tooluniverse-variant-to-mechanism
This skill maps the causal chain from a genetic variant to its disease mechanism by querying regulatory context, target genes, molecular pathways, and phenotypic consequences across multiple evidence layers. It combines data from 7+ databases to construct evidence-graded mechanistic narratives for GWAS hits, eQTL variants, and non-coding regulatory elements.
Tooluniverse-variant-to-mechanism traces variants through regulatory, molecular, and disease evidence to build mechanistic models.
AI-generated summary based on this skill's SKILL.md
Install
mims-harvard/ToolUniverse/tooluniverse-variant-to-mechanism · repository language: Python
git clone https://github.com/mims-harvard/ToolUniverse
cp -r ToolUniverse/skills/tooluniverse-variant-to-mechanism ~/.claude/skills/tooluniverse-variant-to-mechanismFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does rs7903146 cause type 2 diabetes?
tooluniverse-variant-to-mechanism traces rs7903146 through regulatory, molecular, and disease layers to build a mechanistic model. The skill queries multiple databases to identify which gene(s) the variant affects, retrieves eQTL evidence showing altered expression, maps downstream pathways, and synthesizes findings into a confidence-scored causal narrative linking the variant to diabetes phenotype and pathophysiology.
What is the causal gene for a GWAS locus?
tooluniverse-variant-to-mechanism identifies causal genes using eQTL and L2G (locus-to-gene) evidence. The skill cross-references 7+ databases to distinguish the likely target gene from nearby candidates, grades the strength of evidence at each step, and reports confidence scores so you can prioritize the most supported gene-variant-disease connections for functional validation.
How can I trace a non-coding variant to its disease mechanism?
tooluniverse-variant-to-mechanism connects non-coding variants to downstream pathways and phenotypic consequences by mapping their regulatory context, identifying target genes, and linking altered expression to molecular and clinical outcomes. The skill synthesizes evidence from regulatory databases, eQTL catalogs, and pathway resources to construct a mechanistic chain from variant to phenotype.
How does this variant cause disease mechanistically?
tooluniverse-variant-to-mechanism grades and synthesizes evidence from 7+ databases into a confidence-scored causal narrative. For any variant, the skill retrieves regulatory annotations, eQTL associations, target gene functions, pathway involvement, and disease phenotype links, then integrates these layers into a ranked mechanistic model that explains how the genetic change drives disease.
Can tooluniverse-variant-to-mechanism analyze intronic SNPs?
Yes. tooluniverse-variant-to-mechanism handles intronic and other non-coding variants by querying their regulatory context, identifying target genes through eQTL and enhancer-promoter interactions, and tracing functional impact downstream. The skill maps how intronic variants alter splicing, expression, or regulatory activity to affect molecular pathways and disease phenotypes.
What databases does tooluniverse-variant-to-mechanism integrate?
tooluniverse-variant-to-mechanism combines data from 7+ databases spanning regulatory annotations, eQTL catalogs, locus-to-gene predictions, pathway resources, and disease associations. This multi-database synthesis enables comprehensive evidence grading and construction of mechanistic narratives that link variants through molecular layers to phenotypic consequences with confidence scoring.
SKILL.md
rendered from the published skill — quoted content, verbatim
Variant-to-Mechanism Analysis Skill
Trace the full causal chain from a genetic variant to its disease mechanism: regulatory context, target gene(s), molecular pathways, and phenotypic consequences. Integrates 7+ databases across 3 evidence layers (regulatory, molecular, disease) to build an evidence-graded mechanistic model.
IMPORTANT: Always use English terms in tool calls. Respond in the user's language.
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess.
When to Use This Skill
Apply when users: - Ask "how does rs7903146 cause
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/tooluniverse-variant-to-mechanism/SKILL.md