In Europe, prostate cancer (PCa) is the second most frequent type of cancer in men and the third most lethal. Current clinical practices, often leading to overdiagnosis and overtreatment of indolent tumors, suffer from lack of precision calling for advanced AI models to go beyond SoA by deciphering non-intuitive, high-level medical image patterns and increase performance in discriminating indolent from aggressive disease, early predicting recurrence and detecting metastases or predicting effectiveness of therapies. To date efforts are fragmented, based on single–institution, size-limited and vendor-specific datasets while available PCa public datasets (e.g. US TCIA) are only few hundred cases making model generalizability impossible. The ProCAncer-I project brings together 20 partners, including PCa centers of reference, world leaders in AI and innovative SMEs, with recognized expertise in their respective domains, with the objective to design, develop and sustain a cloud based, secure European Image Infrastructure with tools and services for data handling. The platform hosts the largest collection of PCa multi-parametric (mp)MRI, anonymized image data worldwide (>17,000 cases), based on data donorship, in line with EU legislation (GDPR). Robust AI models are developed, based on novel ensemble learning methodologies, leading to vendor-specific and -neutral AI models for addressing 8 PCa clinical scenarios. To accelerate clinical translation of PCa AI models, we focus on improving the trust of the solutions with respect to fairness, safety, explainability and reproducibility. Metrics to monitor model performance and a causal explainability functionality are developed to further increase clinical trust and inform on possible failures and errors. A roadmap for AI models certification is defined, interacting with regulatory authorities, thus contributing to a European regulatory roadmap for validating the effectiveness of AI-based models for clinical decision making.

Metabolic reprogramming has recently emerged as a key hallmark of cancer. Despite many efforts made to identify metabolic properties of cancer cells, there is a complete lack of understanding of the specific steps in the tumorigenic process when this metabolic rewiring occurs and its biological consequences. In this regard, our previous work has revealed a critical role of glucose metabolism in driving tumor initiation, in particular in the intestine. Importantly, recent studies have demonstrated that intestinal stem cells (ISCs) are the cell of origin of colorectal cancer (CRC), and our preliminary data suggests that glucose metabolism could be important for ISC activity. Based on these findings, we propose to study the specific metabolic properties of intestinal stem cells (ISCs) and its relevance in stem cell dynamics and CRC initiation and progression. Specifically, we will develop three aims: 1. To analyze the role of metabolic reprogramming in ISCs and its contribution to CRC by employing a combination of genetic, metabolic and imaging techniques. 2. To study the metabolic evolution of CRC. In this aim, by using patient-derived xenografts and intestinal organoids expressing a genetically encoded metabolic reporter, we will analyze glucose metabolism in vivo at a single cell level to define step-wise the role of metabolic reprogramming in CRC progression. All together, the successful completion of this proposal will identify the specific cells and steps during CRC where glucose metabolism is functionally relevant and the underlying molecular mechanisms, thus expanding our view of metabolic reprogramming beyond the idea of being just an adaptation to increased proliferation. Importantly, the results derived from this project could potentially be used to improve current therapies by targeting specific metabolic pathways.

It is the ambition of PRESIST-SEQ to provide a new gold standard in single-cell experimental workflows the cancer research community by developing best practices, standard operating procedures (SOPs), and high-quality FAIR data, with the ultimate aim to empower them to unravel therapeutic resistance. Such, that the community can identify urgently needed markers to predict, prevent, and target tumour resistance. Cancer takes 9.6 million lives each year, 90% of which result from untreatable metastatic relapse occurring after initially (seemingly) effective treatment. Therapeutic resistance is hence a primary cause of cancer death that clinically cannot be predicted, prevented, or treated. Addressing the urgent need for smarter therapeutic strategies is however held back by the lack of standardised experimental approaches that enable studying the biology of residual disease and drug tolerant persister cells in full detail. This need encompasses best practices for single-cell sequencing, advanced modelling techniques using patient-derived organoids and xenografts, and data FAIRification for integrated experiments. To address this need, PERSIST-SEQ brings together globally leading groups in single-cell sequencing technologies, cancer modelling and therapeutic resistance. Furthermore, the consortium has a broad range of clinical samples, cell lines, 3D models (PDX and PDOs) and mice models (GEMMs) at its disposal that can be leveraged to answer a broad range of emerging questions. This positions the consortium excellently to (1) design and standardise single-cell experimental approach to study the biology of therapeutic resistance and (2) initiate the largest single-cell profiling initiative on therapeutic resistance. Importantly, PERSIST-SEQ is organised such that it can quickly adapt to emerging insights and techniques during the project, and that ensures the capture of learnings in manners that stimulate replication of workflows elsewhere.