This work package focuses on designing algorithms to study cancer evolution using DNA variations identified through Illumina sequencing data. These DNA variations represent points in the 3.2Gb human genome where differences exist, either between individuals or between cancerous and normal tissues. Researchers analyse these mutations to assess how primary tumours differ and how they grow. By applying explainable AI, they aim to pinpoint tumour cells with mutations that can be targeted by currently available drugs and evaluate whether these cells are likely to recur after the primary tumour is removed. Additionally, the study investigates whether metastases spread in a linear fashion or through branching patterns, which could inform the creation of recommendation systems for predicting cancer progression. This holistic approach supports the development of personalized treatment strategies, tailored to patient-specific data, both before and after the recurrence of the disease.

In the next phase of the project, knowledge extraction algorithms will be utilized on extensive datasets produced in collaboration with European partners in Germany, Switzerland, and the U.K. This stage focuses on addressing critical questions about integrating AI-driven, data-based recommendations into clinical practice. It leverages the vast amounts of data generated by pan-European cancer genome sequencing initiatives to bridge the gap between advanced computational analysis and practical applications in the clinical domain.

This work package focuses on engaging with patient organizations to effectively communicate the results of the research, ensuring that valuable insights are accessible and beneficial to the wider community. Key partners in this effort include Nadacia Vyskum Rakoviny, Rotary Club Slovakia, and Nadacia Nie Rakovine. The goal is to bridge the gap between advanced research findings and the needs of patients and their families, fostering a better understanding of cancer evolution and its implications.