 -
Two Professors Receive Awards from the Korea Robotics Society
< Professor Jee-Hwan Ryu and Professor Ayoung Kim >
The Korea Robotics Society (KROS) conferred awards onto two KAIST professors from the Department of Civil and Environmental Engineering in recognition of their achievements and contributions to the development of the robotics industry in 2019. Professor Jee-Hwan Ryu has been actively engaged in researching the field of teleoperation, and this led him to win the KROS Robotics Innovation (KRI) Award. The KRI Award was newly established in 2019 by the KROS, in order to encourage researchers who have made innovative achievements in robotics. Professor Ryu shared the honor of being the first winner of this award with Professor Jaeheung Park of Seoul National University. Professor Ayoung Kim, from the same department, received the Young Investigator Award presented to emerging robitics researchers under 40 years of age. (END)
2019.12.19 View 7858 -
KAIST and Google Jointly Develop AI Curricula
KAIST selected the two professors who will develop AI curriculum under the auspices of the KAIST-Google Partnership for AI Education and Research. The Graduate School of AI announced the two authors among the 20 applicants who will develop the curriculum next year. They will be provided 7,500 USD per subject.
Professor Changho Suh from the School of Electrical Engineering and Professor Yong-Jin Yoon from the Department of Mechanical Engineering will use Google technology such as TensorFlow, Google Cloud, and Android to create the curriculum.
Professor Suh’s “TensorFlow for Information Theory and Convex Optimization “will be used for curriculum in the graduate courses and Professor Yoon’s “AI Convergence Project Based Learning (PBL)” will be used for online courses. Professor Yoon’s course will explore and define problems by utilizing AI and experiencing the process of developing products that use AI through design thinking, which involves product design, production, and verification. Professor Suh’s course will discus“information theory and convergence,” which uses basic sciences and engineering as well as AI, machine learning, and deep learning.
2019.12.04 View 11287 -
Object Identification and Interaction with a Smartphone Knock
(Professor Lee (far right) demonstrate 'Knocker' with his students.)
A KAIST team has featured a new technology, “Knocker”, which identifies objects and executes actions just by knocking on it with the smartphone. Software powered by machine learning of sounds, vibrations, and other reactions will perform the users’ directions.
What separates Knocker from existing technology is the sensor fusion of sound and motion. Previously, object identification used either computer vision technology with cameras or hardware such as RFID (Radio Frequency Identification) tags. These solutions all have their limitations. For computer vision technology, users need to take pictures of every item. Even worse, the technology will not work well in poor lighting situations. Using hardware leads to additional costs and labor burdens.
Knocker, on the other hand, can identify objects even in dark environments only with a smartphone, without requiring any specialized hardware or using a camera. Knocker utilizes the smartphone’s built-in sensors such as a microphone, an accelerometer, and a gyroscope to capture a unique set of responses generated when a smartphone is knocked against an object. Machine learning is used to analyze these responses and classify and identify objects.
The research team under Professor Sung-Ju Lee from the School of Computing confirmed the applicability of Knocker technology using 23 everyday objects such as books, laptop computers, water bottles, and bicycles. In noisy environments such as a busy café or on the side of a road, it achieved 83% identification accuracy. In a quiet indoor environment, the accuracy rose to 98%.
The team believes Knocker will open a new paradigm of object interaction. For instance, by knocking on an empty water bottle, a smartphone can automatically order new water bottles from a merchant app. When integrated with IoT devices, knocking on a bed’s headboard before going to sleep could turn off the lights and set an alarm. The team suggested and implemented 15 application cases in the paper, presented during the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2019) held in London last month.
Professor Sung-Ju Lee said, “This new technology does not require any specialized sensor or hardware. It simply uses the built-in sensors on smartphones and takes advantage of the power of machine learning. It’s a software solution that everyday smartphone users could immediately benefit from.” He continued, “This technology enables users to conveniently interact with their favorite objects.”
The research was supported in part by the Next-Generation Information Computing Development Program through the National Research Foundation of Korea funded by the Ministry of Science and ICT and an Institute for Information & Communications Technology Promotion (IITP) grant funded by the Ministry of Science and ICT.
Figure: An example knock on a bottle. Knocker identifies the object by analyzing a unique set of responses from the knock, and automatically launches a proper application or service.
2019.10.02 View 25381 -
'Flying Drones for Rescue'
(Video Credit: ⓒNASA JPL)
< Team USRG and Professor Shim (second from the right) >
Having recently won the AI R&D Grand Challenge Competition in Korea, Team USRG (Unmanned System Research Group) led by Professor Hyunchul Shim from the School of Electrical Engineering is all geared up to take on their next challenges: the ‘Defense Advanced Research Projects Agency Subterranean Challenge (DARPA SubT Challenge)’ and ‘Lockheed Martin’s AlphaPilot Challenge’ next month.
Team USRG won the obstacle course race in the ‘2019 AI R&D Grand Challenge Competition’ on July 12. They managed to successfully dominate the challenging category of ‘control intelligence.’ Having to complete the obstacle course race solely using AI systems without any connection to the internet made it difficult for most of the eight participating teams to pass the third section of the race, and only Team USRG passed the long pipeline course during their attempt in the main event. They also demonstrated, after the main event, that their drone can navigate all of the checkpoints including landing on the “H” mark using deep learning.
Their drone flew through polls and pipes, and escaped from windows and mazes against strong winds, amid cheers and groans from the crowd gathered at the Korea Exhibition Center (KINTEX) in Goyang, Korea. The team was awarded three million KRW in prize money, and received a research grant worth six hundred million KRW from the Ministry of Science and ICT (MSIT).
“Being ranked first in the race for which we were never given a chance for a test flight means a lot to our team. Considering that we had no information on the exact size of the course in advance, this is a startling result,” said Professor Shim. “We will carry out further research with this funding, and compete once again with the improved AI and drone technology in the 2020 competition,” he added.
The AI R&D Grand Challenge Competition, which was first started in 2017, has been designed to promote AI research and development and expand its application to addressing high-risk technical challenges with significant socio-economic impact.
This year’s competition presented participants with a task where they had to develop AI software technology for drones to navigate themselves autonomously during complex disaster relief operations such as aid delivery.
Each team participated in one of the four tracks of the competition, and their drones were evaluated based on the criteria for each track. The divisions were broken up into intelligent context-awareness, intelligent character recognition, auditory intelligence, and control intelligence.
Team USRG’s technological prowess has been already well acclaimed among international peer groups. Teamed up with NASA JPL, Caltech, and MIT, they will compete in the subterranean mission during the ‘DARPA SubT Challenge’.
Team CoSTAR, as its name stands for, is working together to build ‘Collaborative SubTerranean Autonomous Resilient Robots.’ Professor Shim emphasized the role KAIST plays in Team CoSTAR as a leader in drone technology.
“I think when our drone technology will be added to our peers’ AI and robotics, Team CoSTAR will bring out unsurpassable synergy in completing the subterrestrial and planetary applications. I would like to follow the footprint of Hubo, the winning champion of the 2015 DARPA Robotics Challenge and even extend it to subterranean exploration,” he said.
These next generation autonomous subsurface explorers are now all optimizing the physical AI robot systems developed by Team CoSTAR. They will test their systems in more realistic field environments August 15 through 22 in Pittsburgh, USA. They have already received funding from DARPA for participating.
Team CoSTAR will compete in three consecutive yearly events starting this year, and the last event, planned for 2021, will put the team to the final test with courses that incorporate diverse challenges from all three events. Two million USD will be awarded to the winner after the final event, with additional prizes of up to 200,000 USD for self-funded teams.
Team USRG also ranked third in the recent Hyundai Motor Company’s ‘Autonomous Vehicle Competition’ and another challenge is on the horizon: Lockheed Martin’s ‘AlphaPilot Challenge’. In this event, the teams will be flying their drones through a series of racing gates, trying to beat the best human pilot. The challenge is hosted by Lockheed Martin, the world’s largest military contractor and the maker of the famed F-22 and F-35 stealth fighters, with the goal of stimulating the development of autonomous drones. Team USRG was selected from out of more than 400 teams from around the world and is preparing for a series of races this fall, beginning from the end of August.
Professor Shim said, “It is not easy to perform in a series of competitions in just a few months, but my students are smart, hardworking, and highly motivated. These events indeed demand a lot, but they really challenge the researchers to come up with technologies that work in the real world. This is the way robotics really should be.”
(END)
2019.07.26 View 10126 -
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 (ehukim@kaist.ac.kr)
https://sites.google.com/view/ehukim
Department of Chemical and Biomolecular Engineering
-Distinguished Professor Sang Yup Lee (leesy@kaist.ac.kr)
Department of Chemical and Biomolecular Engineering
http://mbel.kaist.ac.kr
2019.07.09 View 34551