mims-harvard avatar

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.

skills.sh installs
351
GitHub stars
1.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-polygenic-risk-score --agent claude-code

Installs into .claude/skills of the current project.

Files

Polygenic Risk Score (PRS) Builder

Build and interpret polygenic risk scores for complex diseases using genome-wide association study (GWAS) data.

Reasoning Strategy

A polygenic risk score predicts genetic risk, not disease. A high PRS means elevated risk relative to the population — it does not mean the person will develop the condition, and a low PRS does not confer immunity. PRS performance varies dramatically across ancestries: a European-derived PRS applied to a West African population can lose 50–70% of its predictive power because the underlying GWAS was trained on European allele frequencies and LD patterns. Effect sizes from discovery GWAS are subject to winner's curse (overestimation in single studies); always prefer weights from large meta-analyses or validated PGS Catalog models. PRS should always be interpreted in the context of non-genetic risk factors — for most complex diseases, environmental factors contribute as much or more than genetics.

Sponsors

Details

Repository
github.com/mims-harvard/tooluniverse
Categories
DevOps & CI/CD, Data Science & ML
First seen
Jun 3, 2026

More from mims-harvard/tooluniverse

All 68
1bmad-code-org avatarbmad-quick-devbmad-code-org/bmad-methodDeprecated: forwards to bmad-build. Do not use unless invoked by name.350skills.sh installs
2pmprompt avatarproduct-led-seopmprompt/claude-plugin-product-managementUse when asked to "product-led SEO", "programmatic SEO", "build programmatic pages", "organic acquisition for product", "decide if SEO is worth it", or "optimiz350skills.sh installs
3artwist-polyakov avatarssh-remote-connectionartwist-polyakov/polyakov-claude-skillsSSH connection to remote servers. Use when you need to execute commands on a remote server, check logs, restart services, or manage Docker containers.349skills.sh installs
4davila7 avatarserver-managementdavila7/claude-code-templatesServer management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.349skills.sh installs
5guia-matthieu avatardotcom-secretsguia-matthieu/clawfu-skillsBuild high-converting sales funnels using Russell Brunson's proven framework Use when: **Launching an online product** and need a complete funnel strategy; **Co349skills.sh installs
6pmprompt avatarhooked-modelpmprompt/claude-plugin-product-managementUse when asked to "build habit-forming products", "Hooked model", "trigger action reward investment", "create sticky behavior loops", or "design habit loops". H349skills.sh installs