Engineering
-
2018 KAIST Research Day Honors Outstanding Research Achievements
(KAIST President Sung-Chul Shin and Professor Jong-Hwan Kim) Professor Jong-Hwan Kim from the School of Electrical Engineering was recognized at the 2018 KAIST Research Day as the Research Grand Prize Awardee. The ten most distinguished research achievements of the past year were also recognized.
The Research Grand Prize recognizes the professor whose comprehensive research performance evaluation indicator was the highest over the past five years. The indicator combines the number of research contracts, IPR and royalty income.
During the May 25th ceremony, Professor Hyochoong Bang from the Department of Aerospace Engineering and Professor In so Kweon from the School of Electrical Engineering also won the Best Research Award prize.
This year, the Research Innovation Award went to Professor Dong Soo Han from the School of Computing. The Research Innovation Award combines scores in the categories of foreign patent registrations, contracts of technological transfer, and income from technology fees, technology consultations, and startups.
The Convergence Research Award was given to Professor Junmo Kim from the School of Electrical Engineering and Professor Hyun Myung from the Department of Civil & Environmental Engineering. The Convergence Research Award recognizes the most outstanding research team that created innovative research results over a one-year period.
President Sung-Chul Shin said, “KAIST has selected the ten most outstanding research achievements of 2017 conducted by our faculty and researchers. All of them demonstrated exceptional creativity, which opens new research paths in each field though their novelty, innovation, and impact.”
KAIST hosts Research Day every year to introduce major research performances at KAIST and share knowledge about the research and development.
During Research Day, KAIST also announced the ten most distinguished research achievements contributed by KAIST professors during the previous year. They are listed below.
▲ High-Speed Motion Core Technology for Magnetic Memory by Professor Kab-Jin Kim from the Department of Physics
▲ A Double Well Potential System by Professor Jaeyoung Byeon from the Department of Mathematical Sciences
▲ Cheap and Efficient Dehydrogenation of Alkanes by Professor Mu-Hyun Baik from the Department of Chemistry
▲ A Dynamic LPS Transfer Mechanism for Innate Immune Activation by Professor Ho Min Kim from the Graduate School of Medical Science and Engineering
▲ A Memristive Functional Device and Circuit on Fabric for Fibertronics by Professor Yang-Kyu Choi and Professor Sung-Yool Choi from the School of Electrical Engineering
▲ A Hippocampal Morphology Study Based on a Progressive Template Deformable Model by Professor Jinah Park from the School of Computing
▲ The Development of a 6-DOF Dynamic Response Measurement System for Civil Infrastructure Monitoring by Professor Hoon Sohn from the Department of Civil and Environmental Engineering
▲ Cooperative Tumour Cell Membrane Targeted Phototherapy by Professor Ji-Ho Park from the Department of Bio and Brain Engineering
▲ HUMICOTTA: A 3D-Printed Terracotta Humidifier by Professor Sangmin Bae from the Department of Industrial Design
▲ Ultrathin, Cross-Linked Ionic Polymer Thin Films by Professor Sung Gap Im from the Department of Chemical and Biomolecular Engineering
2018.05.28 View 12748 -
Get Treatment Anywhere and Any Time with Wearable PBM Patch
(PhD Candidate Yongmin Jeon)
There have been many cases in which OLEDs are applied to electronic devices, and now they have even been extended to therapeutic fields. A KAIST research team succeeded in developing a wearable photobiomodulation (PBM) patch to treat wounds. This technology will allow injuries to be treated regardless of location or time.
Professor KyungCheol Choi from the School of Electrical Engineering, in collaboration with Seoul National University Bundang Hospital’s team, conducted research on PBMs which are a clinical method widely used in hospitals. They are considered to be a safe, noninvasive, and nonsurgical method that require relatively low light power.
Conventionally, light-emitting diodes (LEDs) have been used in PBM applications; however, LED devices are usually inflexible and difficult to irradiate light uniformly. They may also produce localized heat. Due to these constraints, it was difficult to enhance the clinical effects of LED devices as they cannot stick to the human body.
Choi’s team developed a wearable patch using flexible OLEDs, allowing people to be treated outside of hospitals. A thin film has been developed for the patch, containing not only flexible OLEDs but also batteries and anti-superheating devices.
Moreover, its thickness is less than 1mm and its weight is less than 1g. This lightweight and ultra-thin patch with a bending radius is 20mm can be used more than 300 hours.
These patches are usable at a temperature below 42℃ to eliminate the risk of low-temperature burns. They also meet the safety regulations of the International Organization for Standardization (ISO) at red wavelengths (600–700 nm).
The wearable PBM patches showed excellent effects with in vitro wounds because they stimulated cell proliferation over 58% of control as well as cell migration over 46% of control under various conditions.
Yongmin Jeon, who led this research, said, “The wearable PBM is effective and convenient, so people can simply purchase it at a pharmacy without having to visit a hospital. If we can adjust the power and wavelength of the OLEDs, its application can be extended to skin care, cancer treatment, Alzheimer’s disease treatment, and mental healthcare.”
Professor Choi added, “We have applied the advantages of flexible OLEDs, which are often used for fabricating displays, to PBMs. This technology will open the way to commercialize portable and highly-efficient wearable photobiomodulation devices.”
This research was published in the front cover of Advanced Materials Technologies on May, 2018.
Figure 1. The patch attached to a human face, a hand and examples of treatment applications
Figure 2. The migration of cells into the scratched area
2018.05.25 View 8022 -
Recombinant E. Coli As a Biofactory for the Biosynthesis of Diverse Nanomaterials
(Distinguished Professor Lee and PhD candidate Choi)
A metabolic research group at KAIST and Chung-Ang University in Korea has developed a recombinant E. coli strain that biosynthesizes 60 different nanomaterials covering 35 elements on the periodic table. Among the elements, the team could biosynthesize 33 novel nanomaterials for the first time, advancing the forward design of nanomaterials through the biosynthesis of various single and multi-elements.
The study analyzed the nanomaterial biosynthesis conditions using a Pourbaix diagram to predict the producibility and crystallinity. Researchers studied a Pourbaix diagram to predict the stable chemical species of each element for nanomaterial biosynthesis at varying levels of reduction potential (Eh) and pH. Based on the Pourbaix diagram analyses, the initial pH of the reaction was changed from 6.5 to 7.5, resulting in the biosynthesis of various crystalline nanomaterials that were previously amorphous or not synthesized.
This strategy was extended to biosynthesize multi-element nanomaterials. Various single and multi-element nanomaterials biosynthesized in this research can potentially serve as new and novel nanomaterials for industrial applications such as catalysts, chemical sensors, biosensors, bioimaging, drug delivery, and cancer therapy.
A research group consisting of PhD candidate Yoojin Choi, Associate Professor Doh Chang Lee, and Distinguished Professor Sang Yup Lee of the Department of Chemical and Biomolecular Engineering at KAIST and Associate Professor Tae Jung Park of the Department of Chemistry at Chung-Ang University reported the synthesis. This study, entitled “Recombinant Escherichia coli as a biofactory for various single- and multi-element nanomaterials,” was published online in the Proceedings of the National Academy of Sciences of the United States of America (PNAS) on May 21.
A recent successful biosynthesis of nanomaterials under mild conditions without requiring physical and chemical treatments has triggered the exploration of the full biosynthesis capacity of a biological system for producing a diverse range of nanomaterials as well as for understanding biosynthesis mechanisms for crystalline versus amorphous nanomaterials.
There has been increased interest in synthesizing various nanomaterials that have not yet been synthesized for various applications including semiconducting materials, enhanced solar cells, biomedical materials, and many others. This research reports the construction of a recombinant E. coli strain that co-expresses metallothionein, a metal binding protein, and phytochelatin synthase that synthesizes the metal-binding peptide phytochelatin for the biosynthesis of various nanomaterials. Subsequently, an E. coli strain was engineered to produce a diverse range of nanomaterials, including those never biosynthesized before, by using 35 individual elements from the periodic table and also by combining multi-elements.
Distinguished Professor Lee said, “An environmentally-friendly and sustainable process is of much interest for producing nanomaterials by not only chemical and physical methods but biological synthesis. Moreover, there has been much attention paid to producing diverse and novel nanomaterials for new industrial applications. This is the first report to predict the biosynthesis of various nanomaterials, by far the largest number of various single- and multi-elements nanomaterials. The strategies used for nanomaterial biosynthesis in this research will be useful for further diversifying the portfolio of nanomaterials that can be manufactured.”
Figure: The biosynthesis of diverse nanomaterials using recombinant E. coli. This schematic diagram shows the overall conceptualization of the biosynthesis of various single and multi-element nanomaterials using recombinant E. coli under incubation with corresponding elemental precursors. The 35 elements that were tested to biosynthesize nanomaterials are shown in black circles on the periodic table.
2018.05.23 View 12411 -
A High-Performance and Cost Effective Hydrogen Sensor
(Research team of Professor Park, Professor Jung, and research fellow Gao Min)
A KAIST research team reported a high-performance and cost effective hydrogen sensor using novel fabrication process based on the combination of polystyrene nanosphere lithography and semiconductor microfabrication processes.
The research team, led by Professor Inkyu Park in the Department of Mechanical Engineering and Professor Yeon Sik Jung in the Department of Materials Science and Engineering, fabricated a nanostructured high-performance hydrogen gas sensor based on a palladium-decorated silicon nanomesh structure made using a polystyrene nanosphere self-assembly method. Their study was featured as the front cover article of journal “Small” (Publisher: Wiley-VCH) on March 8, 2018.
The nanosphere lithography method utilizes the self-assembly of a nanosphere monolayer. This could be an alternative choice for achieving uniform and well-ordered nanopatterns with minimum sub-10 nanometer dimensions. The research team said that the small dimensions of the silicon enhanced the palladium-gating effect and thus dramatically improved the sensitivity.
Hydrogen gas is widely considered to be one of the most promising next-generation energy resources. Also, it is a very important material for various industrial applications such as hydrogen-cooled systems, petroleum refinement, and metallurgical processes. However, hydrogen, which is highly flammable, is colorless and odorless and thus difficult to detect with human senses. Therefore, developing hydrogen gas sensors with high sensitivity, fast response, high selectivity, and good stability is of significant importance for the rising hydrogen economy.
Silicon nanowire-based devices have been employed as efficient components in high-performance sensors for detecting gases and other chemical and biological components. Since the nanowires have a high surface-to-volume ratio, they respond more sensitively to the surrounding environment.
The research team’s gas sensor shows dramatically improved hydrogen gas sensitivity compared with a silicon thin film sensor without nanopatterns. Furthermore, a buffered oxide etchant (BOE) treatment of the silicon nanomesh structure results in an additional performance improvement through suspension of nanomesh strutures from the substrate and surface roughening. The sensor device shows a fast hydrogen response (response time < 5 seconds) and 10 times higher selectivity to hydrogen gas among other gases. Their sensing performance is stable and shows repeatable responses in both dry and high-humidity ambient environments.
Professor Park said that his approach will be very useful for the fabrication of low-cost, high-performance sensors for chemical and biological detection with applications to mobile and wearable devices in the coming era of internet of things (IoTs).
(Figure 1: The front cover image of Small dated on March 8.)
(Figure 2: Gas sensor responses upon the exposure to H2 at various concentrations.)
2018.05.21 View 9919 -
Platinum Catalyst Has Price Lowed and Durability Doubled
(Professor Cho in the Department of Materials Science and Engineering)
Professor EunAe Cho in the Department of Materials Science and Engineering reported a fuel cell catalyst that shows 12 times higher performance and twice the durability than previously used platinum catalyst.
Fuel cells, eco-friendly power generators, are said to be running air purifiers. A hydrogen vehicle powered by fuel cells can allegedly purify more than 98 percent of the particulate matter and ultrafine particles from the amount of air that 70 adults breathe.
Despite this peculiarity, the high price of platinum, which is used as an electrode catalyst, remains a big challenge to accelerating commercialization. In addition, recently developed ‘nano-structured platinum catalysts’ have not yet commercialized due to its meager oxygen reduction reaction and durability in fuel cell.
Addressing all those challenges, Professor Cho’s team reported a platinum catalyst costing 30 percent less but boasting 12 times higher performance.
The research team, to this end, combined the platinum with nickel, then applied various metallic elements for making the most efficient performance. Among others, they found that the addition of gallium can modulate the oxygen intermediate binding energy, leading to enhanced catalytic activity of the oxygen reduction reaction.
They made octahedron nanoparticle platinum-nickel alloy and could efficiently achieve 12-times high performance with the platinum catalyst by adding gallium to the surface of octahedron.
Existing fuel cell catalysts have issues in practical fuel cell applications. However, Professor Cho’s team experimentally proved the high performance of the catalyst even in the fuel cell, and is expected to be practically applied to the existing procedure.
First author JeongHoon Lim said their work demonstrates the gallium-added octahedral nanoparticles can be utilized as a highly active and durable oxygen reduction reaction catalyst in practical fuel cell applications. It will make it feasible for the mass production of the catalysts.
Professor Cho also said, “Our study realized the two main goals: an affordable price and increased performance of fuel cells. We hope this will make a contribution to the market competitiveness of fuel cell electric vehicles.”
This research was described in Nano Letters in April and was supported by the Korea Institute of Energy Technology Evaluation and Planning (KETEP), the National Research Foundation (NRF), and the Agency for Defense Development (ADD).
(Figure: HAADF STEM images with EDX analyses and line scanning profiles of (a) Ga-PtNi/C and (b) PtNi/C during the voltage-cycling tests. The composition changes of Ni, Pt, and Ga atoms in the nanoparticles were determined by EDX (inset in the EDX mapping results)).
2018.05.15 View 8110 -
Capillary Forces at Work for Lithium-Sulfur Batteries
Professor Do Kyung Kim from the KAIST Department of Materials Science and Engineering and his team succeeded in developing high-areal-capacity lithium sulfur batteries (Li-S batteries) by capturing polysulfide with carbon nanofibers. This research will provide new batteries to replace existing lithium rechargeable batteries, shifting the commercialization of related technologies ahead.
Electrical vehicles and large-scale energy storage systems necessitate the development of batteries with high energy density and cost effectiveness, and Li-S batteries are known to be one of the promising alternatives to the predominant lithium ion batteries.
With six times as much energy density, Li-S batteries theoretically thrust electric vehicle to twice the distance of lithium ion batteries. Therefore, they have been spotlighted as next-generation lithium rechargeable batteries because they can go up to 400km once charged.
However, several issues make it challenging to readily commercialize Li-S batteries. The low electrical conductivity of sulfur, volumetric expansion and contraction of the battery during charge and discharge, and permanent damage of the electrode caused by the dissolution of the lithium polysulfide into the electrolyte – known as the “shuttle effect” – are three of the biggest obstacles to commercial-grade Li-S batteries.
While there have been numerous attempts to curb, avoid, or alleviate these issues — such as the physical encapsulation of sulfur using various metal oxides or carbonaceous matrices — most of them entail utilizing zero-dimensional (0D) carbon materials. This encapsulation method has been somewhat effective in enhancing the electrical conductivity of sulfur while simultaneously tolerating some volumetric alterations and suppressing the shuttle effect. The downside of 0D carbon material-based encapsulation methods is their complicated synthetic processing and the limited mass loading of sulfur.
With this in mind, the team set out to employ one-dimensional (1D) carbon materials instead. Unlike the 0D case, 1D carbon materials render a large surface area and a long-range conduction path for electrons and lithium ions. Being 1D also solves the undesirable high-contact resistance problem frequently encountered by 0D carbon material-based encapsulation.
The key to developing the proposed material was to exploit the capillary force to decrease the energy associated with the dissolution of polysulfides. As such, carbon nanofibers (CNFs) were found to be suitable for high-areal-capacity lithium-sulfur batteries since capillary force acting between CNFs can take advantage of the high electrical conductivity with the suppressed dissolution of sulfides.
The research findings show that sulfur was successfully contained in between the CNFs by wetting due to the capillary force without the need for complicated synthetic processing, as in the 0D case. The research results indicate that the sulfur contained per unit area (mg/cm2) is five times greater for the newly implemented method, which then enabled the lithium-sulfur battery to achieve an areal capacity of 7 mAh/cm2, which amounts to as much as at most seven times that of conventional lithium ion batteries.
First author Jong Hyuk Yun stated that the unprecedented methods utilized in this study will help further and widen the progress of lithium batteries in general. Meanwhile, Professor Kim said, “This study brought us closer to commercial-grade high-capacity Li-S batteries, which are applicable for a wide variety of products, including electric vehicles, unmanned aerial vehicles (UAVs), and drones.”
This research, led by PhD candidate Yun, was published in the 18th issue of this year’s Nano Letters.
Figure 1. Electrochemical reaction leading to the containment of the sulfur within the carbon nanofiber and the corresponding specific capacity of the battery over a number of charge-discharge cycles
Figure 2. SEM images of the first discharged electrode containing lithium sulfide at the junction between the nanofibers, and the first charged electrode
Figure 3. carbon nanofiber effectively absorbing liquid based lithium polysulfide
2018.05.14 View 8455 -
New Material for Generating Energy-Efficient Spin Currents
(Professor Byong-Guk Park (left) and Professor Kab-Jin Kim)
Magnetic random access memory (MRAM) is emerging as next-generation memory. It allows information to be kept even without an external power supply and its unique blend of high density and high speed operation is driving global semiconductor manufacturers to develop new versions continuously.
A KAIST team, led by Professor Byong-Guk Park in the Department of Materials Science and Engineering and Professor Kab-Jin Kim in the Department of Physics, recently has developed a new material which enables the efficient generation of a spin current, the core part of operating MRAM. This new material consisting of ferromagnet-transition metal bilayers can randomly control the direction of the generated spin current unlike the existing ones.
They also described a mechanism for spin-current generation at the interface between the bottom ferromagnetic layer and the non-magnetic spacer layer, which gives torques on the top magnetic layer that are consistent with the measured magnetization dependence.
When applying this to spin-orbit torque magnetic memory, it shows the increased efficiency of spin torque and generation of the spin current without an external magnetic field. High-speed operation, the distinct feature of spin-orbit torque-based MRAM that carries its non-volatility, can significantly reduce the standby power better than SRAM.
This new material will expect to speed up the commercialization of MRAM. The research team said that this magnetic memory will further be applied to mobile, wearable, and IoT devices.
This study, conducted in collaboration with Professor Kyung-Jin Lee from Korea University and Dr. Mark Stiles from the National Institute of Standards and Technology in the US, was featured in Nature Materials in March. The research was funded by the Creative Materials Discovery Program of the Ministry of Science and ICT.
(Figure: Ferromagnet-transition metal bilayers which can randomly control the direction of the generated spin current)
2018.05.11 View 11165 -
Yoon Ki Hong Named 2018 Jeong Hun Cho Awardee
(From left: PhD candidate Seungkwan Baek from the Department of Aerospace Engineering, Dr. Yoon Ki Hong from ADD, PhD candidate Wonhee Choi from the School of Mechanical Engineering at Korea University, and Jaehun Lee from Kongju National University High School)
Dr. Yoon Ki Hong from the Agency of Defense Development (ADD) was named the 2018 recipient of the Jong-Hoon Cho Award. The award recognizes outstanding young scientists in the field of aerospace engineering annually. The recipient of this award receives a 25 million KRW prize.
The Award Committee said that Dr. Hong has achieved outstanding work in the field of aerospace engineering. In particular, he conducted research on designing an air heating device which is the crucial component for ground experimental equipment. It is required for testing and evaluating supersonic vehicles’ structural strength tests using technology cannot be imported. In cooperation with his colleagues, he succeeded in developing an air heating device, a feat that has only been accomplished by developed countries. He also verified its operational performance.
Moreover, he received the best paper award from Korean Federation of Science and Minister of Defense Acquisition Program Administration’s Prize.
The award was endowed by the family of the late PhD candidate Jeong Hun Cho, who died in a rocket lab accident in the Department of Aerospace Engineering in 2003. Cho was posthumously conferred an honorary doctorate degree.
In Cho’s memory, his father established the ‘Jeong Hun Cho Award and Scholarship’. Since 2005, the scholarship annually selects three young scholars specializing in aerospace engineering from Cho’s alma maters of KAIST, Korea University, and Kongju National University High School.
In addition to Dr. Hong, the Award Committee chose three students for scholarships: PhD candidate Seungkwan Baek from the Department of Aerospace Engineering, PhD candidate Wonhee Choi from the School of Mechanical Engineering at Korea University, and Jaehun Lee from Kongju National University High School.
2018.05.11 View 11187 -
The First Recipient of the KPS Award in Plasma Physics
( Research Professor Sanghoo Park)
Research Professor Sanghoo Park received the Young Researcher Award in Plasma Physics during the Korean Physical Society (KPS)’s Spring Meeting from April 25 to 27.
He is a KAIST graduate with a PhD in Physics and currently holds the position of research professor in the Department of Nuclear and Quantum Engineering.
The Young Researcher Award in Plasma Physics is given to a specialist in plasma who has the potential to make a contribution to plasma and accelerator physics in Korea.
Professor Park has gained recognition for his work, including awards, publications in 24 journals, and 12 technical patent registrations of plasma, which led to his selection as the recipient of this award.
He is now conducting a leading role in this field nationally and internationally by delving into the study of partially-ionized plasma.
Professor Park said, “It is my great honor to become the first recipient of the Young Researcher Award in Plasma Physics. I will continue to engage in research to develop the field of plasma in Korea.”
2018.05.08 View 7714 -
Cross-Generation Collaborative Labs Open
KAIST opened two cross-generation collaborative labs last month. This novel approach will pair up senior and junior faculty members for sustaining research and academic achievements even after the senior researcher retires.
This is one of the Vision 2031 innovation initiatives established to extend the spectrum of knowledge and research competitiveness. The selected labs will be funded for five years and the funding will be extended if necessary. KAIST will continue to select new labs every year.
A five-member selection committee including the Nobel Laureates Professor Klaus Von Klitzing at the Max-Planck Institute for Solid State Research and Dr. Kurt Wüthrich from ETH Zürich selected the first two labs with senior-junior pairs in March.
(Two renowned scholars' Cross-Generation Collaborative Labs which opened last month.
Distinguished Professor Lee's lab (above) andChair Professor Sung's lab)
Both labs are run by world-renowned scholars: the Systems Metabolic Engineering and Systems Healthcare Laboratory headed by Distinguished Professor Sang-Yup Lee in the Department of Chemical and Biomolecular Engineering and the Acousto-Microfluidics Research Center for Next-Generation Healthcare led by Chair Professor Hyung Jin Sung in the Department of Mechanical Engineering.
Distinguished Professor Lee will be teamed up with Professor Hyun Uk Kim, and their lab aims to mass produce new eco-friendly chemical materials as well as higher-value-added materials which will be used for medicine. The new platform technologies created in the lab are expected to provide information which will benefit human healthcare.
Meanwhile, the Acousto-Microfluidics Research Center for Next-Generation Healthcare will team up with Professors Hyoungsoo Kim and Yeunwoo Cho under Chair Professor Sung. The lab will conduct research on controlling fluids and objects exquisitely on a micro-nano scale by using high-frequency acoustic waves. The lab plans to develop a next-generation healthcare platform for customized diagnoses as well as disease treatment.
KAIST President Sung-Chul Shin, who introduced this novel idea in his research innovation initiative, said that he hopes the Cross-Generation Collaborative Labs will contribute to honoring senior scholars’ research legacies and passing knowledge down to junior researchers in order to further develop their academic achievements. He said, “I sincerely hope the labs will make numerous research breakthroughs in the very near future.”
2018.05.03 View 13496 -
Professor Ju, to Receive Grants from HFSP
(Professor Young Seok Ju)
Professor Young Seok Ju from the Graduate School of Medical Science and Engineering was selected as a young investigator to receive research funds from the Human Frontiers Science Program.
The Human Frontiers Science Program (HFSP) was founded in 1989 with members of the G7 and European Union to stimulate innovative research in the field of life sciences.
Professor Ju placed third out of the eight teams that were selected from 158 applicants representing 60 countries. He is now the fourth Korean to receive a research grant as a young investigator. Professor Jae Kyoung Kim from the Department of Mathematical Sciences also received this prize last year, hence KAIST has produced grant recipients for two consecutive years.
Professor Ju is a medical doctor specializing in cancer genomics and computer biology. He has been studying somatic mutations and their functional consequences in human cancer in a bioinformatics way. He has published papers in international journals including Nature, Science, Genome Research, and Journal of Clinical Oncology.
With a title ‘Tracing AID/APOBEC- and MSI-mediated hyper-mutagenesis in the clonal evolution of gastric cancer,’ Professor Ju will receive 1.05 million dollars for three years along with Professor Bon-Kyoung Koo from the Institute of Molecular Biotechnology at Austrian Academy of Sciences, and Sinppert Hugo from University Medical Center Utrecht.
Professor Ju said, “As a young investigator, it is my great honor to receive this research fund from this organization. Through this internationally collaborative research, I will carry out groundbreaking research to understand the pathophysiology of cancers at a molecular level.”
2018.04.24 View 9908 -
Deep Learning Predicts Drug-Drug and Drug-Food Interactions
A Korean research team from KAIST developed a computational framework, DeepDDI, that accurately predicts and generates 86 types of drug-drug and drug-food interactions as outputs of human-readable sentences, which allows in-depth understanding of the drug-drug and drug-food interactions.
Drug interactions, including drug-drug interactions (DDIs) and drug-food constituent interactions (DFIs), can trigger unexpected pharmacological effects, including adverse drug events (ADEs), with causal mechanisms often unknown. However, current prediction methods do not provide sufficient details beyond the chance of DDI occurrence, or require detailed drug information often unavailable for DDI prediction.
To tackle this problem, Dr. Jae Yong Ryu, Assistant Professor Hyun Uk Kim and Distinguished Professor Sang Yup Lee, all from the Department of Chemical and Biomolecular Engineering at Korea Advanced Institute of Science and Technology (KAIST), developed a computational framework, named DeepDDI, that accurately predicts 86 DDI types for a given drug pair. The research results were published online in Proceedings of the National Academy of Sciences of the United States of America (PNAS) on April 16, 2018, which is entitled “Deep learning improves prediction of drug-drug and drug-food interactions.”
DeepDDI takes structural information and names of two drugs in pair as inputs, and predicts relevant DDI types for the input drug pair. DeepDDI uses deep neural network to predict 86 DDI types with a mean accuracy of 92.4% using the DrugBank gold standard DDI dataset covering 192,284 DDIs contributed by 191,878 drug pairs. Very importantly, DDI types predicted by DeepDDI are generated in the form of human-readable sentences as outputs, which describe changes in pharmacological effects and/or the risk of ADEs as a result of the interaction between two drugs in pair. For example, DeepDDI output sentences describing potential interactions between oxycodone (opioid pain medication) and atazanavir (antiretroviral medication) were generated as follows: “The metabolism of Oxycodone can be decreased when combined with Atazanavir”; and “The risk or severity of adverse effects can be increased when Oxycodone is combined with Atazanavir”. By doing this, DeepDDI can provide more specific information on drug interactions beyond the occurrence chance of DDIs or ADEs typically reported to date.
DeepDDI was first used to predict DDI types of 2,329,561 drug pairs from all possible combinations of 2,159 approved drugs, from which DDI types of 487,632 drug pairs were newly predicted. Also, DeepDDI can be used to suggest which drug or food to avoid during medication in order to minimize the chance of adverse drug events or optimize the drug efficacy. To this end, DeepDDI was used to suggest potential causal mechanisms for the reported ADEs of 9,284 drug pairs, and also predict alternative drug candidates for 62,707 drug pairs having negative health effects to keep only the beneficial effects. Furthermore, DeepDDI was applied to 3,288,157 drug-food constituent pairs (2,159 approved drugs and 1,523 well-characterized food constituents) to predict DFIs. The effects of 256 food constituents on pharmacological effects of interacting drugs and bioactivities of 149 food constituents were also finally predicted. All these prediction results can be useful if an individual is taking medications for a specific (chronic) disease such as hypertension or diabetes mellitus type 2.
Distinguished Professor Sang Yup Lee said, “We have developed a platform technology DeepDDI that will allow precision medicine in the era of Fourth Industrial Revolution. DeepDDI can serve to provide important information on drug prescription and dietary suggestions while taking certain drugs to maximize health benefits and ultimately help maintain a healthy life in this aging society.”
Figure 1. Overall scheme of Deep DDDI and prediction of food constituents that reduce the in vivo concentration of approved drugs
2018.04.18 View 13036