Welcome speech by Béla Merkely, Rector of Semmelweis University and Roland Molontay, the Director of the Organizing Comittee. 

The HuBMAP Human Reference Atlas (HRA) effort aims to develop a common coordinate framework (CCF) for the healthy human body, see HRA Portal at https://humanatlas.io. An international team of organ experts across 25+ consortia are authoring so-called ASCT+B tables that capture the partonomy and typology information for anatomical structures, cell types, and biomarkers used to identify cell types. The ASCT+B tables are used to revise and extend existing CCF-relevant ontologies. In close collaboration with NIAID at NIH, a 3D Reference Object Library was compiled that provides semantically annotated 3D representations of major anatomical structures captured in the ASCT+B tables. The HRA can be extended and explored using several interactive user interfaces: The Registration User Interface (RUI) supports tissue data registration and annotation across 50+ 3D reference organs. The Exploration User Interface (EUI) supports the exploration of semantically and spatially explicit data—from the whole body to the single cell level. The Cell Distance Explorer (CDE) computes and visualizes distance distributions between different cells, cell types, and anatomical structures; and cell types and morphological features. For an introduction to HuBMAP goals, data, and code visit the Visible Human MOOC (VHMOOC). This talk details how HuBMAP, SenNet, GTEx, and other data is mapped to the HRA and how the HRA can be used to harmonize data at scale in support of precision health and precision medicine. 

• Péter Hunyadi: Detection of Homologous Recombination Deficiency by Cell-Free DNA Fragmentomics Analysis in Ovarian Cancer. 

• Mihály Rámpay: Uncovering Spontaneous Neural Synchrony Using AI-Driven Electrophysiological Analysis

• Lilla Kisbenedek: Physics-Informed Neural Networks for Tumor Modeling and Parameter Estimation

• Csaba Kiss: Advancing Causal Inference in Adverse Drug Effect Detection with NLP and Machine Learning

• Tuğba Akman: Computational Modeling of Aromatase Inhibitor Treatment in Breast Cancer Based on the Clinical Trial NeoLetExe

A disease is rarely a consequence of an abnormality in a single gene but reflects perturbations to the complex intracellular network. Network medicine offers a platform to explore systematically not only the molecular complexity of a particular disease, leading to the identification of disease modules and pathways, but also the molecular relationships between apparently distinct (patho) phenotypes. As an application, I will explore how we use network medicine to uncover the role of individual food molecules in our health. Indeed, our current understanding of how diet affects our health is limited to the role of 150 key nutritional components systematically tracked by the USDA and other national databases in all foods. Yet, these nutritional components represent only a tiny fraction of the over 135,000 distinct, definable biochemicals present in our food. While many of these biochemicals have documented effects on health, they remain unquantified in any systematic fashion across different individual foods. Their invisibility to experimental, clinical, and epidemiological studies defines them as the ‘Dark Matter of Nutrition.’ I will speak about our efforts to develop a high-resolution library of this nutritional dark matter, and efforts to understand the role of these molecules on health, opening novel avenues by which to understand, avoid, and control disease.

• Tibor Nánási: LOAPI: A Novel Normalization Method to Handle Nonlinear Covariate Effects in Plasma Proteomics Analysis

• Qiuzhen Li: De-novo Design of Molecular Glues for Targeted Oncogenic Protein Degradation

• Noémi Gyüre: Effect of Network Density and Cortical Parcellation Schemes on Determining Hubs of Functional Brain Networks

• Thanakorn Jaemthaworn: From Gene Expression to Network Topology: Enhancing Insight into Cell Differentiation with Cell-Specific Gene Co-Expression Networks

• Samuel Ropert: Transient Signatures of Community Structure in Epidemics on Networks

• Orsolya Karácsony: Hierarchical Clustering of Pyramidal Cells’ Functional Activity Patterns in Two-Photon Microscopy Videos Reveals Non-invasive Therapeutic Potential in Temporal Lobe Epilepsy

• Hui Guo: Fast Machine Learning Causal Network Analysis Using Genetic Instruments

Drawing from across cultures and across scholarly disciplines, Places & Spaces: Mapping Science demonstrates the power of maps to address vital questions about the contours and content of human knowledge. An interdisciplinary and international advisory board chose each one of the works in the Places & Spaces exhibit as an outstanding example of how visualization can bring patterns in scientific data into focus. The exhibit is curated by the Cyberinfrastructure for Network Science Center at Indiana University. The exhibit has been on display at over 382 venues in 28 countries on 6 continents. It showcases the work of 248 mapmakers who hail from 17 different countries.

• Peter Domjan: Adaptive Bayesian Learning Framework with Precision Entropy Indicator for Biomedical Decision Support

• Tárek Zoltán Magyar: A Fundamental Biophysical Property of the Brain Scales Allometrically: The Spectral Knee

• János Juhász: Computational Modelling and Quantification of Yeast Colony Development

• Borbála Gergics: Modeling Chemotherapy Response in Tumor Spheroids Using Nonlinear Mixed-Effects Approaches

• Fehérvári Péter: MetaBoostR: A Validated and Modular R Framework for Automated, Reproducible Meta-Analysis Across Diverse Effect Measures

Session Chair: Donát Köller

Presenters:

• Christiane Hütter: The Datascope: Redefining Human-Data Interaction Toward Embodied, Real-Time, and Multimodal Interfaces for Scientific Insight

• Iker Núñez-Carpintero: Deep Integrative Multilayer Network-Based Analysis of Rare Neuromuscular Disorders Reveals Overlapping Multiscale Endotypes Involved in Cardiac and Skeletal Muscle Myopathies

• Chloé Bûcheron: Molecular Endotyping for Rare Immune-Mediated Diseases Identifies Therapeutically Relevant Disease Subgroups

• Easin Arafat: An End-to-End AI Pipeline for Automated Brain Tumor Diagnosis and Reporting on MRI Images

• Petra Szili: Resistance to New Antibiotics Promotes the Rise of Hypervirulent Bacteria

• Richárd Ármós: Genetic Background of the Development of Papillary Thyroid Carcinoma

• Emmanuel Niyonshuti: Health Workers' Experiences and Satisfaction with eBuzima EMR in Rwandan Primary Care Settings: A Qualitative Study

• Eugene Rwubaka: Leveraging Synthetic Health Data to Predict Severe Maternal Morbidity Using Machine Learning Models

• Dániel Zentai: The Cryptographic Background of Secure Data Collaboration

• Csaba Kiss: Cross-Platform Analysis of Diet Discourse: Scientific Research, News Media, and Social Media Compared

This presentation highlights the current applications of Computed Tomography (CT) in diagnosing and managing coronary artery disease. It examines how photon-counting CT technology offers higher-resolution imaging with reduced radiation doses, enhancing patient outcomes. Artificial intelligence is explored as a tool for improving image acquisition, interpretation, and predictive accuracy in cardiovascular care. The session also delves into emerging innovations that may further optimize the precision and efficiency of cardiac imaging. Ultimately, attendees will gain insight into today’s imaging practices and the technological trends that are shaping the future of cardiac CT imaging.

• Balázs István Formanek: Semiautomatic Bone Segmentation and Anatomical Parameter Extraction on Digital Hand X-Ray Images

• Réka Bagdy-Bálint: Structured Data Storage: Bridging the Gap Between AI and Data-Driven Healthcare

• Emmanuel Niyonshuti: Predicting Prolonged Hospital Stay in Diabetic Ketoacidosis Patients Using Machine Learning on Synthetic Health Data

• Dezső Miklós: Toward High-Fidelity Patient Journeys for Predictive Healthcare Modeling in Hungary

• Gayathri Sunil: Graph Neural Network and Machine Learning Analysis of Functional Neuroimaging for Understanding Schizophrenia

• Flóra Boróka Németh: Stability and Adaptability of Infrared Molecular Profiles

• Flóra Demeter: Nature Versus Nurture - Does the Genetic Background or the Composition of the Medium Have a Greater Influence on the Transcriptome of Endothelial Cells?

• Zita Ilona Zarándy: Reducing Baseline Variability in Longitudinal Blood Infrared Fingerprints Through Sub-Cohort Stratification 

• Frank Hause: Knowledge-Based Gene Set Intersection Graphs Reveal Functional Master Regulators by Measures of Centrality and Self-Similarity 

• Paul Buttkus: Dynamic Health Monitoring: Predicting COVID-19 with Wearable Sensor Data and catch22 Features 

• Dániel Vörösvácki: CRC Patients Possess More Unique Structural Variations in LINE1 Segments Than Healthy Control 

• Lelja Daruka: The Effect of Food Additives on the Gut Microbiome 

• Antonio Miñarro: Permutation-Based Testing for Network Equality Using Partial Correlation Graphs 

• Onur Yolay: A Modular Surgical Plate System for Postoperative Vertical Adjustment in Orthognathic Surgery: An Innovation Aligned with the Growing CMF Device Market 

• Lajos Lantos: Quality Improvement in Neonatal Transport: A Data-Driven Approach 

• Miguel Azevedo: Exploring How the Structure of the Gene Network of E. Coli Influences Its Early Response to Antibiotics

• Tamás Lakat: Transcriptomic Profiling of Sigma-1 Receptor Agonism in Bleomycin-Induced Pulmonary Fibrosis: Insights Into Therapeutic Mechanisms 

• Laura Bagi: Genetic Clues Linking Flu Vaccine to Protection From Lung Cancer 

• Gábor László Bényei: Analysis of Fine Motor Hand Movements for Early Recognition of Cognitive Decline 

• Zoltán Farkas: Exploring Species-Specific Constraints on Convergent Evolution during Antibiotic Selection in Bacterial Populations 

• Orsolya Karácsony: Principal Component Analysis in Understanding the Difference Between Normal and Pathological Variations of Physical Activity Versus Time in Chronic Fatigue Syndrome 

• Gabriela Gladiola Petroiu: AI-Powered Multi-Sensor System for Real-Time Body Posture Monitoring: Design, Validation, and Applications in Digital Health 

• Szuzina Fazekas: Quest for a Clinically Relevant Medical Image Segmentation Metric: The Definition and Implementation of Medical Similarity Index 

• Luca Anna Joó-Bors: Automated High-Content Image Analysis for Endothelial Toxicology Profiling of E-cigarette Exposure in Healthy and Diabetic Monozygotic Twins 

• Walter Schwertner: Prediction of Pacing-Induced Cardiomyopathy Using Machine Learning in Patients Receiving Conventional Right Ventricular Pacing 

• Marta Lotka: To Understand the Brain’s Fractal Properties, Turn It Into a Spaghetto: Introducing Fractal Space-Curve Analysis (Fsca) 

• Zsuzsa Farkas: Bayesian and Machine Learning Approaches for Analysing Patterns of Antibiotic Resistance in Relation to Biosecurity Measures and Antibiotic Use Based on Data From Pig Farms

• Dániel Zentai: Secure Data Collaboration for Medical Organisations 

• Ádám Pál-Jakab: Network-Based Analysis of Psychosocial and Informational Connections Among Heart Transplant Patients 

• Csaba Varga: AI-Based Screening for Type 2 Diabetes Using Multi-Fingerprint Pattern Recognition 

• Anett Nagy-Szakolczai: Personalized Health Education During COVID-19: Preliminary Findings From the PROACTIVE-19 Trial 

• Balázs Szabó: Comparative Analysis of Informational and Psycho-supportive Connection Networks in Heart Transplant Patients Using Demographic and Psychological Data 

• Pál Bertold: Predicting Diabetes and Pre-Diabetes Risk Within One Year of Acute Pancreatitis Using Integrated Clinical and Pancreatic Radiomics Data

• Dávid Csányi: Radiomic Analysis of Small Cell Lung Cancer

Venue

The Gala Dinner of the Biomedical Data Science Conference will be held in the prestigious Ceremonial Hall (Díszterem) of the Hungarian Academy of Sciences (Magyar Tudományos Akadémia, MTA). Located in the heart of Budapest at 1051 Budapest, Széchenyi István tér 9, this historic venue offers a magnificent setting with its grand architecture and cultural significance.

In this talk, I will give an overview of the computational steps in the analysis of single-cell-based large-scale microscopy experiments. First, I will present a novel microscopic image correction method designed to eliminate illumination and uneven background effects which, left uncorrected, corrupt intensity-based measurements. New single-cell image segmentation methods will be presented using differential geometry, energy minimization, and deep learning methods (www.nucleAIzer.org). I will discuss the Advanced Cell Classifier (ACC), a machine-learning software tool capable of identifying cellular phenotypes based on features extracted from the image. It provides an interface for a user to efficiently train machine learning methods to predict various phenotypes. For cases where discrete cell-based decisions are not suitable, we propose a method to use multi-parametric regression to analyze continuous biological phenomena. To improve the learning speed and accuracy, we propose an active learning scheme that selects the most informative cell samples.

Our recently developed single-cell isolation methods, based on laser-microcapturing and patch clamping, utilize the selection and extraction of specific cell(s) using the above machine learning models. I will show that we successfully performed DNA and RNA sequencing, proteomics, lipidomics, and targeted electrophysiology measurements on the selected cells.

• Mihály Rámpay: Building Crisis Support Tools: Hybrid Anonymization for AI Training and Beyond

• Zsuzsa Farkas: Text Mining Methods for Identification of Emerging Risks in the Food Chain

• Leo Sternlicht: A Quantitative Approach to Biotech Investing: Using AI to Analyze Fundamental and Clinical Data for Capital Allocation

• Zsolt Bagyura & Mónika Hujter: Expanding the Semmelweis Clinical Database With Parameters Extracted From Free Text Documents Using Large Language Models

• Tobias Klomp: Explainable Expert-Driven Machine Learning for Clinical Application(s) - A Novel Interpretable Score for Assessment of Post-COVID Syndrome

• Tobias May: A Knowledge-Based Machine Learning Approach for Algorithmic Treatment Planning for Patients With Post-COVID Syndrome 

• Adrian Pelcaru: Drivers of COVID-19 in Germany and the World 

• Melánia Puskás: Noise Modeling Approaches for Digital Caliper-Based Tumor Volume Estimation in Preclinical Studies 

• Martin Ferenc Dömény: Markov Chain Monte Carlo Method for Tumor Growth Model Identification 

• Dániel András Drexler: Engineering-based Personalization and Optimization of Chemotherapy in Preclinical Breast Cancer Models