Hereditary celebrates its first year with 16 deliverables on time

As we mark the first year of the Hereditary project, we are thrilled to reflect on the significant milestones we’ve achieved together. This year has been a testament to our collective strength, collaboration, and shared commitment to success. With over 100 individuals from 18 institutions across Europe and the US, the Hereditary project has laid a solid foundation for what is sure to be a fruitful and impactful journey ahead.

One of our most notable achievements this year has been the delivery of 16 high-quality deliverables, all on time, demonstrating our efficiency and dedication to project development. We are particularly proud of our December (12th month of the project) performance, where we successfully delivered 7 deliverables, ensuring we closed the year with impressive momentum. These deliverables are now available on our website, and we encourage anyone interested to consult those that are publicly accessible, on our zenodo profile.

16 deliverables in 12 months of existence

The deliverables produced during this first year of the project materialise the consortium’s progress in several of the 5 interconnected layers that make up the framework the project will develop to integrate multimodal health data.

  • Regarding the Federated Networking Infrastructure, we have defined the ethical guidelines for data collection and sharing for model training, as outlined in Deliverable 2.1 (D2.1) led by Università degli Studi di Torino (UNITO). Additionally, we set up the local computing and storage infrastructures in the medical centers, documented in D2.14, led by SURF BV (SURF).
  • In terms of the clinical use cases we focus on, and the data we work with, we have established guidelines for data harmonization and provided evidence-based criteria for the design of neurodegenerative use cases in D2.16, and the documentation for all the required approvals for the clinical studies in D2.19, both led by UNITO. We also conducted the initial evaluation of the integrated brain-gut linkage and behavioral phenotyping for feature extraction in federated learning, documented in D2.3 led by Radboudumc (RUMC).
  • In the Multimodal Semantic Integration Platform, we have developed the conceptual and linguistic systems that describe the medical terminology in D3.4 led by Universidade NOVA de Lisboa (UNL).
  • An important milestone in the project has been the development of the semantic ontology modeling concepts and processes for neurological diseases (Amyotrophic Lateral Sclerosis and Multiple Sclerosis), which includes a preliminary online version of the semantic ontology focusing on these diseases, as well as the design of federated execution methods, documented in D3.1 led by Università degli Studi di Padova (UNIPD). It synthesizes WP2, WP3, and WP4 contributions to provide a comprehensive framework for integrating clinical and genomic data through advanced ontology design and scalable query execution frameworks.
  • The Visual Analytics and Interaction layer has been enriched with the development of the initial conceptualization of the software libraries and documentation for visualization of sequences, networks, text, and high-dimensional data, as well as spatial, image, and simulation data, in the deliverables D5.1 and D5.3, led by Technische Universität Graz (TUGRAZ) and SURF.

In addition, during these first 12 months, Work Package 1 has built the architecture on which the management and execution of the project will be based, through the delivery of the Data Management Plan (D1.1, led by the European Molecular Biology Laboratory (EMBL)), the Quality Assurance and self-assessment Plan (D1.3, led by UNIPD) and the Risk Management Plan (D1.4, led by the European Brain Council (EBC)). In Work Package 6, guidelines for organising and implementing the Health Social Labs methodology were established in D6.1, elaborated by Observa Associazione (OBSERVA). In Work Package 7, KU Leuven developed the preliminary overview of the legal and ethical requirements applicable to the HEREDITARY project in D7.1. And, finally, FEUGA led through D8.1 and D8.4, the initial release of dissemination, communication, IP and exploitation plan, including the project webpage, Book of Style, and social media accounts creation.

What’s next for the HEREDITARY project?

Looking ahead to 2025, we are excited to build upon this motivation, continuing our collaborative efforts and addressing any uncertainties or questions openly to stay aligned. The groundwork for ongoing collaboration has been laid, and the future is bright. Big thanks to our partners and all the people involved in the project for their hard work and dedication. Now it’s time to focus on another year of success and growth in the Hereditary project!

HEREDITARY Project launches “The UCD Mission of Observa”, a video series about the Anschutz Medical Campus (UCD) research activities

We are delighted to introduce our latest video series, made by our partner Observa in the framework of the HEREDITARY project. Guided by Stephen McNamara, a research instructor at the University of Colorado Anschutz Medical Campus, we delve into the potential of AI for early diagnosis of neurodegenerative diseases and ways of communicating with patients and the public.

Each video offers a closer look at the research group’s objectives, methodology, and layers, helping you to understand the impact of this pioneering work on healthcare and data research.

This video series is part of the HEREDITARY voices series.

Episode 1. Clinical tools for diagnosis

In this first episode, Stephen McNamara explains how they are trying to find ocular biomarkers that are able to connect imaging in the eye to broader systemic diseases, such as Parkinson. By looking at images and scans from the back of the eye, they can ultimately determine whether someone has a neurodegenerative disease now or in a near future. In that way, invasive imaging or testing can be avoided, eliminating the uncertainties surrounding these diagnoses.

Episode 2. The Eye: The mirror of the body

The research group is making diagnoses and establishing connections between the whole body from a detailed analysis of the eye. By doing so, it increases certainty about different diseases, improves predictions and helps patients receive specific therapies and treatments.

Episode 3. Information, AI and Decision Making

Information is key, not only to train models to make better disease predictions, but also to ensure that patients are aware of these new scientific treatments and how it can affect their lives. Transparency becomes increasingly relevant in a world where AI is a new and evolving feature.

HEREDITARY Shines at IEEE VIS 2024: TU Graz’s Award-Winning Visualization Technique

In the framework of Work Package 5: Visual Analytics and Interaction, Graz University of Technology (WP5 leader) presented the poster DROPLETS: A Marker Design for visually enhancing Local Cluster Associations on Sunday 13 October as part of a submission to the Bio+MedVis Challenge at IEEE VIS 2024.

The research of TU Graz, focused on the visualisation of high dimensional data, received an award for the novelty and innovative Visualization technique design. It was presented by Stefan Lengauer in a virtual format, who is one of the authors along with Peter Waldert and Tobias Schreck. The summary poster, the full publication, the video presentation and the source code for generating the Droplets layout are available and can be consulted.

This year’s objective of the Bio+MedVis Challenge was to redesign an existing visualization of multi-cell gene expressions of tissue samples. In this, multiple cells are accumulated into pixels. For each pixel, the visualization should convey the prevalence and extent of cell types it is composed of in a proportional relation. The provided baseline technique of superimposed Pie charts limits the perception of regions with coherent cell-type compositions, which constitutes one of the essential visual analytics tasks.

As a response, TU Graz proposed a novel marker design: DROPLETS, a space-saving design for visually enhancing the presence of clusters and regional borders. This concept was evaluated for the given tissue sample and compared with the given baseline and other alternatives.

About the IEEE VIS 2024

IEEE VIS 2024 was the year’s premier forum for advances in theory, methods, and applications of visualization and visual analytics. The conference convened an international community of researchers and practitioners from universities, government, and industry to exchange recent findings on the design and use of visualization tools.

Join us and TU Graz to learn more about Hereditary Project and how visualization techniques help to face the critical challenge of leveraging multimodal health data.

HEREDITARY Project launches “Inside Hereditary with Gianmaria Silvello”, a video series about the project’s work

We are delighted to introduce our latest video series, made by our partner Observa, where we delve into the research of the HEREDITARY project, guided by our esteemed coordinator, Gianmaria Silvello from the University of Padua (UNIPD).

Gianmaria Silvello is a computer science engineer researcher at Department of Information Engineering of the University of Padua. His research spans knowledge management, intelligent information systems, information access, algorithmic fairness, digital libraries and data provenance and citation.

Each video offers a closer look at the project’s objectives, methodology, and layers, helping you to understand the impact of this pioneering work on healthcare and data research.

This video series is part of the HEREDITARY voices series.

Episode 1. The project approach

In this first episode, Gianmaria explains the focus of the project, the interaction between the gut and the brain, and its main challenge: integrating multilingual and multimodal data distributed across several centres. To meet this challenge, the project will rely on federated learning and federated analytics techniques.

 

Episode 2. Federated learning

Federated learning is a machine learning technique that aims to train a model under the principles of collaboration between multiple entities to ensure that information remains decentralized, reinforcing privacy and security.

 

Episode 3. Semantic data integration

Hereditary aims to simplify the way we interact with data in order to achieve a better understanding of it. One of the project main goals is to make data accessible to everyone through a common, accessible language. Therefore, we’ll be able to treat multiple neurological diseases in a unified way, using the same terms or ideas and getting answers that everyone understands.

 

Episode 4. Expected results

Gianmaria talks about Hereditary’s approach to achieving its main holistic goal around gut-brain interplay. Connections between different data from many different perspectives are processed and combined with previously obtained patient information and literature knowledge to illuminate specific aspects of the diseases we didn’t know about before. This will provide a better picture to ultimately find new treatments and better diagnoses.

 

Episode 5. Artificial Intelligence

AI has a central role in the Hereditary project. Deep learning algorithms are being used to process, classify and establish relations between the different elements. Generative AI is also taken into account to extract information from texts, but also to generate new ones. AI is used in many different ways and at different levels, without forgetting that the previous data management and processing is fundamental for the AI to work properly.

HEREDITARY Project releases public Deliverables and launches Zenodo community

We are pleased to announce that the HEREDITARY project, which commenced in January 2024, is now making its public deliverables available to the wider community and stakeholders. These deliverables can be accessed through the Deliverables section under the Resources tab on our project website. This initiative aims to promote transparency and facilitate the dissemination of our research findings and project progress to interested parties.

Currently, we submitted on time 9 deliverables from the different Work Packages of the project, thanks to the collaborative development and review work of the HEREDITARY consortium. Up to now, those that are publicly available are related to Clinical Use Cases, Federated Networking Infrastructure, Health Social Labs and Project Website.

In addition, we are excited to introduce the HEREDITARY community on Zenodo, a renowned European open-access repository. This platform ensures the permanent and open accessibility of scientific publications and public deliverables associated with our project. The Zenodo community will be regularly updated with the latest outputs of the project.

Zenodo is a repository that hosts a wide array of scientific dissemination articles and research data. As part of the European Open Science Cloud, it provides a robust infrastructure for preserving and sharing research outputs, ensuring they remain accessible and reusable by the global scientific community.

We encourage you to explore these resources to stay informed about the advances made by the HEREDITARY project, which will be 11 months old this November. By engaging with our scientific publications and project deliverables, you can gain valuable insights into our innovative research and its potential impact. Discover it today by visiting our Deliverables page and our Zenodo community.

Stay tuned for more updates and new publications as we continue to make strides in our research efforts.

HEREDITARY Project celebrates 6 months of progress

We are thrilled to announce the launch of the official HEREDITARY project website! This marks our first article on the new platform, dedicated to updating you on our progress and achievements.

HEREDITARY, the European Union-funded project dedicated to advancing the integration of multimodal health data, marked a significant milestone in June 2024 with the presentation of its first deliverables and the celebration of the second plenary meeting of the project. Held online, this meeting brought together the project’s consortium of 18 partners. Hosted by the coordinators, Universitá degli Studi di Padova (UNIPD), the meeting included updates on all Work Packages (WPs) and provided an overview of the project’s progress and direction, after the first 6 months of activity.

It has been several months since the inception of the project, and we are proud to report significant strides forward. These include the successful launch of our Data Management Plan (Deliverable 1.1), Quality Assurance and Self-assessment Plan (Deliverable 1.3), Ethical Guidelines (Deliverable 2.1), the Design of neurodegenerative use cases (Deliverable 2.16), Communication, Dissemination, IP Management and Exploitation plan (Deliverable 8.1), and the establishment of our presence across social media platforms and website.

These developments form an arsenal that leaves the project well-positioned to implement its research activity and advance the frontier of knowledge in data, genetics, and health.

Nevertheless, the progress of the HEREDITARY consortium during these first 6 months has gone beyond that: the entire consortium became familiar with the rules for EU-funded project management and monitoring; significant progress was made in multimodal analytics, federated learning, and learning platform; related projects and initiatives were identified to drive project’s liaisons; and the first interviews of HEREDITARY voices were conducted.

The HEREDITARY project was launched in January with a Kick-Off Meeting hosted by UNIPD, HEREDITARY is funded by the Horizon Europe Programme for Research and Innovation under GA No 101137074. The project aims to optimise disease detection, response treatment, and exploration of medical knowledge in neurodegenerative and gut microbiome disorders, by developing a secure distributed system for multimodal health data linkage. Check out our three main objectives here!