interaction
-
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 10324 -
Sangeun Oh Recognized as a 2017 Google Fellow
Sangeun Oh, a Ph.D. candidate in the School of Computing was selected as a Google PhD Fellow in 2017. He is one of 47 awardees of the Google PhD Fellowship in the world.
The Google PhD Fellowship awards students showing outstanding performance in the field of computer science and related research. Since being established in 2009, the program has provided various benefits, including scholarships worth $10,000 USD and one-to-one research discussion with mentors from Google.
His research work on a mobile system that allows interactions among various kinds of smart devices was recognized in the field of mobile computing. He developed a mobile platform that allows smart devices to share diverse functions, including logins, payments, and sensors. This technology provides numerous user experiences that existing mobile platforms could not offer. Through cross-device functionality sharing, users can utilize multiple smart devices in a more convenient manner. The research was presented at The Annual International Conference on Mobile Systems, Applications, and Services (MobiSys) of the Association for Computing Machinery in July, 2017.
Oh said, “I would like to express my gratitude to my advisor, the professors in the School of Computing, and my lab colleagues. I will devote myself to carrying out more research in order to contribute to society.”
His advisor, Insik Shin, a professor in the School of Computing said, “Being recognized as a Google PhD Fellow is an honor to both the student as well as KAIST. I strongly anticipate and believe that Oh will make the next step by carrying out good quality research.”
2017.09.27 View 10128 -
Professor Jinah Park Received the Prime Minister's Award
Professor Jinah Park of the School of Computing received the Prime Minister’s Citation Ribbon on April 21 at a ceremony celebrating the Day of Science and ICT. The awardee was selected by the Ministry of Science, ICT and Future Planning and Korea Communications Commission.
Professor Park was recognized for her convergence R&D of a VR simulator for dental treatment with haptic feedback, in addition to her research on understanding 3D interaction behavior in VR environments. Her major academic contributions are in the field of medical imaging, where she developed a computational technique to analyze cardiac motion from tagging data.
Professor Park said she was very pleased to see her twenty-plus years of research on ways to converge computing into medical areas finally bear fruit. She also thanked her colleagues and students in her Computer Graphics and CGV Research Lab for working together to make this achievement possible.
2017.04.26 View 7936 -
KAIST Hosts the Wearable Computer Contest 2015
Deadlines for Prototype Contest by May 30, 2015 and August 15 for Idea Contest
KAIST will hold the Wearable Computer Contest 2015 in November, which will be sponsored by Samsung Electronics Co., Ltd.
Wearable computers have emerged as next-generation mobile devices, and are gaining more popularity with the growth of the Internet of Things. KAIST has introduced wearable devices such as K-Glass 2, a smart glass with augmented reality embedded. The Glass also works on commands by blinking eyes.
This year’s contest with the theme of “Wearable Computers for Internet of Things” is divided into two parts: the Prototype Competition and Idea Contest.
With the fusion of information technology (IT) and fashion, contestants are encouraged to submit prototypes of their ideas by May 30, 2015. The ten teams that make it to the finals will receive a wearable computer platform and Human-Computer Interaction (HCI) education, along with a prize of USD 1,000 for prototype production costs. The winner of the Prototype Contest will receive a prize of USD 5,000 and an award from the Minister of Science, ICT and Future Planning (MSIP) of the Republic of Korea.
In the Idea Contest, posters containing ideas and concepts of wearable devices should be submitted by August 15, 2015. The teams that make it to the finals will have to display a life-size mockup in the final stage. The winner of the contest will receive a prize of USD 1,000 and an award from the Minister of MSIP.
Any undergraduate or graduate student in Korea can enter the Prototype Competition and anyone can participate in the Idea Contest.
The chairman of the event, Hoi-Jun Yoo, a professor of the Department of Electrical Engineering at KAIST, noted:
“There is a growing interest in wearable computers in the industry. I can easily envisage that there will be a new IT world where wearable computers are integrated into the Internet of Things, healthcare, and smart homes.”
More information on the contest can be found online at http://www.ufcom.org.
Picture: Finalists in the last year’s contest
2015.05.11 View 7182 -
Interactions Features KAIST's Human-Computer Interaction Lab
Interactions, a bi-monthly magazine published by the Association for Computing Machinery (ACM), the largest educational and scientific computing society in the world, featured an article introducing Human-Computer Interaction (HCI) Lab at KAIST in the March/April 2015 issue (http://interactions.acm.org/archive/toc/march-april-2015).
Established in 2002, the HCI Lab (http://hcil.kaist.ac.kr/) is run by Professor Geehyuk Lee of the Computer Science Department at KAIST. The lab conducts various research projects to improve the design and operation of physical user interfaces and develops new interaction techniques for new types of computers. For the article, see the link below:
ACM Interactions, March and April 2015
Day in the Lab: Human-Computer Interaction Lab @ KAIST
http://interactions.acm.org/archive/view/march-april-2015/human-computer-interaction-lab-kaist
2015.03.02 View 8990 -
A KAIST Student Team Wins the ACM UIST 2014 Student Innovation Contest
A KAIST team consisted of students from the Departments of Industrial Design and Computer Science participated in the ACM UIST 2014 Student Innovation Contest and received 1st Prize in the category of People’s Choice.
The Association for Computing Machinery (ACM) Symposium on User Interface Software and Technology (UIST) is an international forum to promote innovations in human-computer interfaces, which takes place annually and is sponsored by ACM Special Interest Groups on Computer-Human Interaction (SIGCHI) and Computer Graphics (SIGGRAPH). The ACM UIST conference brings together professionals in the fields of graphical and web-user interfaces, tangible and ubiquitous computing, virtual and augmented reality, multimedia, and input and output devices.
The Student Innovation Contest has been held during the UIST conference since 2009 to innovate new interactions on state-of-the-art hardware. The participating students were given with the hardware platform to build on—this year, it was Kinoma Create, a JavaScript-powered construction kit that allows makers, professional product designers, and web developers to create personal projects, consumer electronics, and "Internet of Things" prototypes. Contestants demonstrated their creations on household interfaces, and two winners in each of three categories -- Most Creative, Most Useful, and the People’s Choice -- were awarded.
Utilizing Kinoma Create, which came with a built-in touchscreen, WiFi, Bluetooth, a front-facing sensor connector, and a 50-pin rear sensor dock, the KAIST team developed a “smart mop,” transforming the irksome task of cleaning into a fun game. The smart mop identifies target dirt and shows its location on the display built in the rod of a mop. If the user turns on a game mode, then winning scores are gained wherever the target dirt is cleaned.
The People’s Choice award was decided by conference attendees, and they voted the smart mop as their most favorite project.
Professor Tek-Jin Nam of the Department of Industrial Design at KAIST, who advised the students, said, "A total of 24 teams from such prestigious universities as Carnegie Mellon University, Georgia Institute of Technology, and the University of Tokyo joined the contest, and we are pleased with the good results. Many people, in fact, praised the integration of creativity and technical excellence our have shown through the smart mop.”
Team KAIST: pictured from right to left, Sun-Jun Kim, Se-Jin Kim, and Han-Jong Kim
The Smart Mop can clean the floor and offer users a fun game.
2014.11.12 View 10228 -
KAIST develops TransWall, a transparent touchable display wall
At a busy shopping mall, shoppers walk by store windows to find attractive items to purchase. Through the windows, shoppers can see the products displayed, but may have a hard time imagining doing something beyond just looking, such as touching the displayed items or communicating with sales assistants inside the store. With TransWall, however, window shopping could become more fun and real than ever before.
Woohun Lee, a professor of Industrial Design at KAIST, and his research team have recently developed TransWall, a two-sided, touchable, and transparent display wall that greatly enhances users' interpersonal experiences.
With an incorporated surface transducer, TransWall offers audio and vibrotactile feedback to the users. As a result, people can collaborate via a shared see-through display and communicate with one another by talking or even touching one another through the wall. A holographic screen film is inserted between the sheets of plexiglass, and beam projectors installed on each side of the wall project images that are reflected.
TransWall is touch-sensitive on both sides. Two users standing face-to-face on each side of the wall can touch the same spot at the same time without any physical interference. When this happens, TransWall provides the users with specific visual, acoustic, and vibrotactile experiences, allowing them to feel as if they are touching one another.
Professor Lee said, "TransWall concept enables people to see, hear, or even touch others through the wall while enjoying gaming and interpersonal communication. TransWall can be installed inside buildings, such as shopping centers, museums, and theme parks, for people to have an opportunity to collaborate even with strangers in a natural way."
He further added that "TransWall will be useful in places that require physical isolation for high security and safety, germ-free rooms in hospitals, for example." TransWall will allow patients to interact with family and friends without compromising medical safety.
TransWall was exhibited at the 2014 Conference on Computer-Human Interaction (CHI) held from April 26, 2014 to May 1, 2014 in Toronto, Canada.
YouTube Link:
http://www.youtube.com/watch?v=1QdYC_kOQ_w&list=PLXmuftxI6pTXuyjjrGFlcN5YFTKZinDhK
2014.07.15 View 7190 -
ACM Interactions: Demo Hour, March and April 2014 Issue
The
Association for Computing Machinery (ACM), the largest educational and scientific
computing society in the world, publishes a magazine called
Interactions
bi-monthly.
Interactions
is the flagship magazine
for the ACM’s Special Interest Group on Computer-Human Interaction (SIGCHI) with
a global circulation that includes all SIGCHI members.
In
its March and April 2014 issue, the Smart E-book was introduced. It was developed by Sangtae Kim, Jaejeung
Kim, and Soobin Lee at the Information Technology Convergence in KAIST
Institute, KAIST.
For
the article, please go to the link or download the .pdf files below:
Interactions,
March &
April 2014
Demo Hour: Bezel-Flipper
Bezel-Flipper
Interactions_Mar & Apr 2014.pdf
http://interactions.acm.org/archive/view/march-april-2014/demo-hour29
2014.03.28 View 9459 -
Success in Measuring Protein Interaction at the Molecular Level
Professor Tae Young Yoon
- Live observation of two protein interaction in molecular level successful- The limit in measurement and time resolution of immunoprecipitation technique improved by a hundred thousand fold
KAIST Department of Physics Professor Tae Young Yoon’s research team has successfully observed the interaction of two proteins live on molecular level and the findings were published in the October edition of Nature Protocols.
Professor Yoon’s research team developed a fluorescent microscope that can observe a single molecule. The team grafted the immunoprecipitation technique, traditionally used in protein interaction analysis, to the microscope to develop a “live molecular level immunoprecipitation technique”. The team successfully and accurately measured the reaction between two proteins by repeated momentary interactions in the unit of tens of milliseconds.
The existing immunoprecipitation technique required at least one day to detect interaction between two proteins. There were limitations in detecting momentary or weak interactions. Also, quantitative analysis of the results was difficult since the image was measured by protein-band strength. The technique could not be used for live observation.
The team aimed to drastically improve the existing technique and to develop accurate method of measurement on molecular level. The newly developed technology can enable observation of protein interaction within one hour. Also, the interaction can be measured live, thus the protein interaction phenomenon can be measured in depth.
Moreover, every programme used in the experiment was developed and distributed by the research team so source energy is secured and created the foundation for global infra.
Professor Tae Young Yoon said, “The newly developed technology does not require additional protein expression or purification. Hence, a very small sample of protein is enough to accurately analyse protein interaction on a kinetic level.” He continued, “Even cancerous protein from the tissue of a cancer patient can be analysed. Thus a platform for customised anti-cancer medicine in the future has been prepared, as well.”
Figure 1. Mimetic diagram comparing the existing immunoprecipitation technique and the newly developed live molecular level immunoprecipitation technique
2013.12.11 View 7490 -
A magnetic pen for smartphones adds another level of conveniences
Utilizing existing features on smartphones, the MagPen provides users with a compatible and simple input tool regardless of the type of phones they are using.
A doctoral candidate at the Korea Advanced Institute of Science and Technology (KAIST) developed a magnetically driven pen interface that works both on and around mobile devices. This interface, called the MagPen, can be used for any type of smartphones and tablet computers so long as they have magnetometers embedded in.
Advised by Professor Kwang-yun Wohn of the Graduate School of Culture Technology (GSCT) at KAIST, Sungjae Hwang, a Ph.D. student, created the MagPen in collaboration with Myung-Wook Ahn, a master"s student at the GSCT of KAIST, and Andrea Bianchi, a professor at Sungkyunkwan University.
Almost all mobile devices today provide location-based services, and magnetometers are incorporated in the integrated circuits of smartphones or tablet PCs, functioning as compasses. Taking advantage of built-in magnetometers, Hwang"s team came up with a technology that enabled an input tool for mobile devices such as a capacitive stylus pen to interact more sensitively and effectively with the devices" touch screen. Text and command entered by a stylus pen are expressed better on the screen of mobile devices than those done by human fingers.
The MagPen utilizes magnetometers equipped with smartphones, thus there is no need to build an additional sensing panel for a touchscreen as well as circuits, communication modules, or batteries for the pen. With an application installed on smartphones, it senses and analyzes the magnetic field produced by a permanent magnet embedded in a standard capacitive stylus pen.
Sungjae Hwang said, "Our technology is eco-friendly and very affordable because we are able to improve the expressiveness of the stylus pen without requiring additional hardware beyond those already installed on the current mobile devices. The technology allows smartphone users to enjoy added convenience while no wastes generated."
The MagPen detects the direction at which a stylus pen is pointing; selects colors by dragging the pen across smartphone bezel; identifies pens with different magnetic properties; recognizes pen-spinning gestures; and estimates the finger pressure applied to the pen.
Notably, with its spinning motion, the MagPen expands the scope of input gestures recognized by a stylus pen beyond its existing vocabularies of gestures and techniques such as titling, hovering, and varying pressures. The tip of the pen switches from a pointer to an eraser and vice versa when spinning. Or, it can choose the thickness of the lines drawn on a screen by spinning.
"It"s quite remarkable to see that the MagPen can understand spinning motion. It"s like the pen changes its living environment from two dimensions to three dimensions. This is the most creative characteristic of our technology," added Sungjae Hwang.
Hwang"s initial research result was first presented at the International Conference on Intelligent User Interfaces organized by the Association for Computing Machinery and held on March 19-22 in Santa Monica, the US.
In the next month of August, the research team will present a paper on the MagPen technology, entitled "MagPen: Magnetically Driven Pen Interaction On and Around Conventional Smartphones" and receive an Honorable Mention Award at the 15th International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI 2013) to be held in Germany.
In addition to the MagPen, Hwang and his team are conducting other projects to develop different types of magnetic gadgets (collectively called "MagGetz") that include the Magnetic Marionette, a magnetic cover for a smartphone, which offers augmented interactions with the phone, as well as magnetic widgets such as buttons and toggle interface.
Hwang has filed ten patents for the MagGetz technology.
Youtube Links: http://www.youtube.com/watch?v=NkPo2las7wc, http://www.youtube.com/watch?v=J9GtgyzoZmM
2013.07.25 View 9916 -
KAIST shocks the world with its creativity
Researchers at KAIST yielded great results at the world’s leading international Human Computer Interaction Society.
Professor Lee Gi Hyuk’s (Department of Computer Sciences) and Professor Bae Seok Hyung’ (Department of Industrial Design) respective teams received awards in two criteria in student innovation contest and was the only domestic university that presented their thesis at the ACM Symposium on User Interface Software.
The ACM UIST holds a student innovation contest prior to its opening. This year’s topic was the pressure sensing multi touch pad of Synaptics and involved 27 prestigious universities including MIT and CMU.
The KAIST team (Ki Son Joon Ph.D. candidate, Son Jeong Min M.A. candidate of Department of Computer Sciences and Woo Soo Jin M.A. candidate of Department of Industrial Design) designed a system that allows modulated control by attaching a simple structure to the pressure sensing multi touch pad.
The second KAIST team (Huh Seong Guk Ph.D. candidate, Han Jae Hyun Ph.D. candidate, Koo Ji Sung Ph.D. candidate at the Department of Computer Sciences, and Choi Ha Yan M.A. candidate at Department of Industrial Design) designed a system that utilizes a highly elastic fiber to allow the sensing of lateral forces. They also created a slingshot game application which was the second most popular system.
In the thesis session Professor Bae’s team (Lee DaWhee Ph.D. candidate, Son Kyung Hee Ph.D. candidate, Lee Joon Hyup M.A. candidate at Department of Industrial Design) presented a thesis that dealt with the technology that innovated the table pen for displays.
The new ‘phantom pen’ solved the issue arising from the hiding effect of the pen’s contact point and the display error due to the thickness of the display. In addition the ‘phantom pen’ has the ability to show the same effects as crayons or markers in a digital environment.
2012.11.29 View 9716 -
The thermal fluctuation and elasticity of cell membranes, lipid vesicles, interacting with pore-forming peptides were reported by a research team at KAIST.
A research team from KAIST, consisted of Sung-Min Choi, Professor of Nuclear and Quantum Engineering Department, and Ji-Hwan Lee, a doctoral student in the Department, published a paper on the “thermal fluctuation and elasticity of lipid vesicles interacting with pore-forming peptides.” The paper was carried by Physical Review Letters, an internationally renowned peer-review journal on physics on July 16, 2010.
Cell membranes, which consist of lipid bilayers, play important roles in cells as barriers to maintain concentrations and matrices to host membrane proteins. During cellular processes such as cell fission and fusion, the cell membranes undergo various morphological changes governed by the interplay between protein and lipid membranes. There have been many theoretical and experimental approaches to understand cellular processes driven by protein-lipid membrane interactions. However, it is not fully established how the membrane elastic properties, which play an important role in membrane deformation, are affected by the protein-membrane interactions.
Antimicrobial peptides are one of the most common examples of proteins that modify membrane morphology. While the pore-forming mechanisms of antimicrobial peptides in lipid bilayers have been widely investigated, there have been only a few attempts to understand the mechanisms in terms of membrane elastic properties. In particular, the effects of pore formation on the membrane fluctuation and elastic properties, which provide key information to understand the mechanism of antimicrobial peptide activity, have not been reported yet. The research team reports the thermal fluctuation and elasticity of lipid vesicles interacting with pore-forming peptides, which were measured by neutron spin-echo spectroscopy.
The results of this study are expected to pay an important role in understanding the elastic behavior and morphological changes of cell membranes induced by protein-membrane interactions, and may provide new insights for developing new theoretical models for membrane fluctuations which include the membrane mediated interaction between protein patches.
(a) (b)
Figure
(a) Schematics for bound melittin and pores in lipid bilayers
(b) P NMR signal ratio (with/without Mn2+) of DOPC LUV-melittin vs P/L at 30˚C. The dashed line is a guide for eyes.
2010.07.23 View 11215