by Admin | 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.
by Admin | Apr 7, 2026 | Citizen Science and Public Engagement
This interview was conducted by OBSERVA, a partner in the HEREDITARY consortium, as part of its efforts to promote citizen engagement and give visibility to the voices of people living with neurodegenerative diseases. In this first part of a three-part full interview, Dolores Ayala Velázquez shares her personal journey, reflecting on how her scientific background intersects with her experience as a patient and how she navigates the daily challenges of living with Progressive Bulbar Palsy (PBP).
Could you briefly tell us your personal story and how your experience as a patient and your scientific training coexist within it?
I am a person with extensive academic training and experience in teaching, research, and cultural outreach. I hold Bachelor’s, Master’s, and Doctoral degrees in Science, specializing in Physics, particularly Statistical Physics, Fluid Theory, and Auditory Acoustics. I have also completed several diplomas in Education, Teaching, Family, and Counseling for individuals from childhood to old age. I also hold a Bachelor’s degree in Religious Studies. I was a teacher for 50 years.
I have a beautiful family consisting of my husband, our two daughters and one son, and three grandchildren in their teens.
In 2021, the symptoms of dyslalia gradually appeared, making it increasingly difficult for me to express myself freely and fluently. As I spoke, my voice became hoarse, losing its tone, timbre, and volume, making it impossible for my listeners to understand me. Regarding food, I knew I couldn’t drink any cold liquids because I would choke, although I could still manage to drink hot tea or punch. Dry foods like rice and stringy foods like meat would get stuck in my throat; sometimes I could eat them, and other times I couldn’t.
In 2022, a speech therapist diagnosed me with dysphagia and dyslalia. This marked the beginning of the process to determine the diagnosis of my condition, which took nearly two years, that is Progressive Bulbar Palsy (PBP), thankfully not Bulbar ALS. However, I still fear that it could develop due to the uncertainty surrounding the understanding of these diseases.
The aspect of how my experience as a patient and my scientific training coexist is a very interesting question for me, because my first reaction upon receiving the news of ALS and that I had about three years to live, was to think that what I had done before was not useful to face this reality, therefore, I had wasted my life on things that did not serve me and I began to wonder what I could do to give meaning to my life in just three years.
It was a very painful experience. It took me several months to realize I was wrong and that everything I had learned and the effort it took to achieve it were valuable because they are part of who I am. So, I am not defenseless; rather, I possess extensive training in addressing, understanding, and resolving complex problems. So ALS is just one more complex problem, with initial conditions and treatment strategies yet to be defined, regardless of what the specialists say, who, from experience, I know aren’t always right. Instead of becoming more saddened or letting the weight of a neurodegenerative disease crush me, I decided to research everything known about it, to understand its effects on the body and learn how to manage it.
From your perspective, what does it mean to live with a neurodegenerative disease beyond the clinical aspect?
From my experience, living with a neurodegenerative disease like PBP means dealing with the daily challenges posed by my diet, speech, saliva management, facial expression, and posture, among others.
- Nutrition. While I was able to eat enough to nourish my body and allow it to perform its vital functions, and to have some energy to think, move, and maintain a degree of independence, my weight remained stable (for one year and eight months). As the situation worsened and I consumed what little I ate simply through the effort of eating, I began to lose weight rapidly (from 60 kg to 47 kg in seven months). I was so lacking in energy that I had poor balance, I felt dizzy when turning my head, and I looked listless, very tired, and vulnerable. The ultra-protein, ultra-calorie diet recommended by the nutritionist helped me begin to regain weight. Then I understood the function of the gastrostomy, which several specialists had tried to explain to me, but without telling me: “Your difficulties eating orally can put your life at risk.” Since June 2024 I have had a gastrostomy tube through which I receive the ultra-protein and ultra-calorie food that my body requires and I have regained my weight, in fact I now weigh 62 kg. Switching from oral feeding to tube feeding has important implications, because depending on the digestive process I can go from constipation to loose stools, also considering substitutes like fiber and laxatives, which must be adapted each day to the particular needs of my body and in these I am the only specialist, and it is not convenient for me to leave the responsibility in the hands of the gastroenterologist or the nutritionist, because unexpected and very uncomfortable accidents can happen to me.
- Speech and communication. To speak, I use my mouth, and it’s constantly filled with excessive saliva, which is sometimes more like mucus or phlegm because of how thick it gets. Besides its consistency, saliva plays a very important role in speech, particularly in where it concentrates. When it’s in the oral cavity, I can produce sounds with my chest and head, but the saliva makes them sound nasal and muffled, which makes them difficult to understand. If phlegm concentrates between the soft palate, pharynx, and tongue, producing sounds becomes more difficult. This is because, feeling a blockage in the throat that also affects the vocal cords, it is harder to produce sounds with the chest, and impossible to do so with the head due to the blockage caused by the thick membrane of phlegm, which seems to be boiling in a witch’s cauldron and makes me feel like I am suffocating because air cannot pass through either the airway or the mouth. It’s easy to imagine that under these conditions, the sounds I produce end up being the noises of a monster from beyond the grave, no matter how hard I try to articulate them correctly. Thus, the intelligibility of my speech is chaotic; at times it might be more or less understandable, but then it shifts to otherworldly, nonsensical sounds. There’s an additional, very serious problem: the psychological and emotional impact of hearing myself speak. Because while I’m talking to myself, my voice sounds clear and crisp as before, and I even forget how I’m speaking as I utter the words out loud. I admit that sometimes I feel like crying, and other times like despairing. Fortunately, I manage to control myself and find (or am asked to use) the whiteboard or the phone app to communicate my ideas.
- Saliva management. Besides the difficulties saliva creates when I speak, it’s difficult to control it with my lips. Previously, I couldn’t even close my lips, much less achieve the necessary lip seal to contain saliva and food; I was constantly drooling. Now it happens intermittently, when the amount of saliva is excessive and I can’t manage it in my mouth. But in both cases, I need to have a cloth handy to dry my mouth and remove the excess saliva. Experiencing this when I’m alone is desperate, distressing, uncomfortable, and annoying, and when I’m around others, it feels embarrassing and inappropriate. I imagine it must be disgusting or repulsive to them, which makes me feel even worse. In fact, I find it incredible that with all the medical resources available, no alternative ways have been found to control excessive saliva production, beyond botulinum toxin, which doesn’t work for some of us.
- Facial expression. I like to smile to show the joy I feel in life and knowing that I am loved in a special way by God. Between 2019 and 2020, I was still giving talks via webinars or Zoom. On one occasion, one of my daughters, who was watching me from her computer, sent me a message saying, “Mommy, please smile, you look sad and your cheeks are droopy like a Saint Bernard’s.” Initially, I didn’t understand what she meant, but I made an effort to smile more during the talk. Then it dawned on me that she was referring to our dogs, with their droopy cheeks and sad, drooling faces. After the conference, I decided to look in the mirror to confirm what my daughter had told me, and sure enough, even though I was “smiling,” all you could see was my expressionless, wooden face. This really affected me, and I worked hard to get my smile back, which I finally managed after a period of sustained effort and dedication.
- Posture. Believe it or not, while I was eating only through my mouth, I never felt like I couldn’t support my head with my neck. It wasn’t until shortly after they inserted the feeding tube that I started to feel my head getting heavy and tilting to one side, and now it happens more frequently, for example, after I take a bath. I have to be very careful to prevent it from tilting to one side.
Are you part of a patient association or community? Could you briefly describe it (size, location, main activities)?
No. In the process of identifying the diagnosis of my disease, I had the opportunity to attend the ALS Clinic at the Mayo Clinic in Florida and it made a very good impression on me. There, they told me about two organizations in Mexico City that we could contact to join a community with ALS patients. We got in touch with the Foundation that serves people with limited financial resources, and since it’s located on the opposite side of our city, we’ve focused on helping the families by giving them food baskets to celebrate Christmas. The second association required us to register beforehand, before establishing contact and communicating with its representatives. Given our circumstances, this didn’t seem appropriate, and we decided against following their procedures. This association has greater financial and educational resources and a website with useful information.
Truthfully, I fear contact because I have always been and am an empathetic person (I have the diagnosis of being highly sensitive), now that I feel vulnerable and can barely cope with my own problem, it seems to me that the suffering of others is extreme and I begin to devalue my situation and think “I should do this, I could do that, I need to overcome this other thing”, and it increases my tension and anguish.
What role do you think patient communities play in research and in the daily lives of those living with these diseases?
Nearly 40 years ago, my husband and I founded the non-profit organization Oirá y Hablará (Hear and Speak) to support parents and other family members of deaf children in helping them reach their full potential and integrate into society, without their disability being a limiting factor. This happened when we learned that our son had profound deafness with a speech threshold of 95 dB. As physicists, my husband and I could provide scientific, technical, and human support through our own experience as parents of a little boy of just three years old, who had to learn to communicate and develop his potential to survive in life. But the most important thing about Oirá y Hablará were the experiences that the parents, siblings, uncles, and grandparents shared with us about their interaction with their little ones with limited hearing, from funny anecdotes to very profound lessons, which made us reflect and encouraged us not to be defeated by difficult situations and to keep going, enthusiastically and joyfully taking advantage of the experiences that we received month after month at the association meeting.
Based on these experiences and my own current one, I believe these communities possess a legacy of knowledge about the impact of illness on each individual, because we know its effects are individual, different for each person, depending on their physical, psychological, cultural, and emotional state. Furthermore, the difficulties we face and the harm caused by the ego and superiority attitudes of some of the specialists who treat us – doctors, scientists, technicians, and therapists – and also by some caregivers, are not taken into account.
What the sick person needs is respect, closeness, and understanding. But it seems they forget that we are people with the same dignity as children of God as those who do not suffer from any of these illnesses. We need to be heard and have our voices heard, because what we have to say is very valuable, so valuable that no one else can express it as we can. Despite our difficulty in communicating it, we patients are the experts on what we feel physically, mentally, and emotionally each day, because it’s about our experiences, pains, and personal difficulties that we encounter moment after moment. If mice are closely observed when used as guinea pigs to test drugs or equipment, the least we can expect is that we, as human beings, are actively listened to and taken seriously, because we are the primary and genuine source of information for specialists.
In my opinion, specialists would greatly benefit from learning about the experiences and difficulties faced by people with ALS, for example, those who share their stories at meetings of associations for people with similar illnesses. This knowledge can help specialists reassess the situation of the person or people in their care and provide them with valuable insights and ingenious ideas on how to resolve unforeseen or difficult situations that others have already encountered. Furthermore, the staff of these institutions possess a wealth of knowledge and experience regarding the symptoms, attitudes, feelings, and specific situations of people with rare diseases, which can be extremely useful when developing research projects.
by Admin | 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.
by Admin | 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:
by Admin | Feb 12, 2026 | Hereditary
On 5–6 February 2026, the HEREDITARY consortium gathered at Universidade Nova de Lisboa (UNL), Portugal, for its 5th Plenary Meeting and the first in-person meeting of the project’s third year. Over two intensive days, partners reviewed progress, aligned on strategic priorities, and advanced key technical developments that will shape the next phase of the project.
The meeting followed directly after the Federated Learning Workshop (3–4 February), creating strong momentum around HEREDITARY’s core mission: enabling privacy-preserving, multimodal data analysis across European medical centres.
Opening the meeting, Project Coordinator Gianmaria Silvello (UNIPD) provided a comprehensive overview of the project’s current status. With the first review completed and 41 Deliverables successfully delivered, the consortium is now fully focused on addressing reviewers’ recommendations and consolidating technical achievements into high-impact results.
Throughout the first day, each Work Package presented its latest developments and next steps, demonstrating strong cross-WP integration and alignment with the project’s strategic objectives. The review of ongoing activities confirmed steady technical progress across data infrastructure, semantic integration, analytics, visualization, legal frameworkandcitizen science, which reinforces the coordination between clinical, technical, social and legal dimensions.
A central highlight of the meeting was the Federated Learning and Federated Analytics sessions. On the second day, SURF reported on the Federated Learning workshop and the evolution of infrastructure leadership. Discussions explored the idea of creating a living document to guide institutions in setting up secure federated learning environments. On the Federated Analytics side, the Hereditary Data Network (HDN) architecture and deployment roadmap were presented by UNIPD, ensuring a real HDN query system running by December 2026, with a clear maintenance plan, and preparing a demonstrator for reviewers in early 2027. These developments mark a decisive step towards operational federated workflow execution across heterogeneous clinical and genomic datasets.
After this, the five HEREDITARY use cases were reviewed in detail, with particular emphasis on: data storage and sources clarification, strengthening the causal interpretation of results and ensuring robust legal alignment. The consortium reaffirmed that clinical relevance and methodological rigour must be a cenral topic in the project.
Looking Ahead
With federated learning infrastructure maturing, HDN endpoints being installed, FAIRification progressing, and use cases consolidating clinical relevance, the consortium is moving decisively towards delivering a scalable, privacy-preserving framework for multimodal health data analysis in Europe.
The meeting concluded with a clear set of next action points:
- Online Plenary Meeting planned for June 2026.
- Steering Committee meeting planned for April 2026.
- Federated Learning Workshop at AAU (May 2026).
The next two years will be key to the project’s results and impact, and HEREDITARY is aligned, coordinated and ready. Check out some photos from the event here:
by Admin | Feb 2, 2026 | Hereditary
Over the past few months, HEREDITARY has released a new series of 10 interviews on its YouTube channel, offering an inside look at the ongoing work and structure within the project. Recorded during the HEREDITARY consortium meeting held in Barcelona back in February 2025, this series brings together project partners who share insights into their own expertise and role as Work Packages Leaders, in order to explore and understand the scope of HEREDITARY’s activities.
The series includes seven interviews dedicated to the HEREDITARY Work Packages, in which consortium members explain their objectives, challenges and the main tasks currently under development. In addition, the series features three complementary interviews focusing on some key topics: Self-Supervised Learning, Visualization Techniques, and the European Health Data Space and the AI Act in the European context. Together, these videos provide a broader perspective on the methodological, technological, health-releated and regulatory aspects surrounding HEREDITARY’s research.
Below you can find the full list of interviews included in this series.
WP1 – Project Management
Giorgio Maria Di Nunzio (Università di Padova) explains how WP1 coordinates the HEREDITARY project, overseeing general, technical, ethics & risks, and data management to ensure the project progresses efficiently and ethically.
WP2 – Clinical Use Cases and Federated Networking Infrastructure
Umberto Manera (University of Turin) discusses WP2’s federated learning approach to analyze sensitive medical data and its five use cases covering ALS, Parkinson’s disease, and the gut-brain axis.
WP3 – Multimodal Semantic Integration Platform
Daniele Dell’Aglio (Aalborg University) presents WP3, which enables privacy-preserving data sharing across multiple data owners (such as hospitals and clinics) using knowledge graphs, ontologies, and federated methods to support analytics workflows.
WP4 – Multimodal Analytics & Learning Platform
Henning Müller and Manfredo Atzori (HES-SO Valais) describe WP4’s multimodal platform for integrating heterogeneous biomedical data, using self-supervised learning and spatio-temporal analytics to uncover new relationships.
WP5 – Visual Analytics and Interaction
Tobias Schreck (TU Graz) introduces WP5’s visual analytics platform, which combines machine learning and interactive visualizations to explore complex multimodal datasets and support decision-making.
WP6 – Citizen Science and Public Engagement
Chiara Lovati and Giuseppe Pellegrini (Observa) explain WP6’s Health Social Laboratories, which engage citizens and stakeholders to align research with real-life needs through collaborative dialogue.
WP7 – Legal, Ethical, and Regulatory Frameworks
Elisabetta Biasin (KU Leuven) highlights WP7’s role in ensuring HEREDITARY complies with privacy, data protection, AI, and security regulations throughout the project.
The Science Behind Self-Supervised Learning
Manfredo Atzori (Università di Padova) explains how self-supervised learning models extract patterns from raw multimodal biomedical data, helping identify subgroups and improve prognosis in neurodegenerative diseases.
Visualization Techniques for Multimodal Data
Tobias Schreck (TU Graz) presents HEREDITARY’s visual analytics methods, showing how integrating multiple data types into interactive platforms reveals hidden patterns and supports hypothesis generation.
European Health Data Space (EHDS) and AI Act in the European context
Lotte Cools (KU Leuven) discusses how EHDS and the AI Act shape access to health data and the use of AI in HEREDITARY, ensuring research remains innovative while legally and ethically compliant.
by Admin | Jan 29, 2026 | Events, Hereditary
DETECH 2026, the DEfinition and Term Extraction Challenge, organized as part of the HEREDITARY project, will take place on June 24, 2026, at University of Zadar, Croatia, as a hybrid satellite event of MDTT 2026, Multilingual Digital Terminology Today: Design, representation formats and management systems.
The training data for DETECH 2026 is now available in GitHub, and the challenge is officially open to participation. We welcome anyone interested in automatic term extraction, definition generation, biomedical NLP, and medical terminology to take part in the event. Teams and individual researchers can register until March 13, 2026, and start experimenting with the dataset ahead of the evaluation phase.
What is DETECH?
DETECH focuses on automatic extraction of domain-specific terms and the generation of natural language definitions for medical concepts. The 2026 edition will focus on the gut–brain interplay, offering a real-world testbed for NLP methods in gastroenterology, neuroscience, and genetics.
Challenge Tasks
The challenge features two main tasks:
- Task A – Term Extraction: Identify relevant single-word and multi-word terms from English texts on the gut–brain axis.
- Task B – Definition Generation: Create natural language definitions for the extracted concepts, using corpus-based evidence or automatic text generation techniques.
Key dates for DETECH 2026
- January 22: Training data release
- March 13: Registration deadline for participation
- March 20: Test data release
- March 27: Submission of runs
- April 7: Submission of reports
- April 15: Results announced
- April 21: Review feedback
- May 15: Camera-ready report submission
- June 15: Registration deadline for the event
- June 24: Day of the challenge
Who Can Participate?
Researchers, academics, and industry teams working in NLP, biomedical informatics, terminology, or lexicography. Each team can submit up to five runs per subtask and external resources such as pre-trained models, lexicons, or ontologies are allowed but must be properly documented. Manual runs are also accepted but will not be ranked.
Submissions & Evaluation
All submissions must include a technical report detailing the approach, experiments, and results. Reports will be peer-reviewed and published in the CEUR-WS online open-access platform, which is indexed in Scopus. Accepted papers can later be extended for submission to journals or edited volumes, providing further visibility for participants’ research.
What is MDTT 2026?
The “Multilingual Digital Terminology Today: Design, Representation Formats and Management Systems” (MDTT 2026) is the fifth international conference dedicated to the design, representation, and management of digital terminology resources. This event focuses on methods for analyzing user needs, designing and validating terminological resources, and developing effective representation formats and management systems.
Stay tuned for registration details and submission instructions, which will soon be available. We look forward to seeing you at DETECH 2026, where innovation in explainable, data-driven medical terminology meets cutting-edge NLP research!
Programme (Wednesday 24 June, 2026)
14:30 – 16:00 | Session 1
14:30 – 15:00 | Opening
15:00 – 15:30 | “Adapting TBXTools to automatic terminology extraction with BERT”. Gonzalo López-Sánchez, Patricia Morales-Hurtado, Mercè Vàzquez, Albert Morales-Moreno, and Silvia Rodríguez Vázquez.
15:30 – 16:00 | “A QTT-Informed System for Biomedical Term Extraction and Definition Generation”. Diego A. Burgos, Antonio Tamayo Herrera, Giovanni Díaz, and Carlos Mario Pérez-Pérez.
16:00 – 16:30 | Coffee break
16:30 – 18:00 | Session 2
16:30 – 17:00 | “GutBrainTerm_Extractor: Generative AI for Medical Terminology Extraction in the Gut–Brain Domain”. Helena Ortiz Garduño and Esther Castillo Pérez.
17:00 – 17:30 | “TermHunter: Neural Biomedical Term Extraction and Ontology-Enhanced Definition Generation with Structured Prompting”. Nina Hosseini-Kivanani and Rossella Resi.
17:30 – 18:00 | “Description of the LISN system for extracting terms”. Thierry Hamon.
18:00 – 18:15 | Closing
by Admin | Jan 13, 2026 | Citizen Science and Public Engagement, Hereditary
HEREDITARY‘s ‘World Café Outcome: Priorities and Gaps’ report was released. The report captures key insights from a dynamic held on October 16, 2025, during EBC‘s . Diverse stakeholders, including researchers, healthcare professionals, innovators, individuals with lived experience, and patient organisation representatives, collaborated to identify solutions to challenges in multimodal health data integration, explainability of AI-based risk prediction models, and metadata alignment in a federated environment. Highlights include strategies for data standardisation, inclusive data collection, cross-sectoral collaboration, ethical AI tools, and balancing EU regulation processes to advance health research and inform brain health policy decisions.
Project representatives of the Harnessing Health Data Cluster had a chance to exchange views on the topics via interactive discussions, and three key insights were identified at the end of the meeting:
- Greater standardisation is needed at every stage of the data lifecycle (from data collection and analysis to sharing), along with clearer documentation of data sources.
- Providing education and training for healthcare professionals on required data elements can support standardisation and collection of high-quality, usable data.
- Empowering patients in data sharing consent processes and building awareness of underrepresented populations fosters patient inclusion in research.
Read the full outcomes of the HEREDITARY World Café in the REPORT.
by Admin | Jan 12, 2026 | Hereditary
The European Horizon Europe project HEREDITARY has successfully reached Month 24 of its execution, marking the halfway point of its four-year duration. This milestone confirms the project’s strong progress and consolidates the solid foundations laid during its first two years of activity, with major deliverables completed and progress achieved.
The end of 2025 closed with particularly positive news for the consortium. HEREDITARY successfully passed its first periodic review at Month 18, with all deliverables approved. Both the external reviewers and the Project Officer praised the high quality of the work, the coherence of the technical developments, and the overall advancement of the project in line with its ambitious objectives.
In December, the consortium reached another remarkable achievement: 14 deliverables were submitted in a single day, representing the highest delivery peak foreseen throughout the entire project. These deliverables span all core scientific and technical work packages, covering clinical use cases, federated and privacy-preserving data infrastructures, semantic integration, advanced analytics, visualisation tools, citizen engagement, project management, and exploitation and intellectual property planning. Altogether, they account for more than 400 pages of technical and scientific results, reflecting an extraordinary collective effort by all partners. At the end of the article, you can review the complete list of all the reports submitted. Check them all out in the Deliverables section of our website.
Among the key achievements at this midpoint, there are also two important milestones: the first operational version of the federated workflow execution engine, enabling secure and distributed analysis across institutions, on top of the federated data management infrastructure, and the progress in data FAIRification, strengthening the discoverability and alignment of HEREDITARY data resources with European initiatives and standards. Both can be consulted in Deliverables 3.2 and Deliverable 3.6, respectively.
Reaching Month 24 represents not only a quantitative success in terms of deliverables and milestones, but also a qualitative one. The results produced so far demonstrate that HEREDITARY is effectively advancing towards its vision of building a federated, interoperable and privacy-preserving ecosystem for the integration and analysis of multimodal health data, with a particular focus on neurodegenerative and gut–brain related disorders.
Looking ahead, the consortium enters the second half of the project with a clear roadmap. The coming period will focus on maturing core scientific contributions, integrating results across work packages, and consolidating HEREDITARY into a coherent and impactful ecosystem.
14 Deliverables Submitted at M24 (December 2025)
| Deliverable | Title | Brief description | Dissemination level |
|---|
| D1.5 | Risk Management Plan, 2nd report | Updated analysis of project risks identified after the second year of implementation, including mitigation and contingency measures. | EU Classified |
| D2.4 | Linkage and feature extraction from gut–brain, intermediate evaluation | Integrated brain–gut linkage and behavioural phenotyping to extract features for federated learning, including an intermediate evaluation at M24. | Public (PU) |
| D2.22 | UCD clinical studies documentation | Regulatory, ethical and data access documentation required for the UCD-led clinical studies, including approvals and MTAs where applicable. | Public (PU) |
| D3.2 | Federated workflow execution methods: first release | First release of the federated query execution engine, including intermediate implementations, optimisations, documentation and testing. | Public (PU) |
| D3.6 | FAIRification of participating data resources | Report on improvements in FAIRness of HEREDITARY data sources, with emphasis on discoverability and alignment with EU initiatives. | Public (PU) |
| D3.11 | Pilot of the genomics data science ontology interconversion | Pilot demonstrator of a clinical ontology conversion tool enabling interoperability with genomic and other biomedical data. | Public (PU) |
| D4.1 | KDE datasets and methods: first release | Open dataset including newly predicted links from the HEREDITARY knowledge graph using several knowledge graph embedding methods. | Public (PU) |
| D4.3 | Learning models and spatio-temporal harmonization | Design and first implementation of multimodal learning algorithms, self-supervised methods, and initial harmonisation libraries. | Public (PU) |
| D5.2 | Demonstrator of visualization components for sequences, networks, text, and high dimensional data | Software libraries implementing visualisation components for heterogeneous data types, including sequences, networks and text. | Public (PU) |
| D5.4 | Prototype of the visualization components for spatial, image, and simulation data | Prototype visualisation libraries addressing spatial data, biomedical images and simulation-based datasets. | Public (PU) |
| D5.7 | Requirement analysis and user studies: Initial results | Initial requirements analysis and early evaluation results derived from user studies of WP5 visual analytics tools. | Public (PU) |
| D5.10 | First evaluation challenge: report on the data, results, and integration with EOSC | Report on the first evaluation challenge, including datasets, results, open lab proceedings and integration within EOSC. | Public (PU) |
| D6.7 | World café outcome: Priorities and gaps | Synthesis of stakeholder perspectives collected during the World Café, identifying priorities and gaps relevant to HEREDITARY. | Public (PU) |
| D8.5 | Mid Term IPR plan | Mid-term Intellectual Property Rights plan outlining preliminary protection and exploitation strategies for project results. | Sensitive (SEN) |
Check them all in the Deliverables section of the website.
by Admin | Nov 28, 2025 | Events, Hereditary
The HEREDITARY project is launching the GutBrainIE Task #6 of the BioASQ Lab as part of the CLEF 2026 conference, to be held from September 21-24, 2026 at the Friedrich-Schiller-Universität in Jena, Germany.
The GutBrainIE is a Natural Language Processing (NLP) challenge focusing on advancing information extraction from biomedical literature. In this edition participants will be asked to develop and benchmark NLP systems capable of extracting structured knowledge from PubMed abstracts related to the gut-brain axis and its associations with Alzheimer’s disease, Parkinson’s disease, Multiple Sclerosis, Amyotrophic Lateral Sclerosis (ALS), and mental health.
Subtasks Overview
The GutBrainIE task is divided into two main subtasks. In the first task, participants are asked to identify and classify specific text spans into predefined categories, while in the second one they have to determine if a particular relationship defined between two categories holds or not.
These tasks are also divided into 4 four subtasks covering entity recognition, disambiguation, and relation extraction:
- Subtask 6.1.1 – Named Entity Recognition (NER)
Participants must identify text spans and classify them into one of 13 predefined categories, such as bacteria, chemical or microbiota.
- Subtask 6.1.2 – Named Entity Recognition and Disambiguation (NERD)
Following the Subtask 6.1.1, entity mentions must be linked to concept identifiers from selected biomedical reference resources.
- Subtask 6.2.1 – Mention-Level Relation Extraction (M-RE)
Teams must detect relations between specific entity mentions within abstracts.
- Subtask 6.2.2 – Concept-Level Relation Extraction (C-RE)
This subtask is related to the concept level, enabling systems to capture deeper knowledge connections.
Each task requires participants to submit structured tuples following clearly defined formats, with examples available in the official submission guidelines.
Growing International Participation
Interest in GutBrainIE continues to expand. Last year, 17 teams worldwide took part in entity and relation extraction challenges within BioASQ. The 2026 edition significantly extends the scope by introducing:
- A new entity linking task.
- One of the largest domain-specific relation extraction collections.
- Enhanced annotation efforts involving 10+ domain experts.
- Collaboration with 70+ trained layman annotators.
- A revised and improved dataset building upon previous editions.
Early registrants receive priority access to the training datasets, making this a valuable opportunity for research groups working on entity extraction, relation extraction, or entity disambiguation in specialized domains.
Registration for CLEF 2026 is open until April 2026!
Recent Comments