What DANN predicts
DANN (Deleterious Annotation of genetic variants using Neural Networks) predicts whether a variant is likely to be disease-causing. It can score coding and non-coding variants, not only missense changes.
Score range
DANN scores run from 0 to 1. Higher values mean a higher predicted chance of a harmful effect. The Gene Inspector help guide uses a score higher than 0.96 as a high-score review threshold.
How the model was built
DANN was developed as a neural-network extension of the CADD approach. The method uses 949 genomic features and was trained on more than 16 million variants, comparing observed human variation with simulated variants enriched for harmful effects.
In Gene Inspector Pro
Gene Inspector Pro shows DANN next to other predictor values. Use it to prioritize variants for review, then check consequence, allele frequency, ClinVar, inheritance, genotype quality, and source evidence.