Construction and Enhancement of an RNA-Based Knowledge Graph for Discovering New RNA Drugs

Cutting-edge technologies in RNA biology are pushing the study of fundamental biological processes and human diseases and accelerate the development of new drugs tailored to the patient's biomolecular characteristics. Even if many structured and unstructured data sources report the interaction among different RNA molecules and some other biomedical entities (e.g., drugs, diseases, genes), we still lack a comprehensive and well-described RNA-centered Knowledge Graph (KG) that contains such information and sophisticated services that support the user in its creation, maintenance, and enhancement. This PhD project aims to create a biomedical KG (named RNA-KG) to represent, and eventually infer, biological, experimentally validated interactions between different RNA molecules. We also wish to enhance the KG content and develop sophisticated services designed ad-hoc to support the user in predicting uncovered relationships and identifying new RNA-based drugs. Services will rely on deep learning methods that consider the heterogeneity of the graph and the presence of an ontology that describes the possible relationships existing among the involved entities. Moreover, we will consider Large Language Models (LLMs) in combination with RNA-KG for interacting with the user with the ground truth information contained in our KG for extracting relationships from unstructured data sources.