In recent years, growing attention to the gut microbiota has led to increasing use of complex clinical reports, such as those provided by microbiome and multi-omic analyses. Irritable bowel syndrome (IBS) is a relevant area of application, characterized by a chronic functional disorder of the gastrointestinal tract. Having clear and easily interpretable diagnostic tools increases the capacity of diagnosis and helps patients to better understand the content of the reports, which are often static and rich in scientific data, making them complex to understand for both patients and non-specialist physicians. This work proposes the development of a dynamic platform for the visualization and interactive management of microbiome clinical reports. Starting from existing reports, a prototype web interface capable of presenting data in a modular, adaptable, and customizable way has been designed and proposed. The prototype also allows the generation of reports in PDF format, both in a dynamic version (with the possibility of filtering and exploring different sections) and in a static version (useful for printing or clinical sharing). The added value of this solution lies in readability and quick access to the information.

Microbiome sequencing offers significant potential for advancing clinical diagnostics, but its adoption is hindered by challenges in data processing, standardization, and the translation of complex genomic data into actionable clinical insights. The GenDAI project addresses these challenges by developing a novel, integrated medical diagnostics platform that leverages Artificial Intelligence (AI), powered by Genomic Foundation Models (GFMs), to accelerate and improve the analysis of microbiome data. The platform's primary goal is to provide a fully automated, reproducible, and compliant end-to-end solution, from data ingestion to clinical reporting, to support personalized medicine, with an initial focus on Inflammatory Bowel Disease (IBD). This paper presents an overview of GenDAI's vision, outlining its user-centered methodological approach and the conceptual architecture of its core components. The architecture integrates four key pillars: (1) a fully automated and auditable diagnostics workflow, (2) a secure and compliant cloud platform for long-term data management based on Open Archival Information System (OAIS) and Findable, Accessible, Interoperable, Reusable (FAIR) principles, (3) an advanced AI engine for biomarker discovery using GFMs, and (4) interactive, usercentered reporting tools designed to enhance explainability and clinical trust. By providing a holistic and ethically-grounded framework, GenDAI aims to bridge the gap between advanced genomic research and practical clinical application.

This paper focuses on the aspects of responsibility and ethics when using AI systems in the contexts of health and genomics. The present proposal also aims to address the important need to consider how the use of AI systems in the field of genomics affects human life and its implications. As AI systems increasingly participate in diagnostic and predictive decision-making, they introduce new challenges concerning moral agency, transparency, and human oversight. The discussion aims to examine how these technologies, while offering unprecedented analytical capabilities, simultaneously reshape the ethical landscape of medical practice and genomic research.

Artificial intelligence has become integral to the life sciences, enabling large-scale data analysis and accelerating discovery. However, deploying these analytical capabilities depends on cloud infrastructures that are often complex to design, validate, and operate. Current approaches rely heavily on manual, time-consuming configuration by experts. This paper explores how artificial intelligence, specifically Large Language Models, can support not only genomic data analysis but also the automated creation of the underlying computational infrastructure. We propose a methodology that translates naturallanguage user stories and requirements into cloud-architectural specifications and containerized deployments, bridging the gap between user intent and executable infrastructure. Preliminary results indicate that LLM-driven synthesis can reduce human effort in defining container relationships and deployment logic, advancing automation in cloud-native bioinformatics.

This paper presents a cloud-native architecture for clinical metagenomic diagnostics developed as part of the Horizon Europe project GenDAI. The architecture integrates automated, reproducible, and auditable workflows with deterministic elasticity, compliant data stewardship, explainable Artificial Intelligence (AI), and verifiable reporting. Requirements derived from clinical practice inform a unified modeling, implementation, and evaluation strategy for a modular platform that combines workflow orchestration, data governance, AI-powered modeling, and cloud-native reporting. The system embeds provenance-bydesign, policy-as-code enforcement, and deterministic elasticity across all layers to enable reproducible, compliant, and trustworthy metagenomic diagnostics. This work provides a principled pathway for translating research-grade tools into regulator-ready diagnostic services while maintaining transparency, reproducibility, and long-term trust.

The increasing adoption of Large Language Models (LLMs) has significantly lowered technical barriers across various domains, enabling tasks such as code generation, database querying, and service composition. This work explores the potential of LLMs to facilitate human access to heterogeneous data in Cyber-Physical Systems (CPS). The proposed system interprets natural language queries and, by leveraging in-context learning, dynamically synthesizes data integration pipelines that compose data services, thus enabling access to information from multiple sources. The execution of a pipeline generates a table that fulfills the input query, effectively integrating and structuring the retrieved data. This paper presents the design and implementation of the proposed solution and its evaluation using a real-world case study and the BIRD benchmark dataset. The results demonstrate its effectiveness in improving data retrieval, data service design, and execution in CPS.

Abstract The continuous evolution of digital technologies applied to the more traditional world of industrial automation led to Industry 4.0, which envisions production processes subject to continuous monitoring and able to dynamically respond to changes that can affect the production at any stage (resilient factory). The concept of agility, which is a core element of Industry 4.0, is defined as the ability to quickly react to breaks and quickly adapt to changes. Accurate approaches should be implemented aiming at managing, optimizing and improving production processes. In this vision paper, we show how process management (BPM) can benefit from the availability of raw data from the industrial internet of things to obtain agile processes by using a top-down approach based on automated synthesis and a bottom-up approach based on mining.

In recent decades, manufacturing practices have undergone a significant transformation, with the integration of computers and automation playing a central role. Concurrently, there has been a growing interest in utilizing intelligent techniques to effectively manage manufacturing processes. These processes entail the seamless integration of various activities across the supply chain. Given the diverse range of actors in a supply chain, each one with distinct characteristics such as cost, quality, and probability of failure, task assignment becomes a crucial challenge. In such a complex scenario, manual decision-making becomes impractical, necessitating the adoption of automated techniques to effectively address these challenges in a resilient and adaptive manner. This article proposes a service-oriented approach to model each manufacturing actor within the supply chain. Furthermore, it categorizes automated synthesis approaches for smart manufacturing on the basis ofi)the characteristics of each actor, which are retrieved by their Industrial API, andii)the goal(s) of the manufacturing process. Finally, the article evaluates three distinct approaches that implement automated synthesis techniques for composing services and generating operational plans.

Recent years witnessed a growing interest in the employment of intelligent techniques for the management of manufacturing processes in smart manufacturing. These processes may include tens of resources distributed among several different companies composing the supply chain. The status of the different resources evolves over time in terms of cost, quality, and probability of breakdunavailability, thus requiring the process to be adaptive and resilient to disruptions. Due to the high number of involved resources, making decisions manually soon become unfeasible, thus requiring automated techniques to solve the problem. In this paper, we discuss the potential and limitations of automated reasoning techniques for making modern supply chains adaptive and resilient by relying on the information provided by resources through their APIs.