Can I download the entire ClinVar database?

Yes, the skill provides automation patterns for downloading bulk data from the NCBI FTP site in XML, VCF, and tab-delimited formats.

Does this skill support both GRCh37 and GRCh38?

Yes, it includes instructions for downloading and processing ClinVar data mapped to both major human genome assemblies.

Can I use this skill to annotate VCF files?

Yes, the skill provides specific workflows using bcftools and Python to annotate variant call sets with ClinVar clinical significance and metadata.

How do I handle conflicting variant interpretations?

The skill guides you through a resolution strategy based on star ratings (review status), submission dates, and expert panel classifications.

Is an API key required for programmatic access?

While not strictly required, the skill recommends using an NCBI API key to increase the E-utilities rate limit from 3 to 10 requests per second.

ClinVar Genomic Database

Name: ClinVar Genomic Database
Author: lifangda

bylifangda

•

数据科学与机器学习

Queries and interprets NCBI ClinVar data to evaluate human genetic variants and their clinical significance.

This skill provides a comprehensive toolkit for accessing and analyzing the NCBI ClinVar database, the primary archive for human genetic variation and phenotype relationships. It enables users to perform complex variant searches, interpret ACMG/AMP pathogenicity classifications, and automate data retrieval through E-utilities APIs or bulk FTP downloads. Whether you are annotating VCF files for a genomic pipeline or resolving conflicting variant interpretations, this skill provides the domain-specific guidance and implementation patterns needed for professional genomic medicine and research workflows.

主要功能

01Advanced ClinVar searching by gene, condition, or clinical significance

02Programmatic access via NCBI E-utilities API and Biopython integration

03Automated VCF annotation and filtering using bcftools and Python

04Standardized interpretation of pathogenicity classifications and star ratings

05Bulk data processing from FTP sites in XML, VCF, and tab-delimited formats

0616 GitHub stars

使用场景

01Annotating patient variant call sets (VCF) with clinical pathogenicity data

02Building local genomic databases for research pipelines using monthly ClinVar releases

03Resolving conflicting variant interpretations through review status and evidence analysis

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add lifangda/claude-plugins clinvar-database

For use in Claude.ai and ChatGPT

Download Skill