My research is focused on developing algorithms, methods and models for computational drug discovery & design, protein function prediction and heterogeneous biological data integration/harmonization for advanced analysis pipelines & tools. These methods/models leverage machine learning, deep learning, generative AI, data mining and graph theory. I draw inspiration from advanced approaches in fields such as natural language processing and computer vision, adapting and refining these techniques and architectures to create innovative, domain-specific solutions for biomedical challenges.
Our work is structured into three main components: (i) the integration of diverse biological data from open-access repositories to construct a comprehensive framework of existing knowledge; (ii) the development and application of novel in-silico methods to large-scale datasets to identify and fill gaps in current understanding; and (iii) the detailed analysis of well-annotated data enriched with computational predictions to extract mechanistic insights. We ensure that all produced datasets and source code are published in open-access repositories, facilitating reproducibility and enabling further exploration by the research community.