#DeCoding HEREDITARY: making health data understandable through visual analytics

by | Jun 9, 2026 | Hereditary

One of the biggest challenges in HEREDITARY is not only to collect and secure integrate data, but also to make sense of it. 

Researchers, clinicians, policymakers and citizens are increasingly confronted with vast amounts of information coming from medical images, genetic data, microbiome profiles, electronic health records, simulations and many other sources. While these datasets hold enormous potential to advance our understanding of health and disease, their complexity can make them difficult to interpret and use effectively. 

This is where HEREDITARY’s Work Package 5 (WP5), coordinated by TU Graz, comes in. Through the development of innovative visual analytics methods and interactive exploration tools, WP5 helps transform complex multimodal data into understandable insights that can support research, prevention and decision-making across the healthcare ecosystem. 

Today, we are excited to showcase a big result coming from this work: the launch of the HEREDITARY Demos & Visualisation Components Portal, publicly available at: https://demos.hereditary-project.eu/.

 

From research prototypes to publicly accessible demonstrators 

Over the last two years, WP5 has progressively transformed visualisation concepts into operational demonstrators and interactive applications. 

The developments reported in a series of deliverables (D5.1, D5.2, D5.3 & D5.4) include visualisation components for: 

  • High-dimensional biomedical data.
  • Knowledge graphs and semantic resources.
  • Brain imaging and spatial data.
  • Time-series and biosignal analysis.
  • Simulation and modelling outputs.
  • Natural language-assisted visual analytics. 

A key principle throughout this work has been openness and reusability. To make these developments accessible to a broader audience, TU Graz has established a dedicated demonstrator infrastructure that hosts and deploys visual analytics applications developed within HEREDITARY. The new Demos & Visualisation Components Portal now brings many of these innovations together in a single public entry point. 

Created through close collaboration between TU Graz and partners across the consortium, including experts in medical research, federated infrastructures, machine learning, data management and semantic technologies, the portal demonstrates how advanced visual analytics can support the exploration of multimodal health data. The portal currently includes 15 demonstrators, videos (in some cases) and code (available in most of them), from semantic exploration and cohort analysis to brain imaging, machine learning interpretation and simulation-based research.

 

Exploring the gut-brain connection through visual analytics 

Among the flagship developments showcased in the portal is the Gut Brain Explorer, an advanced visual analytics application designed to explore relationships between gut microbiota and brain activity. 

The tool combines multiple linked visualisations to allow researchers to investigate outputs generated through Linked Independent Component Analysis (LICA), integrating microbiome information with functional brain imaging data. Users can interactively explore microbiota distributions, modality contributions and brain activity patterns through coordinated views. 

The component has already demonstrated its scientific value during project evaluations, supporting researchers in identifying biologically relevant gut-brain associations.

 

Making complex biomedical data easier to explore 

Several other demonstrators address complementary challenges in data exploration and interpretation. 

Clusters in Focus helps researchers identify and compare meaningful patient subgroups within high-dimensional biomedical datasets, supporting tasks such as biomarker discovery and phenotyping. 

Neurodegen-Vis combines interactive visual analytics with LLM-powered assistance to support the exploration of healthcare datasets. The tool enables users to investigate correlations and dependencies in medical data while receiving guidance through natural language interaction. Privacy-preserving mechanisms are integrated to protect sensitive information. 

OnSET (Ontology and Semantic Exploration Toolkit) helps users navigate complex knowledge graphs and ontologies through natural language querying and visual graph exploration, making semantic resources more accessible to non-experts.

 

Building trust through transparency and interaction 

One of HEREDITARY’s core ambitions is to ensure that advanced AI and data-driven methods remain understandable and trustworthy for the people who use them. Visualisation plays a crucial role in achieving this goal. 

By allowing users to interact directly with data, inspect results, understand relationships and explore evidence behind conclusions, visual analytics can help make complex technologies more transparent and interpretable. This is particularly important in healthcare, where trust, explainability and human oversight remain essential. 

As HEREDITARY progresses, new demonstrators and functionalities will continue to be added, further expanding the ecosystem of tools available for exploring multimodal biomedical data, semantic resources and AI-driven analyses. 

🔗 Explore all the demonstrators and get in touch with the team responsible for each one: https://demos.hereditary-project.eu/ 

#DeCoding Federated Analytics: unlocking knowledge across borders and datasets

by | Apr 28, 2026 | Hereditary

How can researchers study complex diseases across Europe when sensitive and health data cannot leave hospitals or research centres and speaks several languages?

This is one of the key challenges HEREDITARY is addressing, and part of the answer lies in a powerful combination of a federated learning infrastructure, semantic integration and federated analytics.

In this new #DeCoding article, we take a closer look at how Work Package 3 (WP3) is building the foundations that make this possible: the Hereditary Ontology (HERO) and the Hereditary Data Network (HDN).

 

From federated learning to federated analytics

In a previous #DeCoding article, we explored federated learning, a method that allows AI models to be trained across multiple institutions without centralising raw data. But before researchers can analyse data across institutions, they need to ensure they are actually talking about the same things. In healthcare, the same clinical concept can be recorded differently depending on the hospital, the specialty, or even the country. This makes it difficult to combine or compare data.

To solve this, HEREDITARY has developed the Hereditary Ontology (HERO): a shared semantic layer that provides a common language for all partners. This allows different datasets to be understood in a consistent way. It enables researchers to formulate questions without needing to know local database structures, by integrating clinical, genomic and imaging data into a unified conceptual model, covering key neurological diseases domains, such as Amyotrophic lateral sclerosis (ALS) and Multiple sclerosis (MS), and designed to expand to others like Parkinson’s and Alzheimer’s.

This semantic integration is essential: without it, federated analytics wouldn’t be possible.

 

From data silos to a connected network

Building on this ontology, HEREDITARY has developed the Hereditary Data Network (HDN), a federated infrastructure that allows data to be analysed across institutions while remaining locally stored. Data stays where it is, but knowledge can travel. Instead of moving individual patient data to a central repository, HDN enables researchers to send queries to different institutions and receive aggregated results. It is based on a central component that coordinates queries, local endpoints at each institution that execute them on their own data and results that are returned and combined, without exposing sensitive information.

This approach represents a fully federated and privacy-by-design architecture. Privacy controls are integrated in the query processing layer of HDN:

  • Each query is assessed before running and it is automatically assigned with a privacy risk score.
  • Each institution decides what are the risk thresholds they can safely handle.
  • If a query exceeds that thresholds, no data is returned or privacy mitigation measures are applied.

This ensures that data owners remain in full control, while still enabling meaningful research across institutions.

 

How federated analytics works in practice? 

A researcher might ask a question like: “What is the average age at onset of ALS patients?”. 

Instead of accessing a central database, the system: 

  1. Translates the question into a standardised query using HERO.
  2. Sends it to multiple institutions.
  3. Executes it locally at each site.
  4. Returns aggregated results.
  5. Combines them into a single answer, obtaining a response that incorporate insights across different datasets while respecting privacy and institutional autonomy. 

 

Progress so far and what comes next 

By now, HEREDITARY has already made significant progress. The project has delivered the first version of its federated workflow execution methods (D3.2) and demonstrated how semantic integration and federated querying can work together. Also, the HDN prototype has shown that distributed queries can be executed across heterogeneous datasets, integrating privacy-aware query mechanisms. For those with a technical interest, various resources relating to these developments can be found on the project’s Open Hub. 

Looking ahead, the project is focusing on scaling and real-world deployment. Over the first half of 2026, HDN endpoints are being installed across several partners (University of Turin, Radboud University Medical Centre and University of Colorado), enabling future live queries on real datasets. The goal is to have a fully operational federated query system running at consortium level by the end of 2026, along with a shared catalogue of queries and a clear maintenance plan.  

Ultimately, what HEREDITARY is building goes beyond technology. It is a new way of doing research in several fields: one where data does not need to move to generate knowledge, where institutions can collaborate without losing control and privacy, and where complexity is managed through shared understanding. The Federated analytics layer, powered by HERO and the HDN, is a key step in that direction.

 

Learn more about Federated Analytics in the following videos, where our coordinator, Gianmaria Silvello (University of Padova) and Daniele Dell’Aglio (Aalborg University) share their insights and perspectives on the topic:

#DeCoding the Gut–Brain Axis: from multimodal data to behavioural insights

by | Apr 13, 2026 | Hereditary

How are our gut and brain connected, and how does this relationship influence the way we think, feel and behave? Within the HEREDITARY project, this question is at the heart of ongoing research in Work Package 2, where partners are exploring the complex interplay between microbiota, brain activity, and human behaviour. 

The Deliverable 2.4: Linkage and feature extraction from gut-brain, intermediate evaluation, led by Radboud University Medical Center, marks an important step forward in this journey. Building on earlier work, it provides new evidence that combining multimodal data with advanced AI can reveal meaningful patterns linking the gut and the brain, bringing us closer to understanding this intricate biological system.

From data to discovery: integrating the gut and the brain 
At the core of this research lies a simple but ambitious idea: to move beyond isolated measurements, and, instead, analyse the gut and brain as a connected system. 
To achieve this, HEREDITARY researchers worked with data from the Healthy Brain Study (HBS), a large cohort of deeply characterised individuals. By combining brain imaging (resting-state fMRI), gut microbiota profiles, and behavioural and physiological data, the team applied a supervised multimodal data integration method (an advanced AI method) known as SuperBigFLICA, an extension of Linked Independent Component Analysis (LICA), designed to work with large-scale, heterogeneous datasets. This approach allows researchers to identify latent components (shared patterns across different types of data), which, in this context, correspond to hidden structures in the data that capture how microbiome composition, brain connectivity, and individual behavioural are interrelated. 
One of the most relevant outcomes of this work is the identification of robust gut-brain components (multivariate patterns that simultaneously involve microbiome features and brain activity). In particular, one component revealed a strong interaction between gut microbial composition, brain networks linked to reward and emotion (such as limbic and default mode networks), and health and behavioural measures such as anxiety sensitivity, life stress, and Body Mass Index (BMI). 
In an independant validation, this component was also able to predict food-related behaviour from an independent task. This task reflects how individuals value unhealthy vs. healthy food, and their likelihood of choosing unhealthy options. These findings validate the feasibility of supervised multimodal integration and identify promising biological targets for follow-up analyses. It shows that gut–brain interactions are not only measurable, but also meaningfully linked to real-life behaviour. 
Advancing Use Cases 4 and 5 
These findings directly contribute to HEREDITARY’s Use Case 4 and lay the groundwork for Use Case 5. 
  • Use Case 4 focuses on understanding gut–brain interactions in healthy populations. The intermediate results confirm that it is possible to identify stable and biologically meaningful gut–brain patterns at population scale. 
  • Use Case 5 will extend this approach to clinical data, exploring whether similar patterns can explain variations in mental health conditions and maladaptive behaviours, with broader applications in the prediction of other gut (.eg. Ulcerative Colitis) and brain related conditions (e.g. depressive episodes).
What comes next?
The work does not stop here. The HEREDITARY project will evaluate the robustness of the discovered components, apply them to broader clinical data, and extend analyses to metabolic markers and future hypotheses-driven studies on stress, diet, and hedonic eating. It will directly address disease relevance by examining whether the same multivariate gut–brain components explain variation in psychopathology and maladaptive eating in psychiatric populations. 
The next phase of the research will deepen the analysis of how gut–brain interactions relate to behaviour. These analyses will continue to leverage multimodal datasets (including brain imaging, microbiome data, stress responses and behavioural tasks) to further explore how stress, anxiety and dietary factors influence food choices through gut–brain mechanisms, and how the interaction between the gut microbiome and reward-related brain connectivity contributes to stress-related eating patterns in daily life. In parallel, future work will focus on defining what constitutes a “healthy” gut–brain profile and ensuring robust clinical interpretation of results.
HEREDITARY is receiving EOSC EU Node funding to advance Federated Learning experiments
 by  | Mar 3, 2026 | Hereditary
The HEREDITARY project has been granted 40,000 credits from the European Open Science Cloud (EOSC EU Node) to support, among other things, its federated learning activities within a secure European research infrastructure.
About the EOSC EU Node
The European Open Science Cloud (EOSC EU Node) is the operational platform of the EOSC Federation, designed to facilitate open, collaborative and data-driven research in Europe. It supports multidisciplinary scientific work by providing access to digital research services such as computing and storage resources, containerized environments, and collaborative tools through institutional credentials. The platform promotes the sharing and reuse of research outputs in a secure, GDPR-compliant cloud ecosystem based on FAIR data principles and a credit-based access model.
The awarded credits will be used to deploy and maintain the central server required for federated learning experiments on EOSC virtual machines. Federated learning allows multiple institutions to collaboratively train machine learning models without sharing sensitive data. By using EOSC infrastructure, HEREDITARY can efficiently manage firewall configurations and incoming connections, overcoming common technical barriers associated with institutional IT restrictions.
The EOSC EU Node credits will support several weeks of experimentation, with server configurations adapted to different model sizes and algorithmic requirements. In parallel, HEREDITARY is exploring the development of an API-based solution that would allow researchers to deploy experiment-specific software containers through the EOSC Cloud Container platform. This approach aims to streamline workflows, facilitate testing and deployment, and potentially deliver open-source tools that could benefit the broader research community.
#DeCoding Federated Learning: from Infrastructure design to secure collaboration across Europe
 by  | Feb 24, 2026 | Hereditary
How can hospitals collaborate on sensitive medical data without ever sharing the data itself? This is the core question behind Federated Learning (FL), and one of the key technological pillars of the HEREDITARY project.
Over the past two years, HEREDITARY has progressively designed, deployed and tested a federated learning infrastructure capable of connecting medical centres across Europe while ensuring that raw patient data never leaves its original location. What began as a technical design challenge has now evolved into a secure network supporting distributed machine learning experiments across heterogeneous datasets.
Building the Foundations: Computing Infrastructures
Federated Learning only works if each participating centre has the technical capacity to train models locally and communicate securely with the rest of the network. The first step was ensuring this. Under Deliverable D2.14 in Month 9 and lead by SURF, partners established secure computing infrastructures capable of handling sensitive clinical and genomic data, equipping centres with appropriate storage, processing power and secure communication channels. Thanks to this, data owners can process data locally, train models without centralising records and exchange model updates securely within the federation.
With local infrastructures in place, the next step was to design and validate the full federated learning architecture. Deliverable D2.11 in Month 18 presents a federated infrastructure that is secure, flexible and deployable across heterogeneous environments, including high-performance computing systems and cloud platforms. Encrypted communication via gRPC/TLS was implemented to protect model exchanges, while Secure Aggregation mechanisms (SecAgg/SecAgg+) were integrated to prevent the central server from accessing individual model updates.
The system was engineered to support both horizontal federated learning (same data types across centres) and vertical federated learning (different data modalities distributed across centres). Dedicated project workshops demonstrated that both approaches could run successfully across geographically distributed nodes, even when accounting for network latency between countries. By Month 18, HEREDITARY had a federated network capable of running both horizontal and vertical learning experiments on ALS data, without moving any raw records.
Securing the Communication: Communication Protocols
Security does not stop at this point. Deliverable D2.15 in Month 22 dives deeper into how model updates are protected during training. SURF analysed and validated advanced communication protocols within the federated learning framework. Three key mechanisms were the driving force behind this:
  • Secure Aggregation ensures that the server can combine model updates without seeing any individual contribution. Clients (Medical Centres) mask their updates using cryptographic techniques so that when all updates are aggregated, the masks cancel out, but no single update can be inspected independently. Tests showed no significant decrease in model performance, with only a modest increase in runtime due to additional communication steps.
  • Differential Privacy was also evaluated, introducing controlled noise to model updates to further reduce the risk of information leakage, again with minimal performance degradation.
  • Trusted Execution Environments were explored as an additional layer of security, though their hardware requirements make them less practical in heterogeneous clinical environments.
Beyond Simulation: paving the way for actual implementation
One key lesson emerging from this work is that federated learning is relatively straightforward in simulation, but deploying it across real institutions introduces new challenges: hardware variability, network latency across countries, IT coordination and regulatory compliance. Through interactive workshops and live experiments, HEREDITARY has moved beyond theoretical experimentation to operational deployment.
Today, the project operates a federated network linking multimodal clinical data without centralising any raw records. Advanced AI models can be trained across distributed datasets and privacy-enhancing technologies can be implemented with limited performance trade-offs. The infrastructure is reliable, secure and resilient. This “data stays at source” approach aligns closely with the principles of the European Health Data Space, demonstrating that privacy-preserving, cross-border health data collaboration is technically feasible.
The next step will arrive in June 2026, when the project moves from validated design to consolidated implementation. Deliverable D2.12 will formalise the full implementation of the federated infrastructure, while Federated Learning will demonstrate its clinical relevance through Deliverable D2.17, presenting intermediate results from the neurodegenerative use cases. Together, these upcoming milestone will mark a transition from infrastructure validation to scientific and clinical impact.
Learn more about Federated Learning in the following video, where Douwe van der Wal (SURF) and Henning Müller (HES-SO Valais) share their insights and perspectives on the topic: