Alessandro Lussana

This paper evaluates kinase activity inference methods using phosphoproteomics data and benchmarking approaches, finding that curated kinase-substrate libraries significantly impact results.

This study develops a machine learning model to predict kinase-substrate relationships from omics data, improving upon existing methods and providing a web tool for analysis.

PhosX infers kinase activity changes from phosphoproteomics data using substrate sequence specificity, outperforming existing methods without requiring prior kinase-substrate knowledge.

This paper improves transcriptome-wide association studies by predicting gene expression from regulatory sequence composition, leading to new gene-phenotype associations.