ICBRA 2026

Keynote Speaker

Prof. Christopher Nugent

Ulster University, UK

Chris was awarded a first class honours in BEng Electronic Systems and a PhD in Biomedical Engineering where he researched the optimisation of Neural Network ensembles for medical classification purposes. He was appointed as full Professor of Biomedical Engineering in 2008. From 2015-2017 he was the Director of the Computer Science Research Institute at Ulster University and in 2017 he was appointed Head of the School of Computing. He is currently serving his third term in this role. His research interests are focussed at the intersection of IoT and AI specifically to support human activity recognition within smart environments. This has involved research in the topics of activity recognition and behaviour modelling, technology adoption modelling and optimisation of AI based classification models. To date he has successfully supervised 47 PhD students to completion and in 2024 he was recognised on Stanford's top 2% most highly cited scientists and is currently ranked No. 1 internationally on Google Scholar for citations in the area of Ambient Assisted Living. He has been instrumental in initiating, preparing, supporting and managing a number of externally funded Research Projects. The total funding allocated to Ulster as a result of these projects is in excess of £52M. In 2016 he was awarded a Senior Distinguished Research Fellowship by Ulster University. He is currently a visiting Professor in Pervasive and Mobile Computing at Lulea Technical University (Sweden), a visiting Professor in Computing at Shandong Jianzhu University (China) and a Visiting Professor in Computing at Dalian University of Technology (China). Since 2008 he has served as an Associate Editor for the Editorial Board of the IEEE Engineering Medicine and Biology Conference, Healthcare Information Systems Theme and he is currently serving as a member of Ireland’s Commission on Care for Older People.

Prof. Hesham H. Ali

University of Nebraska Omaha, USA

Hesham H. Ali is a Professor of Computer Science and the director of the University of Nebraska Omaha (UNO) Bioinformatics Core Facility. He served as the Dean of the College of Information Science and Technology at UNO between 2006 and 2021. He has been a research collaborator at Mayo Clinic Research Hospital since 2022. He has published numerous articles in various computing and informatics fields of research, including scheduling, distributed systems, data analytics, wireless networks, and Bioinformatics. He has published two books in scheduling and graph algorithms, and several book chapters in Bioinformatics. He has been serving as the PI or Co-PI of several projects funded by NSF, NIH and Nebraska Research Initiative in the areas of AI, Bioinformatics, Data Analytics and Wireless Networks. For the last 25 years, he has also been leading a Bioinformatics Research Group that focuses on developing innovative computational approaches to model complex biomedical systems and analyze big bioinformatics data using AI tools, Network models, and graph algorithms. The research group is currently developing next generation data analytics tools for analyzing large heterogeneous biological and health data associated with various biomedical research areas, particularly projects associated with infectious diseases, microbiome studies, early childhood development and aging research. He has led many local and national outreach initiatives, including Bioinformatics training workshops, Women in IT initiatives, IT education and training programs, and IT summer internship camps.odels can leverage the new biomarkers in supporting advanced biomedical research and lead to the next generation of healthcare.

Invited Speakers of ICBRA 2026

Prof. Chanchal Mitra

University of Hyderabad

Chanchal Mitra did his Bachelors and Masters from the University of Calcutta and Ph.D. from the Tata Institute of Fundamental Research (University of Bombay). He did his post doctoral work at the State University of New York at Albany (The University at Albany), USA and also at the University of Lund, Sweden. His research interests are Bioinformatics, Computational Biology and Biosensors (enzyme based). He joined University of Hyderabad in 1985 as a lecturer and retired in 2015 as Professor of Biochemistry. He has supervised several Ph.D. students, project students and research associates. He has over 100 publications in peer reviewed journals. According to google scholar, he has citations 1272, h-index of 20 and i10-index of 31. He lives in Hyderabad, India (2023).

Dr. Roberto Sotero

Diaz-University of Calgary, Canada

Roberto C. Sotero earned his BSc in Nuclear Physics in 2003 and his PhD in Physics in 2009, both from Havana, Cuba. He then pursued a postdoctoral fellowship at the Montreal Neurological Institute from 2010 to 2014. In 2014, he joined the Department of Radiology at the University of Calgary, where he currently holds the position of Associate Professor. Roberto's expertise lies in developing computational models of brain activity, bridging gaps in imaging across various scales and between brain structure and function. His work focuses on the essential biophysical properties that influence empirical dynamics. Recently, he began integrating machine learning techniques with biophysical modelling. Through these hybrid models, he aims to address critical health challenges, particularly the early detection of autism spectrum disorder.

Speech Title: "Physics-Informed Neural Networks for Multiscale Brain Modeling: From Traveling Waves to Directed Functional Connectivity"

Abstract: Modeling the human brain's complex dynamics from fMRI data poses a significant challenge, as traditional data analysis methods often overlook underlying physical principles. This talk presents a novel framework using Physics-Informed Neural Networks (PINNs) to directly embed biophysical models into deep learning architectures, yielding a more comprehensive understanding of brain function. We demonstrate two key applications: modeling large-scale traveling waves by incorporating a damped wave model, and estimating directed functional connectivity (dFC) by constraining the PINN with a Brain Dynamics Model (BDM). This latter approach allows for simultaneous estimation of biophysical parameters and dFC between all brain regions, a task intractable with traditional methods. Applying our dFC method to a large dataset of individuals with Autism Spectrum Disorder (ASD) and neurotypical controls, we found significant sex-specific differences in connectivity. Our results highlight the potential of PINNs as a powerful tool for identifying neurological biomarkers and unraveling the complexities of the brain in health and disease.

Dr. Kevin Lin

University of Virginia, USA

Kevin Lin earned his BA in Mathematics from the University of Washington in 2017 and PhD in Data Science from the University of Virginia in 2024. His research focuses on deep learning methods for medical image pathology and his research areas include Bayesian Entropy Quantization, Computer Vision, and Domain Adaptation. During his PhD, Kevin’s published papers earned three international ACM conference awards. Following graduation, Kevin continues his research as a Data Scientist at the University of Virginia collaborating with medical researchers in early disease detection by detecting cells of interest in patient-informed approaches. By prioritizing precision medicine objectives in deep learning models, he ensures that patient-specific characteristics are properly addressed in medical image segmentation.

Speech Title: "The Importance of Imperfections in Medical AI Approaches"

Abstract: At its core, patient care focuses on the individual. Catered care directed to the observed and communicated symptoms from each observation. Current medical AI approaches imprecisely aggregate significant amounts of patient data while failing to address the differences present in each patient. Medical AI approaches must start with the foremost pillar of medical ethics: Beneficence or “Doing good for the patient and promoting their well-being,” which is a day-one concept for medical students in the United States. With medical AI approaches being tested at scale in hospitals around the world, adequate effort must also be done to ensure that while some patient care can be applied wholesale to a population, effective medical care necessitates treating the patient in front of you. The proposed approach leverages uncertainty quantification and a similarity metric for observations created through a dropout approach. Through evaluation of a dataset with patients diagnosed with Eosinophilic Esophagitis, this approach improves a multisource domain adversarial network (MDAN) results indicating that in addition to aligning with current medical practices, prioritizing individual level differences instead of aggregating medical data uniformly can provide strong results.

Dr. Yan W. Asmann

Mayo Clinic, USA

Dr. Yan Asmann is a Professor of Biomedical Informatics in the Division of Computational Biology and Department of Quantitative Health Sciences at Mayo Clinic. She has developed and published multiple analytical algorithms and methodological papers, including two recent studies that apply machine learning and artificial intelligence models to genomic data. Dr. Asmann has been involved in cancer research for over 15 years, collaborating with both clinicians and basic scientists. She co-created and co-leads the Mayo Clinic Neoantigen Vaccine Therapy program and serves as co- Principal Investigator (PI) of several FDA-approved single-patient, Phase I, and Phase II trials for immune checkpoint inhibitor and neoantigen vaccine combination therapies. Additionally, she is co-PI of a U24 grant from the National Cancer Institute (NCI) for the Cancer Adoptive Cell Therapy (Can-ACT) Network Coordinating Center. Dr. Asmann also heads the data science team of the Mayo Clinic Comprehensive Cancer Center's Novel Biotherapeutics Program.

Speech Title: "The Data Science of Cancer Neoantigen Discovery and Prioritization"

Abstract: Neoantigen-based immunotherapies rely on accurate identification of tumor-specific peptides presented on HLA molecules. We have developed and iteratively refined a suite of bioinformatics tools, including REAL-neo and SPLICE-neo, that facilitate comprehensive predictions of both HLA class I and II neoantigens derived from somatic mutations, gene fusions, and aberrant RNA splicing events. Our pipelines integrate multiomics data, implement stringent quality control measures, and utilize advanced logic models to reconstruct and prioritize tumor-specific epitopes across various cancer types. These analytical innovations have resulted in significant clinical impact. In a recent trial, personalized neoantigen vaccines developed using our pipelines induced a durable partial response lasting over 26 months in a patient with metastatic translocation renal cell carcinoma, a disease that is typically resistant to immunotherapy. Together, these computational frameworks not only expand the search space for neoantigens but also facilitate the clinical implementation of patient-specific cancer vaccines. This presentation will outline the analytical strategies, validation methods, and early clinical outcomes, illustrating how rigorous informatics can connect molecular profiling with precision immunotherapy.

Dr. Anima Kujur

Heidelberg University, Germany

Dr. Anima Kujur is a postdoctoral researcher at the Interdisciplinary Centre for Scientific Computing (IWR), Heidelberg University, Germany. She holds a Ph.D. in Computer Science and Technology, specializing in deep learning for radiological image classification and segmentation. She also has dual master's degrees in Applied Mathematics and Computer Science. Her research focuses on integrating AI into neuroscience, particularly in medical imaging and neural time-series analysis. She has worked extensively with MRI, fMRI, and EEG/iEEG data, developing AI-driven models for disease diagnosis, prediction, and biomarker discovery. Her expertise spans image processing, temporal pattern extraction, and predictive modeling using recurrent neural networks and Koopman operator theory. Dr. Kujur is dedicated to advancing AI-enhanced decision support systems for healthcare, bridging machine learning, computational neuroscience, and clinical applications. She is passionate about interdisciplinary research and mentoring young researchers in the field.

Speech Title: "Multimodal Neuroimaging Integration Using Deep Learning and Koopman Operator-Based Analysis of Neural Signal Dynamics"

Abstract: Biomedical signal and image analysis play a key role in modern diagnostics. However, many machine learning methods still struggle with the complex and nonlinear nature of neural and physiological data. In this presentation, I will discuss two distinct directions: first, multi-modal medical image analysis; and second, brain signal analysis through the lens of dynamical systems theory. I begin with multi-modal medical imaging for neurological disorders such as Alzheimer’s disease. A deep learning framework is used to integrate multimodal MRI and fMRI data to simultaneously predict structural abnormalities and analyze functional brain activity. By combining the strengths of both modalities, our model captures static anatomical patterns from MRI alongside dynamic functional signals from fMRI to improve diagnostic accuracy and track disease progression across imaging modalities. The focus then shifts to EEG/iEEG signal analysis, where the temporal evolution of brain signals is modeled using tools from dynamical systems theory. EEG signals change over time in response to external or internal stimuli, and these changes can be understood as the result of complex underlying neural dynamics. To analyze this, we integrate Koopman operator theory with deep learning, aiming to develop more interpretable and predictive models. We specifically use Koopman-informed Recurrent Neural Networks (RNNs), also known as Sampled RNNs, which are well-suited for modeling time-dependent data like EEG/iEEG. These networks allow us to capture important temporal dependencies in brain activity, which are essential for applications such as sharp wave ripple detection from local field potentials (LFPs)—a key task in understanding memory and neural rhythms, especially in epilepsy research. By combining deep learning with dynamical systems modeling, this work offers a strong foundation for analyzing complex biomedical data. It also highlights how mathematical models and AI can come together to create more interpretable and data-driven solutions for healthcare challenges.

Assoc. Prof. Yingxue Ren

Mayo Clinic, USA

Dr. Ren is an Associate Professor of Biomedical Informatics in the Department of Quantitative Health Sciences at Mayo Clinic. Her research focuses on developing and applying novel bioinformatics approaches to translational science to help identify novel disease risk factors and therapeutic targets, specifically for neurodegenerative diseases. Her expertise is omics analysis of disease models, including whole exome and genome sequencing, bulk and single cell transcriptomics, cell type deconvolution, proteomics, lipidomics, metabolomics, epigenomics, as well as multiomics integration. She is currently co-PI or co-I on 9 NIH or foundation grants, and has authored over 50 publications. Her research will enable the discovery and validation of novel therapeutic targets for the treatment of neurodegenerative diseases.

Speech Title: "Scplotter: A Unified Framework for Advanced Visualization in Single-Cell and Imaging Biology"

Abstract: The rapid growth of single-cell sequencing and imaging technologies has transformed biomedical research, enabling unprecedented insights into cellular heterogeneity, immune repertoire dynamics, and disease mechanisms. However, the complexity of multi-modal datasets—spanning transcriptomes, immune receptor sequences, imaging data and clinical metadata—demands visualization tools that integrate analytical depth with intuitive design. Current solutions remain fragmented, forcing researchers to juggle specialized packages for basic plotting, statistical analysis, and cross-modal harmonization. To address these challenges, we introduce scplotter, an R package that unifies advanced visualization for single-cell RNA sequencing, immune repertoire and imaging data. Built on a modular, extensible framework, scplotter bridges the gap between exploratory analysis and publication-ready outputs by embedding statistical metrics directly into visualizations, enabling dynamic plot-type switching, and harmonizing diverse data types. Its ability to resolve critical workflow fragmentation and ethical challenges in modern single-cell and imaging studies positions it as an indispensable asset for researchers studying cellular ecosystems in immunology, oncology, and beyond.

Dr. Mohammad Rizwan

University of Lodz, Poland

Mohammad Rizwan has a BSc (Honours) in Biotechnology, and an MSc and an MPhil respectively in Biochemistry and Nano Sciences. Dr Rizwan was awarded a PhD in Biotechnology in 2018 at the University of Brunei Darussalam, Brunei. Following he was appointed from 2018-2020 to work as “Research & Development Innovation Officer” at Bangor University, United Kingdom. Further, in 2021 he worked as an “Advanced Researcher in Residence”, at the University of Lodz, Poland. Subsequently, since 2021 Dr Rizwan is working in the position of University Professor and Principal Investigator at the Sub-Department of Electroanalysis and Electrochemistry, University of Lodz, Poland. To date, he has authored or co-authored over thirty articles having over 980 citations. Further, Dr Rizwan has delivered invited lectures at different conferences as one of the international expert speakers. Besides, he has presented his work in person at prestigious conferences across the globe including in India, Brunei, China, Indonesia, and Poland as well as in national and international virtual conferences. His current research focuses on bioelectrochemistry, biomimetic electrified interfaces, bioengineered interfaces, electrochemical biosensor devices and nanoimmunochips development. For more information on his work and publications, visit his LinkedIn profile: https://www.linkedin.com/in/rizwan-phd/.

Speech Title: "Development of Electrochemical Immunosensor for the Detection of Prostate Specific Antigen using a Bioengineered Novel Interface"

Abstract: Cancer has become the second leading and most common cause of death globally, and due to its life-threatening factors, early diagnosis and detection of the tumour markers are crucial. However, due to the complexity of cancer cells, they are notorious for being difficult to detect as they are too small and diverse. Thus, the detection of crucial biomarkers is essential for early detection of concerned types of cancers. For example, the presence of prostate-specific antigen (PSA) in the urine of an individual is an important marker of prostate cancer (PCa). Further, PCa is one of the leading causes of death in men on the planet and is responsible for around 30 % of all deaths of men due to cancer in Europe. Therefore, this presentation will showcase the development of an electrochemical immunosensor for the sensitive detection of PSA using the bioengineered novel interface.

Dr. Souvik Kar

International Neuroscience Institute, Germany

Dr. Souvik Kar holds a Master degree in Zoology from India, and received the prestigious Georg Christoph Lichtenberg international scholarship to pursue his Ph.D in Neuroscience at the Hannover Medical School in Hannover, Germany. Following completion of his doctoral research work, he joined INI Hannover as a senior scientist, where he set up his own research lab, and established the biobank facility. Currently, Dr. Kar supervises the central biobank facility at INI Hannover which has the largest collection of human cerebral cavernous malformation (CCM) patient tissue and blood samples in Germany. Also, his lab was the first to identify crucial non-coding RNAs (microRNAs, snoRNAs, and lncRNAs) in CCM patients harboring lesions in the brainstem region. His key major achievements in the field of cerebrovascular biology include the characterization of crucial coding as well as non-coding RNAs as predictive biomarkers in patients harboring lesions in the brainstem regions.. Such biomarkers will be important for early clinical diagnosis and serve as potential theraupetic targets for CCM treatment. Also, he is a recipient of multiple national as well as international research grants, including the recent European Era-net-neuron 2022-2027 grant on cerebrovascular diseases. He is currently acting as a member of the medical advisory board for the German Cavernoma patient organization.

Speech Title: "Adhesion GPCR ADGRL4/ELDT1 as a novel potential Prognostic Biomarker for Cerebral Cavernous Malformation Diseases"

Abstract: Cerebral cavernous malformations (CCM) are angiographically occult vascular anomalies of the brain characterized by dilated capillaries, increased vascular permeability, and loss of endothelial junctional protein complexes [1]. Loss-of-function mutations in one of the three genes, namely KRIT1/CCM1, CCM2, and PDCD10/CCM3, have been associated with the disease pathogenesis. Despite recent advances in understanding the molecular mechanism of the disease, current lack of therapies and its unpredictable clinical behavior pose significant challenge in the identification of diagnostic biomarkers. The ETLD1 (epidermal growth factor, latrophilin and seven transmembrane domain-containing protein 1), a G-protein coupled receptor (GPCR) protein is an angiogenic biomarker, and has been suggested as a key therapeutic target for stroke and high-grade gliomas [2]. However, the relevance of ELTD1 in CCM pathogenesis remains unexplored. To identify and validate the expression of ELTD1 mRNA and protein levels in CCM disease, we employed various molecular biology methods such as RNA-seq, qRT-PCR, immunohistochemistry, and western blot. Through different analyses in human CCM patients, and in-vivo and in-vitro studies, herein we show the association between CCM and ELTD1, a known biomarker of angiogenesis and inflammation. Whole RNA transcriptome approach demonstrated ELTD1 is differentially expressed, whereas gene expression analysis revealed ELTD1 is significantly up-regulated in surgically resected tissue and plasma samples from CCM patients. Immunoexpression of ELTD1 showed a strong ELTD1-immunoreactivity in endothelial cells lining affected lesions. Further, we confirmed up-regulation of ELTD1 in cellular and animal models of CCM pathogenesis. Taken together, our results reveal for the first time a strong involvement of ELTD1 in CCM pathogenesis. Future clinical studies in larger patient cohorts and animal models of CCM disease will identify its role as a prognostic biomarker for early clinical diagnosis and risk stratification.