Tooluniverse Polygenic Risk Score

This builds polygenic risk scores from GWAS summary statistics, calculating weighted sums across variants to estimate genetic predisposition to complex diseases. It pulls associations from GWAS Catalog and Open Targets, filters for genome-wide significance (p < 5e-8), and standardizes scores to population percentiles. The reasoning strategy is unusually thorough about what PRS actually means: relative risk not diagnosis, ancestry-dependent accuracy, and the massive performance drop when European-trained models hit non-European populations. Use this for risk stratification research or explaining genetic contributions to multifactorial conditions. Just remember it's querying public databases, not running LD clumping or fine-mapping, so you're getting raw associations that would need pruning for production use.