About CIBB

Topics of interest include, but are not limited to:

• Machine learning methods applied to health care and biomedical datasets

Short description:

Machine learning has become a pivotal tool for analyzing biomedical and biological datasets, especially in the Big Data era. In fact, machine learning algorithms can identify hidden relationships and structures in health care data, and leverage them to formulate accurate predictions about similar or future data instances. For example, machine learning software has been able to predict the diagnoses of patients with cancer simply by processing patients' clinical features, allowing scientists to save time and money compared to traditional wet-lab experiments. Computational researchers have also utilized machine learning to infer knowledge about patients by analyzing biological datasets, particularly those featuring genetics and epigenomic traits. Data mining approaches applied to such datasets can lead to significant discoveries, enhancing our understanding of molecular biology and providing new insights into patients’ diseases. Moreover, recent advancements in this context foresee the exploitation of clinical knowledge, represented in different forms such as medical protocols, by defining methods to integrate and inject such knowledge into machine learning algorithms. This way, the best of both approaches (knowledge-based and data-based) can be leveraged. Our special session on ""Machine learning for structured data in clinical informatics and medical biology"" aims to advance these scientific fields by inviting researchers to demonstrate the potential and advancements of machine learning algorithms in making accurate computational predictions in healthcare datasets and patient-oriented biological datasets.

Special Session Proposers

• Davide Chicco, Università di Milano-Bicocca, Italy.
• Giuseppe Jurman, Fondazione Bruno Kessler, Italy.
• Wei Liu, Fujian Agriculture and Forestry University, China.
• Matthijs Warrens, Rijksuniversiteit Groningen, the Netherlands.
• Luca Oneto, Università di Genova, Italy.
• Davide Bacciu, Università di Pisa, Italy.
• Sara Montagna, Università di Urbino "Carlo Bo", Italy.

Contacts

davide.chicco@gmail.com

Topics of interest include, but are not limited to:

• Network-based approaches in bioinformatics (e.g., protein-protein interaction networks, metabolic pathways, regulatory networks)
• Graph Neural Networks in biomedical applications (e.g., disease diagnosis, drug repurposing, patient stratification)
• Multi-omics data integration using networks and GNNs
• Graph representation learning for medical imaging and diagnostics
• Explainability and interpretability of GNNs in healthcare
• Scalability and efficiency of graph-based models in biomedical big data
• Applications of network science in epidemiology and public health
• Ethical considerations and bias in network-driven biomedical AI

Short description:

We are pleased to invite submissions to the Special Session on Networks and Graph Neural Networks for Bridging Bioinformatics and Medicine. The rapid advancements in network science and graph-based deep learning have revolutionized biomedical research. Complex biological systems, including protein interactions, gene regulatory networks, and disease ontologies, can be effectively modeled using networks. Graph neural networks (GNNs) further provide a powerful framework to learn from these structures, enabling significant progress in disease classification, drug discovery, and precision medicine. This special session aims to bring together researchers and practitioners from bioinformatics, medicine, and artificial intelligence to explore how networks and GNNs can bridge the gap between computational methods and clinical applications. We encourage contributions that develop new methodologies, provide novel applications, or highlight challenges and future directions in the field. We welcome submissions on, but not limited to, the following topics:

Special Session Proposers

• Pietro Hiram Guzzi, Magna Græcia University of Catanzaro, Italy.
• Ugo Lomoio, Magna Græcia University of Catanzaro, Italy.
• Barbara Puccio, Magna Græcia University of Catanzaro, Italy.
• Annamaria De Filippo, Magna Græcia University of Catanzaro, Italy.
• Pierangelo Veltri, Magna Græcia University of Catanzaro, Italy.
• Patrizia Vizza, Magna Græcia University of Catanzaro, Italy.

Contacts

hguzzi@unicz.it

Topics of interest include, but are not limited to:

• Applications of Generative AI in Translational Bioinformatics:
• Personalized medicine and tailored treatment plans
• Drug discovery acceleration through AI-driven molecular simulations
• Predictive analytics for disease progression and patient risk assessment
• Virtual clinical trials and AI-enhanced biomedical research
• Methodological Advances in Generative AI for Bioinformatics:
• Advancements in deep learning frameworks (VAEs, GANs, Diffusion Models) for biomedical data synthesis
• Transformer models for biomedical text and protein sequence generation
• Conditional and query-based data generation tailored to patient-specific clinical features
• Metrics for validating synthetic high-dimensional and complex biomedical data
• Real-world applications of synthetic data to enhance clinical decision-making and precision medicine
• Ethical, Societal, and Computational Challenges:
• Data privacy concerns and strategies for secure AI implementations
• Algorithmic bias and fairness in AI-driven biomedical predictions
• Interpretability and explainability of generative models in healthcare
• High computational costs and approaches to improving efficiency
• Future Directions in AI-Driven Bioinformatics:
• Enhancing AI for real-time decision-making in clinical applications
• Integrating generative AI with multi-omics data for precision medicine
• Frameworks for theethical use and governance of generative AI in biomedicine

Short description:

Generative AI is transforming translational bioinformatics by enabling the synthesis, integration, and analysis of biological data for improved healthcare outcomes. This session will explore how advanced generative models, including deep learning and neural networks, enhance various biomedical applications, such as personalized medicine, drug discovery, and predictive analytics. By facilitating complex data integration, generative AI is reshaping bioinformatics research, allowing scientists to extract meaningful insights from vast genomic, clinical, and molecular datasets. As this technology gains prominence, it presents both groundbreaking opportunities and significant challenges. While generative AI can mitigate data imbalance, enhance predictive modeling, and streamline healthcare operations, concerns remain regarding data privacy, algorithmic bias, and interpretability. Furthermore, the computational demands of deep generative models and the need for robust generalization to unseen data complicate their adoption in biomedical research. This session will provide a forum for researchers and trainees to discuss the latest advancements, share case studies, and address the challenges associated with the responsible implementation of generative AI in translational bioinformatics."

Special Session Proposers

• Jake Chen, The University of Alabama at Birmingham, USA.
• Pietro Pinoli, Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Italy.
• Matteo Bregonzio, 81Watts.
• Marco Chierici, Fondazione Bruno Kessler, Italy.
• Giuseppe Jurman, Fondazione Bruno Kessler; Humanitas University, Italy.
• Raffaele Marchesi, Fondazione Bruno Kessler; Università degli Studi di Pavia, Italy.
• Shahryar Noei, Fondazione Bruno Kessler, Italy.
• Francesca Pia Panaccione, Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Italy.
• Matteo Pozzi, Fondazione Bruno Kessler, Italy.

Contacts

• jakechen@uab.edu
• pietro.pinoli@polimi.it

Topics of interest include, but are not limited to:

• Deep Learning for Genomic Data Modeling
• Generative Models for Synthetic Genomes Generation
• Computer vision Integration in Computational Genomics
• Modeling Genome and Pangenome Large Scale Graphs with Graph Neural Networks
• Leveraging Large Language Models (LLMs) in Genomic Data Science
• Explainable AI in Genomics: Methods and Applications
• High-Performance Computing for Scalable Genomic Workflows

Short description:

The growing availability of genomic data represents both a vast resource and a significant computational challenge. This enormous volume of data provides valuable insights into the DNA structure of organisms. However, processing a massive amount of genomics sequences demands substantial computational power. High-Performance Computing (HPC) infrastructures have become pivotal for efficiently exploring, analyzing, and interpreting large genomic collections, enhancing advancements across all fields of computational genomics. Moreover, GPU-accelerated computing enables highly parallelized operations, significantly enhancing the efficiency of deep learning models, large-scale sequence alignments, and genomic simulations. The scope of this special session consists of bringing together researchers working at the intersection of deep learning, High-Performance Computing (HPC) including GPU-accelerated computing, alongside genomic data modeling and analysis. By focusing on the integration of advanced computational techniques with genomic research, the session aims to foster collaboration and innovation in developing new methodologies for tackling the challenges posed by large-scale genomic datasets.

Special Session Proposers

• Umberto Ferraro Petrillo, Dipartimento di Scienze Statistiche, Università di Roma - La Sapienza, Italy.
• Lorenzo Di Rocco, Dipartimento di Scienze Statistiche, Università di Roma - La Sapienza, Italy.
• Ilaria Billato, Dipartimento di Biologia, Università di Padova, Italy.
• Riccardo Ceccaroni, Dipartimento di Scienze Statistiche, Università di Roma - La Sapienza, Italy.
• Emanuel Di Nardo, Dipartimento di Scienze e Tecnologie, Università di Napoli - Parthenope, Italy.

Contacts

umberto.ferraro@uniroma1.it

Topics of interest include, but are not limited to:

• Prediction uncertainty in Health informatics
• Methods for the visualisation of out-of-distribution samples
• Explainable AI
• AI data visualisation
• Out-of-distribution recognition
• Metrics for model evaluation and sample prediction
• Unknown sample prediction techniques
• Mathematical modelling of out-of-distribution recognition
• Open-set versus closed-set recognition
• Application of out-of-distribution recognition
• Methods for active learning

Short description:

To prevent wrong predictions of a Neural Network, we need to better understand and/or visualize the confidence of each individual prediction. For this reason, we ask the community, what happen if a model must predict an out-of-distribution sample/image in an open-world/life scince scenario? In other words, how a model defines a certain in-distribution (test data is assumed to be drawn from the training data), to detect an out-of-distribution event. How explainable deep learning can help us to understand the model prediction performance? In fact, a model can cause prediction failures due to its blindness and poor awareness. Moreover, it conveys high confident in its correctness, which can be problematic for wide range of applications, such as for healthcare applications. For instance, standard metrics for the evaluation of Deep Learning models measure overall model performance on a limit test dataset and provide no indication of the model confidence in the correctness of an individual prediction of new samples. That can result in prediction failure, when a model is faced with out-of-distribution data. Therefore, we should question our self. How can we detect and visualize data to reduce uncertainty in deep learning? The scope of this special session is to ask the research community how they validate and/or visualize their prediction outcome and how we can better predict out-of-distribution samples in the future.

Special Session Proposers

• David Dannhauser, University of Naples (Federico II), Italy.
• Filippo Causa, University of Naples (Federico II), Italy.
• Pasquale Memmolo, Istituto di Scienze Applicate e Sistemi Intelligenti “Eduardo Caianiello", Italy.
• Roberto Tagliaferri, University of Salerno, Italy.

Contacts

david.dannhauser@unina.it

Topics of interest include, but are not limited to:

• Machine learning and deep learning applications in medical imaging
• Explainable Deep Learnig/Machine learning
• Decision Support System based on Deep Learning system
• AI-driven image segmentation and feature extraction
• Automated lesion detection and classification
• Predictive modeling with radiomic biomarkers
• Standardization and reproducibility in radiomics research
• AI in oncology: tumor characterization and treatment response assessment

Short description:

Artificial Intelligence (AI) in medical imaging is revolutionizing diagnostics and prognostics by enabling automated, quantitative analysis of scans, providing clinicians with a valuable decision-support tool. Radiomics plays a key role by extracting high-dimensional quantitative features from images, capturing disease heterogeneity, metabolism, and microenvironment patterns. When integrated with machine / deep learning methods, radiomic biomarkers enhance personalized medicine by predicting outcomes, therapy response, and disease progression. Precisely, deep learning has significantly advanced image classification, improving segmentation, anomaly detection, and predictive modeling. Architectures like ResNet, EfficientNet, and Vision Transformers have strengthened model accuracy and efficiency. However, clinical adoption still faces some challenges, including data standardization, external validation, and model interpretability. Explainable Deep Learning (XDL) helps address these challenges by enhancing transparency and trust, enabling the understanding and justification of deep learning model predictions. Common techniques include activation maps, Grad-CAM, and SHAP (Shapley Additive Explanations), which support clinicians to understand and validate AI-driven decisions. By improving model traceability and reducing biases, XDL fosters collaboration between AI and healthcare professionals, ensuring safer and more ethical applications. By integrating imaging, computational intelligence, and clinical expertise, AI is driving the future of precision medicine, enhancing diagnostic accuracy, and enabling more personalized and effective patient care.

Special Session Proposers

• Ignacio Rojas, University of Granada, Spain.
• Carolina Bezzi, Vita-Salute San Raffaele University, Milan, Italy.
• Olga Valenzuela, University of Granada, Spain.
• Samuele Ghezzo, Vita-Salute San Raffaele University, Milan, Italy.
• Maria Picchio, Vita-Salute San Raffaele University, Milan, Italy.
• Paola Mapelli, Vita-Salute San Raffaele University, Milan, Italy.
• Sara Resta, Vita-Salute San Raffaele University, Milan, Italy, and Politecnico di Milano, Italy.

Contacts

• irojas@ugr.es
• bezzi.carolina@hsr.it

Topics of interest include, but are not limited to:

• AI and machine learning for multi-omics and multimodal data integration
• Computational and statistical approaches for heterogeneous data fusion
• Deep learning models for biomarker discovery and disease characterization
• Explainable AI and interpretable models in healthcare decision-making
• Integration across omics layers and meta-analysis across multiple cohorts
• Predictive modeling for patient stratification and disease progression
• Biomedical signal and image processing using AI
• Federated learning approaches for decentralized medical data
• Natural Language Processing (NLP) for mining clinical and EHR data
• Computational drug discovery and pharmacogenomics through AI
• Integration techniques supporting Digital Twin models in precision healthcare
• Challenges and future directions in large-scale data fusion for biomedical research

Short description:

The explosion of high-throughput technologies has resulted in vast amounts of multi-omics and multimodal biomedical data, ranging from genomics, proteomics, and metabolomics to imaging, electronic health records (EHRs), and real-world sensor data. Integrating these diverse data sources is essential to unravel complex biological mechanisms, drive biomarker discovery, and advance precision medicine. However, the heterogeneity and complexity of these datasets pose significant challenges. This special session aims to bring together experts in computational biology, AI, and biomedical research to discuss cutting-edge integrative methodologies for multi-omics and multimodal data fusion. The session will focus on advanced statistical modeling, machine learning, and deep learning approaches that preserve the unique contributions of each data type while enabling holistic biological and clinical insights. Additionally, we will explore the translation of these integrated models into practical applications in personalized medicine, disease modeling, and healthcare optimization, including their role in developing Digital Twin frameworks for precision health.

Special Session Proposers

• Annamaria Carissimo, Institute for Applied Mathematics of the National Council for Research, Naples, Italy.
• Antonella Iuliano, University of Cambridge, UK.
• Lidia Ghosh, Department of Computer Application at the RCC Institute of Information Technology, Kolkata, India.
• Biswarup Ganguly, Department of Electrical Engineering at NIT Silchar, India.

Contacts

• annamaria.carissimo@cnr.it
• lidiaghosh21@gmail.com

Topics of interest include, but are not limited to:

• Spatial proteomics
• Spatial transcriptomics
• Spatial fluxomics
• Spatial metabolomics
• Tissue Architecture
• Spatial omics data analysis (data integration, clustering, neighborhood, organization)

Short description:

In the single-cell biology era spatial approaches have become fundamental for understanding biological complexity. This has been established by some of the last Nature Methods of the Year (2024- Spatial Proteomic, 2020 Spatially Resolved Transcriptomics). Under the umbrella of Spatial-omics a variety of different techonologies are encompassed, each of them requiring a dedicated bioinformatic approach. The aim of this special session is to bring together researchers who are working on the development of methods and models in the fields of spatial omics data analysis to facilitate the exchange of knowledge and ideas in this innovative and fundamental research area.

Special Session Proposers

• Maddalena Maria Bolognesi, National Research Council, Italy
• Bruno Giovanni Galuzzi, National Research Council, Italy
• Chiara Damiani, University of Milano-Bicocca, Italy
• Francesco Lapi, University of Milano-Bicocca, Italy
• Lorenzo Dall’Olio, Istituto delle Scienze Neurologiche, Bologna, Italy

Contacts

brunogiovanni.galuzzi@cnr.it

Topics of interest include, but are not limited to:

• Predictive models
• net benefit
• discrimination
• calibration
• uncertainty
• regression models
• machine learning

Short description:

There has been a rapid increase in publication of new predictive models in biomedical literature. This has been driven mainly by the widespread availability of data from electronic health record, alongside with routine collection and processing of genetic, genomic, and imaging data. Additionally, the growing application of machine learning and artificial intelligence methods in the biomedical field has played a key role. These advanced techniques enable the inclusion of a broader range of variables, which can enhance prediction models by capturing more detailed and nuanced patterns within the data. However, this growth in prediction modeling also brings about certain methodological challenges. This session would reflect on sources of uncertainty when applying predictive algorithms and models in medical care, on their methodological challenges and clinical utility.

Special Session Proposers

• Paola Rebora, Università di Milano-Bicocca, Italy.

Contacts

paola.rebora@unimib.it

Topics of interest include, but are not limited to:

• Interpretable learning architectures
• XAI in healthcare
• XAI in decision science

Short description:

The rapid integration of Artificial Intelligence (AI) in bioinformatics and biostatistics has led to groundbreaking advancements in data analysis, predictive modeling, and decision support systems. However, the complexity of AI models often poses significant challenges in terms of interpretability and transparency, which are critical for clinical and biomedical applications. This special session focuses on Explainable AI (XAI) methodologies tailored for bioinformatics and biostatistics, emphasizing techniques that enhance model interpretability while maintaining predictive performance. We welcome contributions on model-agnostic and model-specific XAI approaches, including feature attribution methods, rule-based systems, and interpretable deep learning architectures. Applications may include—but are not limited to—genomic and transcriptomic data analysis, survival modeling, biomarker discovery, and personalized medicine. By bringing together researchers and practitioners from AI, bioinformatics, and biostatistics, this session aims to foster discussion on best practices for integrating explainability into complex models. Topics of interest include novel XAI frameworks, fairness and bias assessment in biomedical AI, regulatory considerations, and real-world case studies demonstrating the impact of XAI in healthcare. We invite original research and innovative applications that contribute to bridging the gap between AI-driven discoveries and their interpretability, ensuring transparency, trust, and usability in biomedical decision-making.

Special Session Proposers

• Elia Biganzoli, Università Statale di Milano, Italy.
• Paulo Lisboa, Liverpool John Moores University, UK.

Contacts

elia.biganzoli@unimi.it

Topics of interest include, but are not limited to:

• Surgery and Minimally Invasive Procedures
• Artificial Intelligence for Healthcare
• Rehabilitation and Physical Therapy
• Telemedicine and Remote Care
• Cognitive Robotics
• Collaborative Robotics
• Human-robot interaction
• Ontology in Healthcare
• Diagnostic Imaging and Radiology
• Patient Assistance and Elderly Care
• Medicine Distribution
• Patient Monitoring

Short description:

AI techniques are being increasingly integrated into robots to improve their performance and enhance their capabilities, especially in the medical field. An example of an application of AI in medical robotics is in surgical procedures. AI can be used to improve surgical planning, navigation, and execution. AI techniques can also be used to control the motion of surgical instruments, ensuring precise and accurate movements during the procedure. AI algorithms can be trained to analyze medical images and identify potential abnormalities or diseases. In telemedicine, AI is being used to control computer systems for remote healthcare services. Large datasets can be used to train machine learning algorithms to improve their accuracy and reliability and can also be used to update and refine their performance over time continuously. This allows medical robots to provide more accurate results and can also help reduce the risk of human error. Thus, this special session focuses on the important role of robots with AI in contemporary medicine.

Special Session Proposers

• Daniela D'Auria, Department of Engineering and Sciences of the Universitas Mercatorum, Italy.

Contacts

daniela.dauria@unimib.it

Topics of interest include, but are not limited to:

• Statistical analysis of high-dimensional omics data
• Health big data analytics
• Software tools for bioinformatics, biostatistics, systems and synthetic biology
• Applications of machine learning to bioinformatics or health datasets"

Short description:

The study of complex traits, influenced by multiple genetic variants and environmental factors, remains a key challenge in genomic epidemiology. The integration of high-dimensional omics data with phenotypic information has revolutionized our ability to uncover genetic risk markers, biological mechanisms, and higher-order interactions in large-scale health datasets. This session will explore advanced statistical and computational approaches for analyzing complex traits, leveraging cutting-edge analytical frameworks to better understand the intricate genetic architecture of complex diseases and traits. Emphasis will be placed on innovative statistical epidemiological methods in high-dimensional omics analysis and machine learning applications. Additionally, the session will provide a forum to discuss innovative solutions and novel methodologies, including polygenic risk scores, phenome-wide association studies, Mendelian randomization, imputation techniques, pharmacoepidemiological analytics, multi-omics data analysis and computational models for detecting interactions in high-dimensional genomic data.

Special Session Proposers

• Erika Salvi, Data Science Center and Computational multi-Omics of Neurological Disorders (MIND) Lab, IRCCS Istituto Neurologico “Carlo Besta”, Italy
• Carlo Maj, Center for Human Genetics, University of Marburg, Germany

Contacts

erika.salvi@istituto-besta.it

Topics of interest include, but are not limited to:

• Advanced regression models tailored to epigenetic data
• Machine learning techniques for high-dimensional datasets
• Integration of multi-omics data (e.g., genomics, transcriptomics, proteomics)
• Methods for managing data heterogeneity and batch effects
• Approaches to address multiple testing and improve reproducibility
• Statistical frameworks for analyzing environmental exposure impacts
• Causal inference models in environmental epigenetics
• Computational pipelines and tools for epigenomic data analysis
• Data visualization techniques for complex epigenetic interactions

Short description:

In recent years, the field of epigenetics has undergone rapid development, revealing how environmental exposures can lead to modifications in gene expression without altering the underlying DNA sequence. This special session is designed to address the complex statistical challenges inherent in analyzing environmental epigenetics data and to foster innovative approaches for interpreting these high-dimensional datasets. This session aims to unite experts from biostatistics, computational biology, epigenetics, and environmental health. Our primary objectives are to refine statistical methodologies for managing data heterogeneity, tackle issues related to multiple testing, and enhance reproducibility in epigenomic studies. We seek to develop robust statistical frameworks that can be applied to uncover the intricate interplay between environmental exposures and epigenetic modifications. Participants will explore a range of topics including advanced regression models, machine learning techniques, and the integration of multi-omics data. The session will highlight novel statistical approaches that not only address current analytical challenges but also pave the way for future research. By delving into the latest methodological advancements, we will provide a comprehensive overview that spans theoretical foundations to practical applications, encouraging interdisciplinary dialogue and collaboration. By combining cutting-edge statistical techniques with practical applications, this session aspires to deepen our understanding of the epigenetic mechanisms driving environmental influences. The anticipated impact includes improved public health outcomes through more accurate predictive models and the advancement of personalized medicine. Ultimately, the insights gained here are expected to inspire innovative research directions and enhance collaborative efforts across diverse scientific disciplines.

Special Session Proposers

• Elia Biganzoli, Università Statale di Milano, Italy.
• Valentina Bollati, Università Statale di Milano, Italy.

Contacts

elia.biganzoli@unimi.it

Topics of interest include, but are not limited to:

• Survival analysis
• state transition models
• competing events
• multi-state models
• prediction models
• case detection
• regression models

Short description:

The increasing availability of data from electronic health records and the more routine collection and processing of genetic, genomic, and imaging data has led to increasingly large data sources that have the potential for improving healthcare outcomes, research, and policy decisions. Statistical models as well as machine learning technics have the potential to be useful in a deeper understanding of the underlying processes of disease, progression, and risk factors. The use of electronic health records integrated with additional data sources, including longitudinal markers, gives the possibility to follow the life history of individuals and describing state transitions (e.g. illness-death models), provided that information in time is correctly modeled. The analysis of this type of data is often complicated by various issues including multiple possible competing events, event type misclassification, and imprecise measurement of variables and event times. Moreover, transition might be driven by longitudinal markers or variables that change value in time. The session will aim to show different approaches to deal with the complexity of the modeling of disease state transitions using electronic health records.

Special Session Proposers

• Paola Rebora, Università di Milano-Bicocca, Italy.

Contacts

paola.rebora@unimib.it

Topics of interest include, but are not limited to:

• Parameterization and verification of biomedical models
• Individual-aware models to assess the impact of genetic variation on cellular regulatory network
• Cancer progression models
• Epidemiological models
• Multiscale models and simulation of biological systems
• Space-temporal models and simulation of biological systems
• Robustness of cellular networks
• Emergent properties in complex biological systems
• Metabolic and signaling pathways analysis and engineering
• Genetic variants impact on epigenetic elements
• Models for personalized and targeted therapies
• Patient classification and stratification
• Drug combination, repositioning, and recommendation for personalized medicine
• Clinical data integration into systems biology models
• Single-cell and spatial transcriptomics analysis

Short description:

Computational biology is a field that involves the analysis of biological systems at various levels of complexity, using appropriate modeling frameworks and computational methods. With the advancement of computational biology approaches and modeling systems, the current challenge is to employ these techniques to define personalized models that identify tailored drugs and therapies, thus realizing the personalized medicine paradigm. This special session aims to bring together researchers who are working on the development of methods and models applied in the fields of computational biology and systems medicine to facilitate the exchange of knowledge and ideas in these innovative and fundamental research areas. The workshop will be sponsored by the National Biodiversity Future Center (NBFC) (https://www.nbfc.it/).

Special Session Proposers

• Simone Avesani, University of Verona, Italy
• Gospel Ozioma Nnadi, University of Verona, Italy
• Roberta Sirovich, University of Turin, Italy
• Michele Tebaldi, University of Verona, Italy
• Manuel Tognon, University of Verona, Italy
• Eva Viesi, University of Verona, Italy

Contacts

eva.viesi@univr.it

Topics of interest include, but are not limited to:

• Biomedical signal processing, Personalised medicine for diagnosis and prognosis

Short description:

Aims This special session explores how the brain operates near criticality, a delicate balance between order and chaos that optimises neural adaptability and function. We use advanced computational approaches to bridge theoretical neuroscience with practical diagnostics, neurostimulation, and brain-computer interface (BCI) applications. The session will bring together experts to discuss how complexity-based methods can improve our understanding of brain health and pathology, leading to innovative clinical and technological advances. Scope Key topics will include:

• The role of criticality in brain function, from consciousness research to neurodevelopmental, psychiatric and neurodegenerative disorders.
• Novel signal processing techniques to improve BCI performance by increasing decoding accuracy and brain state classification.
• Personalised non-invasive brain stimulation (NIBS) strategies that adapt to individual neural dynamics for optimised therapeutic outcomes.
• Multimodal integration of EEG, MEG, fMRI and TMS-EEG with computational models to uncover new brain function and dysfunction biomarkers.

This session promotes interdisciplinary collaboration between neuroscience, biomedical engineering and computational sciences and highlights state-of-the-art methods for assessing and modulating brain activity. Impact Understanding brain criticality has transformative implications for neuroscience and neurotechnology. Identifying novel complexity-based biomarkers can improve early diagnosis, refine neurostimulation therapies and enhance BCI applications. Participants will gain insights into how these approaches are shaping the future of personalised medicine, neurological rehabilitation and human-machine interaction. Join us to explore how harnessing brain criticality can make a difference in neuroscience and biomedical engineering!

Special Session Proposers

• Camillo Porcaro, Neuroscience Departmant (DNS) and Padova Neuroscience Center (PNC), Università degli Studi di Padova, Italy.

Contacts

camillo.porcaro@unipd.it

Topics of interest include, but are not limited to:

• Computational models for early detection of mental health issues
• Computational tools for continuous monitoring
• Computational models for personalized interventions
• Computational models for disease risk stratification
• Computational models for multimodal data analysis
• Computational models for emotion recognition
• Bias and Fairness in Mental Health and Well-being AI

Short description:

The development of computational methods specifically designed for mental health and well-being is critical to address global challenges ensuring an ethical, transformative impact on user outcomes. These methods could provide insights into understanding, diagnosing, and monitoring mental health conditions, by delivering personalized and cost-effective solutions to improve health outcomes and quality of care, and enabling early intervention, real-time support, and long-term well-being. They could analyze and integrate data from brain activity, behavior, and symptom patterns to explain underlying mechanisms of psychological responses, as well as possible neuropsychiatric pathways and trajectories of care for mental disorders. However, the adoption of computational models in this specific context, opens several challenges that should be addressed, ranging from the need of high-quality datasets, that requires continuous interplay among researchers of different disciplines, to the design of systems that protect user privacy, ensure equity, and prevent algorithmic biases in sensitive mental health applications, to name a few. The special session on ""Computational Methods for Mental Health and Well-Being"" aims to provide a cross-disciplinary exchange that combines computer science, psychology, mental healthcare, and ethics, reflecting the growing importance of technology in improving mental well-being, and stimulating collaborative discussions that might focus on integrating computational methods into healthcare systems, and identifying gaps in research or applications, discussing the opportunities and risks presented by the technology adoption to manage very sensitive data.

Special Session Proposers

• Francesca Gasparini, Dipartimento di Informatica, Sistemistica e Comunicazione, Università di Milano-Bicocca, Italy.
• Cristina Crocamo, Dipartimento di Medicina e Chirurgia, Università di Milano-Bicocca, Italy.
• Anna Maria Bianchi, Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Italy.

Contacts

francesca.gasparini@unimib.it

Topics of interest include, but are not limited to:

• Sequence Assembly and Annotation
• Comparative Genomics
• Metagenomic Analysis
• Pangenomics
• Machine Learning in Microbiology
• Network Analysis
• Microbiome Research
• Antimicrobial Resistance
• Microbial Ecology
• Data Visualization and Integration

Short description:

This special session explores computational approaches driving advancements in our understanding of the microbial world. Microbes play crucial roles in diverse ecosystems, from human health and disease to biogeochemical cycles and industrial processes. Unlocking their secrets requires sophisticated computational tools capable of analyzing the massive datasets generated by modern sequencing technologies. This session aims to showcase the latest computational intelligence methods applied to microbial genomics, pangenomics, and metagenomics. We invite submissions that address, but are not limited to: novel algorithms for sequence assembly and annotation, machine learning approaches for predicting microbial function and interactions, network analysis for exploring microbial communities, and statistical methods for comparative genomics and metagenomic data analysis. We particularly encourage contributions that tackle the challenges of data integration, visualization, and interpretation in the context of complex microbial datasets. The scope of this session encompasses diverse applications of computational microbiology, including: understanding the role of the microbiome in human health and disease, discovering novel antimicrobials and therapeutic targets, engineering microbial communities for biotechnological applications, and assessing the impact of environmental changes on microbial ecosystems. This special session will have an impact by resulting in a better understanding of microbial life and its effects on our planet. It will serve as a forum for information sharing, the development of fresh partnerships, and the inspiration of future lines of inquiry in this quickly developing field.

Special Session Proposers

• Vincenzo Bonnici, Department of Mathematical, Physical and Computer Sciences, University of Parma, Italy.
• Alessia Levante, Department of Food and Drug, University of Parma, Italy.
• Gabriele Andrea Lugli, Laboratory of Probiogenomics, Department of Chemistry, Life Sciences and Environmental Sustainability, University of Parma, Italy.
• Christian Milani, Laboratory of Probiogenomics, Department of Chemistry, Life Sciences and Environmental Sustainability, University of Parma, Italy.

Contacts

vincenzo.bonnici@unipr.it

Topics of interest include, but are not limited to:

• Computational transcriptomics and spatial transcriptomic data analysis
• Single-cell and Multi-omics data analysis and models
• Computational pangenomics
• High-performance computing for omics data
• Algorithms and data structures for bioinformatics
• Knowledge management in bioinformatics and medical informatics
• Drug development and pharmacovigilance
• Artificial intelligence and machine learning in bioinformatics
• Advanced technique for bio-medical content visualization
• Bio-inspired computing for bioinformatics
• Computational modeling and flux balance analysis

Short description:

The national CINI (Consorzio Interuniversitario Nazionale di Informatica) InfoLife laboratory fosters collaboration among researchers with an informatics background engaged in bioinformatics and related fields, working in synergy with their international partners. Italy plays a pivotal role in advancing computational approaches across various bioinformatics domains, from the development of specialized algorithms and efficient data structures to high-level data analysis and innovative visualization techniques. This special session aims to provide a comprehensive overview of ongoing research and emerging trends within Italian research institutes of Informatics and their collaborators. It serves as a platform for showcasing current advancements, discussing future perspectives, and fostering interdisciplinary collaborations. This session also represents a valuable opportunity for Italian researchers and their international partners to present their research directions, exchange insights, and engage with the broader scientific community. By bringing together experts from different backgrounds, it encourages dialogue, strengthens international ties, and contributes to the continued evolution of bioinformatics research.

Special Session Proposers

• Roberto Pagliarini, Assistant Professor at the Department of Mathematics, Computer Science and Physics, University of Udine, Italy.
• Bruno Galuzzi, Researcher at the Institute of Bioimaging and Molecular Physiology (CNR-IBFM), Italy..
• Giacomo Baruzzo, Assistant Professor (RTT) at the Department of Information Engineering, University of Padova, Italy..
• Mikele Milia, Ph.D. Student in Information Engineering at the Department of Information Engineering, University of Padova, Italy..
• Leonardo Pellegrina, Assistant Professor (RTT) at the Department of Information Engineering, University of Padova, Italy..
• Simone Pernice, Assistant Professor (RTDa) at the Computer Science Department, University of Turin, Italy..

Contacts

giacomo.baruzzo@unipd.it