What is the primary purpose of the ClinVar Database skill?

The skill allows Claude to help users query and interpret human genetic variant data from NCBI ClinVar, specifically focusing on clinical significance and pathogenicity.

Does this skill support programmatic access to ClinVar?

Yes, it includes detailed instructions and code snippets for using NCBI's E-utilities API via curl, Python, and Biopython, including rate limit management.

Can I use this skill to automate VCF file annotation?

Absolutely. It provides examples using bcftools and Python libraries like PyVCF to add clinical significance metadata directly to your variant files.

What should I do if a variant has conflicting interpretations?

The skill provides a multi-step resolution strategy, including checking review star ratings, examining submission dates, and prioritizing expert panel classifications.

How does the skill handle different genome builds?

It provides specific workflows and FTP paths for both GRCh37 and GRCh38 genome builds to ensure compatibility with various genomic pipelines.

ClinVar Database Integration

Name: ClinVar Database Integration
Author: Microck

byMicrock

•

数据科学与机器学习

Queries and interprets NCBI ClinVar data for human genetic variant pathogenicity and clinical significance.

This skill provides expert guidance for interacting with the NCBI ClinVar archive, a critical resource for genomic medicine that tracks relationships between human genetic variants and phenotypes. It enables Claude to assist with complex genomic tasks, including searching by gene or condition, interpreting ACMG/AMP pathogenicity classifications, and utilizing technical access methods such as the NCBI E-utilities API or bulk FTP downloads. It is an essential tool for bioinformaticians and researchers needing to automate variant annotation, resolve conflicting interpretations, and build robust genomic data pipelines.

主要功能

01Advanced querying by gene, clinical significance, or condition via web and API

0281 GitHub stars

03Standardized interpretation of ACMG/AMP pathogenicity classifications and star ratings

04Programmatic access templates for NCBI E-utilities (esearch, esummary, efetch)

05Bulk data processing workflows for XML, VCF, and tab-delimited formats

06Strategies for resolving conflicting variant interpretations and tracking updates

使用场景

01Constructing local genomic databases from monthly ClinVar XML and FTP releases

02Annotating variant call sets (VCFs) with clinical significance and review status

03Automating the identification of high-confidence pathogenic variants for specific diseases

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microck/ordinary-claude-skills clinvar-database

For use in Claude.ai and ChatGPT

Download Skill