Francis P. Crawley

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 describes a biobanking initiative collecting genetic and clinical data from over 1,000 SARS-CoV-2-positive individuals to study multi-organ involvement and genetic factors in COVID-19 severity.

The paper proposes a post-Mendelian genetic model integrating common and rare variants to predict severe vs. mild COVID-19 outcomes in an Italian cohort.