Functional enrichment of a literature-based regulatory network for axillary lymph node metastasis in breast cancer using graph embedding techniques

Breast cancer (BC) is the leading cause of cancer-related death among women worldwide. The mortality risk increases significantly when tumour cells metastasise to the axillary lymph nodes (ALNs). The immune response plays a crucial role in this metastatic process. Therefore, a deeper mechanistic understanding of tumour-immune interactions is essential for developing effective, disease-modifying therapies for BC. Thus, this project aims to functionally enrich a previously developed regulatory network model of ALN metastasis in BC, originally derived from the literature data. The idea is to explore graph embedding techniques (such as node2vec) to analyse and predict functional interactions within the network effectively. Various machine learning techniques will be applied to support this enrichment process. The final model is expected to offer a systems-level perspective on tumour progression and aid in identifying biomarker and therapeutic targets in breast cancer patients.

Supervisors: Jérôme Noailly, Alba Fischer