GE
-
KAIST Discovers Molecular Switch that Reverses Cancerous Transformation at the Critical Moment of Transition
< (From left) PhD student Seoyoon D. Jeong, (bottom) Professor Kwang-Hyun Cho, (top) Dr. Dongkwan Shin, Dr. Jeong-Ryeol Gong >
Professor Kwang-Hyun Cho’s research team has recently been highlighted for their work on developing an original technology for cancer reversal treatment that does not kill cancer cells but only changes their characteristics to reverse them to a state similar to normal cells. This time, they have succeeded in revealing for the first time that a molecular switch that can induce cancer reversal at the moment when normal cells change into cancer cells is hidden in the genetic network.
KAIST (President Kwang-Hyung Lee) announced on the 5th of February that Professor Kwang-Hyun Cho's research team of the Department of Bio and Brain Engineering has succeeded in developing a fundamental technology to capture the critical transition phenomenon at the moment when normal cells change into cancer cells and analyze it to discover a molecular switch that can revert cancer cells back into normal cells.
A critical transition is a phenomenon in which a sudden change in state occurs at a specific point in time, like water changing into steam at 100℃. This critical transition phenomenon also occurs in the process in which normal cells change into cancer cells at a specific point in time due to the accumulation of genetic and epigenetic changes.
The research team discovered that normal cells can enter an unstable critical transition state where normal cells and cancer cells coexist just before they change into cancer cells during tumorigenesis, the production or development of tumors, and analyzed this critical transition state using a systems biology method to develop a cancer reversal molecular switch identification technology that can reverse the cancerization process. They then applied this to colon cancer cells and confirmed through molecular cell experiments that cancer cells can recover the characteristics of normal cells.
This is an original technology that automatically infers a computer model of the genetic network that controls the critical transition of cancer development from single-cell RNA sequencing data, and systematically finds molecular switches for cancer reversion by simulation analysis. It is expected that this technology will be applied to the development of reversion therapies for other cancers in the future.
Professor Kwang-Hyun Cho said, "We have discovered a molecular switch that can revert the fate of cancer cells back to a normal state by capturing the moment of critical transition right before normal cells are changed into an irreversible cancerous state."
< Figure 1. Overall conceptual framework of the technology that automatically constructs a molecular regulatory network from single-cell RNA sequencing data of colon cancer cells to discover molecular switches for cancer reversion through computer simulation analysis. Professor Kwang-Hyun Cho's research team established a fundamental technology for automatic construction of a computer model of a core gene network by analyzing the entire process of tumorigenesis of colon cells turning into cancer cells, and developed an original technology for discovering the molecular switches that can induce cancer cell reversal through attractor landscape analysis. >
He continued, "In particular, this study has revealed in detail, at the genetic network level, what changes occur within cells behind the process of cancer development, which has been considered a mystery until now." He emphasized, "This is the first study to reveal that an important clue that can revert the fate of tumorigenesis is hidden at this very critical moment of change."
< Figure 2. Identification of tumor transition state using single-cell RNA sequencing data from colorectal cancer. Using single-cell RNA sequencing data from colorectal cancer patient-derived organoids for normal and cancerous tissues, a critical transition was identified in which normal and cancerous cells coexist and instability increases (a-d). The critical transition was confirmed to show intermediate levels of major phenotypic features related to cancer or normal tissues that are indicative of the states between the normal and cancerous cells (e). >
The results of this study, conducted by KAIST Dr. Dongkwan Shin (currently at the National Cancer Center), Dr. Jeong-Ryeol Gong, and doctoral student Seoyoon D. Jeong jointly with a research team at Seoul National University that provided the organoids (in vitro cultured tissues) from colon cancer patient, were published as an online paper in the international journal ‘Advanced Science’ published by Wiley on January 22nd.
(Paper title: Attractor landscape analysis reveals a reversion switch in the transition of colorectal tumorigenesis) (DOI: https://doi.org/10.1002/advs.202412503)
< Figure 3. Reconstruction of a dynamic network model for the transition state of colorectal cancer.
A new technology was established to build a gene network computer model that can simulate the dynamic changes between genes by integrating single-cell RNA sequencing data and existing experimental results on gene-to-gene interactions in the critical transition of cancer. (a). Using this technology, a gene network computer model for the critical transition of colorectal cancer was constructed, and the distribution of attractors representing normal and cancer cell phenotypes was investigated through attractor landscape analysis (b-e). >
This study was conducted with the support of the National Research Foundation of Korea under the Ministry of Science and ICT through the Mid-Career Researcher Program and Basic Research Laboratory Program and the Disease-Centered Translational Research Project of the Korea Health Industry Development Institute (KHIDI) of the Ministry of Health and Welfare.
< Figure 4. Quantification of attractor landscapes and discovery of transcription factors for cancer reversibility through perturbation simulation analysis. A methodology for implementing discontinuous attractor landscapes continuously from a computer model of gene networks and quantifying them as cancer scores was introduced (a), and attractor landscapes for the critical transition of colorectal cancer were secured (b-d). By tracking the change patterns of normal and cancer cell attractors through perturbation simulation analysis for each gene, the optimal combination of transcription factors for cancer reversion was discovered (e-h). This was confirmed in various parameter combinations as well (i). >
< Figure 5. Identification and experimental validation of the optimal target gene for cancer reversion. Among the common target genes of the discovered transcription factor combinations, we identified cancer reversing molecular switches that are predicted to suppress cancer cell proliferation and restore the characteristics of normal colon cells (a-d). When inhibitors for the molecular switches were treated to organoids derived from colon cancer patients, it was confirmed that cancer cell proliferation was suppressed and the expression of key genes related to cancer development was inhibited (e-h), and a group of genes related to normal colon epithelium was activated and transformed into a state similar to normal colon cells (i-j). >
< Figure 6. Schematic diagram of the research results. Professor Kwang-Hyun Cho's research team developed an original technology to systematically discover key molecular switches that can induce reversion of colon cancer cells through a systems biology approach using an attractor landscape analysis of a genetic network model for the critical transition at the moment of transformation from normal cells to cancer cells, and verified the reversing effect of actual colon cancer through cellular experiments. >
2025.02.05 View 24838 -
KAIST Uncovers the Principles of Gene Expression Regulation in Cancer and Cellular Functions
< (From left) Professor Seyun Kim, Professor Gwangrog Lee, Dr. Hyoungjoon Ahn, Dr. Jeongmin Yu, Professor Won-Ki Cho, and (below) PhD candidate Kwangmin Ryu of the Department of Biological Sciences>
A research team at KAIST has identified the core gene expression networks regulated by key proteins that fundamentally drive phenomena such as cancer development, metastasis, tissue differentiation from stem cells, and neural activation processes. This discovery lays the foundation for developing innovative therapeutic technologies.
On the 22nd of January, KAIST (represented by President Kwang Hyung Lee) announced that the joint research team led by Professors Seyun Kim, Gwangrog Lee, and Won-Ki Cho from the Department of Biological Sciences had uncovered essential mechanisms controlling gene expression in animal cells.
Inositol phosphate metabolites produced by inositol metabolism enzymes serve as vital secondary messengers in eukaryotic cell signaling systems and are broadly implicated in cancer, obesity, diabetes, and neurological disorders.
The research team demonstrated that the inositol polyphosphate multikinase (IPMK) enzyme, a key player in the inositol metabolism system, acts as a critical transcriptional activator within the core gene expression networks of animal cells. Notably, although IPMK was previously reported to play an important role in the transcription process governed by serum response factor (SRF), a representative transcription factor in animal cells, the precise mechanism of its action was unclear.
SRF is a transcription factor directly controlling the expression of at least 200–300 genes, regulating cell growth, proliferation, apoptosis, and motility, and is indispensable for organ development, such as in the heart.
The team discovered that IPMK binds directly to SRF, altering the three-dimensional structure of the SRF protein. This interaction facilitates the transcriptional activity of various genes through the SRF activated by IPMK, demonstrating that IPMK acts as a critical regulatory switch to enhance SRF's protein activity.
< Figure 1. The serum response factor (SRF) protein, a key transcription factor in animal cells, directly binds to inositol polyphosphate multikinase (IPMK) enzyme and undergoes structural change to acquire DNA binding ability, and precisely regulates growth and differentiation of animal cells through transcriptional activation. >
The team further verified that disruptions in the direct interaction between IPMK and SRF lead to the reduced functionality and activity of SRF, causing severe impairments in gene expression.
By highlighting the significance of the intrinsically disordered region (IDR) in SRF, the researchers underscored the biological importance of intrinsically disordered proteins (IDPs). Unlike most proteins that adopt distinct structures through folding, IDPs, including those with IDRs, do not exhibit specific structures but play crucial biological roles, attracting significant attention in the scientific community.
Professor Seyun Kim commented, "This study provides a vital mechanism proving that IPMK, a key enzyme in the inositol metabolism system, is a major transcriptional activator in the core gene expression network of animal cells. By understanding fundamental processes such as cancer development and metastasis, tissue differentiation from stem cells, and neural activation through SRF, we hope this discovery will lead to the broad application of innovative therapeutic technologies."
The findings were published on January 7th in the international journal Nucleic Acids Research (IF=16.7, top 1.8% in Biochemistry and Molecular Biology), under the title “Single-molecule analysis reveals that IPMK enhances the DNA-binding activity of the transcription factor SRF" (DOI: 10.1093/nar/gkae1281).
This research was supported by the National Research Foundation of Korea's Mid-career Research Program, Leading Research Center Program, and Global Research Laboratory Program, as well as by the Suh Kyungbae Science Foundation and the Samsung Future Technology Development Program.
2025.01.24 View 8663 -
A Way for Smartwatches to Detect Depression Risks Devised by KAIST and U of Michigan Researchers
- A international joint research team of KAIST and the University of Michigan developed a digital biomarker for predicting symptoms of depression based on data collected by smartwatches
- It has the potential to be used as a medical technology to replace the economically burdensome fMRI measurement test
- It is expected to expand the scope of digital health data analysis
The CORONA virus pandemic also brought about a pandemic of mental illness. Approximately one billion people worldwide suffer from various psychiatric conditions. Korea is one of more serious cases, with approximately 1.8 million patients exhibiting depression and anxiety disorders, and the total number of patients with clinical mental diseases has increased by 37% in five years to approximately 4.65 million. A joint research team from Korea and the US has developed a technology that uses biometric data collected through wearable devices to predict tomorrow's mood and, further, to predict the possibility of developing symptoms of depression.
< Figure 1. Schematic diagram of the research results. Based on the biometric data collected by a smartwatch, a mathematical algorithm that solves the inverse problem to estimate the brain's circadian phase and sleep stages has been developed. This algorithm can estimate the degrees of circadian disruption, and these estimates can be used as the digital biomarkers to predict depression risks. >
KAIST (President Kwang Hyung Lee) announced on the 15th of January that the research team under Professor Dae Wook Kim from the Department of Brain and Cognitive Sciences and the team under Professor Daniel B. Forger from the Department of Mathematics at the University of Michigan in the United States have developed a technology to predict symptoms of depression such as sleep disorders, depression, loss of appetite, overeating, and decreased concentration in shift workers from the activity and heart rate data collected from smartwatches.
According to WHO, a promising new treatment direction for mental illness focuses on the sleep and circadian timekeeping system located in the hypothalamus of the brain, which directly affect impulsivity, emotional responses, decision-making, and overall mood.
However, in order to measure endogenous circadian rhythms and sleep states, blood or saliva must be drawn every 30 minutes throughout the night to measure changes in the concentration of the melatonin hormone in our bodies and polysomnography (PSG) must be performed. As such treatments requires hospitalization and most psychiatric patients only visit for outpatient treatment, there has been no significant progress in developing treatment methods that take these two factors into account. In addition, the cost of the PSG test, which is approximately $1000, leaves mental health treatment considering sleep and circadian rhythms out of reach for the socially disadvantaged.
The solution to overcome these problems is to employ wearable devices for the easier collection of biometric data such as heart rate, body temperature, and activity level in real time without spatial constraints. However, current wearable devices have the limitation of providing only indirect information on biomarkers required by medical staff, such as the phase of the circadian clock.
The joint research team developed a filtering technology that accurately estimates the phase of the circadian clock, which changes daily, such as heart rate and activity time series data collected from a smartwatch. This is an implementation of a digital twin that precisely describes the circadian rhythm in the brain, and it can be used to estimate circadian rhythm disruption.
< Figure 2. The suprachiasmatic nucleus located in the hypothalamus of the brain is the central biological clock that regulates the 24-hour physiological rhythm and plays a key role in maintaining the body’s circadian rhythm. If the phase of this biological clock is disrupted, it affects various parts of the brain, which can cause psychiatric conditions such as depression. >
The possibility of using the digital twin of this circadian clock to predict the symptoms of depression was verified through collaboration with the research team of Professor Srijan Sen of the Michigan Neuroscience Institute and Professor Amy Bohnert of the Department of Psychiatry of the University of Michigan.
The collaborative research team conducted a large-scale prospective cohort study involving approximately 800 shift workers and showed that the circadian rhythm disruption digital biomarker estimated through the technology can predict tomorrow's mood as well as six symptoms, including sleep problems, appetite changes, decreased concentration, and suicidal thoughts, which are representative symptoms of depression.
< Figure 3. The circadian rhythm of hormones such as melatonin regulates various physiological functions and behaviors such as heart rate and activity level. These physiological and behavioral signals can be measured in daily life through wearable devices. In order to estimate the body’s circadian rhythm inversely based on the measured biometric signals, a mathematical algorithm is needed. This algorithm plays a key role in accurately identifying the characteristics of circadian rhythms by extracting hidden physiological patterns from biosignals. >
Professor Dae Wook Kim said, "It is very meaningful to be able to conduct research that provides a clue for ways to apply wearable biometric data using mathematics that have not previously been utilized for actual disease management." He added, "We expect that this research will be able to present continuous and non-invasive mental health monitoring technology. This is expected to present a new paradigm for mental health care. By resolving some of the major problems socially disadvantaged people may face in current treatment practices, they may be able to take more active steps when experiencing symptoms of depression, such as seeking counsel before things get out of hand."
< Figure 4. A mathematical algorithm was devised to circumvent the problems of estimating the phase of the brain's biological clock and sleep stages inversely from the biodata collected by a smartwatch. This algorithm can estimate the degree of daily circadian rhythm disruption, and this estimate can be used as a digital biomarker to predict depression symptoms. >
The results of this study, in which Professor Dae Wook Kim of the Department of Brain and Cognitive Sciences at KAIST participated as the joint first author and corresponding author, were published in the online version of the international academic journal npj Digital Medicine on December 5, 2024. (Paper title: The real-world association between digital markers of circadian disruption and mental health risks) DOI: 10.1038/s41746-024-01348-6
This study was conducted with the support of the KAIST's Research Support Program for New Faculty Members, the US National Science Foundation, the US National Institutes of Health, and the US Army Research Institute MURI Program.
2025.01.20 View 5879 -
KAIST Develops Neuromorphic Semiconductor Chip that Learns and Corrects Itself
< Photo. The research team of the School of Electrical Engineering posed by the newly deveoped processor. (From center to the right) Professor Young-Gyu Yoon, Integrated Master's and Doctoral Program Students Seungjae Han and Hakcheon Jeong and Professor Shinhyun Choi >
- Professor Shinhyun Choi and Professor Young-Gyu Yoon’s Joint Research Team from the School of Electrical Engineering developed a computing chip that can learn, correct errors, and process AI tasks
- Equipping a computing chip with high-reliability memristor devices with self-error correction functions for real-time learning and image processing
Existing computer systems have separate data processing and storage devices, making them inefficient for processing complex data like AI. A KAIST research team has developed a memristor-based integrated system similar to the way our brain processes information. It is now ready for application in various devices including smart security cameras, allowing them to recognize suspicious activity immediately without having to rely on remote cloud servers, and medical devices with which it can help analyze health data in real time.
KAIST (President Kwang Hyung Lee) announced on the 17th of January that the joint research team of Professor Shinhyun Choi and Professor Young-Gyu Yoon of the School of Electrical Engineering has developed a next-generation neuromorphic semiconductor-based ultra-small computing chip that can learn and correct errors on its own.
< Figure 1. Scanning electron microscope (SEM) image of a computing chip equipped with a highly reliable selector-less 32×32 memristor crossbar array (left). Hardware system developed for real-time artificial intelligence implementation (right). >
What is special about this computing chip is that it can learn and correct errors that occur due to non-ideal characteristics that were difficult to solve in existing neuromorphic devices. For example, when processing a video stream, the chip learns to automatically separate a moving object from the background, and it becomes better at this task over time.
This self-learning ability has been proven by achieving accuracy comparable to ideal computer simulations in real-time image processing. The research team's main achievement is that it has completed a system that is both reliable and practical, beyond the development of brain-like components.
The research team has developed the world's first memristor-based integrated system that can adapt to immediate environmental changes, and has presented an innovative solution that overcomes the limitations of existing technology.
< Figure 2. Background and foreground separation results of an image containing non-ideal characteristics of memristor devices (left). Real-time image separation results through on-device learning using the memristor computing chip developed by our research team (right). >
At the heart of this innovation is a next-generation semiconductor device called a memristor*. The variable resistance characteristics of this device can replace the role of synapses in neural networks, and by utilizing it, data storage and computation can be performed simultaneously, just like our brain cells.
*Memristor: A compound word of memory and resistor, next-generation electrical device whose resistance value is determined by the amount and direction of charge that has flowed between the two terminals in the past.
The research team designed a highly reliable memristor that can precisely control resistance changes and developed an efficient system that excludes complex compensation processes through self-learning. This study is significant in that it experimentally verified the commercialization possibility of a next-generation neuromorphic semiconductor-based integrated system that supports real-time learning and inference.
This technology will revolutionize the way artificial intelligence is used in everyday devices, allowing AI tasks to be processed locally without relying on remote cloud servers, making them faster, more privacy-protected, and more energy-efficient.
“This system is like a smart workspace where everything is within arm’s reach instead of having to go back and forth between desks and file cabinets,” explained KAIST researchers Hakcheon Jeong and Seungjae Han, who led the development of this technology. “This is similar to the way our brain processes information, where everything is processed efficiently at once at one spot.”
The research was conducted with Hakcheon Jeong and Seungjae Han, the students of Integrated Master's and Doctoral Program at KAIST School of Electrical Engineering being the co-first authors, the results of which was published online in the international academic journal, Nature Electronics, on January 8, 2025.
*Paper title: Self-supervised video processing with self-calibration on an analogue computing platform based on a selector-less memristor array ( https://doi.org/10.1038/s41928-024-01318-6 )
This research was supported by the Next-Generation Intelligent Semiconductor Technology Development Project, Excellent New Researcher Project and PIM AI Semiconductor Core Technology Development Project of the National Research Foundation of Korea, and the Electronics and Telecommunications Research Institute Research and Development Support Project of the Institute of Information & communications Technology Planning & Evaluation.
2025.01.17 View 6045 -
“Cross-Generation Collaborative Labs” for Semiconductor, Chemistry, and Computer Science Opened
< Photo of Professor Hoi-Jun Yoo (center) of the School of Electrical Engineering at the signboard unveiling ceremony >
KAIST held a ceremony to mark the opening of three additional ‘Cross-Generation Collaborative Labs’ on the morning of January 7th, 2025.
The “Next-Generation AI Semiconductor System Lab” by Professor Hoi-Jun Yoo of the School of Electrical Engineering, the “Molecular Spectroscopy and Chemical Dynamics Lab” by Professor Sang Kyu Kim of the Department of Chemistry, and the “Advanced Data Computing Lab” by Professor Sue Bok Moon of the School of Computer Science are the three new labs given the honored titled of the “Cross-Generation Collaborative Lab”.
The Cross-Generation Collaborative Lab is KAIST’s unique system that was set up to facilitate the collaboration between retiring professors and junior professors to continue the achievements and know-how the elders have accumulated over their academic career. Since its introduction in 2018, nine labs have been named to be the Cross-Generation Labs, and this year’s new addition brings the total up to twelve.
The ‘Next-Generation AI Semiconductor System Lab’ led by Professor Hoi-Jun Yoo will be operated by Professor Joo-Young Kim of the same school.
Professor Hoi-Jun Yoo is a world-renowned scholar with outstanding research achievements in the field of on-device AI semiconductor design. Professor Joo-Young Kim is an up-and-coming researcher studying large language models and design of AI semiconductors for server computers, and is currently researching technologies to design PIM (Processing-in-Memory), a core technology in the field of AI semiconductors.
Their research goal is to systematically collaborate and transfer next-generation AI semiconductor design technology, including brain-mimicking AI algorithms such as deep neural networks and generative AI, to integrate core technologies, and to maximize the usability of R&D outputs, thereby further solidifying the position of Korean AI semiconductor companies in the global market.
Professor Hoi-Jun Yoo said, “I believe that, we will be able to present a development direction of for the next-generation AI semiconductors industries at home and abroad through collaborative research and play a key role in transferring and expanding global leadership.”
< Professor Sang Kyu Kim of the Department of Chemistry (middle), at the signboard unveiling ceremony for his laboratory >
The “Molecular Spectroscopy and Chemical Dynamics Laboratory”, where Professor Sang Kyu Kim of the Department of Chemistry is in charge, will be operated by Professor Tae Kyu Kim of the same department, and another professor in the field of spectroscopy and dynamics will join in the future.
Professor Sang Kyu Kim has secured technologies for developing unique experimental equipment based on ultrashort lasers and supersonic molecular beams, and is a world leader who has been creatively pioneering new fields of experimental physical chemistry.
The research goal is to describe chemical reactions and verify from a quantum mechanical perspective and introduce new theories and technologies to pursue a complete understanding of the principles of chemical reactions. In addition, the accompanying basic scientific knowledge will be applied to the design of new materials.
Professor Sang Kyu Kim said, “I am very happy to be able to pass on the research infrastructure to the next generation through this system, and I will continue to nurture it to grow into a world-class research lab through trans-generational collaborative research.”
< Photo of Professor Sue Bok Moon (center) at the signboard unveiling ceremony by the School of Computing >
Lastly, the “Advanced Data Computing Lab” led by Professor Sue Bok Moon is joined by Professor Mee Young Cha of the same school and Professor Wonjae Lee of the Graduate School of Culture Technology.
Professor Sue Bok Moon showed the infinite possibilities of large-scale data-based social network research through Cyworld, YouTube, and Twitter, and had a great influence on related fields beyond the field of computer science.
Professor Mee Young Cha is a data scientist who analyzes difficult social issues such as misinformation, poverty, and disaster detection using big data-based AI. She is the first Korean to be recognized for her achievements as the director of the Max Planck Institute in Germany, a world-class basic science research institute. Therefore, there is high expectation for synergy effects from overseas collaborative research and technology transfer and sharing among the participating professors of the collaborative research lab. Professor Wonjae Lee is researching dynamic interaction analysis between science and technology using structural topic models.
They plan to conduct research aimed at improving the analysis and understanding of negative influences occurring online, and in particular, developing a hateful precursor detection model using emotions and morality to preemptively block hateful expressions.
Professor Sue Bok Moon said, “Through this collaborative research lab, we will play a key role in conducting in-depth collaborative research on unexpected negative influences in the AI era so that we can have a high level of competitiveness worldwide.”
The ceremonies for the unveiling of the new Cross-Generation Collaborative Lab signboard were held in front of each lab from 10:00 AM on the 7th, in the attendance of President Kwang Hyung Lee, Senior Vice President for Research Sang Yup Lee, and other key officials of KAIST and the new staff members to join the laboratories.
2025.01.07 View 3836 -
KAIST develops ‘Hoverbike’ to roam the future skies
< Photo 1. A group photo of the research team >
Hoverbike is a kind of next-generation mobility that can complement the existing transportation system and can be used as an air transportation means without traffic congestion through high-weight payloads and long-distance flights. It is expected that domestic researchers will contribute to the development of the domestic PAV* and UAM markets by developing a domestically developed manned/unmanned hybrid aircraft that escapes dependence on foreign technology through the development of a high-performance hoverbike.
*PAV: Personal Aerial Vehicle. It is a key element of future urban air mobility (UAM, Urban Air Mobility) and constitutes an important part of the next-generation transportation system.
KAIST (President Kwang-Hyung Lee) announced on the 27th of December that the research team of Professor Hyochoong Bang of the Department of Aerospace Engineering successfully developed the core technology of a highly reliable multipurpose vertical takeoff and landing hoverbike that can be operated by both manned and unmanned vehicles.
This research was participated by the research teams of Professor Jae-Hung Han, Professor Ji-yun Lee, Professor Jae-myung Ahn, Professor Han-Lim Choi, and Professor Chang-Hun Lee of the Department of Aerospace Engineering at KAIST, Professor Dongjin Lee of the Department of Unmanned Aerial Vehicles at Hanseo University, and Professor Jong-Oh Park of the Department of Electronics Engineering at Dong-A University.
The research team secured key technologies related to the optimal design of a multipurpose aircraft, hybrid propulsion system, highly reliable precision navigation and flight control system, autonomous flight, and fault detection for the development of a high-performance hoverbike.
< Figure 1. Key features of high-reliability multi-purpose hoverbike >
The hoverbike platform introduced a gasoline engine-based hybrid system to overcome the shortcomings of battery-based drones, achieving approximately 60% better performance and maximum payload weight compared to overseas technology levels. Through this, it is expected to be utilized in various fields such as emergency supply delivery, logistics, and rescue activities for civilian use, and military transport and mission support for military use.
The navigation system was applied by implementing multi-sensor fusion technology based on DGPS/INS* to enable stable flight even in environments without GPS or with weak signals using high-reliability precision navigation technology.
*DGPS/INS: Navigation solution combining high accuracy of Differential GPS (DGPS) and Inertial Navigation System (INS)
In addition, high-reliability flight control technology was developed to enable reliable maneuvering even under external factors such as payload and wind, and model uncertainty, and fault detection technology was also developed.
A guidance technique to automatically land on a helipad after selecting a safe automatic landing area by configuring a high-reliability autonomous flight system was implemented with high accuracy. Stable operation is possible even in complex environments through obstacle avoidance and automatic landing autonomous flight technology.
< Figure 2. Hoverbike prototype model >
Professor Hyochoong Bang, the research director, emphasized, “We have proven the high practicality of the hoverbike in various environments through high-reliability flight control and precision navigation technology.” He added, “The hoverbike is a promising research result that can not only provide a major path leading to PAVs and future aircraft, but also surpass existing drone technology by several levels. This achievement is even more meaningful because it is the result of five years of effort by eight joint research teams, including the project’s practitioners, PhD students Kwangwoo Jang and Hyungjoo Ahn.”
This study aims to secure core technologies for manned/unmanned multipurpose hoverbikes that can be utilized as new concept aircraft in the defense and civilian sectors. It started as the Defense Acquisition Program Administration’s Defense Technology for Future Challenge Research and Development Project in 2019 and was completed in 2024 under the management of the Agency for Defense Development. It is scheduled to be exhibited for the first time at the 2025 Drone Show Korea (DSK2025), which will be held at BEXCO in Busan from February 26 to 28, 2025.
2024.12.27 View 3968 -
KAIST Develops Foundational Technology to Revert Cancer Cells to Normal Cells
Despite the development of numerous cancer treatment technologies, the common goal of current cancer therapies is to eliminate cancer cells. This approach, however, faces fundamental limitations, including cancer cells developing resistance and returning, as well as severe side effects from the destruction of healthy cells.
< (From top left) Bio and Brain Engineering PhD candidates Juhee Kim, Jeong-Ryeol Gong, Chun-Kyung Lee, and Hoon-Min Kim posed for a group photo with Professor Kwang-Hyun Cho >
KAIST (represented by President Kwang Hyung Lee) announced on the 20th of December that a research team led by Professor Kwang-Hyun Cho from the Department of Bio and Brain Engineering has developed a groundbreaking technology that can treat colon cancer by converting cancer cells into a state resembling normal colon cells without killing them, thus avoiding side effects.
The research team focused on the observation that during the oncogenesis process, normal cells regress along their differentiation trajectory. Building on this insight, they developed a technology to create a digital twin of the gene network associated with the differentiation trajectory of normal cells.
< Figure 1. Technology for creating a digital twin of a gene network from single-cell transcriptome data of a normal cell differentiation trajectory. Professor Kwang-Hyun Cho's research team developed a digital twin creation technology that precisely observes the dynamics of gene regulatory relationships during the process of normal cells differentiating along a differentiation trajectory and analyzes the relationships among key genes to build a mathematical model that can be simulated (A-F). In addition, they developed a technology to discover key regulatory factors that control the differentiation trajectory of normal cells by simulating and analyzing this digital twin. >
< Figure 2. Digital twin simulation simulating the differentiation trajectory of normal colon cells. The dynamics of single-cell transcriptome data for the differentiation trajectory of normal colon cells were analyzed (A) and a digital twin of the gene network was developed representing the regulatory relationships of key genes in this differentiation trajectory (B). The simulation results of the digital twin confirm that it readily reproduces the dynamics of single-cell transcriptome data (C, D). >
Through simulation analysis, the team systematically identified master molecular switches that induce normal cell differentiation. When these switches were applied to colon cancer cells, the cancer cells reverted to a normal-like state, a result confirmed through molecular and cellular experiments as well as animal studies.
< Figure 3. Discovery of top-level key control factors that induce differentiation of normal colon cells. By applying control factor discovery technology to the digital twin model, three genes, HDAC2, FOXA2, and MYB, were discovered as key control factors that induce differentiation of normal colon cells (A, B). The results of simulation analysis of the regulatory effects of the discovered control factors through the digital twin confirmed that they could induce complete differentiation of colon cells (C). >
< Figure 4. Verification of the effect of the key control factors discovered using colon cancer cells and animal experiments on the reversibility of colon cancer. The key control factors of the normal colon cell differentiation trajectory discovered through digital twin simulation analysis were applied to actual colon cancer cells and colon cancer mouse animal models to experimentally verify the effect of cancer reversibility. The key control factors significantly reduced the proliferation of three colon cancer cell lines (A), and this was confirmed in the same way in animal models (B-D). >
This research demonstrates that cancer cell reversion can be systematically achieved by analyzing and utilizing the digital twin of the cancer cell gene network, rather than relying on serendipitous discoveries. The findings hold significant promise for developing reversible cancer therapies that can be applied to various types of cancer.
< Figure 5. The change in overall gene expression was confirmed through the regulation of the identified key regulatory factors, which converted the state of colon cancer cells to that of normal colon cells. The transcriptomes of colon cancer tissues and normal colon tissues from more than 400 colon cancer patients were compared with the transcriptomes of colon cancer cell lines and reversible colon cancer cell lines, respectively. The comparison results confirmed that the regulation of the identified key regulatory factors converted all three colon cancer cell lines to a state similar to the transcriptome expression of normal colon tissues. >
Professor Kwang-Hyun Cho remarked, "The fact that cancer cells can be converted back to normal cells is an astonishing phenomenon. This study proves that such reversion can be systematically induced."
He further emphasized, "This research introduces the novel concept of reversible cancer therapy by reverting cancer cells to normal cells. It also develops foundational technology for identifying targets for cancer reversion through the systematic analysis of normal cell differentiation trajectories."
This research included contributions from Jeong-Ryeol Gong, Chun-Kyung Lee, Hoon-Min Kim, Juhee Kim, and Jaeog Jeon, and was published in the online edition of the international journal Advanced Science by Wiley on December 11. (Title: “Control of Cellular Differentiation Trajectories for Cancer Reversion”) DOI: https://doi.org/10.1002/advs.202402132
< Figure 6. Schematic diagram of the research results. Professor Kwang-Hyun Cho's research team developed a source technology to systematically discover key control factors that can induce reversibility of colon cancer cells through a systems biology approach and a digital twin simulation analysis of the differentiation trajectory of normal colon cells, and verified the effects of reversion on actual colon cancer through molecular cell experiments and animal experiments. >
The study was supported by the Ministry of Science and ICT and the National Research Foundation of Korea through the Mid-Career Researcher Program and Basic Research Laboratory Program. The research findings have been transferred to BioRevert Inc., where they will be used for the development of practical cancer reversion therapies.
2024.12.23 View 99115 -
KAIST Proposes a New Way to Circumvent a Long-time Frustration in Neural Computing
The human brain begins learning through spontaneous random activities even before it receives sensory information from the external world. The technology developed by the KAIST research team enables much faster and more accurate learning when exposed to actual data by pre-learning random information in a brain-mimicking artificial neural network, and is expected to be a breakthrough in the development of brain-based artificial intelligence and neuromorphic computing technology in the future.
KAIST (President Kwang-Hyung Lee) announced on the 16th of December that Professor Se-Bum Paik 's research team in the Department of Brain Cognitive Sciences solved the weight transport problem*, a long-standing challenge in neural network learning, and through this, explained the principles that enable resource-efficient learning in biological brain neural networks.
*Weight transport problem: This is the biggest obstacle to the development of artificial intelligence that mimics the biological brain. It is the fundamental reason why large-scale memory and computational work are required in the learning of general artificial neural networks, unlike biological brains.
Over the past several decades, the development of artificial intelligence has been based on error backpropagation learning proposed by Geoffery Hinton, who won the Nobel Prize in Physics this year. However, error backpropagation learning was thought to be impossible in biological brains because it requires the unrealistic assumption that individual neurons must know all the connected information across multiple layers in order to calculate the error signal for learning.
< Figure 1. Illustration depicting the method of random noise training and its effects >
This difficult problem, called the weight transport problem, was raised by Francis Crick, who won the Nobel Prize in Physiology or Medicine for the discovery of the structure of DNA, after the error backpropagation learning was proposed by Hinton in 1986. Since then, it has been considered the reason why the operating principles of natural neural networks and artificial neural networks will forever be fundamentally different.
At the borderline of artificial intelligence and neuroscience, researchers including Hinton have continued to attempt to create biologically plausible models that can implement the learning principles of the brain by solving the weight transport problem.
In 2016, a joint research team from Oxford University and DeepMind in the UK first proposed the concept of error backpropagation learning being possible without weight transport, drawing attention from the academic world. However, biologically plausible error backpropagation learning without weight transport was inefficient, with slow learning speeds and low accuracy, making it difficult to apply in reality.
KAIST research team noted that the biological brain begins learning through internal spontaneous random neural activity even before experiencing external sensory experiences. To mimic this, the research team pre-trained a biologically plausible neural network without weight transport with meaningless random information (random noise).
As a result, they showed that the symmetry of the forward and backward neural cell connections of the neural network, which is an essential condition for error backpropagation learning, can be created. In other words, learning without weight transport is possible through random pre-training.
< Figure 2. Illustration depicting the meta-learning effect of random noise training >
The research team revealed that learning random information before learning actual data has the property of meta-learning, which is ‘learning how to learn.’ It was shown that neural networks that pre-learned random noise perform much faster and more accurate learning when exposed to actual data, and can achieve high learning efficiency without weight transport.
< Figure 3. Illustration depicting research on understanding the brain's operating principles through artificial neural networks >
Professor Se-Bum Paik said, “It breaks the conventional understanding of existing machine learning that only data learning is important, and provides a new perspective that focuses on the neuroscience principles of creating appropriate conditions before learning,” and added, “It is significant in that it solves important problems in artificial neural network learning through clues from developmental neuroscience, and at the same time provides insight into the brain’s learning principles through artificial neural network models.”
This study, in which Jeonghwan Cheon, a Master’s candidate of KAIST Department of Brain and Cognitive Sciences participated as the first author and Professor Sang Wan Lee of the same department as a co-author, was presented at the 38th Neural Information Processing Systems (NeurIPS), the world's top artificial intelligence conference, on December 14th in Vancouver, Canada. (Paper title: Pretraining with random noise for fast and robust learning without weight transport)
This study was conducted with the support of the National Research Foundation of Korea's Basic Research Program in Science and Engineering, the Information and Communications Technology Planning and Evaluation Institute's Talent Development Program, and the KAIST Singularity Professor Program.
2024.12.16 View 6067 -
KAIST Scientifically Identifies a Method to Prevent Dental Erosion from Carbonated Drinks
A Korean research team, which had previously visualized and scientifically proven the harmful effects of carbonated drinks like cola on dental health using nanotechnology, has now identified a mechanism for an effective method to prevent tooth damage caused by these beverages.
KAIST (represented by President Kwang Hyung Lee) announced on the 5th of December that a team led by Professor Seungbum Hong from the Department of Materials Science and Engineering, in collaboration with Seoul National University's School of Dentistry (Departments of Pediatric Dentistry and Oral Microbiology) and Professor Hye Ryung Byon’s research team from the Department of Chemistry, has revealed through nanotechnology that silver diamine fluoride (SDF)* forms a fluoride-containing protective layer on the tooth surface, effectively inhibiting cola-induced erosion.
*SDF (Silver Diamine Fluoride): A dental agent primarily used for the treatment and prevention of tooth decay. SDF strengthens carious lesions, suppresses bacterial growth, and halts the progression of cavities.
The team analyzed the surface morphology and mechanical properties of tooth enamel on a nanoscale using atomic force microscopy (AFM). They also examined the chemical properties of the nano-film formed by SDF treatment using X-ray photoelectron spectroscopy (XPS)* and Fourier-transform infrared spectroscopy (FTIR)*.
*XPS (X-ray Photoelectron Spectroscopy): A powerful surface analysis technique used to investigate the chemical composition and electronic structure of materials.
*FTIR (Fourier-Transform Infrared Spectroscopy): An analytical method that identifies the molecular structure and composition of materials by analyzing how they absorb or transmit infrared light.
The findings showed significant differences in surface roughness and elastic modulus between teeth exposed to cola with and without SDF treatment. Teeth treated with SDF exhibited minimal changes in surface roughness due to erosion (from 64 nm to 70 nm) and maintained a high elastic modulus (from 215 GPa to 205 GPa).
This was attributed to the formation of a fluoroapatite* layer by SDF, which acted as a protective shield.
*Fluoroapatite: A phosphate mineral with the chemical formula Ca₅(PO₄)₃F (calcium fluoro-phosphate). It can occur naturally or be synthesized biologically/artificially and plays a crucial role in strengthening teeth and bones.
< Figure 1. Schematic of the workflow. Surface morphology and mechanical properties of untreated and treated silver diamine fluoride (SDF) treated enamel exposed to cola were analyzed over time using atomic force microscopy (AFM). >
Professor Young J. Kim from Seoul National University's Department of Pediatric Dentistry noted, "This technology could be applied to prevent dental erosion and strengthen teeth for both children and adults. It is a cost-effective and accessible dental treatment."
< Figure 2. Changes in surface roughness and elastic modulus according to time of exposure to cola for SDF untreated and treated teeth. After 1 hour, the surface roughness of the SDF untreated teeth rapidly became rougher from 83 nm to 287 nm and the elastic modulus weakened from 125 GPa to 13 GPa, whereas the surface roughness of the SDF treated teeth changed only slightly from 64 nm to 70 nm and the elastic modulus barely changed from 215 GPa to 205 GPa, maintaining a similar state to the initial state. >
Professor Seungbum Hong emphasized, "Dental health significantly impacts quality of life. This research offers an effective non-invasive method to prevent early dental erosion, moving beyond traditional surgical treatments. By simply applying SDF, dental erosion can be prevented and enamel strengthened, potentially reducing pain and costs associated with treatment."
This study, led by the first author Aditi Saha, a PhD student in KAIST’s Department of Materials Science and Engineering, was published in the international journal Biomaterials Research on November 7 under the title "Nanoscale Study on Noninvasive Prevention of Dental Erosion of Enamel by Silver Diamine Fluoride". The research was supported by the National Research Foundation of Korea.
2024.12.11 View 4002 -
KAIST Awarded Presidential Commendation for Contributions in Software Industry
- At the “25th Software Industry Day” celebration held in the afternoon on Monday, December 2nd, 2024 at Yangjae L Tower in Seoul
- KAIST was awarded the “Presidential Commendation” for its contributions for the advancement of the Software Industry in the Group Category
- Korea’s first AI master’s and doctoral degree program opened at KAIST Kim Jaechul Graduate School of AI
- Focus on training non-major developers through SW Officer Training Academy "Jungle", Machine Learning Engineer Bootcamp, etc., talents who can integrate development and collaboration, and advanced talents in the latest AI technologies.
- Professor Minjoon Seo of KAIST Kim Jaechul Graduate School of AI received Prime Minister’s Commendation for his contributions for the advancement of the software industry.
< Photo 1. Professor Kyung-soo Kim, the Senior Vice President for Planning and Budget (second from the left) and the Manager of Planning Team, Mr. Sunghoon Jung, stand at the stage after receiving the Presidential Commendation as KAIST was selected as one of the groups that contributed to the advancement of the software industry at the "25th Software Industry Day" celebration. >
“KAIST has been leading the way in achieving the grand goal of fostering 1 million AI talents in Korea by services that pan from providing various educational opportunities, from developing the capabilities of experts with no computer science specialty to fostering advanced professionals. I would like to thank all members of KAIST community who worked hard to achieve the great feat of receiving the Presidential Commendations.” (KAIST President Kwang Hyung Lee)
KAIST (President Kwang Hyung Lee) announced on December 3rd that it was selected as a group that contributed to the advancement of the software industry at the “2024 Software Industry Day” celebration held at the Yangjae El Tower in Seoul on the 2nd of December and received a presidential commendation.
The “Software Industry Day”, hosted by the Ministry of Science and ICT and organized by the National IT Industry Promotion Agency and the Korea Software Industry Association, is an event designed to promote the status of software industry workers in Korea and to honor their achievements.
Every year, those who have made significant contributions to policy development, human resource development, and export growth for industry revitalization are selected and awarded the ‘Software Industry Development Contribution Award.’
KAIST was recognized for its contribution to developing a demand-based, industrial field-centric curriculum and fostering non-major developers and convergence talents with the goal of expanding software value and fostering excellent human resources.
< Photo 2. Senior Vice President for Planning and Budget Kyung-soo Kim receiving the commendation as the representative of KAIST >
Specifically, it first opened the SW Officer Training Academy "Jungle" to foster convergent program developers equipped with the abilities to handle both the computer coding and human interactions for collaborations. This is a non-degree program that provides intensive study and assignments for 5 months for graduates and intellectuals without prior knowledge of computer science.
KAIST Kim Jaechul Graduate School of AI opened and operated Korea’s first master's and doctoral degree program in the field of artificial intelligence. In addition, it planned a “Machine Learning Engineers’ Boot Camp” and conducted lectures and practical training for a total of 16 weeks on the latest AI technologies such as deep learning basics and large language models. It aims to strengthen the practical capabilities of start-up companies while lowering the threshold for companies to introduce AI technology.
Also, KAIST was selected to participate in the 1st and 2nd stages of the Software-centered University Project and has been taking part in the project since 2016. Through this, it was highly evaluated for promoting curriculum based on latest technology, an autonomous system where students directly select integrated education, and expansion of internships.
< Photo 3. Professor Minjoon Seo of Kim Jaechul Graduate School of AI, who received the Prime Minister's Commendation for his contribution to the advancement of the software industry on the same day >
At the awards ceremony that day, Professor Minjoon Seo of KAIST Kim Jaechul Graduate School of AI also received the Prime Minister's Commendation for his contribution to the advancement of the software industry. Professor Seo was recognized for his leading research achievements in the fields of AI and natural language processing by publishing 28 papers in top international AI conferences over the past four years.
At the same time, he was noted for his contributions to enhancing the originality and innovation of language model research, such as △knowledge encoding, △knowledge access and utilization, and △high-dimensional inference performance, and for demonstrating leadership in the international academic community.
President Kwang Hyung Lee of KAIST stated, “Our university will continue to do its best to foster software talents with global competitiveness through continuous development of cutting-edge curriculum and innovative degree systems.”
2024.12.03 View 4987 -
KAIST Secures Core Technology for Ultra-High-Resolution Image Sensors
A joint research team from Korea and the United States has developed next-generation, high-resolution image sensor technology with higher power efficiency and a smaller size compared to existing sensors. Notably, they have secured foundational technology for ultra-high-resolution shortwave infrared (SWIR) image sensors, an area currently dominated by Sony, paving the way for future market entry.
KAIST (represented by President Kwang Hyung Lee) announced on the 20th of November that a research team led by Professor SangHyeon Kim from the School of Electrical Engineering, in collaboration with Inha University and Yale University in the U.S., has developed an ultra-thin broadband photodiode (PD), marking a significant breakthrough in high-performance image sensor technology.
This research drastically improves the trade-off between the absorption layer thickness and quantum efficiency found in conventional photodiode technology. Specifically, it achieved high quantum efficiency of over 70% even in an absorption layer thinner than one micrometer (μm), reducing the thickness of the absorption layer by approximately 70% compared to existing technologies.
A thinner absorption layer simplifies pixel processing, allowing for higher resolution and smoother carrier diffusion, which is advantageous for light carrier acquisition while also reducing the cost. However, a fundamental issue with thinner absorption layers is the reduced absorption of long-wavelength light.
< Figure 1. Schematic diagram of the InGaAs photodiode image sensor integrated on the Guided-Mode Resonance (GMR) structure proposed in this study (left), a photograph of the fabricated wafer, and a scanning electron microscope (SEM) image of the periodic patterns (right) >
The research team introduced a guided-mode resonance (GMR) structure* that enables high-efficiency light absorption across a wide spectral range from 400 nanometers (nm) to 1,700 nanometers (nm). This wavelength range includes not only visible light but also light the SWIR region, making it valuable for various industrial applications.
*Guided-Mode Resonance (GMR) Structure: A concept used in electromagnetics, a phenomenon in which a specific (light) wave resonates (forming a strong electric/magnetic field) at a specific wavelength. Since energy is maximized under these conditions, it has been used to increase antenna or radar efficiency.
The improved performance in the SWIR region is expected to play a significant role in developing next-generation image sensors with increasingly high resolutions. The GMR structure, in particular, holds potential for further enhancing resolution and other performance metrics through hybrid integration and monolithic 3D integration with complementary metal-oxide-semiconductor (CMOS)-based readout integrated circuits (ROIC).
< Figure 2. Benchmark for state-of-the-art InGaAs-based SWIR pixels with simulated EQE lines as a function of TAL variation. Performance is maintained while reducing the absorption layer thickness from 2.1 micrometers or more to 1 micrometer or less while reducing it by 50% to 70% >
The research team has significantly enhanced international competitiveness in low-power devices and ultra-high-resolution imaging technology, opening up possibilities for applications in digital cameras, security systems, medical and industrial image sensors, as well as future ultra-high-resolution sensors for autonomous driving, aerospace, and satellite observation.
Professor Sang Hyun Kim, the lead researcher, commented, “This research demonstrates that significantly higher performance than existing technologies can be achieved even with ultra-thin absorption layers.”
< Figure 3. Top optical microscope image and cross-sectional scanning electron microscope image of the InGaAs photodiode image sensor fabricated on the GMR structure (left). Improved quantum efficiency performance of the ultra-thin image sensor (red) fabricated with the technology proposed in this study (right) >
The results of this research were published on 15th of November, in the prestigious international journal Light: Science & Applications (JCR 2.9%, IF=20.6), with Professor Dae-Myung Geum of Inha University (formerly a KAIST postdoctoral researcher) and Dr. Jinha Lim (currently a postdoctoral researcher at Yale University) as co-first authors. (Paper title: “Highly-efficient (>70%) and Wide-spectral (400 nm -1700 nm) sub-micron-thick InGaAs photodiodes for future high-resolution image sensors”)
This study was supported by the National Research Foundation of Korea.
2024.11.22 View 4462 -
KAIST Proposes AI Training Method that will Drastically Shorten Time for Complex Quantum Mechanical Calculations
- Professor Yong-Hoon Kim's team from the School of Electrical Engineering succeeded for the first time in accelerating quantum mechanical electronic structure calculations using a convolutional neural network (CNN) model
- Presenting an AI learning principle of quantum mechanical 3D chemical bonding information, the work is expected to accelerate the computer-assisted designing of next-generation materials and devices
The close relationship between AI and high-performance scientific computing can be seen in the fact that both the 2024 Nobel Prizes in Physics and Chemistry were awarded to scientists for their AI-related research contributions in their respective fields of study. KAIST researchers succeeded in dramatically reducing the computation time for highly sophisticated quantum mechanical computer simulations by predicting atomic-level chemical bonding information distributed in 3D space using a novel AI approach.
KAIST (President Kwang-Hyung Lee) announced on the 30th of October that Professor Yong-Hoon Kim's team from the School of Electrical Engineering developed a 3D computer vision artificial neural network-based computation methodology that bypasses the complex algorithms required for atomic-level quantum mechanical calculations traditionally performed using supercomputers to derive the properties of materials.
< Figure 1. Various methodologies are utilized in the simulation of materials and materials, such as quantum mechanical calculations at the nanometer (nm) level, classical mechanical force fields at the scale of tens to hundreds of nanometers, continuum dynamics calculations at the macroscopic scale, and calculations that mix simulations at different scales. These simulations are already playing a key role in a wide range of basic research and application development fields in combination with informatics techniques. Recently, there have been active efforts to introduce machine learning techniques to radically accelerate simulations, but research on introducing machine learning techniques to quantum mechanical electronic structure calculations, which form the basis of high-scale simulations, is still insufficient. >
The quantum mechanical density functional theory (DFT) calculations using supercomputers have become an essential and standard tool in a wide range of research and development fields, including advanced materials and drug design, as they allow fast and accurate prediction of material properties.
*Density functional theory (DFT): A representative theory of ab initio (first principles) calculations that calculate quantum mechanical properties from the atomic level.
However, practical DFT calculations require generating 3D electron density and solving quantum mechanical equations through a complex, iterative self-consistent field (SCF)* process that must be repeated tens to hundreds of times. This restricts its application to systems with only a few hundred to a few thousand atoms.
*Self-consistent field (SCF): A scientific computing method widely used to solve complex many-body problems that must be described by a number of interconnected simultaneous differential equations.
Professor Yong-Hoon Kim’s research team questioned whether recent advancements in AI techniques could be used to bypass the SCF process. As a result, they developed the DeepSCF model, which accelerates calculations by learning chemical bonding information distributed in a 3D space using neural network algorithms from the field of computer vision.
< Figure 2. The deepSCF methodology developed in this study provides a way to rapidly accelerate DFT calculations by avoiding the self-consistent field process (orange box) that had to be performed repeatedly in traditional quantum mechanical electronic structure calculations through artificial neural network techniques (green box). The self-consistent field process is a process of predicting the 3D electron density, constructing the corresponding potential, and then solving the quantum mechanical Cohn-Sham equations, repeating tens to hundreds of times. The core idea of the deepSCF methodology is that the residual electron density (δρ), which is the difference between the electron density (ρ) and the sum of the electron densities of the constituent atoms (ρ0), corresponds to chemical bonding information, so the self-consistent field process is replaced with a 3D convolutional neural network model. >
The research team focused on the fact that, according to density functional theory, electron density contains all quantum mechanical information of electrons, and that the residual electron density — the difference between the total electron density and the sum of the electron densities of the constituent atoms — contains chemical bonding information. They used this as the target for machine learning.
They then adopted a dataset of organic molecules with various chemical bonding characteristics, and applied random rotations and deformations to the atomic structures of these molecules to further enhance the model’s accuracy and generalization capabilities. Ultimately, the research team demonstrated the validity and efficiency of the DeepSCF methodology on large, complex systems.
< Figure 3. An example of applying the deepSCF methodology to a carbon nanotube-based DNA sequence analysis device model (top left). In addition to classical mechanical interatomic forces (bottom right), the residual electron density (top right) and quantum mechanical electronic structure properties such as the electronic density of states (DOS) (bottom left) containing information on chemical bonding are rapidly predicted with an accuracy corresponding to the standard DFT calculation results that perform the SCF process. >
Professor Yong-Hoon Kim, who supervised the research, explained that his team had found a way to map quantum mechanical chemical bonding information in a 3D space onto artificial neural networks. He noted, “Since quantum mechanical electron structure calculations underpin materials simulations across all scales, this research establishes a foundational principle for accelerating material calculations using artificial intelligence.”
Ryong-Gyu Lee, a PhD candidate in the School of Electrical Engineering, served as the first author of this research, which was published online on October 24 in Npj Computational Materials, a prestigious journal in the field of material computation. (Paper title: “Convolutional network learning of self-consistent electron density via grid-projected atomic fingerprints”)
This research was conducted with support from the KAIST High-Risk Research Program for Graduate Students and the National Research Foundation of Korea’s Mid-career Researcher Support Program.
2024.10.30 View 4881