Genetic risk estimates


This section is under development.

Most people are generally familiar with the concept of polygenic risk scores (PRS). PRS can be distilled to a number that summarizes the estimated effect of many genetic variants on an individual's phenotype, typically calculated as a weighted sum of trait-associated alleles. It reflects an individual's estimated genetic predisposition for a given trait and can be used as a predictor for that trait. Generally, you need a huge reference genome-wide association studies (GWAS) and massive sample sizes to build one that functions well. This puts the user at the mercy of what has been published, as these models generally rely on massive GWAS for parameter weights. With GenoML, you can calculate a genetic risk estimate for your potentially novel phenotype/trait of interest on the fly. As an option, you can also add an existing PRS to your model build to extend that PRS and treat it as one of many features.

Calculating genetic risk estimates in GenoML#