BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Biomedical Mathematics Group - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Biomedical Mathematics Group
X-ORIGINAL-URL:https://www.ibs.re.kr/bimag
X-WR-CALDESC:Events for Biomedical Mathematics Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260424T100000
DTEND;TZID=Asia/Seoul:20260424T120000
DTSTAMP:20260503T223118
CREATED:20260406T092550Z
LAST-MODIFIED:20260406T103749Z
UID:12365-1777024800-1777032000@www.ibs.re.kr
SUMMARY:Foundation Models for Wearable Movement Data in Mental Health Research - Aqsa Awan
DESCRIPTION:In this tallk\, we discuss the paper “Foundation Models for Wearable Movement Data in Mental Health Research” by Franklin Y. Ruan et al.\, arXiv\, 2025. \nAbstract \nPretrained foundation models and transformer architectures have driven the success of large language models (LLMs) and other modern AI breakthroughs. However\, similar advancements in health data modeling remain limited due to the need for innovative adaptations. Wearable movement data offers a valuable avenue for exploration\, as it’s a core feature in nearly all commercial smartwatches\, well established in clinical and mental health research\, and the sequential nature of the data shares similarities to language. We introduce the Pretrained Actigraphy Transformer (PAT)\, the first open source foundation model designed for time-series wearable movement data. Leveraging transformer-based architectures and novel techniques\, such as patch embeddings\, and pretraining on data from 29\,307 participants in a national U.S. sample\, PAT achieves state-of-the-art performance in several mental health prediction tasks. PAT is also lightweight and easily interpretable\, making it a robust tool for mental health research.
URL:https://www.ibs.re.kr/bimag/event/foundation-models-for-wearable-movement-data-in-mental-health-research-aqsa-awan/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260417T100000
DTEND;TZID=Asia/Seoul:20260417T120000
DTSTAMP:20260503T223118
CREATED:20260403T080037Z
LAST-MODIFIED:20260406T060603Z
UID:12336-1776420000-1776427200@www.ibs.re.kr
SUMMARY:Discovering network dynamics with neural symbolic regression - Olive Cawiding
DESCRIPTION:In this tallk\, we discuss the paper “Discovering network dynamics with neural symbolic regression” by Zihan Yu et al.\, Nature Com. Science\, 2026. \nAbstract  \nNetwork dynamics are fundamental to analyzing the properties of high-dimensional complex systems and understanding their behavior. Despite the accumulation of observational data across many domains\, mathematical models exist in only a few areas with clear underlying principles. Here we show that a neural symbolic regression approach can bridge this gap by automatically deriving formulas from data. Our method reduces searches on high-dimensional networks to equivalent one-dimensional systems and uses pretrained neural networks to guide accurate formula discovery. Applied to ten benchmark systems\, it recovers the correct forms and parameters of underlying dynamics. In two empirical natural systems\, it corrects existing models of gene regulation and microbial communities\, reducing prediction error by 59.98% and 55.94%\, respectively. In epidemic transmission across human mobility networks of various scales\, it discovers dynamics that exhibit the same power-law distribution of node correlations across scales and reveal country-level differences in intervention effects. These results demonstrate that machine-driven discovery of network dynamics can enhance understandings of complex systems and advance the development of complexity science.
URL:https://www.ibs.re.kr/bimag/event/discovering-network-dynamics-with-neural-symbolic-regression-olive-cawiding/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260410T110000
DTEND;TZID=Asia/Seoul:20260410T120000
DTSTAMP:20260503T223118
CREATED:20260205T074338Z
LAST-MODIFIED:20260311T121617Z
UID:12182-1775818800-1775822400@www.ibs.re.kr
SUMMARY:A Data-Driven Computational Framework for Identifiability and Nonlinear Dynamics Discovery in Complex Systems - Wenrui Hao
DESCRIPTION:Data-driven modeling is essential for deciphering complex biological systems\, yet its utility is often constrained by two fundamental hurdles: the inability to guarantee parameter identifiability and the high computational cost of learning nonlinear dynamics. This talk introduces a unified computational framework designed to overcome these challenges\, bridging theoretical rigor with scalable machine learning. \n\nThe first component of the framework establishes a computational foundation for practical identifiability. By leveraging the Fisher Information Matrix and its theoretical links to coordinate identifiability\, we propose an efficient method for identifiability assessment. We further introduce regularization-based strategies to manage non-identifiable parameters\, thereby enhancing model reliability and facilitating robust uncertainty quantification. \n\nTo address the discovery of nonlinear dynamics\, we present the Laplacian Eigenfunction-Based Neural Operator (LE-NO). This operator learning framework is specifically engineered for modeling reaction–diffusion equations. By projecting nonlinear operators onto Laplacian eigenfunctions\, LE-NO achieves superior computational efficiency and generalization across varying boundary conditions\, effectively bypassing the limitations of large-scale architectures and data scarcity. \n\nFinally\, we demonstrate the framework’s utility in the context of Alzheimer’s disease modeling. We show that this integrated approach ensures reliable parameter inference while capturing the intricate nonlinear dynamics of disease progression\, providing a critical step toward the development of high-fidelity digital twins for neurodegenerative pathology. \n  \nZoom : 997 8258 4700 (pw : 1234)
URL:https://www.ibs.re.kr/bimag/event/a-data-driven-computational-framework-for-identifiability-and-nonlinear-dynamics-discovery-in-complex-systems-wenrui-hao/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Online Colloquium
ATTACH;FMTTYPE=image/jpeg:https://www.ibs.re.kr/bimag/cms/wp-content/uploads/2026/02/Wenrui-Hao-2-e1770278378786.jpg
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260403T110000
DTEND;TZID=Asia/Seoul:20260403T120000
DTSTAMP:20260503T223118
CREATED:20260205T073900Z
LAST-MODIFIED:20260311T121601Z
UID:12177-1775214000-1775217600@www.ibs.re.kr
SUMMARY:Stochastics in medicine: Delaying menopause and missing drug doses - Sean Lawley
DESCRIPTION:Stochastic modeling and analysis can help answer pressing medical questions. In this talk\, I will attempt to justify this claim by describing recent work on two problems in medicine. The first problem concerns ovarian tissue cryopreservation\, which is a proven tool to preserve ovarian follicles prior to gonadotoxic treatments. Can this procedure be applied to healthy women to delay or eliminate menopause? How can it be optimized? The second problem concerns medication nonadherence. What should you do if you miss a dose of medication? How can physicians design dosing regimens that are robust to missed/late doses? I will describe (a) how stochastics theory offers insights into these questions and (b) the mathematical questions that emerge from this investigation. \n  \nZoom : 997 8258 4700 (pw : 1234)
URL:https://www.ibs.re.kr/bimag/event/stochastics-in-medicine-delaying-menopause-and-missing-drug-doses-sean-lawley/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Online Colloquium
ATTACH;FMTTYPE=image/jpeg:https://www.ibs.re.kr/bimag/cms/wp-content/uploads/2026/02/Sean-Lawley-scaled-e1770278430433.jpg
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260327T100000
DTEND;TZID=Asia/Seoul:20260327T113000
DTSTAMP:20260503T223118
CREATED:20260326T001251Z
LAST-MODIFIED:20260326T001251Z
UID:12316-1774605600-1774611000@www.ibs.re.kr
SUMMARY:A multi-agent reinforcement learning framework for exploring dominant strategies in iterated and evolutionary games - Fanpeng Song
DESCRIPTION:In this talk\, we discuss the paper “A multi-agent reinforcement learning framework for exploring dominant strategies in iterated and evolutionary games” by Qi Su et al.\, Nat. Comm.\, 2026. \nAbstract \nExploring dominant strategies in iterated games holds theoretical and practical significance across diverse domains. Previous studies\, through mathematical analysis of limited cases\, have unveiled classic strategies such as tit-for-tat\, generous-tit-for-tat\, win-stay-lose-shift\, and zero-determinant strategies. While these strategies offer valuable insights into human decision-making\, they represent only a small subset of possible strategies\, constrained by limited mathematical and computational tools available to explore larger strategy spaces. To bridge this gap\, we propose an approach using multi-agent reinforcement learning to delve into complex decision-making processes that go beyond human intuition. Our approach has led to the discovery of a strategy that we call memory-two bilateral reciprocity strategy. Memory-two bilateral reciprocity strategy consistently outperforms a wide range of strategies in pairwise interactions while achieving high payoffs. When introduced into an evolving population with diverse strategies\, memory-two bilateral reciprocity strategy demonstrates dominance and fosters higher levels of cooperation and social welfare in both homogeneous and heterogeneous structures\, as well as across various game types. This high performance is verified by simulations and mathematical analysis. Our work highlights the potential of multi-agent reinforcement learning in uncovering dominant strategies in iterated and evolutionary games.
URL:https://www.ibs.re.kr/bimag/event/a-multi-agent-reinforcement-learning-framework-for-exploring-dominant-strategies-in-iterated-and-evolutionary-games-fanpeng-song/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260325T160000
DTEND;TZID=Asia/Seoul:20260325T170000
DTSTAMP:20260503T223118
CREATED:20260205T073506Z
LAST-MODIFIED:20260311T121525Z
UID:12171-1774454400-1774458000@www.ibs.re.kr
SUMMARY:Stochastic theory of complex biochemical reaction networks - Chen Jia
DESCRIPTION:Biochemical reaction networks and gene regulatory networks in cells are prototypical examples of complex systems\, characterized by highly nonlinear and stochastic\, multilevel dynamical interactions. Gaining a deep understanding of the stochastic dynamics and thermodynamic principles governing biochemical reaction networks not only helps elucidate the intrinsic mechanisms underlying cell fate decisions and the onset and progression of diseases\, but also provides new theoretical paradigms for the study of complex systems. This line of research has become one of the forefront interdisciplinary areas\, bridging mathematics\, physics\, biology\, chemistry\, statistics\, and intelligent science. In this talk\, I will present our recent research progress in this area\, with the hope of stimulating further discussion and inspiring new ideas. \n  \nZoom : 997 8258 4700 (pw : 1234)
URL:https://www.ibs.re.kr/bimag/event/stochastic-theory-of-complex-biochemical-reaction-networks-chen-jia/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Online Colloquium
ATTACH;FMTTYPE=image/jpeg:https://www.ibs.re.kr/bimag/cms/wp-content/uploads/2026/02/Chen-Jia-e1770278480855.jpg
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260320T100000
DTEND;TZID=Asia/Seoul:20260320T113000
DTSTAMP:20260503T223118
CREATED:20260304T051107Z
LAST-MODIFIED:20260304T051107Z
UID:12253-1774000800-1774006200@www.ibs.re.kr
SUMMARY:Temporal tissue dynamics from a spatial snapshot - Kang Min Lee
DESCRIPTION:In this talk\, we discuss the paper “Temporal tissue dynamics from a spatial snapshot” by Jonathan Somer et al.\, Nature\, 2026. \nAbstract \nPhysiological and pathological processes such as inflammation and cancer emerge from interactions between cells over time1. However\, methods to follow cell populations over time within the native context of a human tissue are lacking because a biopsy offers only a single snapshot. Here we present one-shot tissue dynamics reconstruction (OSDR)\, an approach to estimate a dynamical model of cell populations based on a single tissue sample. OSDR uses spatial proteomics to learn how the composition of cellular neighbourhoods influences division rate\, providing a dynamical model of cell population change over time. We apply OSDR to human breast cancer data2\,3\,4\, and reconstruct two fixed points of fibroblasts and macrophage interactions5\,6. These fixed points correspond to hot and cold fibrosis7\, in agreement with co-culture experiments that measured these dynamics directly8. We then use OSDR to discover a pulse-generating excitable circuit of T and B cells in the tumour microenvironment\, suggesting temporal flares of anticancer immune responses. Finally\, we study longitudinal biopsies from a triple-negative breast cancer clinical trial3\, in which OSDR predicts the collapse of the tumour cell population in responders but not in non-responders\, based on early-treatment biopsies. OSDR can be applied to a wide range of spatial proteomics assays to enable analysis of tissue dynamics based on patient biopsies.
URL:https://www.ibs.re.kr/bimag/event/temporal-tissue-dynamics-from-a-spatial-snapshot-kang-min-lee/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260313T100000
DTEND;TZID=Asia/Seoul:20260313T233000
DTSTAMP:20260503T223118
CREATED:20260304T045936Z
LAST-MODIFIED:20260304T045936Z
UID:12251-1773396000-1773444600@www.ibs.re.kr
SUMMARY:A multimodal sleep foundation model for disease prediction - Jinwoo Hyun
DESCRIPTION:In this talk\, we discuss the paper “A multimodal sleep foundation model for disease prediction” by Rahul Thapa et al.\, Nature Medicine\, 2026. \nAbstract \nSleep is a fundamental biological process with broad implications for physical and mental health\, yet its complex relationship with disease remains poorly understood. Polysomnography (PSG)—the gold standard for sleep analysis—captures rich physiological signals but is underutilized due to challenges in standardization\, generalizability and multimodal integration. To address these challenges\, we developed SleepFM\, a multimodal sleep foundation model trained with a new contrastive learning approach that accommodates multiple PSG configurations. Trained on a curated dataset of over 585\,000 hours of PSG recordings from approximately 65\,000 participants across several cohorts\, SleepFM produces latent sleep representations that capture the physiological and temporal structure of sleep and enable accurate prediction of future disease risk. From one night of sleep\, SleepFM accurately predicts 130 conditions with a C-Index of at least 0.75 (Bonferroni-corrected P < 0.01)\, including all-cause mortality (C-Index\, 0.84)\, dementia (0.85)\, myocardial infarction (0.81)\, heart failure (0.80)\, chronic kidney disease (0.79)\, stroke (0.78) and atrial fibrillation (0.78). Moreover\, the model demonstrates strong transfer learning performance on a dataset from the Sleep Heart Health Study—a dataset that was excluded from pretraining—and performs competitively with specialized sleep-staging models such as U-Sleep and YASA on common sleep analysis tasks\, achieving mean F1 scores of 0.70–0.78 for sleep staging and accuracies of 0.69 and 0.87 for classifying sleep apnea severity and presence. This work shows that foundation models can learn the language of sleep from multimodal sleep recordings\, enabling scalable\, label-efficient analysis and disease prediction.
URL:https://www.ibs.re.kr/bimag/event/a-multimodal-sleep-foundation-model-for-disease-prediction-jinwoo-hyun/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260227T100000
DTEND;TZID=Asia/Seoul:20260227T113000
DTSTAMP:20260503T223118
CREATED:20260219T012250Z
LAST-MODIFIED:20260219T012250Z
UID:12219-1772186400-1772191800@www.ibs.re.kr
SUMMARY:TwinCell: Large Causal Cell Model for Reliable and Interpretable Therapeutic Target Prioritisation - Yun Min Song
DESCRIPTION:In this talk\, we discuss the paper “TwinCell: Large Causal Cell Model for Reliable and Interpretable Therapeutic Target Prioritisation” by J.-B. Morlot et al.\, bioarxiv\, 2026. \nAbstract \nDrug discovery is impeded by the difficulty of translating targets from preclinical models to patients. Here\, we present TwinCell\, a Large Causal Cell Model (LCCM) capable of generalising from in vitro cell lines to patient-derived cell types while providing biologically meaningful interpretations of its predictions. Rather than predicting perturbation outcomes\, TwinCell focuses on identifying the upstream regulators driving the transition between diseased and healthy states. By integrating single-cell foundation model embeddings with a multiomics interactome\, TwinCell constrains predictions to mechanistically plausible signalling routes. To validate this approach\, we introduce TwinBench\, a novel benchmarking framework to assess virtual cell models generalisation capability while correcting for popularity bias and mode collapse through empirical p-value estimation. When applied to in clinico data\, TwinCell recovers known drug targets aligned with the biology of the disease and demonstrates generalisation performance on targets unseen during training. This highlights the model’s ability to learn mechanistic principles in a biological context. TwinCell represents a significant step toward building reliable and interpretable virtual cells for target identification bridging the gap between high-throughput in vitro experiments and clinical insights.
URL:https://www.ibs.re.kr/bimag/event/twincell-large-causal-cell-model-for-reliable-and-interpretable-therapeutic-target-prioritisation-yun-min-song/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260220T100000
DTEND;TZID=Asia/Seoul:20260220T113000
DTSTAMP:20260503T223118
CREATED:20260203T014207Z
LAST-MODIFIED:20260219T012056Z
UID:12168-1771581600-1771587000@www.ibs.re.kr
SUMMARY:GenAI-Net: A Generative AI Framework for Automated Biomolecular Network Design - Dongju Lim
DESCRIPTION:In this talk\, we discuss the paper “GenAI-Net: A Generative AI Framework for Automated Biomolecular Network Design” by M. Filo et al.\, arxiv\, 2026. \nAbstract \nBiomolecular networks underpin emerging technologies in synthetic biology—from robust biomanufacturing and metabolic engineering to smart therapeutics and cell-based diagnostics—and also provide a mechanistic language for understanding complex dynamics in natural and ecological systems. Yet designing chemical reaction networks (CRNs) that implement a desired dynamical function remains largely manual: while a proposed network can be checked by simulation\, the reverse problem of discovering a network from a behavioral specification is difficult\, requiring substantial human insight to navigate a vast space of topologies and kinetic parameters with nonlinear and possibly stochastic dynamics. Here we introduce GenAI-Net\, a generative AI framework that automates CRN design by coupling an agent that proposes reactions to simulation-based evaluation defined by a user-specified objective. GenAI-Net efficiently produces novel\, topologically diverse solutions across multiple design tasks\, in- cluding dose responses\, complex logic gates\, classifiers\, oscillators\, and robust perfect adaptation in deterministic and stochastic settings (including noise reduction). By turning specifications into families of circuit candidates and reusable motifs\, GenAI-Net provides a general route to programmable biomolecular circuit design and accelerates the translation from desired function to implementable mechanisms.
URL:https://www.ibs.re.kr/bimag/event/quantum-inspired-approach-to-analyzing-complex-system-dynamics-dongju-lim/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260213T100000
DTEND;TZID=Asia/Seoul:20260213T113000
DTSTAMP:20260503T223118
CREATED:20260203T013928Z
LAST-MODIFIED:20260203T013928Z
UID:12166-1770976800-1770982200@www.ibs.re.kr
SUMMARY:Intelligent in-cell electrophysiology - Chitaranjan Mahapatra
DESCRIPTION:In this talk\, we discuss the paper “Intelligent in-cell electrophysiology: Reconstructing intracellular action potentials using a physics-informed deep learning model trained on nanoelectrode array recordings” by K. Rahmani et al.\, Nat. Comm\, 2025. \nAbstract \nIntracellular electrophysiology is essential in neuroscience\, cardiology\, and pharmacology for studying cells’ electrical properties. Traditional methods like patch-clamp are precise but low-throughput and invasive. Nanoelectrode Arrays (NEAs) offer a promising alternative by enabling simultaneous intracellular and extracellular action potential (iAP and eAP) recordings with high throughput. However\, accessing intracellular potentials with NEAs remains challenging. This study presents an AI-supported technique that leverages thousands of synchronous eAP and iAP pairs from stem-cell-derived cardiomyocytes on NEAs. Our analysis revealed strong correlations between specific eAP and iAP features\, such as amplitude and spiking velocity\, indicating that extracellular signals could be reliable indicators of intracellular activity. We developed a physics-informed deep learning model to reconstruct iAP waveforms from extracellular recordings recorded from NEAs and Microelectrode arrays (MEAs)\, demonstrating its potential for non-invasive\, long-term\, high-throughput drug cardiotoxicity assessments. This AI-based model paves the way for future electrophysiology research across various cell types and drug interactions.
URL:https://www.ibs.re.kr/bimag/event/intelligent-in-cell-electrophysiology-chitaranjan-mahapatra/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260210T160000
DTEND;TZID=Asia/Seoul:20260210T180000
DTSTAMP:20260503T223118
CREATED:20260126T084409Z
LAST-MODIFIED:20260126T084537Z
UID:12148-1770739200-1770746400@www.ibs.re.kr
SUMMARY:Toward a Foundation Model for Molecular Tasks - Sungbin Lim
DESCRIPTION:Abstract \n(국문) 최근 거대언어모델(LLM)을 기술의 발전은 AI4Science 분야에서 Foundation Model 개발에 대한 세계적인 관심을 촉발하였다. 그 중에서도 신약 및 신소재 개발에 연계된 Molecular 도메인에서의 Foundation Model 연구는 막대한 산업적 영향력과 가치를 가지고 있다. 본 발표에서는 분자 구조 생성\, 물성\, 및 반응 예측 문제에 적용되기 위해 필요한 Multimodal LLM 연구 성과와 방향성을 소개하고자 한다. \n(English) The advancement of Large Language Models (LLMs) is drawing huge interest in developing Foundation Models for the field of AI4Science. In particular\,  Foundation Model research within the molecular domain\, specifically linked to drug discovery and advanced materials\, holds immense industrial impact and value. In this presentation\, we introduce recent achievements in Multimodal LLM research for molecular structure generation\, property prediction\, and chemical reaction forecasting. This is a joint work with LG AI Research.
URL:https://www.ibs.re.kr/bimag/event/toward-a-foundation-model-for-molecular-tasks-sungbin-lim/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Seminar
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260210T133000
DTEND;TZID=Asia/Seoul:20260210T150000
DTSTAMP:20260503T223118
CREATED:20260209T054541Z
LAST-MODIFIED:20260404T011156Z
UID:12203-1770730200-1770735600@www.ibs.re.kr
SUMMARY:IBS BIMAG 2025 Winter Internship Presentation
DESCRIPTION:Assigned time\nChair\nTopic\nMentee\nMentor\nTitle\n\n\n \n\n13:30–13:35\nMyna Lim\nDigital Health &\nClinical Methodology\nSuhyeon Hwang\nMyna Lim\nDevelopment of a Shortened Version of Cognitive Flexibility Inventory (CFI)\n\n\n13:35–13:40\nSugwon Cho\nMyna Lim\nMachine Learning–Based Development of a Short-Form Scale for Subjective Perceptions of Sleep Medications\n\n\n13:45–13:50\nTaekeun Kim\nKangmin Lee\nRevealing pattern of slow wave activity for insomnia diagnosis\n\n\n13:50–13:55\nJeongmin Kim\nJin Woo Hyun\nIterative Multi-Kernel Self-Supervised Learning for Multimodal Wearable Data\n\n \n\n13:55–14:00\nKangmin Lee\nSleep\nMinjae Kim\nKangmin Lee\nImproving prediction of circadian phase with mathematical model of sleep\n\n\n14:00–14:05\nDaewon Jeong\nYun Min Song\nAnalysis of Sleep Patterns Leading to Improved Sleep and Enhanced Alertness\n\n\n14:05–14:10\nSeunghun Lee\nYun Min Song\nAnalysis on relation between alertness and sleep quality during treatment\n\n \n\n14:10–14:15\nHyeong Jun Jang\nMolecular &\nCellular dynamics\nJunyoung Lee\nHyeong Jun Jang\nAI-based expansion of the validity condition for enzyme kinetic model\n\n\n14:15–14:20\nSe Jun Ahn\nHyeong Jun Jang\nPractical application of 2D-3D reaction-diffusion model in transporter\n\n\n14:20–14:25\nJaehun Jeong\nGyuyoung Hwang\nUnifying framework for circadian temperature robustness: The roles of waveform and intercellular coupling\n\n\n14:25–14:30\nJaehyuk Yang\nHyun Kim\nImproving Spatial Gene Prediction via scLENS-Driven SpaGE\n\n\n14:30–14:35\nMath & AI\nfor dynamics\nGia Hyun\nDongju Lim\nWeak form estimation of history-dependent epidemiological dynamics\n\n\n14:35–14:40\nGyeongwan Gu\nJin Woo Hyun\nDeep Predictor-Corrector Networks for Robust Parameter Estimation in Non-autonomous System with Discontinuous Inputs\n\n\n14:40–14:45\nJiwon Jang\nGyuyoung Hwang\nFlow matching with Physics-informed principle to solve inverse problem\n\n\n14:45–14:50\nMinjun Kim & Taekwan Kim\nKangmin Lee\nCharacterizing Circadian Modulation of Heart Rate Through Physics-Informed Neural Network Inference
URL:https://www.ibs.re.kr/bimag/event/ibs-bimag-2025-winter-internship-presentation/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Lunch Lab Meeting Seminar
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260206T100000
DTEND;TZID=Asia/Seoul:20260206T113000
DTSTAMP:20260503T223118
CREATED:20260203T013529Z
LAST-MODIFIED:20260203T013529Z
UID:12164-1770372000-1770377400@www.ibs.re.kr
SUMMARY:Multi-Marginal Flow Matching with Adversarially Learnt Interpolants - Gyuyoung Hwang
DESCRIPTION:In this talk\, we discuss the paper “Multi-Marginal Flow Matching with Adversarially Learnt Interpolants” by O. Kviman et al.\, 2025\, arxiv. \nAbstract \nLearning the dynamics of a process given sampled observations at several time points is an important but difficult task in many scientific applications. When no ground-truth trajectories are available\, but one has only snapshots of data taken at discrete time steps\, the problem of modelling the dynamics\, and thus inferring the underlying trajectories\, can be solved by multi-marginal generalisations of flow matching algorithms. This paper proposes a novel flow matching method that overcomes the limitations of existing multi-marginal trajectory inference algorithms. Our proposed method\, ALI-CFM\, uses a GAN-inspired adversarial loss to fit neurally parametrised interpolant curves between source and target points such that the marginal distributions at intermediate time points are close to the observed distributions. The resulting interpolants are smooth trajectories that\, as we show\, are unique under mild assumptions. These interpolants are subsequently marginalised by a flow matching algorithm\, yielding a trained vector field for the underlying dynamics. We showcase the versatility and scalability of our method by outperforming the existing baselines on spatial transcriptomics and cell tracking datasets\, while performing on par with them on single-cell trajectory prediction.
URL:https://www.ibs.re.kr/bimag/event/multi-marginal-flow-matching-with-adversarially-learnt-interpolants-gyuyoung-hwang/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260130T100000
DTEND;TZID=Asia/Seoul:20260130T120000
DTSTAMP:20260503T223118
CREATED:20260116T013852Z
LAST-MODIFIED:20260116T013852Z
UID:12138-1769767200-1769774400@www.ibs.re.kr
SUMMARY:Generic Temperature Response of Large Biochemical Networks - Shingo Gibo
DESCRIPTION:In this talk\, we discuss the paper “Generic Temperature Response of Large Biochemical Networks” by Julian B. Voits and Ulrich S. Schwarz\, PRX Life\, 2025. \nAbstract  \nBiological systems are remarkably susceptible to relatively small temperature changes. The most obvious example is fever\, when a modest rise in body temperature of only few Kelvin has strong effects on our immune system and how it fights pathogens. Another very important example is climate change\, when even smaller temperature changes lead to dramatic shifts in ecosystems. Although it is generally accepted that the main effect of an increase in temperature is the acceleration of biochemical reactions according to the Arrhenius equation\, it is not clear how it affects large biochemical networks with complicated architectures. For developmental systems such as fly and frog\, it has been shown that the system response to temperature deviates in a characteristic manner from the linear Arrhenius plot of single reactions\, but a rigorous explanation has not been given yet. Here we use a graph-theoretical interpretation of the mean first-passage times of a biochemical master equation to give a statistical description. We find that in the limit of large system size and if the network has a bias towards a target state\, then the Arrhenius plot is generically quadratic\, in excellent agreement with numerical simulations for large networks as well as with experimental data for developmental times in fly. We also discuss under which conditions this generic response can be violated\, for example for linear chains\, which have only one spanning tree.
URL:https://www.ibs.re.kr/bimag/event/generic-temperature-response-of-large-biochemical-networks-shingo-gibo/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260123T100000
DTEND;TZID=Asia/Seoul:20260123T120000
DTSTAMP:20260503T223118
CREATED:20260116T013712Z
LAST-MODIFIED:20260119T002842Z
UID:12136-1769162400-1769169600@www.ibs.re.kr
SUMMARY:A wearable-based aging clock associates with disease and behavior - Myna Lim
DESCRIPTION:In this talk\, we discuss the paper\, “A wearable-based aging clock associates with disease and behavior” by A. C. Miller et al.\, Nature Comm\, 2025. \nAbstract  \nAging biomarkers play a vital role in understanding longevity\, with the potential to improve clinical decisions and interventions. Existing aging clocks typically use blood\, vitals\, or imaging collected in a clinical setting. Wearables\, in contrast\, can make frequent and inexpensive measurements throughout daily living. Here we develop PpgAge\, an aging clock using photoplethysmography at the wrist from a consumer wearable. Using the Apple Heart & Movement Study (n = 213\,593 participants; >149 million participant-days)\, our observational analysis shows that this non-invasive and passively collected aging clock accurately predicts chronological age and captures signs of healthy aging. Participants with an elevated PpgAge gap (i.e.\, predicted age greater than chronological age) have significantly higher diagnosis rates of heart disease\, heart failure\, and diabetes. Elevated PpgAge gap is also a significant predictor of incident heart disease events (and new diagnoses) when controlling for relevant risk factors. PpgAge also associates with behavior\, including smoking\, exercise\, and sleep. Longitudinally\, PpgAge exhibits a sharp increase during pregnancy and concurrent with certain types of cardiac events.
URL:https://www.ibs.re.kr/bimag/event/mapping-the-genetic-landscape-across-14-psychiatric-disorders-myna-lim/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260115T100000
DTEND;TZID=Asia/Seoul:20260115T113000
DTSTAMP:20260503T223118
CREATED:20260109T124602Z
LAST-MODIFIED:20260109T124602Z
UID:12099-1768471200-1768476600@www.ibs.re.kr
SUMMARY:Quantifying interventional causality by knockoff operation - Olive Cawiding
DESCRIPTION:In this talk\, we discuss the paper\, “Quantifying interventional causality by knockoff operation” by Xinyan Zhang and Luonan Chen\, Science Advances\, 2025. \nAbstract  \nCausal inference between measured variables is crucial to understand the underlying mechanism of complex biological processes at a network level but remains challenging in computational biology. We propose an innovative causal criterion\, knockoff conditional mutual information (KOCMI)\, to accurately infer interventional direct causality without prior knowledge of the network structure using either time-independent or time-series data. KOCMI performs knockoff operation on a variable as its virtual intervention\, which preserves the original network structure\, and then identifies the causality between two variables by estimating the distributional invariance before and after such a virtual intervention. We show that\, algorithmically\, KOCMI enables quantification of causal relationship\, even for networks with loops\, and\, theoretically\, is also consistent with the do-calculus causal analyses but without their prerequisite of the network structure. KOCMI shows superior performance on benchmark and real datasets\, comparing with existing methods. Overall\, KOCMI provides a powerful tool in inferring interventional causality\, which is theoretically ensured and experimentally validated by real intervention data.
URL:https://www.ibs.re.kr/bimag/event/quantifying-interventional-causality-by-knockoff-operation-olive-cawiding/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260114T150000
DTEND;TZID=Asia/Seoul:20260114T170000
DTSTAMP:20260503T223118
CREATED:20251229T113203Z
LAST-MODIFIED:20260108T022014Z
UID:12063-1768402800-1768410000@www.ibs.re.kr
SUMMARY:Leveraging Large-Scale Perturbome Data for Complex Disease Target Discovery- Sang-Min Park
DESCRIPTION:Complex diseases\, such as cancer\, sarcopenia\, and immune disorders\, arise from abnormalities in multiple genes and pathways\, posing significant challenges to conventional single-target drug discovery strategies. To address this\, we developed a perturbome-based analytical framework that integrates transcriptomic signatures\, network pharmacology\, and machine learning to identify effective therapeutic candidates. Central to this approach is the KORE-Map (Korean Medicine Omics Resource Extension Map)\, a systematically curated transcriptomic repository of herbal medicine perturbations in diverse cellular and disease contexts. Using KORE-Map\, we reconstructed perturbome landscapes of traditional prescriptions such as Bojungikki-tang and Jakyak-gamcho-tang\, as well as natural compounds including ginsenosides and licochalcone B. By integrating differential expression\, pathway activity\, and synergic index modeling\, we demonstrated how perturbome data can reveal druggable axes for overcoming resistance to targeted and immune therapies in cancer\, attenuating muscle atrophy\, and modulating inflammatory responses. Importantly\, perturbome-guided candidate prioritization was validated through multi-omics profiling and functional assays\, underscoring its translational value. Our findings highlight perturbome data analysis as a powerful strategy for navigating the complexity of disease biology and accelerating drug discovery.
URL:https://www.ibs.re.kr/bimag/event/leveraging-large-scale-perturbome-data-for-complex-disease-target-discovery-sang-min-park/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Seminar
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260109T100000
DTEND;TZID=Asia/Seoul:20260109T113000
DTSTAMP:20260503T223118
CREATED:20251231T002857Z
LAST-MODIFIED:20251231T002857Z
UID:12078-1767952800-1767958200@www.ibs.re.kr
SUMMARY:scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction - Aqsa Awan
DESCRIPTION:In this talk\, we discuss the paper “scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction” by Z. Liang et al.\, arxiv\, 2025. \nAbstract \nThis paper introduces the Single-Cell Perturbation Prediction Diffusion Model (scPPDM)\, the first diffusion-based framework for single-cell drug-response prediction from scRNA-seq data. scPPDM couples two condition channels\, pre-perturbation state and drug with dose\, in a unified latent space via non-concatenative GD-Attn. During inference\, factorized classifier-free guidance exposes two interpretable controls for state preservation and drug-response strength and maps dose to guidance magnitude for tunable intensity. Evaluated on the Tahoe-100M benchmark under two stringent regimes\, unseen covariate combinations (UC) and unseen drugs (UD)\, scPPDM sets new state-of-the-art results across log fold-change recovery\, delta correlations\, explained variance\, and DE-overlap. Representative gains include +36.11%/+34.21% on DEG logFC-Spearman/Pearson in UD over the second-best model. This control interface enables transparent what-if analyses and dose tuning\, reducing experimental burden while preserving biological specificity.
URL:https://www.ibs.re.kr/bimag/event/scppdm-a-diffusion-model-for-single-cell-drug-response-prediction-aqsa-awan/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20260102T100000
DTEND;TZID=Asia/Seoul:20260102T113000
DTSTAMP:20260503T223118
CREATED:20251231T002614Z
LAST-MODIFIED:20251231T002614Z
UID:12076-1767348000-1767353400@www.ibs.re.kr
SUMMARY:Seasonal timing and interindividual differences in shiftwork adaptation - Kang Min Lee
DESCRIPTION:In this talk\, we discuss the paper “Seasonal timing and interindividual differences in shiftwork adaptation” by R. Kim et al.\, npj digital medicine\, 2025. \nAbstract  \nMillions of shift workers in the U.S. face an increased risk of depression\, cancer\, and metabolic disease\, yet individual responses to shift work vary widely. We find that a conserved biological system of morning and evening oscillators\, which evolved for seasonal timing\, may contribute to these interindividual differences. In this study\, we analyze seasonality in medical interns working shifts\, revealing that summer-winter variation correlates with increased circadian misalignment after shift work. Mathematical modeling suggests that seasonal timing influences the rate of adaptation to new schedules\, predicting differential effects on morning and evening oscillators. Additionally\, we examine genetic polymorphisms linked to seasonality in animals and find that human variants can impact how quickly circadian rhythms respond to schedule changes. Based on our findings\, we hypothesize that the vast interindividual differences in shift work adaptation—critical for shift worker health—can in part be explained by biological mechanisms for seasonal timing.
URL:https://www.ibs.re.kr/bimag/event/seasonal-timing-and-interindividual-differences-in-shiftwork-adaptation-kang-min-lee/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251230T160000
DTEND;TZID=Asia/Seoul:20251230T170000
DTSTAMP:20260503T223118
CREATED:20251224T001815Z
LAST-MODIFIED:20251229T112942Z
UID:12054-1767110400-1767114000@www.ibs.re.kr
SUMMARY:Rationalizing Therapeutics: Mathematical Insights into Drug and Cell Therapy Development - Seokjoo Chae
DESCRIPTION:Mathematical modeling provides essential quantitative insights that accelerate drug and cell therapy development. In this presentation\, we utilize kinetic frameworks to optimize the design of molecular glues by elucidating their biophysical determinants and identify a key target for NK cell-mediated immunotherapy through systematic data analysis. Collectively\, we demonstrate how mathematical strategies can effectively guide and advance the development of next-generation therapeutics.
URL:https://www.ibs.re.kr/bimag/event/rationalizing-therapeutics-mathematical-insights-into-drug-and-cell-therapy-development-seokjoo-chae/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Seminar
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251230T150000
DTEND;TZID=Asia/Seoul:20251230T160000
DTSTAMP:20260503T223118
CREATED:20251224T001705Z
LAST-MODIFIED:20251224T001718Z
UID:12052-1767106800-1767110400@www.ibs.re.kr
SUMMARY:Expanding the Data Analysis Toolkit: Explainable AI\, Causal Learning\, and Time-Series Foundation Models - Daeil Jang
DESCRIPTION:Recent advances in data science have expanded the scope of data analysis beyond prediction accuracy toward interpretability\, causal understanding\, and generalizable learning across complex data structures. This lecture introduces three emerging methodological approaches that can be directly leveraged in modern data analysis workflows. \nFirst\, the lecture presents explainable artificial intelligence (XAI) techniques\, focusing on SHAP and its extension to time-series explainability\, to illustrate how model predictions can be decomposed into meaningful variable- and time-specific contributions. Second\, it introduces machine-learning and deep-learning–based causal inference models\, highlighting how these methods move beyond association to estimate intervention effects and heterogeneous impacts while maintaining interpretability. Third\, the lecture explores recent time-series foundation models—such as Lag-LLaMA and TabPFN-based approaches—that enable transferable learning across diverse time-series tasks with minimal task-specific training. \nRather than treating these approaches as isolated research trends\, this lecture frames them as complementary analytical tools that address key questions in data analysis: What drives model predictions? What would change under intervention? And how can models generalize across time and settings? Through this integrated perspective\, the lecture aims to provide practical insight into how these three methods can be applied to real-world data analysis and inspire new research and application opportunities.
URL:https://www.ibs.re.kr/bimag/event/expanding-the-data-analysis-toolkit-explainable-ai-causal-learning-and-time-series-foundation-models-daeil-jang/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Seminar
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251229T163000
DTEND;TZID=Asia/Seoul:20251229T183000
DTSTAMP:20260503T223118
CREATED:20251224T001444Z
LAST-MODIFIED:20251224T001528Z
UID:12049-1767025800-1767033000@www.ibs.re.kr
SUMMARY:Distribution shift in machine learning: robustness\, invariance\, and a causal view - Wooseok Ha
DESCRIPTION:Classical machine learning models are typically trained under the assumption that the training (source) and test (target) data are drawn from the same distribution. However\, real-world data are rarely clean or consistent\, and distribution shifts between the source and target domains are ubiquitous. Despite its importance\, addressing distribution shifts is highly difficult. The fundamental challenge is that the problem is mathematically ill-posed: shifts can occur in many different forms\, and no single method can handle all of them. While numerous algorithms have been proposed in recent years to solve distribution shifts\, most are empirical-driven and lack solid foundations. In this talk\, I will provide a broad overview of approaches to address distribution shift based on invariance and distributional robustness\, and explain how these methods are intrinsically connected to a causal perspective. In particular\, I will show why it is crucial to carefully formulate assumptions that relate the source and target domains for reliable generalization\, and how assumptions grounded in the causal system enable the analysis of algorithms under both unsupervised and semi-supervised settings.
URL:https://www.ibs.re.kr/bimag/event/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Seminar
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251226T100000
DTEND;TZID=Asia/Seoul:20251226T120000
DTSTAMP:20260503T223118
CREATED:20251026T141349Z
LAST-MODIFIED:20251226T002150Z
UID:11798-1766743200-1766750400@www.ibs.re.kr
SUMMARY:N-BEATS: Neural basis expansion analysis for interpretable time series forecasting - Jinwoo Hyun
DESCRIPTION:In this talk\, we discuss the paper “N-BEATS: Neural basis expansion analysis for interpretable time series forecasting” by B. Oreshkin et al.\, ICLR\, 2020. \nAbstract \nWe focus on solving the univariate times series point forecasting problem using deep learning. We propose a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers. The architecture has a number of desirable properties\, being interpretable\, applicable without modification to a wide array of target domains\, and fast to train. We test the proposed architecture on several well-known datasets\, including M3\, M4 and TOURISM competition datasets containing time series from diverse domains. We demonstrate state-of-the-art performance for two configurations of N-BEATS for all the datasets\, improving forecast accuracy by 11% over a statistical benchmark and by 3% over last year’s winner of the M4 competition\, a domain-adjusted hand-crafted hybrid between neural network and statistical time series models. The first configuration of our model does not employ any time-series-specific components and its performance on heterogeneous datasets strongly suggests that\, contrarily to received wisdom\, deep learning primitives such as residual blocks are by themselves sufficient to solve a wide range of forecasting problems. Finally\, we demonstrate how the proposed architecture can be augmented to provide outputs that are interpretable without considerable loss in accuracy.
URL:https://www.ibs.re.kr/bimag/event/journal-club-jinwoo-hyun/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251212T110000
DTEND;TZID=Asia/Seoul:20251212T123000
DTSTAMP:20260503T223118
CREATED:20251026T141250Z
LAST-MODIFIED:20251215T043112Z
UID:11796-1765537200-1765542600@www.ibs.re.kr
SUMMARY:Quantifying interventional causality by knockoff operation - Yun Min Song
DESCRIPTION:In this talk\, we discuss the paper “Causal disentanglement for single-cell representations and controllable counterfactual generation” by Yicheng Gao et al.\, Nature Communications\, 2025. \nAbstract  \nConducting disentanglement learning on single-cell omics data offers a promising alternative to traditional black-box representation learning by separating the semantic concepts embedded in a biological process. We present CausCell\, which incorporates the factual information about causal relationships among disentangled concepts within a diffusion model to generate more reliable disentangled cellular representations\, with the aim of increasing the explainability\, generalizability and controllability of single-cell data\, including spatial-temporal omics data\, relative to those of the existing black-box representation learning models. Two quantitative evaluation scenarios\, i.e.\, disentanglement and reconstruction\, are presented to conduct the first comprehensive single-cell disentanglement learning benchmark\, which demonstrates that CausCell outperforms the state-of-the-art methods in both scenarios. Additionally\, CausCell can implement controllable generation by intervening with the concepts of single-cell data when given a causal structure. It also has the potential to uncover biological insights by generating counterfactuals from small and noisy single-cell datasets.
URL:https://www.ibs.re.kr/bimag/event/journal-club-yun-min-song/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251205T110000
DTEND;TZID=Asia/Seoul:20251205T120000
DTSTAMP:20260503T223118
CREATED:20250826T005255Z
LAST-MODIFIED:20250826T005331Z
UID:11476-1764932400-1764936000@www.ibs.re.kr
SUMMARY:Empirical modeling of bifurcations and chaos from time series - Stephan Munch
DESCRIPTION:Abstract \nMany natural systems exhibit complex dynamics and are prone to sudden changes or ‘regime shifts’. At the same time\, many of these systems are sparsely observed posing considerable challenges for modeling and control. Here I will describe recent developments in empirical dynamic modeling (EDM) for inference of bifurcations and anticipation of unseen dynamical regimes from ecological time series.
URL:https://www.ibs.re.kr/bimag/event/empirical-modeling-of-bifurcations-and-chaos-from-time-series-stephan-munch/
LOCATION:ZOOM ID: 997 8258 4700 (Biomedical Mathematics Online Colloquium)\, (pw: 1234)
CATEGORIES:Biomedical Mathematics Online Colloquium
ATTACH;FMTTYPE=image/jpeg:https://www.ibs.re.kr/bimag/cms/wp-content/uploads/2025/08/head2-e1756169564670.jpg
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251201T093000
DTEND;TZID=Asia/Seoul:20251202T150000
DTSTAMP:20260503T223118
CREATED:20251125T084153Z
LAST-MODIFIED:20251125T084415Z
UID:11903-1764581400-1764687600@www.ibs.re.kr
SUMMARY:2025 KAI-X Global Conference in Sleep Synergy
DESCRIPTION:Conference Webpage Link: https://sites.google.com/view/2025-kai-x-sleep-synergy/home
URL:https://www.ibs.re.kr/bimag/event/2025-kai-x-global-conference-in-sleep-synergy/
LOCATION:KAIST W13 Conference Room (1F)\, 291 Daehak-ro Yuseong-gu\, Daejeon\, Daejeon\, 34141\, Korea\, Republic of
CATEGORIES:Workshops and Conferences
ATTACH;FMTTYPE=image/jpeg:https://www.ibs.re.kr/bimag/cms/wp-content/uploads/2025/11/unnamed-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251121T100000
DTEND;TZID=Asia/Seoul:20251121T120000
DTSTAMP:20260503T223118
CREATED:20251026T141157Z
LAST-MODIFIED:20251121T000249Z
UID:11794-1763719200-1763726400@www.ibs.re.kr
SUMMARY:Modeling personalized heart rate response to exercise and environmental factors with wearables data - Dongju Lim
DESCRIPTION:In this talk\, we discuss the paper “Modeling personalized heart rate response to exercise and environmental factors with wearables data” by Nazaret et al.\, npj digital medicine\, 2023. \nAbstract \nHeart rate (HR) response to workout intensity re ects tness and cardiorespiratory health. Physiological models have been developed to describe such heart rate dynamics and characterize cardiorespiratory tness. However\, these models have been limited to small studies in controlled lab environments and are challenging to apply to noisy—but ubiquitous—data from wearables. We propose a hybrid approach that combines a physiological model with exible neural network components to learn a personalized\, multidimensional representation of tness. The physiological model describes the evolution of heart rate during exercise using ordinary differential equations (ODEs). ODE parameters are dynamically derived via a neural network connecting personalized representations to external environmental factors\, from area topography to weather and instantaneous workout\nintensity. Our approach ef ciently ts the hybrid model to a large set of 270\,707 workouts collected from wearables of 7465 users from the Apple Heart and Movement Study. The resulting model produces tness representations that accurately predict full HR response to exercise intensity in future workouts\, with a per-workout median error of 6.1 BPM [4.4–8.8 IQR]. We further demonstrate that the learned representations correlate with traditional metrics of cardiorespiratory tness\, such as VO2 max (explained variance\n0.81 ± 0.003). Lastly\, we illustrate how our model is naturally interpretable and explicitly describes the effects of environmental factors such as temperature and humidity on heart rate\, e.g.\, high temperatures can increase heart rate by 10%. Combining physiological ODEs with exible neural networks can yield interpretable\, robust\, and expressive models for health applications.
URL:https://www.ibs.re.kr/bimag/event/journal-club-dongju-lim/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251112T160000
DTEND;TZID=Asia/Seoul:20251112T170000
DTSTAMP:20260503T223118
CREATED:20251107T041235Z
LAST-MODIFIED:20251107T042030Z
UID:11845-1762963200-1762966800@www.ibs.re.kr
SUMMARY:Generative Models and Causality - Kyungwoo Song
DESCRIPTION:This seminar examines how generative AI advances three foundational tasks in causality\, treated as distinct\, modular problems: (1) causal inference via intervention‑effect estimation\, (2) causal graph analysis\, and (3) detection of causal mechanism shifts and change points. First\, for causal inference\, we consider procedures in which generative models align domain knowledge with observational signals to represent treatment\, confounding\, and temporal context. This enables stable estimation of intervention effects and principled policy evaluation without relying on explicit counterfactual generation. Second\, for causal graph analysis\, we outline strategies that combine language‑grounded knowledge extraction and constraint proposals with statistical checks to improve the reliability of directionality and structure\, yielding interpretable hypothesis spaces and testable causal claims. Third\, for shift detection\, we describe methods that disentangle changes in functional mechanisms from changes in noise\, supporting early diagnosis of performance degradation\, targeting of monitoring resources\, and evidence‑based model updates in deployed settings. Across these tasks\, generative AI serves as a computational aide for knowledge alignment\, hypothesis proposal and pruning\, uncertainty annotation\, and experiment‑design suggestions. We conclude with a brief outlook on a causal agent that orchestrates data ingestion\, hypothesis formation\, intervention‑effect estimation\, shift monitoring\, and policy revision\, offering an integrated\, yet auditable and modular\, workflow for reliability‑centered decision support.
URL:https://www.ibs.re.kr/bimag/event/generative-models-and-causality-kyungwoo-song/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Seminar
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251112T160000
DTEND;TZID=Asia/Seoul:20251112T170000
DTSTAMP:20260503T223118
CREATED:20250826T004501Z
LAST-MODIFIED:20251101T143038Z
UID:11471-1762963200-1762966800@www.ibs.re.kr
SUMMARY:(Cancelled) TBD - Amir Sharafkhaneh
DESCRIPTION:–
URL:https://www.ibs.re.kr/bimag/event/tbd-amir-sharafkhaneh/
LOCATION:ZOOM ID: 997 8258 4700 (Biomedical Mathematics Online Colloquium)\, (pw: 1234)
CATEGORIES:Biomedical Mathematics Online Colloquium
ATTACH;FMTTYPE=image/jpeg:https://www.ibs.re.kr/bimag/cms/wp-content/uploads/2025/08/1516440570570-e1756169081265.jpeg
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
END:VCALENDAR