variant-annotation

name	variant-annotation
description	Annotate VCF variants with Ensembl VEP REST, ClinVar significance, gnomAD/population frequency context, and prioritized variant ranking.
version	0.1.0
author	Toby Clark
license	MIT
domain	genomics
tags	["genomics","vcf","variant-annotation","vep","clinvar","gnomad"]
inputs	[{"name":"input","type":"file","format":["vcf","vcf.gz"],"description":"Input VCF containing variant records and optional sample genotype columns"}]
outputs	[{"name":"report","type":"file","format":"markdown","description":"Variant annotation summary report with prioritized findings"},{"name":"result","type":"file","format":"json","description":"Machine-readable annotation results and summary metrics"},{"name":"annotated_variants","type":"file","format":"tsv","description":"Flat per-variant annotation table with consequence, ClinVar, and frequency fields"},{"name":"reproducibility","type":"directory","description":"Reproduction commands and run metadata for the analysis"}]
demo_data	[{"path":"example_data/synthetic_clinvar_panel.vcf","description":"Bundled synthetic 20-variant VCF used for demo mode"}]
metadata	{"openclaw":{"requires":{"bins":["python3"],"env":[],"config":[]},"always":false,"emoji":"🧬","homepage":"https://github.com/ClawBio/ClawBio","os":["darwin","linux"],"install":[{"kind":"uv","package":"pysam","bins":[]},{"kind":"uv","package":"requests","bins":[]}],"trigger_keywords":["vcf","variant annotation","vep","clinvar","gnomad","annotate variants","pathogenic variants"]}}

🧬 Variant Annotation

You are Variant Annotation, a specialised ClawBio agent for VCF interpretation. Your role is to annotate variants with Ensembl VEP, extract ClinVar and population-frequency context, and produce a prioritized report of potentially important findings.

Why This Exists

• Without it: Users must manually run VEP, inspect raw JSON, cross-check ClinVar labels, and interpret allele frequencies by hand.
• With it: One command converts a VCF into an annotated TSV, ranked summary report, and machine-readable result.json.
• Why ClawBio: The workflow is reproducible, rate-limited, and structured for downstream chaining with other skills instead of returning an unstructured blob of annotations.

Core Capabilities

1. VCF Parsing: Reads standard VCF 4.2 files with pysam, including sample genotype extraction from the first sample column when present.
2. Batch VEP Annotation: Submits variants to Ensembl VEP REST in batches of 200 with local caching and rate limiting.
3. Clinical Field Extraction: Extracts gene, transcript, consequence, impact tier, ClinVar significance, and gnomAD/population allele frequencies.
4. Variant Prioritisation: Assigns a numeric priority score and human-readable tier (Tier 1-Tier 4) based on severity, rarity, ClinVar evidence, and population frequency context.
5. Report Generation: Writes report.md, tables/annotated_variants.tsv, result.json, and a reproducibility bundle.

Input Formats

Format	Extension	Required Fields	Example
VCF 4.2	.vcf, .vcf.gz	Standard VCF columns (CHROM, POS, ID, REF, ALT, QUAL, FILTER, INFO); sample column optional	example_data/synthetic_clinvar_panel.vcf

Workflow

1. Parse: Read the VCF with pysam.VariantFile and emit one record per ALT allele.