This special session aims to bring together researchers and practitioners from the fields of bioinformatics, high-performance computing, and data-intensive systems to exchange innovative ideas, challenges, and results related to computational efficiency in biological data analysis.

We invite the submission of original research papers addressing theoretical advances, algorithmic innovations, software tools, or practical applications that contribute to the efficient and scalable processing of biological data.

Topics of Interest include, but are not limited to:

• - Design and implementation of scalable bioinformatics algorithms on multicore, cluster, and cloud infrastructures.
• - Hybrid parallelism and workload optimization for large-scale biological computations.
• - Green and sustainable computing practices in bioinformatics and computational biology.
• - Memory- and energy-efficient methods for genome, transcriptome, and proteome analysis.
• - Multithreaded computing strategies for shared-memory systems.
• - Performance modeling, tuning, and prediction for bioinformatics applications in heterogeneous systems.
• - Integration of Big Data technologies and AI for accelerating biological data processing.
• - High-throughput and distributed pipelines for omics data analysis.
• - Exploitation of GPUs, FPGAs, and emerging accelerators (TPUs, NPUs, etc.) in computational biology.
• - Cloud, edge, and grid computing paradigms for bioinformatics services.
• - Scalable software architectures and reproducible workflow management in life sciences.
• - Fault tolerance, reliability, and benchmarking of bioinformatics tools under parallel and distributed environments.
• - Advanced visualization, simulation, and modeling techniques supported by parallel computing.

Organizers:
Dr. Juan José Escobar , Department of Software Engineering, University of Granada, Granada, Spain

Motivation: The surge in multi-omics and clinical data demands scalable analysis beyond traditional systems. Cloud computing enables elastic, AI-driven bioinformatics, yet challenges in cost, security, and reproducibility persist. This Special Session aims to address these challenges and provide a focused platform on cloud-native bioinformatics, including scalable architectures, HPC-cloud integration, distributed pipelines, AI-driven cloud platforms, and secure biological data management.

Objectives: To unite experts to explore scalable, secure cloud-based bioinformatics; highlight AI-driven omics applications; promote reproducible, cost-efficient workflows; and advance next-generation cloud platforms for global biological data analysis.

Topics include, but are not limited to:

• Cloud Architectures & Scalable Systems:
• - Cloud-native architectures for large biological datasets
• - HPC–cloud hybrid systems for genomics and proteomics
• - Scalable computing frameworks: Kubernetes, Docker, Serverless, Spark
• - Multi-cloud, hybrid cloud, and edge-cloud models for omics data
• Data Processing Pipelines:
• - Cloud-based processing of genomics, transcriptomics, proteomics, metabolomics
• - Scalable pipelines for NGS, variant calling, and genome assembly
• - High-throughput microbiome and metagenomics analysis
• - Workflow orchestration: Nextflow, Snakemake, CWL, WDL
• AI/ML and Advanced Analytics in the Cloud:
• - Large-scale training of biological AI/ML/DL models
• - Cloud deployment of BioGPT, protein foundation models, AlphaFold workflows
• - Federated learning & privacy-preserving ML for biomedical applications
• - Cloud-AI in drug discovery, biomarker detection, and clinical decision support
• Security, Compliance, and Governance:
• - Secure handling of clinical and biological datasets in the cloud
• - Blockchain for secure biomedical data sharing
• - HIPAA, GDPR, and biomedical data regulatory compliance
• - Access control, encryption, and data governance frameworks
• Systems Biology & Big Data Integration:
• - Cloud-based integration of multi-omics data
• - Graph analytics for systems biology and pathway modeling
• - Visualization, simulation, and modeling of biological processes at cloud scale

Organizers:
Dr. S. B. Goyal, Department of Computer Science & Engineering Chitkara University Institute of Engineering & Technology Chitkara University, Punjab, INDIA
Dr. Vikram Singh, Department of Computer Science & Engineering Chaudhary Devi Lal University, Sirsa, Haryana, INDIA

The rapidly expanding use of microbiome and metagenomic sequencing in health, ecology, and biotechnology demands advanced machine learning methods capable of handling high dimensionality, sparsity, compositional constraints, technical variability, and complex ecological structure. This special session aims to bring together researchers developing innovative analytical, statistical, and ML approaches—from compositional data analysis, cross-cohort harmonization, and synthetic data generation to phylogeny-aware models, causal inference, and multiomic integration. The goal is to accelerate robust, interpretable, and scalable microbiome science, moving beyond mere biomarker discovery toward functional understanding and translational applications.

Topics include, but are not limited to:

• - Disease screening and prediction via the gut microbiome
• - Multiomic integration and systems-level microbiome analysis
• - Metagenome functional content prediction from marker gene
• - Compositional Data Analysis (CoDA) for microbiome workflows
• - Advances in differential abundance testing
• - Feature selection for microbiome biomarker discovery
• - Advances in amplicon data harmonization and cross-cohort microbiome meta-analysis
• - Phenotype classification using microbiome data
• - Explainable AI, interfaces and metrics tailored to microbiome-specific data properties
• - Gut–brain axis modeling
• - Reproductive microbiome analysis and low-biomass contamination correction
• - Phylogenetic information in machine learning and taxonomy-aware ML methods
• - Synthetic microbiome data generation for benchmarking and model training
• - Microbiome correlation networks
• - Microbiome time series analysis and dynamic modeling
• - Metagenome-Assembled Genomes (MAGs) and whole metagenome sequencing pipelines
• - Advances in taxonomic classification workflows
• - Phylogenetic tree construction innovations

Organizer:
Ignacio Garach,

Department of Computer Engineering, Automation and Robotics, University of Granada, Spain.

Prof. Luis J. Herrera,

Department of Computer Engineering, Automation and Robotics, University of Granada, Spain.

This exploration delves into the transformative impact of combining image processing, computer vision, artificial intelligence (AI), machine learning (ML), and generative AI across diverse domains. As these technologies converge, they enhance our ability to analyse and interpret visual data, leading to ground-breaking applications in healthcare, automotive, entertainment, and more. By leveraging advanced algorithms and neural networks, organizations can create smarter systems that improve efficiency, accuracy, and creativity. This synergy not only streamlines processes but also fosters innovation, enabling businesses to deliver unprecedented solutions and experiences. As we move forward, understanding and harnessing these technologies will be crucial in shaping the future of innovation across all domains.

Topics to be discussed in this special session include (but are not limited to) the following:

• - AI-Driven Image Enhancement.
• - Metaverse and Virtual Environments.
• - Real-Time Image Processing Algorithms.
• - Ethical Considerations and Bias in AI.
• - Blockchain in Image Authentication.
• - AI/ML in Natural Language Processing.
• - AI/ML in disaster management.
• - AI/ML in healthcare.
• - Application of Deep Learning in Large Language Model (LLM).
• - Machine Learning and AI techniques for Big Data.
• - Predictive Modelling.
• - Bio-Inspired Computational Intelligence.

Organizers:
Dr. Lakshita Aggarwal , School of Engineering & Technology, Vivekananda Institute of Professional Studies – Technical Campus

Large-scale AI models (such as large language models (LLMs), protein foundation models, and multimodal generative systems) are rapidly transforming biomedical research. These models enable breakthroughs in molecular design, protein function prediction, multi-omics integration, medical imaging interpretation, and clinical decision support. However, challenges remain in areas such as scalability, interpretability, and clinical translation.

This special session aims to gather researchers working on large AI models for biological and clinical applications. The objectives are to:

• - Present recent advances in LLMs, protein models, generative models, and vision–language models applied to biomedicine.
• - Highlight impactful applications in genomics, proteomics, pathology, radiology, drug discovery, and precision medicine.
• - Discuss challenges in model efficiency, safety, fairness, and deployment in clinical workflows.
• - Foster collaboration across AI, bioinformatics, and medical communities.

Topics include, but are not limited to:

• - Large language models and biomedical text analysis
• - Large language models and biomedical text analysis
• - Protein, molecule, and multi-omics foundation models
• - Multimodal and vision - language models for imaging and pathology
• - Generative models for drug design and molecular discovery
• - Model compression, efficient fine-tuning, and scalable deployment
• - Explainable and trustworthy biomedical AI
• - Cloud, distributed, and privacy-preserving infrastructures
• - Benchmarking and reproducibility of large biomedical models

Organizer:
Dr. Nguyen Quoc Khanh Le,

College of Medicine, Taipei Medical University, Taiwan

The rapid adoption of deep learning and artificial intelligence has transformed bioinformatics and biomedical research, yet many challenges remain unresolved. High-dimensional biological datasets, heterogeneous data sources, and the need for reproducibility demand approaches that are not only powerful but also interpretable and statistically rigorous. Traditional machine learning methods continue to offer significant advantages in these contexts. They provide transparency, lower computational cost, and strong theoretical foundations, which are essential for specific decision-making and life science research.

This special session will focus on new computational techniques and methodological advances in classical machine learning applied to bioinformatics and biomedicine. It will address strategies for data mining approaches, integration of heterogeneous datasets, and modelling and simulation frameworks. Comparative studies between traditional machine learning and modern deep learning will be encouraged, as well as hybrid solutions that combine the strengths of both paradigms.

Contributions should emphasize multidisciplinary aspects and practical applications aiming to demonstrate how robust and interpretable models can complement or outperform black-box AI solutions.

Organizer:
Dr. Jan Urban,

Laboratory of Machine Vision in Aquaculture, 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.

The healthcare landscape is presently transforming at a rapid pace owing to the implementation of artificial intelligence (AI), data analytics, and health-related digital platforms. Over the past few years, medical or healthcare documentation has already evolved from merely taking the form of electronic health records (EHRs) to including high-resolution medical images, genomic data, clinical reports in multiple modes, and artificial intelligence-based diagnostic results. In spite of the dramatic improvement in medical decision-support capabilities, there are some severe concerns in medical documentation.

The nature of data in electronic health records is very personal and sensitive, making healthcare records vulnerable to hacking and attacks. Traditional measures for securing healthcare records are now ineffective for high-dimensional biomedical data in AI-enabled healthcare settings. Further, the adoption of deep learning models for healthcare use adds new issues to the healthcare space regarding data rights and proper use and sharing of data without compromising healthcare record safety.

Recent developments in AI and deep learning provide exciting opportunities to overcome these challenges delivered by intelligent, adaptive, and context-aware security solutions using deep learning-based methods for encryption, watermarking, authentication, anomaly detection, and privacy-preserving data concealment, ensuring a diagnostic quality level for clinical usability in medical data but at a robust security level as well. The current state of research in this emerging field still looks very scattered across various fields; therefore, a proper platform for researchers across biomedical engineering, AI, bioinformatics, and healthcare security specialists is demanded.

The motivation for this special session stems from the increasing interest in reliable, privacy-conscious, medical-record management schemes with the ability to facilitate the next-generation medical services in the digital healthcare sector. Through the interdisciplinary discussions and illustrating the recent developments in the session, the session aims to fill the gap between the AI-based security-related research activities and their related biomedical/clinical implementation.

The main objective of the special session is to offer an interdisciplinary platform where the proposed AI-enabled privacy and security approaches and strategies for the next generation of medical records can be shared and discussed. It is also aimed at gathering experts in the fields of artificial intelligence, biomedical engineering, and security of healthcare data.

Specifically, the objectives of the session are to:

• - Encourage the use of advanced AI and deep learning technologies for securing biomedical files, including electronic health care data,bioimages, and multimodal biomedical data.
• - Emphasize cutting-edge techniques for ensuring privacy, like deep learning-assisted encryption, watermarking, reversible data hiding, or secure authentication mechanisms.
• - Exhort the conduct of research aimed at ensuring the integrity and trustworthiness of medical data used in clinical decision-making.
• - Encourage discussion on sharing secure data. This could include interaction with hospitals, cloud providers, or AI systems.
• - Encourage interdisciplinary collaboration among professionals in artificial intelligence technology, bioinformatics, medical imaging, cybersecurity, and digital health care.
• - Encourage the establishment of ethical, trustworthy, and sustainable healthcare systems along the lines of Precision Medicine and future digital healthcare initiatives.

Organizer:
Dr. Ashima Anand,

Assistant Professor, Department of Computer Science and Engineering Thapar Institute of Engineering and Technology, Patiala, Punjab, India