Genomics is concerned with the sequencing and analysis of an organism’s genome. It is involved in the understanding of how every single gene can affect the entire genome. This goal is mainly afforded using the current, cost-effective, high throughput sequencing technologies. These technologies produce a huge amount of data that usually require high performance computing solutions and opens new ways for the study of genomics, but also transcriptomics, gene expression, and systems biology, among others. The continuous improvements and broader applications on sequencing technologies is producing a continuous new demand of improved high-throughput bioinformatics tools. Genomics is concerned with the sequencing and analysis of an organism genome taking advantage of the current, cost-effective, high throughput sequencing technologies. Continuous improvement on genomics is producing a continuous new demand of enhanced high-throughput bioinformatics tools. In this context, the generation, integration and interpretation of genetic and genomic data is driving a new era of healthcare and patient management. Medical genomics (or genomic medicine) is this emerging discipline that involves the use of genomic information about a patient as part of the clinical care with diagnostic or therapeutic purposes to improve the health outcomes. Moreover, it can be considered a subset of precision medicine that is having an impact in the fields of oncology, pharmacology, rare and undiagnosed diseases, and infectious diseases.The aim of this special session is to bring together researchers in medicine, genomics, and bioinformatics to translate medical genomics research into new diagnostic, therapeutic, and preventive medical approaches. Therefore, we invite authors to submit original research, new tools or pipelines, or their update, and review articles on relevant topics, such as (but not limited to):

• -Tools for data pre-processing (quality control and filtering)
• -Tools for sequence mapping
• -Tools for the comparison of two read libraries without an external reference.
• -Tools for genomic variants (such as variant calling or variant annotation)
• -Tools for functional annotation: identification of domains, orthologues, genetic markers, controlled vocabulary (GO, KEGG, InterPro...)
• -Tools for gene expression studies
• -Tools for Chip-Seq data
• -Integrative workflows and pipelines

Organizers:
Dr. Javier Pérez Florido, Bioinformatics Research Area, Fundación Progreso y Salud, Seville, Spain.
Dr. Rosario Carmona, Bioinformatics Research Area, Fundación Progreso y Salud, Seville, Spain.
Dr. Francisco M. Ortuño, University of Granada,Spain.

The health management landscape is rapidly transforming with the integration of cutting-edge health technologies such as wearable sensors, cameras, mobile applications, robotics, and telemedicine systems. These dynamic technologies are advancing, offering new solutions for early diagnosis, remote monitoring, personalized treatments, and enhanced rehabilitation strategies based on individual needs. By harnessing the capabilities of these innovations, diseases can be sensitively identified and objectively assessed, producing quantifiable measures to detect subtle changes related to treatment response and disease progression. In addition, continuous instrumental monitoring offers the opportunity to improve treatment strategies by collecting ecological data directly at patients' homes during their daily lives. Personalized health care requires the collaboration of physicians, biomedical engineers, data scientists, electronic engineers, and other specialized professionals. A multidisciplinary approach is essential to implement clinical practices through computational tools and innovative analytical methods, managing and interpreting the significant amount of data generated by these technologies.

This special session aims to provide a comprehensive exploration of healthcare technologies and computational solutions designed for clinical decision support. The main goal is to facilitate objective assessment, diagnosis, long-term monitoring, and personalized therapeutic and rehabilitation strategies for patients facing acute conditions or chronic disorders. The collection of articles will include the clinical application of various computational technologies and tools. The overall goal is to improve disease management and monitoring, ultimately improving patients' quality of life. Authors are invited to submit original and unpublished research articles that are in line with the theme of the session. Topics of interest include, but are not limited to:

• -Wearable sensors for health monitoring
• -Camera-based systems and computer vision applications in healthcare
• -Mobile applications for remote patient monitoring and management
• -Telemedicine systems for clinical decision support
• -Robotics in healthcare for rehabilitation and assistance
• -Artificial intelligence applications for personalized healthcare
• -Advanced biomedical signal processing for disease detection and assessment
• -Machine learning approaches for clinical decision support
• -Data analytics and interpretation of health-related data
• -Clinical applications of digital health technologies
• -Long-term monitoring solutions for chronic disorders
• -Ecological data collection and analysis in free-living conditions
• -Human-computer interaction in healthcare settings
• -Ethical considerations in the use of health technologies
• -Challenges and opportunities in the implementation of computational solutions in clinical practice.

Organizer:
Prof. Luigi Borzì,

Luigi Borzì, Assistant Professor @ Analytics and Technologies for Health Lab - Department of Control and Computer Engineering & Polito Biomedical Engineering Lab, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy.

Prof. Borzì is an Assistant Professor in the Department of Control and Computer Engineering at the Polytechnic University of Turin and works on medical applications of artificial intelligence and wearable technologies. He received his B.Sc. and M.Sc. in Biomedical Engineering and Ph.D. in Computer and Control Engineering from the Polytechnic University of Turin. He is Associate Editor of the journals Smart Health and PLOS ONE and a member of the editorial board of the journals Frontiers in Digital Health and Frontiers in Robotics and AI. He has served on the Technical Program Committee of several international conferences, including the IEEE International Conference on Digital Health, IEEE International Symposium on Computer-Based Medical Systems, IEEE International Conference on E-health Networking, Application & Services, IEEE International Conference on ICT Solutions for eHealth, IEEE International Conference on Application of Information and Communication Technologies, and the ACM International Symposium on Wearable Computers. His research interests include machine learning, wearable technology, digital health, data analytics, wireless body sensor networks and medical IoT..

Deep Learning (DL) is currently the state-of-the-art for efficiently analyzing complex and high dimensional data in biomedical and bioinformatics applications. These data range from medical images and genomics and proteomics sequences, to electrocardiograms, to name a few. Deep learning methods, as an evolution of artificial neural networks, is able to provide high performing solutions due to their ability to handle large datasets, learn complex relationships and learn automatic feature representations. Nevertheless, DL is not only relevant for biomedical data analysis, but it is also of interest for information retrieval, or for the development of models based on natural language processing (NLP).

In this special session, we call for new research on applications that, using DL approaches, can provide efficient solutions for the diverse palette of problems that entail the analysis of biomedical and bioinformatics data, or their use in healthcare and medical applications. Authors are invited to submit original and unpublished research articles that are in line with the theme of the session. Topics of interest include, but are not limited to:

• -Medical image analysis using convolutional neural networks
• -Transformer-based methods.
• -Recurrent neural networks.
• -Generative Models.
• -Reinforcement learning based on DL.
• -Feature representation learning
• -Methods for the interpretation and explanation of ML/DL models (XAI) applied to the analysis of biomedical data.
• -Information retrieval based on DL methods.
• -Applications of DL NLP models, including Large Language Models.

Organizers:

Associate Prof. Caroline König, Computer Science Department at Universitat Politècnica de Catalunya, UPC BarcelonaTech, in Barcelona, Spain.

Caroline König is associate professor with the Computer Science Department at Universitat Politècnica de Catalunya, UPC BarcelonaTech, in Barcelona, Spain, as well as principal investigator of the European PERMEPSY project. She is involved in the development of artificial intelligence applications for the analysis of molecular dynamics data in proteomics. Her research interests are on ML approaches for automatic feature extraction from multimodal sequential data, anomaly detection and explainability of ML models.

Prof. Alfredo Vellido, Universitat Politècnica de Catalunya.

Alfredo Vellido is full professor at Universitat Politècnica de Catalunya, UPC BarcelonaTech, in Barcelona, Spain. He is member of the Spanish IABiomed Society and CIBER-BBN network, as well as Chair of the Explainable Machine Learning (EXML) Task Force for the IEEE-CIS Data Mining and Big Data Analytics Technical Committee. He has over 25 years of experience on biomedical applications of ML and bioinformatics, areas in which he has published widely.

Motivation and Objectives The era of artificial intelligence (AI) is here right now and already affecting everyday life. The availability of the approaches, tools, and models in combination with computational power and cloud solutions allows us to achieve results quickly even without prior expert knowledge. However, the robustness, persistence, and ethics of such solutions remains big question in society. Especially in biomedical and bioinformatics tasks, it is crucial to validate the interpretation of the results and deeply understand conditionality and consequences to avoid typical bias and artefacts of current AI capabilities. It is extremely necessary to have such awareness for time lapse and time sequences analysis, since such datasets are already sensitive to aliasing and extrapolation affects.

In this special section should be provided case studies, metastudies, pipelines, and preliminary results of biological time series analysis, focused on the features extraction, comparisons of classical machine learning and modern deep learning methods, and discussion of challenges and possible problems of inadequate usage, confidence, and interpretation of existing and future AI tools. The topic could also cover questions of data binning, false precision, or continualization

Organizer:
Prof. Jan Urban,

Dr. Jan Urban, Laboratory of Signal and Image Processing, Institute of Complex Systems, South Bohemian Research Center of Aquaculture and Biodiversity of Hydrocenoses, Faculty of Fisheries and Protection of Waters, University of South Bohemia, Czech Republic.

Dr. Urban obtained his master degree in Cybernetics and control techniques, and his PhD in Biophysics. He gained work experiences in Sweden, Norway, Austria, USA, and Spain. His work is focused on data acquisition, representation, processing, analysis, and multivariate statistics of complex datasets from biological origin.

Signal processing focuses on analysing, modifying and synthesizing signals such as sound, images and biological measurements. Signal processing techniques can be used to improve transmission, storage efficiency and subjective quality and to also emphasize or detect components of interest in a measured signal and is a very relevant topics in medicine.

Any signal transduced from a biological or medical source could be called a biosignal. The signal source could be at the molecular level, cell level, or a systemic or organ level. A wide variety of such signals are commonly encountered in the clinic, research laboratory, and sometimes even at home. Examples include the electrocardiogram (ECG), or electrical activity from the heart; speech signals; the electroencephalogram (EEG), or electrical activity from the brain; evoked potentials (EPs, i.e., auditory, visual, somatosensory, etc.), or electrical responses of the brain to specific peripheral stimulation; the electroneurogram, or field potentials from local regions in the brain; action potential signals from individual neurons or heart cells; the electromyogram (EMG), or electrical activity from the muscle; the electroretinogram from the eye; and so on.

In the other side, medical imaging is the technique and process of creating visual representations of the interior of a body for clinical analysis and medical intervention, as well as visual representation of the function of some organs or tissues (physiology). Medical imaging seeks to reveal internal structures hidden by the skin and bones, as well as to diagnose and treat disease. Medical imaging also establishes a database of normal anatomy and physiology to make it possible to identify abnormalities. Although imaging of removed organs and tissues can be performed for medical reasons, such procedures are usually considered part of pathology instead of medical imaging.

Organizer

Prof. Dr. L.Wang, Computer Science Department at Univ Calif San Diego, USA.

With continuous advancements of biomedical instruments and the associated ability to collect diverse types of valuable biological data, numerous recent research studies have been focusing on how to best extract useful information from the ‘Big biomedical Data’ currently available. While drug design has been one of the most essential areas of biomedical research, the drug design process for the most part has not fully benefited from the recent explosion growth of biological data and bioinformatics algorithms. With the incredible overhead associated with the traditional drug design process in terms of time and cost, new alternative methods, possibly based on computational approaches, are very much needed to propose innovative ways to propose effective drugs and new treatment options. Employing advanced computational tools for drug design and precision treatments has been the focus of many research studies in recent years. For example, drug repurposing has gained significant attention from biomedical researchers and pharmaceutical companies as an exciting new alternative for drug discovery that benefits from the computational approaches. This new development also promises to transform healthcare to focus more on individualized treatments, precision medicine and lower risks of harmful side effects. Other alternative drug design approaches that are based on analytical tools include the use of medicinal natural plants and herbs as well as using genetic data for developing multi-target drugs.

Any signal transduced from a biological or medical source could be called a biosignal. The signal source could be at the molecular level, cell level, or a systemic or organ level. A wide variety of such signals are commonly encountered in the clinic, research laboratory, and sometimes even at home. Examples include the electrocardiogram (ECG), or electrical activity from the heart; speech signals; the electroencephalogram (EEG), or electrical activity from the brain; evoked potentials (EPs, i.e., auditory, visual, somatosensory, etc.), or electrical responses of the brain to specific peripheral stimulation; the electroneurogram, or field potentials from local regions in the brain; action potential signals from individual neurons or heart cells; the electromyogram (EMG), or electrical activity from the muscle; the electroretinogram from the eye; and so on.

Organizer

Prof. Hesham H. Ali, UNO Bioinformatics Core Facility. College of Information Science and Technology. University of Nebraska at Omaha.

The exponential growth of Real-world Data (RWD) has been identified as one of the major sources of transformation in the healthcare industry. RWD is a vast and growing collection of data sources, such as electronic health records, claims data, wearables, and social media, that can provide valuable insights into patient health. However, unlocking the true potential of RWD requires a collaborative effort from healthcare professionals, ethicists, data scientists, and AI experts.

In this session, we will explore how RWD can help facilitate evidence-based decision-making, generate new knowledge, or provide patient-centric solutions while acknowledging its limitations and potential dangers. Our goal is to encourage a lively exchange of ideas at the crossroads of biomedical big data, artificial intelligence (AI), and statistical learning. Topics of interest include but are not limited to:

• - Cutting-edge techniques for cleaning, integrating, and analyzing diverse RWD sources.
• - Specific use cases of AI in disease prediction, risk stratification, treatment optimization, and drug discovery.
• - AI-powered insights uncovering hidden patterns for personalized medicine, proactive interventions, and improved clinical workflows.
• - Generative modeling: from imputation to EHR summarization and synthetic patient generation.
• - Real-world examples showcasing the impact of RWD-driven projects on healthcare outcomes.
• - Ongoing research efforts refining analytical methods, addressing data quality challenges, and ensuring ethical AI development.
• - Limitations and dangers: Data quality and standardization challenges, privacy and security concerns, algorithmic bias and fairness, black box modeling, regulatory landscapes, and ethical considerations.

Organizers:
Dr. Javier Pérez Florido, Bioinformatics Research Area, Fundación Progreso y Salud, Seville, Spain.
Dr. Carlos Loucera , Bioinformatics Research Area, Fundación Progreso y Salud, Seville, Spain.
Dr. Francisco M. Ortuño, University of Granada,Spain.