Suggest pathogenic cutoff of quantile_score

Help & Support
1

Hi there,

I am using dna_model.score_variant to evaluate some putative pathogenic variants, and it returns both a raw_score and a quantile_score. The FAQ suggests using quantile_score as an indicator of whether the raw score is unusually large. I was wondering if there is a recommended cutoff for interpreting these scores—for example, to classify a variant as “pathogenic,” or to use it as supporting evidence such as PP3 (supporting).

Thanks,

2

Hello,

Thank you for reaching out and welcome to the community!

We do not have a recommended cutoff. The calibration approach might also differ for different classes of variants / predicted modalities. Please let us know if you or others have any suggestions on how to best approach this question.

Thanks!