From mims-harvard-tooluniverse
Interprets GWAS SNPs by rsID: aggregates variant annotations, trait associations, fine-mapping evidence, locus-to-gene predictions, and clinical significance from GWAS Catalog, Open Targets Genetics, ClinVar.
npx claudepluginhub joshuarweaver/cascade-data-analytics --plugin mims-harvard-tooluniverseThis skill uses the workspace's default tool permissions.
**SNP interpretation**: a GWAS hit is a REGION, not a single causal variant. The lead SNP may not be causal — it may be in LD with the causal variant. Always check LD structure and functional annotation before concluding a specific SNP is mechanistically responsible. Fine-mapping (SuSiE, FINEMAP credible sets) narrows the causal set but rarely identifies a single variant with certainty. L2G sco...
Conducts multi-round deep research on GitHub repos via API and web searches, generating markdown reports with executive summaries, timelines, metrics, and Mermaid diagrams.
Dynamically discovers and combines enabled skills into cohesive, unexpected delightful experiences like interactive HTML or themed artifacts. Activates on 'surprise me', inspiration, or boredom cues.
Generates images from structured JSON prompts via Python script execution. Supports reference images and aspect ratios for characters, scenes, products, visuals.
SNP interpretation: a GWAS hit is a REGION, not a single causal variant. The lead SNP may not be causal — it may be in LD with the causal variant. Always check LD structure and functional annotation before concluding a specific SNP is mechanistically responsible. Fine-mapping (SuSiE, FINEMAP credible sets) narrows the causal set but rarely identifies a single variant with certainty. L2G scores integrate eQTL, chromatin interaction, and distance data to predict the causal gene — a lead SNP mapping to gene A may actually regulate gene B 500 kb away via a distal enhancer.
LOOK UP DON'T GUESS: never assume a SNP's functional consequence, mapped gene, or population frequency — always call gwas_get_snp_by_id and OpenTargets_get_variant_info to retrieve current annotations.
Interpret genetic variants (SNPs) from GWAS studies by aggregating evidence from multiple sources to provide comprehensive clinical and biological context.
Use Cases:
The skill provides a comprehensive interpretation of SNPs by:
User Input: rs7903146
↓
[1] SNP Lookup
→ Get location, consequence, MAF
→ gwas_get_snp_by_id
↓
[2] Association Search
→ Find all trait/disease associations
→ gwas_get_associations_for_snp
↓
[3] Fine-Mapping (Optional)
→ Get credible set membership
→ OpenTargets_get_variant_credible_sets
↓
[4] Gene Predictions
→ Extract L2G scores for causal genes
→ (embedded in credible sets)
↓
[5] Clinical Summary
→ Aggregate evidence
→ Identify key traits and genes
↓
Output: Comprehensive Interpretation Report
rs_id (str): dbSNP rs identifier
include_credible_sets (bool, default=True): Query fine-mapping data
p_threshold (float, default=5e-8): Genome-wide significance thresholdmax_associations (int, default=100): Maximum associations to retrieveReturns SNPInterpretationReport containing:
{
'rs_id': 'rs7903146',
'chromosome': '10',
'position': 112998590,
'ref_allele': 'C',
'alt_allele': 'T',
'consequence': 'intron_variant',
'mapped_genes': ['TCF7L2'],
'maf': 0.293
}
[
{
'trait': 'Type 2 diabetes',
'p_value': 1.2e-128,
'beta': '0.28 unit increase',
'study_id': 'GCST010555',
'pubmed_id': '33536258',
'effect_allele': 'T'
},
...
]
[
{
'study_id': 'GCST90476118',
'trait': 'Renal failure',
'finemapping_method': 'SuSiE-inf',
'p_value': 3.5e-42,
'predicted_genes': [
{'gene': 'TCF7L2', 'score': 0.863}
],
'region': '10:112950000-113050000'
},
...
]
Genome-wide significant associations with 100 traits/diseases:
- Type 2 diabetes
- Diabetic retinopathy
- HbA1c levels
...
Identified in 20 fine-mapped loci.
Predicted causal genes: TCF7L2
See QUICK_START.md for platform-specific examples.
gwas_get_snp_by_id: Get SNP annotationgwas_get_associations_for_snp: Get all trait associationsOpenTargets_get_variant_info: Get variant details with population frequenciesOpenTargets_get_variant_credible_sets: Get fine-mapping credible sets with L2Ginclude_credible_sets=True for clinical decisions