Agent skill

Gwas Trait To Gene

by lamm-mit in lamm-mit/scienceclaw

ToolUniverse workflow — Gwas Trait To Gene. An agent skill from lamm-mit/scienceclaw.

Apache-2.0Auto-check passedResearch & Science

Install Gwas Trait To Gene

skills CLI
$ npx skills add lamm-mit/scienceclaw --skill gwas-trait-to-gene -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lamm-mit/scienceclaw gwas-trait-to-gene --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gwas-trait-to-gene .claude/skills/gwas-trait-to-gene && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gwas-trait-to-gene
GitHub stars
246
Token cost
~2.2k tokens
SKILL.md length
710 words
Files
3 (incl. scripts)
Skills in repo
86
Repo updated
First seen
Licence
Apache-2.0

At a glance

ToolUniverse workflow — Gwas Trait To Gene. An agent skill from lamm-mit/scienceclaw.

  • Works in 4 steps: Gene Mapping Uncertainty → Population Bias → Sample Size Dependence → …
  • Research & Science work in your project
  • SKILL.md covers Overview, Use Cases, Workflow and Key Concepts, plus 10 more sections
  • Runs Python scripts from its folder

What it does

Gwas Trait To Gene is an agent skill from lamm-mit/scienceclaw. ToolUniverse workflow — Gwas Trait To Gene

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/run.py`).

It sits in Research & Science. The licence is Apache-2.0.

When your agent uses it

  • Research & Science work in your project

Example prompts

  • “/gwas-trait-to-gene”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Gene Mapping Uncertainty
  2. Population Bias
  3. Sample Size Dependence
  4. Validation Bug

What it can do on your machine

Read from SKILL.md and the folder at commit ab9aba1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • ebi.ac.uk
    • genetics.opentargets.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gwas Trait To Gene loads about 2.2k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 710 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 710 words, ~2,220 tokens.

Download SKILL.mdSave it as .claude/skills/gwas-trait-to-gene/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
gwas-trait-to-gene
description
ToolUniverse workflow — Gwas Trait To Gene
source
https://github.com/mims-harvard/ToolUniverse/tree/main/skills/tooluniverse-gwas-trait-to-gene

name: tooluniverse-gwas-trait-to-gene description: Discover genes associated with diseases and traits using GWAS data from the GWAS Catalog (500,000+ associations) and Open Targets Genetics (L2G predictions). Identifies genetic risk factors, prioritizes causal genes via locus-to-gene scoring, and assesses druggability. Use when asked to find genes associated with a disease or trait, discover genetic risk factors, translate GWAS signals to gene targets, or answer questions like "What genes are associated with type 2 diabetes?"

GWAS Trait-to-Gene Discovery

Discover genes associated with diseases and traits using genome-wide association studies (GWAS)

Overview

This skill enables systematic discovery of genes linked to diseases/traits by analyzing GWAS data from two major resources:

  • GWAS Catalog (EBI/NHGRI): Curated catalog of published GWAS with >500,000 associations
  • Open Targets Genetics: Fine-mapped GWAS signals with locus-to-gene (L2G) predictions

Use Cases

Clinical Research

  • "What genes are associated with type 2 diabetes?"
  • "Find genetic risk factors for coronary artery disease"
  • "Which genes contribute to Alzheimer's disease susceptibility?"

Drug Target Discovery

  • Identify genes with strong genetic evidence for disease causation
  • Prioritize targets based on L2G scores and replication across studies
  • Find genes with genome-wide significant associations (p < 5e-8)

Functional Genomics

  • Map disease-associated variants to candidate genes
  • Analyze genetic architecture of complex traits
  • Understand polygenic disease mechanisms

Workflow

1. Trait Search → Search GWAS Catalog by disease/trait name
       ↓
2. SNP Aggregation → Collect genome-wide significant SNPs (p < 5e-8)
       ↓
3. Gene Mapping → Extract mapped genes from associations
       ↓
4. Evidence Ranking → Score by p-value, replication, fine-mapping
       ↓
5. Annotation (Optional) → Add L2G predictions from Open Targets

Key Concepts

Genome-wide Significance

  • Standard threshold: p < 5×10⁻⁸
  • Accounts for multiple testing burden across ~1M common variants
  • Higher confidence: p < 5×10⁻¹⁰ or replicated across studies

Gene Mapping Methods

  • Positional: Nearest gene to lead SNP
  • Fine-mapping: Statistical refinement to credible variants
  • Locus-to-Gene (L2G): Integrative score combining multiple evidence types

Evidence Confidence Levels

  • High: L2G score > 0.5 OR multiple studies with p < 5e-10
  • Medium: 2+ studies with p < 5e-8
  • Low: Single study or marginal significance

Required ToolUniverse Tools

GWAS Catalog (11 tools)
  • gwas_get_associations_for_trait - Get all associations for a trait (sorted by p-value)
  • gwas_search_snps - Search SNPs by gene mapping
  • gwas_get_snp_by_id - Get SNP details (MAF, consequence, location)
  • gwas_get_study_by_id - Get study metadata
  • gwas_search_associations - Search associations with filters
  • gwas_search_studies - Search studies by trait/cohort
  • gwas_get_associations_for_snp - Get all associations for a SNP
  • gwas_get_variants_for_trait - Get variants for a trait
  • gwas_get_studies_for_trait - Get studies for a trait
  • gwas_get_snps_for_gene - Get SNPs mapped to a gene
  • gwas_get_associations_for_study - Get associations from a study
Open Targets Genetics (6 tools)
  • OpenTargets_search_gwas_studies_by_disease - Search studies by disease ontology
  • OpenTargets_get_study_credible_sets - Get fine-mapped loci for a study
  • OpenTargets_get_variant_credible_sets - Get credible sets for a variant
  • OpenTargets_get_variant_info - Get variant annotation (frequencies, consequences)
  • OpenTargets_get_gwas_study - Get study metadata
  • OpenTargets_get_credible_set_detail - Get detailed credible set information

Parameters

Required

  • trait - Disease/trait name (e.g., "type 2 diabetes", "coronary artery disease")

Optional

  • p_value_threshold - Significance threshold (default: 5e-8)
  • min_evidence_count - Minimum number of studies (default: 1)
  • max_results - Maximum genes to return (default: 100)
  • use_fine_mapping - Include L2G predictions (default: true)
  • disease_ontology_id - Disease ontology ID for Open Targets (e.g., "MONDO_0005148")
Show full SKILL.md (270 more words)Show less

Output Schema

python
{
  "genes": [
    {
      "symbol": str,              # Gene symbol (e.g., "TCF7L2")
      "min_p_value": float,       # Most significant p-value
      "evidence_count": int,      # Number of independent studies
      "snps": [str],              # Associated SNP rs IDs
      "studies": [str],           # GWAS study accessions
      "l2g_score": float | null,  # Locus-to-gene score (0-1)
      "credible_sets": int,       # Number of credible sets
      "confidence_level": str     # "High", "Medium", or "Low"
    }
  ],
  "summary": {
    "trait": str,
    "total_associations": int,
    "significant_genes": int,
    "data_sources": ["GWAS Catalog", "Open Targets"]
  }
}

Example Results

Type 2 Diabetes

TCF7L2:  p=1.2e-98, 15 studies, L2G=0.82 → High confidence
KCNJ11:  p=3.4e-67, 12 studies, L2G=0.76 → High confidence
PPARG:   p=2.1e-45, 8 studies,  L2G=0.71 → High confidence
FTO:     p=5.6e-42, 10 studies, L2G=0.68 → High confidence
IRS1:    p=8.9e-38, 6 studies,  L2G=0.54 → High confidence

Alzheimer's Disease

APOE:    p=1.0e-450, 25 studies, L2G=0.95 → High confidence
BIN1:    p=2.3e-89,  18 studies, L2G=0.88 → High confidence
CLU:     p=4.5e-67,  16 studies, L2G=0.82 → High confidence
ABCA7:   p=6.7e-54,  14 studies, L2G=0.79 → High confidence
CR1:     p=8.9e-52,  13 studies, L2G=0.75 → High confidence

Best Practices

1. Use Disease Ontology IDs for Precision

# Instead of:
discover_gwas_genes("diabetes")  # Ambiguous

# Use:
discover_gwas_genes(
    "type 2 diabetes",
    disease_ontology_id="MONDO_0005148"  # Specific
)

2. Filter by Evidence Strength

# For drug targets, require strong evidence:
discover_gwas_genes(
    "coronary artery disease",
    p_value_threshold=5e-10,    # Stricter than GWAS threshold
    min_evidence_count=3,       # Multiple independent studies
    use_fine_mapping=True       # Include L2G predictions
)

3. Interpret Results Carefully

  • Association ≠ Causation: GWAS identifies correlated variants, not necessarily causal genes
  • Linkage Disequilibrium: Lead SNP may tag the true causal variant in a nearby gene
  • Fine-mapping: L2G scores provide better causal gene evidence than positional mapping
  • Functional Evidence: Validate with orthogonal data (eQTLs, knockout models, etc.)

Limitations

  1. Gene Mapping Uncertainty

    • Positional mapping assigns SNPs to nearest gene (may be incorrect)
    • Fine-mapping available for only a subset of studies
    • Intergenic variants difficult to map
  2. Population Bias

    • Most GWAS in European populations
    • Effect sizes may differ across ancestries
    • Rare variants often under-represented
  3. Sample Size Dependence

    • Larger studies detect more associations
    • Older small studies may have false negatives
    • p-values alone don't indicate effect size
  4. Validation Bug

    • Some ToolUniverse tools have oneOf validation issues
    • Use validate=False parameter if needed
    • This is automatically handled in the Python implementation
  • Variant-to-Disease Association: Look up specific SNPs (e.g., rs7903146 → T2D)
  • Gene-to-Disease Links: Find diseases associated with known genes
  • Drug Target Prioritization: Rank targets by genetic evidence
  • Population Genetics Analysis: Compare allele frequencies across populations

Data Sources

GWAS Catalog

  • Curator: EBI and NHGRI
  • URL: https://www.ebi.ac.uk/gwas/
  • Coverage: 100,000+ publications, 500,000+ associations
  • Update Frequency: Weekly

Open Targets Genetics

  • Curator: Open Targets consortium
  • URL: https://genetics.opentargets.org/
  • Coverage: Fine-mapped GWAS, L2G predictions, QTL colocalization
  • Update Frequency: Quarterly

Citation

If you use this skill in research, please cite:

Buniello A, et al. (2019) The NHGRI-EBI GWAS Catalog of published genome-wide
association studies. Nucleic Acids Research, 47(D1):D1005-D1012.

Mountjoy E, et al. (2021) An open approach to systematically prioritize causal
variants and genes at all published human GWAS trait-associated loci.
Nature Genetics, 53:1527-1533.

Support

For issues with:

  • Skill functionality: Open issue at tooluniverse/skills
  • GWAS data: Contact GWAS Catalog or Open Targets support
  • Tool errors: Check ToolUniverse tool status

© lamm-mit, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/gwas-trait-to-gene of lamm-mit/scienceclaw.

  • SKILL.md
  • scripts/__pycache__/run.cpython-313.pyc
  • scripts/run.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Gwas Trait To Gene next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gwas Trait To Gene compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gwas Trait To Gene this skilllamm-mit/scienceclaw246—~2.2kAutomated safety check: PassApache-2.0
Hypothesis Generationspacering-net/codeg3.9k14 repos~3.6kAutomated safety check: NotesMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Nature Paper CardYuan1z0825/nature-skills47k2 repos~2.1kAutomated safety check: PassApache-2.0
Content Research Writerweapp-tailwindcss/weapp-tailwindcss1.9k25 repos~3.5kAutomated safety check: PassMIT
Last30daysmvanhorn/last30days-skill64k—~7.9kAutomated safety check: NotesMIT

Similar skills

  • Hypothesis Generation

    spacering-net/codeg

    Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

    3.9k GitHub starsUsed in 14 repos~3.6k tokens
    Research & ScienceAuto-check: notes
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed
  • Content Research Writer

    weapp-tailwindcss/weapp-tailwindcss

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.

    1.9k GitHub starsUsed in 25 repos~3.5k tokens
    Research & ScienceAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated yesterday
    Research & ScienceAuto-check: notes
  • Peer Review

    spacering-net/codeg

    Structured manuscript/grant review with checklist-based evaluation.

    3.9k GitHub starsUsed in 17 repos~5.9k tokens
    Research & ScienceAuto-check: notes

More from lamm-mit/scienceclaw

All 86 skills in this repo
  • Fred Economic Data

    lamm-mit/scienceclaw

    Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources.

    246 GitHub starsUsed in 4 repos~3k tokens
    Auto-check passed
  • Drug Research

    lamm-mit/scienceclaw

    Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.

    246 GitHub starsUsed in 3 repos~1.7k tokens
    Auto-check passed
  • Imaging Data Commons

    lamm-mit/scienceclaw

    Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.

    246 GitHub starsUsed in 5 repos~11k tokens
    Auto-check passed
  • Rowan

    lamm-mit/scienceclaw

    Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.

    246 GitHub starsUsed in 4 repos~3.1k tokens
    Auto-check: warnings
  • Infographics

    lamm-mit/scienceclaw

    Create professional infographics using Nano Banana Pro AI with smart iterative refinement.

    246 GitHub starsUsed in 6 repos~4.4k tokens
    Auto-check: notes
  • Disease Research

    lamm-mit/scienceclaw

    Generate comprehensive disease research reports using 100+ ToolUniverse tools.

    246 GitHub stars~946 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Gwas Trait To Gene

What does Gwas Trait To Gene do?

ToolUniverse workflow — Gwas Trait To Gene. An agent skill from lamm-mit/scienceclaw. Gwas Trait To Gene is an agent skill from lamm-mit/scienceclaw.

When should I use Gwas Trait To Gene?

Gwas Trait To Gene fits situations like: research & Science work in your project.

How do I install Gwas Trait To Gene in Claude Code?

Run `npx skills add lamm-mit/scienceclaw --skill gwas-trait-to-gene -a claude-code`. Or copy the skill folder (skills/gwas-trait-to-gene in lamm-mit/scienceclaw) into .claude/skills/gwas-trait-to-gene in your project. Claude Code loads it when a task matches its description.

How do I install Gwas Trait To Gene in Codex?

Run `npx skills add lamm-mit/scienceclaw --skill gwas-trait-to-gene -a codex`. Or copy the skill folder (skills/gwas-trait-to-gene in lamm-mit/scienceclaw) into .agents/skills/gwas-trait-to-gene in your project. Codex loads it when a task matches its description.

Can I use Gwas Trait To Gene in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lamm-mit/scienceclaw --skill gwas-trait-to-gene -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gwas-trait-to-gene, .gemini/skills/gwas-trait-to-gene, .github/skills/gwas-trait-to-gene and .opencode/skills/gwas-trait-to-gene in your project.

What does Gwas Trait To Gene need to run?

Going by SKILL.md and its folder, Gwas Trait To Gene needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Gwas Trait To Gene access the network?

SKILL.md names 2 domains. As links in the text: ebi.ac.uk and genetics.opentargets.org. This is read from the text; nothing was executed.

Is Gwas Trait To Gene safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Gwas Trait To Gene use?

Gwas Trait To Gene is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gwas Trait To Gene use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gwas Trait To Gene?

Skills that share tags, products or a category with Gwas Trait To Gene: Hypothesis Generation (spacering-net/codeg, 3.9k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars), Nature Paper Card (Yuan1z0825/nature-skills, 47k stars) and Content Research Writer (weapp-tailwindcss/weapp-tailwindcss, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gwas Trait To Gene?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 246 GitHub stars. The repository holds 86 skills in this directory. The repository was last updated on August 21, 2026.

Source: lamm-mit/scienceclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.