Multi-omics data have revolutionized biomedical research by providing a comprehensive understanding of biological systems and the molecular mechanisms of disease development. However, analyzing multi-omics data is challenging due to high dimensionality and limited sample sizes, necessitating proper data-reduction pipelines to ensure reliable analyses. Additionally, its multimodal nature requires effective data-integration pipelines. While several dimensionality reduction and data fusion algorithms have been proposed, crucial aspects are often overlooked. Specifically, the choice of projection space dimension is typically heuristic and uniformly applied across all omics, neglecting the unique high dimension small sample size challenges faced by individual omics. This paper introduces a novel multi-modal dimensionality reduction pipeline tailored to individual views. By leveraging intrinsic dimensionality estimators, we assess the curse-of-dimensionality impact on each view and propose a two-step reduction strategy for significantly affected views, combining feature selection with feature extraction. Compared to traditional uniform reduction pipelines in a crucial and supervised multi-omics analysis setting, our approach shows significant improvement. Additionally, we explore three effective unsupervised multi-omics data fusion methods rooted in the main data fusion strategies to gain insights into their performance under crucial, yet overlooked, settings.

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.