Is an API key required for NCBI E-utilities?

An API key is not required for basic use but is recommended for automation, as it increases the rate limit from 3 to 10 requests per second.

How does this skill access ClinVar data?

It provides patterns for accessing data via the NCBI E-utilities API, the public FTP site for bulk downloads, and structured web search queries for targeted variant identification.

Can it help with VCF annotation?

Yes, it includes specific command-line and Python-based code patterns for annotating VCF files using tools like bcftools, PyVCF, and pandas for rapid clinical analysis.

Does this skill support both GRCh37 and GRCh38 builds?

Yes, the skill provides specific instructions for downloading and processing the correct ClinVar VCF datasets for both major human genome assembly builds.

What do the ClinVar star ratings signify?

The star ratings (0 to 4) represent the review status and level of confidence in a variant classification, ranging from single submissions with no criteria to expert panel reviews and practice guidelines.

ClinVar Genomic Database Assistant

Name: ClinVar Genomic Database Assistant
Author: Microck

byMicrock

•

数据科学与机器学习

Interfaces with NCBI ClinVar to query, interpret, and process human genetic variant clinical significance data for genomic medicine.

关于

This skill empowers Claude to act as a specialized assistant for genomic research and clinical genetics by providing deep integration with the NCBI ClinVar database. It enables users to perform complex variant searches, interpret pathogenicity classifications based on ACMG/AMP guidelines, navigate E-utilities APIs, and process large-scale genomic files like VCFs and XML releases. Whether you are annotating variant call sets, resolving conflicting interpretations, or automating bulk data downloads via FTP, this skill provides the domain-specific logic and implementation patterns necessary for high-accuracy genomic data analysis and bioinformatics workflow development.

主要功能

Resolution strategies for conflicting variant interpretations and star ratings
Guidance for processing VCF, XML, and tab-delimited genomic data formats
Query ClinVar via E-utilities API and advanced web interface patterns
Automated workflows for VCF annotation and bulk FTP data retrieval
Standardized interpretation of clinical significance (Pathogenic, Benign, VUS)
81 GitHub stars

使用场景

Annotating clinical variant call sets (VCF) with pathogenicity and review status
Building bioinformatics pipelines that integrate real-time ClinVar API data
Automating the retrieval of pathogenic variant lists for specific genes or conditions

关于

主要功能

Resolution strategies for conflicting variant interpretations and star ratings
Guidance for processing VCF, XML, and tab-delimited genomic data formats
Query ClinVar via E-utilities API and advanced web interface patterns
Automated workflows for VCF annotation and bulk FTP data retrieval
Standardized interpretation of clinical significance (Pathogenic, Benign, VUS)
81 GitHub stars

使用场景

Annotating clinical variant call sets (VCF) with pathogenicity and review status
Building bioinformatics pipelines that integrate real-time ClinVar API data
Automating the retrieval of pathogenic variant lists for specific genes or conditions