Genomic applications for laboratory Diagnostics supported by Artificial Intelligence

Informations projet

GenDAI

N° de convention de subvention: 101182801

DOI

10.3030/101182801

Date de signature de la CE 1 Août 2024

Date de début 1 Septembre 2024

Date de fin 31 Août 2027

Financé au titre de

• Marie Skłodowska-Curie Actions (MSCA)

Coût total

Aucune donnée

Contribution de l’UE

€ 1 145 400,00

Coordonné par

FTK-FORSCHUNGSINSTITUT FUR TELEKOMMUNIKATION UND KOOPERATION EV
Germany

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Documents, reports (2)

User Requirements & Modelling

Compilation of detailed user requirements, conceptual designs, and various models including Use Context Models, Use Case Models, Information Models, Component Models, Architecture Models, and UI Models, complemented by an ethical proposal and management plan.

GenDAI Interactive Reporting Visualisations

The identified visual structures will be reported according to the user needs, the operating scenarios and the analytical tasks identified in WP1, and the different identified users. This deliverable is related to T5.1 and T5.2.

Other (4)

GenDAI Safe component, Long-Term Archiving System and Access Control Services

A secure and efficient data management solution to be integrated with the GenDAI Diagnostics processing pipeline. In addition the delivery of the long-term archiving system, integrated with sophisticated access control services, to ensure secure storage, retrieval, and management of project data over an extended period with full reproducibility.

Updated Integrated Diagnostics Pipeline

The first delivery of the GenDAI Diagnostics pipeline will be done after the integration of inital AI models and focus on automated sample (pre)processing and classification, the determination of microbiome composition from (raw) sequence data using an interactive report, improved data management and long-term archiving with a focus on reproducibility and enhanced security. All GenDAI Diagnostics deliveries will include source code, ready-to-run docker images, documentation, and user manuals.The early results available in M18 will be used for the first piloting phase to gather early enduser feedback.

GenDAI Discovery Classification, Configuration & Methodology

This initial delivery will focus on providing a simple classification model based on the improved BiGaMi algorithm to support early piloting and user feedback. It includes data and methodologies used in implementing the AI models as well configuration and technical requirements for model deployment.

Dissemination, Communication and Exploitation Plan

Outlines the GenDAI DC and E strategies, including rules for shared publications and preliminary assessment of IPR and exploitable results.

Data Management Plan (1)

Data Management Plan, Knowledge Management Resources and Quality & Risk Management Plan,

A comprehensive Data, Document and Knowledge Management Ecosystem to ensure full compliance along the project timeline.Describes the data management life cycle for the data to be collected, stored, processed, generated or distributed by the project.The Quality and Risk Management Plan represents a text of reference for management and monitoring activities to be realised during the lifetime of the project.

Publications

Conference proceedings (21)

On the Impact of Embedding Anisotropy in Genomic Language Models for Bacterial Taxonomy

Auteurs: Mike Leske; Francesca Bottacini; Rafael Ricardo de Castro Cuadrat; Haithem Afli; Bruno Gabriel Nascimento Andrade
Publié dans: Gen² Workshop on Generative AI in Genomics, ICLR 2026, 2026
Éditeur: OpenReview / ICLR workshop

GASE: Generatively Augmented Sentence Encoding

Auteurs: Manuel Frank, Haithem Afli
Publié dans: Findings of the Association for Computational Linguistics: EMNLP 2025, 2025
Éditeur: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-EMNLP.291

Responsible Use of AI in Genomics and Ethical Implications

Auteurs: Giulia Ricci, Paolo Buono, Thomas Krause, Philippe Tamla, Matthias Hemmje, Francesca De Luzi, Francesco Leotta, Andrea Marrella, Flavia Monti, Massimo Mecella
Publié dans: 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2026
Éditeur: IEEE
DOI: 10.1109/BIBM66473.2025.11356943

Realizing Modular Digital Hermeneutics: A Microservice-based Approach

Auteurs: Bianca Mix, Markus Bortenhauser, Sebastian Bruchhaus, Alexander Duttenhöfer
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

Revisiting Data Visualizations in Diagnostic Reports

Auteurs: Paolo Buono, Philippe Tamla, Thomas Krause, Francesca De Luzi, Flavia Monti, Massimo Mecella
Publié dans: 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2026
Éditeur: IEEE
DOI: 10.1109/BIBM66473.2025.11356146

Supporting Professional Conference Organizers in Expert-Finding Tasks using Knowledge Graphs and Topic Modeling

Auteurs: Benedict Hartmann, Nico Lindemann
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

Time-Stratified Architecture for Real-Time Analysis of Behavioural Signals in Telehealth

Auteurs: Dennis Maier, Marco Xaver Bornschlegl
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs

Auteurs: Manuel Frank, Haithem Afli
Publié dans: Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 2026
Éditeur: Association for Computational Linguistics
DOI: 10.18653/V1/2026.EACL-LONG.130

Explanation-Driven Visual Interventions in Genomics

Auteurs: Andrea Esposito, Paolo Buono, Rosa Lanzilotti
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

A Symbiotic AI Approach for Trustable and Interactive Microbiome Data Interpretation

Auteurs: Francesco Greco, Giuseppe Desolda, Antonio Piccinno
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

Towards a Medically and Legally Sufficient Documented Argumentation Model for Medical Information Retrieval Systems

Auteurs: Alexander Duttenhöfer, Till Menke, Bianca Mix
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

A Prototype Implementation Supporting Intelligent Big Data Analysis

Auteurs: Sebastian Bruchhaus, Alexander Kreibich, Thoralf Reis, Marco X. Bornschlegl
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

Towards an Intelligent Scientific Publication Management System: Motivation, Methodological Foundations, and Conceptual Design

Auteurs: Bao Khanh Nguyen, Binh Vu
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

The GenDAI Cloud-Native Infrastructure and Data Stewardship for Clinical Metagenomic Diagnostics

Auteurs: Philippe Tamla, Thomas Krause, Matthias Hemmje, Flavia Monti, Francesca De Luzi, Massimo Mecella, Bruno Andrade, Paolo Buono, Andrea Molinari
Publié dans: 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2026
Éditeur: IEEE
DOI: 10.1109/BIBM66473.2025.11356811

Towards a Model for Supporting Cloud-based Information Extraction from MICE Content

Auteurs: Gladys Kouakam, Nico Lindemann, Philippe Tamla
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

C2PA and eIDAS 2.0 - a Reference Framework for Content Verification and Protection in the EU

Auteurs: Stefan Wagenpfeil, Joyce Amy Kolenda, Waldemar Nauvomets, Tim Ternovik, Jakob Wenzig
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

From Reads to Reports: A Vision for a GFM-Powered Genomic Diagnostic Platform

Auteurs: Thomas Krause, Philippe Tamla, Andrea Leoni, Flavia Monti, Francesca De Luzi, Jamie Fitz Gerald, Bruno Andrade, Haithem Afli, Massimo Mecella, Paolo Buono, Andrea Molinari, Matthias Hemmje
Publié dans: 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2026
Éditeur: IEEE
DOI: 10.1109/BIBM66473.2025.11356528

Supporting Conference Organizers in Expert-Finding Tasks using Transformer-based Embedding and Retrieval

Auteurs: Tom Eichhorn, Benedict Hartmann, Nico Lindemann
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

Trustable, Reproducible, and Intelligent Information Visualization Systems (TRI-IVIS)

Auteurs: Paolo Buono, Philippe Tamla, Thomas Krause, Haithem Afli, Matthias Hemmje
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

Multimedia, RAG, and LLMs in High-Security Environments - a reference implementation for the AI2MMIR architecture

Auteurs: Stefan Wagenpfeil, Angelina Chernikov
Publié dans: CEUR Workshop Proceedings, Numéro Vol-4227, 2026, ISSN 1613-0073
Éditeur: CEUR-WS.org

LLM-Driven Cloud-Based Infrastructure Design

Auteurs: Andrea Sepielli, Marco Calamo, Filippo Bianchini, Francesca De Luzi, Matteo Marinacci, Flavia Monti, Jacopo Rossi, Massimo Mecella, Philippe Tamla, Thomas Krause, Matthias Hemmje
Publié dans: 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2026
Éditeur: IEEE
DOI: 10.1109/BIBM66473.2025.11356715

Monographic books (1)

Engineering Information Systems with Large Language Models

Publié dans: 2025
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-92285-5