Ernestina Menasalvas

This study investigates gender differences in drug repositioning by analyzing adverse drug reactions, with a focus on rare diseases.

REDIRECTION predicts disease-drug links for drug repurposing using graph-based deep learning on biomedical data, achieving high AUROC and AUPRC scores.

The paper uses clustering to analyze disease similarities based on biological and phenotypical features, finding that weighted biological similarities can improve disease classification.

DISNET extracts phenotypic disease information from public sources to create customizable disease networks for drug repositioning.

This paper addresses gaps in UMLS disease mappings by using alternative expert-curated sources, resolving over 50% of missing mappings for some vocabularies.

The paper reviews the evolution of disease networks and evaluates their functional units to inform drug repurposing and prediction model development.