Giovanna Maria Dimitri

The paper provides a unified pathway representation of mechanotransduction and inflammation using SBML and network biology approaches, highlighting RAC1 as a potential therapeutic target.

The paper predicts protein functions using a semantic-based regularization kernel method with logic rules, showing improved performance in bioinformatics applications.

The paper analyzes the human transcriptome using co-expression networks and identifies biologically meaningful clusters and associations with CRP and cancer metastasis.

This paper develops a deep learning architecture for fusing multiple 3D neuroimaging modalities into informative latent embeddings, demonstrating their ability to cluster subjects into separable phenotypic strata.