Gabriele Malagoli

XplainTDA identifies molecular determinants of topological structures in single-cell multi-omics data through perturbation-based analysis.

SEAGALL uses geometry-aware graph attention networks to extract biologically relevant features from single-cell data, revealing cell identity drivers beyond marker genes.

This paper introduces a graph-based topic modelling method for single-cell multi-omic data, showing improved performance in clustering and biological interpretation.

This study uses topic modeling to cluster breast cancer single-cell data and identify gene signatures, improving interpretability and accuracy in distinguishing drug-sensitive and resistant cell types.