The first IVDR-approved commercial software solutions for AI-powered RNA-based companion and precision cancer diagnostics of acute myeloid leukaemia and bladder cancer

Informations projet

QIandQD

N° de convention de subvention: 101161230

DOI

10.3030/101161230

Date de signature de la CE 25 Avril 2024

Date de début 1 Mai 2024

Date de fin 30 Avril 2027

Financé au titre de

• The European Innovation Council (EIC)

Coût total

€ 3 559 500,00

Contribution de l’UE

€ 2 491 650,00

Coordonné par

QLUCORE AB
Sweden

Periodic Reporting for period 2 - QIandQD (The first IVDR-approved commercial software solutions for AI-powered RNA-based companion and precision cancer diagnostics of acute myeloid leukaemia and bladder cancer)

Période du rapport: 2025-05-01 au 2026-04-30

Résumé du contexte et des objectifs généraux du projet

Molecular profiling of tumours is important for providing cancer patients with the correct diagnosis, most effective treatment and accurate prognosis. Next-generation sequencing (NGS)-based technologies are increasingly being included in clinical guidelines as a complement to traditional laboratory techniques. NGS-based tumour profiling, such as RNA-sequencing (RNA-seq), offers a more comprehensive picture of processes that control tumour heterogeneity compared to single biomarker assays that are currently used in the clinic.

Qlucore develops visualisation-based analytical solutions with an established position in the NGS market. We aim to develop software solutions integrating machine learning-based classification models for gene expression signatures and gene fusion analysis from RNA-seq. In the current project we focus on models for classifying two cancer types, acute myeloid leukaemia (AML) and bladder cancer (BC), into clinically relevant subtypes to provide more accurate diagnosis and prognosis.

Website reference: https://qlucore.com/collaborations-and-partners

Travail effectué depuis le début du projet jusqu’à la fin de la période considérée dans le rapport et principaux résultats atteints jusqu’à présent

Work package (WP) 1 focuses on project management and has delivered plans for an efficient management stucture. WP1 continuosly works to ensure that the project delivers on time.

WP2 focuses on communication and dissemination activities and continously report about the project progress through various channels.

WP3 is responsible for generating RNA-seq data and has secured ethics approvals for the use of samples and data from the AML and BC cohorts. We have produced standard operating procedures (SOPs) to ensure laboratory workflows and bioinformatic pipelines generate data of high quality. Qlucore works in close collaboration with two research groups at Lund University that generate the gene expression data. During the second reporting period the project has processed an additional 166 AML and 300 BC RNA-seq samples of high quality.

WP4 is responsible for training gene expression-based classifier models for subtyping AML and BC, using data generated in WP3. During the second reporting period we have validated the performance of two early prototype classifiers with external data. We switched to neural networks for training classifiers, and trained new classifiers on the expanded data, both generated within the project and sourced from public resources. The new classifiers reached much improved performance and will be moved into analytical and clinical performance evaluation in the coming year.

WP5 is responsible for the development of the Qlucore Insigths and Qlucore Diagnostics softwares. During the second reporting period we have developed support for neural network-bases classifiers and functionality for a tier system to prioritize clinically relevant gene fusions. Report functionallity and layout has also been improved.

Progrès au-delà de l’état des connaissances et impact potentiel prévu (y compris l’impact socio-économique et les conséquences sociétales plus larges du projet jusqu’à présent)

Not applicable yet.