Dario Ghersi

Form Follows Function: A New Paradigm of Pancreatic Cancer Progression

This paper identifies geometric and spatial patterns in pancreatic cancer that correlate with aggressive behavior and develops an AI tool to improve clinical evaluation and treatment planning.

Towards Equitable MHC Binding Predictions: Computational Strategies to Assess and Reduce Data Bias

This paper develops a machine learning framework to assess and reduce data bias in MHC binding predictions across racial and ethnic groups.

A novel computational approach to identify cancer cells in scRNA-seq data

This paper identifies cancer cells in scRNA-seq data by combining copy number variation inference with putative driver mutation load to improve downstream analysis.

SwarmTCR: a computational approach to predict the specificity of T Cell Receptors

SwarmTCR predicts T cell receptor specificity using a nearest-neighbor approach, outperforming TCRdist on specific epitopes with single-cell and bulk data.

ACE2 fragment as a decoy for novel SARS-Cov-2 virus

The paper identifies a minimal ACE2 fragment that binds to SARS-CoV-2 spike protein and could act as a decoy to block viral entry.

Uncovering and characterizing splice variants associated with survival in lung cancer patients

The paper develops a computational method to identify splice variants linked to patient survival in lung cancer and predicts rewired protein interactions, finding variants involved in DNA repair.

High diversity, turnover, and structural constraints characterize TCR α and β repertoire selection

The paper examines TCR α and β repertoire dynamics during EBV infection, finding that persistent clonotypes are highly expanded in acute infection and replaced by new clonotypes in convalescence.