Agent Skill: Clinical VCF Variant Prioritization & VEP Skill
📌 Description
Parses multi-sample VCF files, queries Ensembl VEP REST API, filters ClinVar pathogenicity ratings, and maps driver mutations to FDA targeted drugs.
🤖 Agent Execution Protocol
When an AI Agent is tasked with ensembl-vep-variant-annotator:
- Input Validation: Verify that the required input files or coordinates are supplied.
- Environment Check: Ensure dependencies (
PyVCF, Ensembl VEP API, ClinVar, Open Targets) are installed. - Execution: Run the protocol pipeline snippet below.
- Output Generation: Produce actionable Markdown/JSON summaries with publication figures.
💻 Protocol Code Snippet
import requests
def query_vep_variant(chrom, pos, ref, alt):
url = f"https://rest.ensembl.org/vep/human/region/{chrom}:{pos}-{pos}:1/{alt}?content-type=application/json"
r = requests.get(url)
return r.json() if r.status_code == 200 else {}
📥 Input & Output Specifications
Input Contract
- Target Files: Valid input data matching domain formats.
- Parameters: Quality thresholds and cutoffs.
Output Contract
- Results Table: Structured summary dataframe or matrix.
- Visualization: Rendered SVG/PNG figures.
📄 License
Distributed under the MIT License. See LICENSE for details.