Federated network medicine for laboratory data in paediatric oncology (FLabNet)

In FLabNet, we will harness the potential of algorithmic network biology and distributed machine learning to address two exemplary unmet needs in paediatric oncology: prediction of chemotherapy side effects like neutropenic fever and early-stage detection of rare malignant diseases such as myeloproliferative neoplasms. Based on >54 million laboratory test results from >500,000 patients from the Core Dataset of the German Medical Informatics Initiative (MII), we will create personalised networks, where nodes represent individual laboratory measurements and edges encode patient-specific relationships. We hypothesise the emerging personal graph representations to capture the unique spectra and dependencies of the individual patients’ health and disease characteristics. The networks will be used as signatures for label-efficient graph-based pre- dictors such as graph kernels; and we will provide privacy-preserving federated implementations of our predictors that are fully interoperable with MII standards. To achieve its objectives, our consortium combines expertise in algorithmic systems biology (FAU), paediatric oncology (UKER), quantitative analysis of laboratory data (UKER), federated learning for biomedicine (Bitspark GmbH & FAU), and professional software development (Bitspark GmbH). These synergistic skill sets will enable us to combine laboratory diagnostics, computational systems medicine, and privacy- preserving machine learning, advancing the state of the art in quantitative analysis of laboratory data for precision medicine in paediatric oncology and beyond.