mims-harvard avatar

Tooluniverse Gwas Study Explorer

This pulls GWAS study data from NHGRI-EBI GWAS Catalog and Open Targets Genetics to compare genome-wide association studies for the same trait. You can run meta-analyses across cohorts, calculate heterogeneity statistics like I² to see if effect sizes are consistent, and check which loci actually replicate across populations. The workflow is compute-first: retrieve associations with the ToolUniverse tools, then run Python code to aggregate effect sizes, generate forest plots, and assess study quality by sample size and ancestry. Useful when you need to know if a genetic signal holds up across studies or if you're seeing population-specific effects versus methodological noise. The documentation is thorough on when heterogeneity means you shouldn't trust a combined estimate.

skills.sh installs
359
GitHub stars
1.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-gwas-study-explorer --agent claude-code

Installs into .claude/skills of the current project.

Files

GWAS Study Deep Dive & Meta-Analysis

Compare GWAS studies, perform meta-analyses, and assess replication across cohorts


Overview

The GWAS Study Deep Dive & Meta-Analysis skill enables comprehensive comparison of genome-wide association studies (GWAS) for the same trait, meta-analysis of genetic loci across studies, and systematic assessment of replication and study quality. It integrates data from the NHGRI-EBI GWAS Catalog and Open Targets Genetics to provide a complete picture of the genetic architecture of complex traits.

Key Capabilities

  1. Study Comparison: Compare all GWAS studies for a trait, assessing sample sizes, ancestries, and platforms
  2. Meta-Analysis: Aggregate effect sizes across studies and calculate heterogeneity statistics
  3. Replication Assessment: Identify replicated vs novel findings across discovery and replication cohorts
  4. Quality Evaluation: Assess statistical power, ancestry diversity, and data availability

Sponsors

Details

Repository
github.com/mims-harvard/tooluniverse
Categories
Data Science & ML, Design & UI/UX
First seen
Jun 3, 2026

More from mims-harvard/tooluniverse

All 68
1mims-harvard avatartooluniverse-metabolomicsmims-harvard/tooluniverseMetabolomics research — metabolite identification, study analysis, and database searches across HMDB, MetaboLights, Metabolomics Workbench, KEGG. Use for annota358skills.sh installs
2davila7 avatarmoe-trainingdavila7/claude-code-templatesTrain Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense mode357skills.sh installs
3levnikolaevich avatarln-510-quality-coordinatorlevnikolaevich/claude-code-skillsUse when coordinating story quality evaluation with mandatory research, worker summaries, agent review, regression evidence, and bounded refinement.357skills.sh installs
4pskoett avatardx-data-navigatorpskoett/pskoett-ai-skillsQuery Developer Experience (DX) data via the DX Data MCP server PostgreSQL database. Use this skill when analyzing developer productivity metrics, team performa355skills.sh installs
5aliyun avataralibabacloud-resourcecenter-searchaliyun/alibabacloud-aiops-skillsAlibaba Cloud Resource Center - Global Resource Inventory, Search & Statistics Skill. Provides cross-region, cross-product, and cross-account resource inventory354skills.sh installs
6lyndonkl avatargrant-proposal-assistantlyndonkl/claudeGuides creation and review of competitive grant proposals (NIH R01/R21/K, NSF, foundations) by applying reviewer-perspective thinking to ensure clear hypotheses353skills.sh installs