Andrea Cossarizza

The paper develops flowMagic, a machine learning tool for automated flow cytometry gating trained on expert data and citizen science gaming annotations, achieving high accuracy in cell population identification.

This study compares conventional and spectral flow cytometry for high-parameter T-cell phenotyping, finding that spectral flow cytometry provides better resolution and sensitivity, especially with optimized panels.

The paper develops a machine learning model to predict COVID-19 severity using exonic variants from whole exome sequencing data, finding that variants across all frequency categories contribute to severity.

The paper identifies shorter androgen receptor polyQ alleles as protective against severe COVID-19 in males using machine learning on whole-exome sequencing data from the GEN-COVID cohort.

The paper identifies ACE2 gene variants associated with interindividual variability in COVID-19 susceptibility in the Italian population using whole-exome-sequencing data.

This study shows DNA Topoisomerase I regulates R-loop formation by causing gains and losses at different genomic regions, affecting replication and cell cycle progression.