KEYWORD |
Diseases associations finding through deep learning algorithms
Parole chiave AI, BIOINFORMATICS, COMPUTATIONAL BIOLOGY, DEEP LEARNING, PERSONALIZED MEDICINE
Riferimenti ROBERTA BARDINI, STEFANO DI CARLO, ALESSANDRO SAVINO
Riferimenti esterni Lorenzo Martini
Riccardo Smeriglio
Gruppi di ricerca DAUIN - GR-24 - reSilient coMputer archItectures and LIfE Sci - SMILIES
Descrizione The proposed thesis project uses deep learning algorithms to identify associations between diseases based on their genetic and molecular characteristics. Traditional disease classification often relies on observable symptoms, potentially overlooking shared biological pathways that could link seemingly unrelated conditions. This research aims to develop a deep-learning model that can detect and predict potential disease associations through pathway-level analysis, offering new insights into complex biological mechanisms. The project involves curating large-scale biomedical datasets, preprocessing the data, and designing a deep-learning architecture incorporating pathway annotations and biological embeddings. The model will be trained, fine-tuned, and validated against known associations to ensure robustness and accuracy. Additionally, the interpretability of the model's predictions will be explored to extract meaningful biological insights. This research aims to contribute a novel computational approach to understanding disease connections, with potential applications in drug repurposing and personalized medicine, ultimately enhancing understanding of disease networks and improving therapeutic strategies.
Scadenza validita proposta 07/01/2026
PROPONI LA TUA CANDIDATURA