AVADA Improves Automated Genetic Variant Database 2 Construction Directly from Full Text Literature

17 The primary literature on human genetic diseases with high penetrance includes descriptions of 18 large numbers of pathogenic variants that can be essential for clinical diagnosis. Variant 19 databases such as ClinVar and HGMD collect pathogenic variants by manual curation of either 20 voluntary submissions or the published literature. AVADA (Automatically curated VAriant 21 DAtabase) represents the first automated tool designed to construct a comprehensive database of 22 highly penetrant genetic variants directly from full-text articles about human genetic disease. 23