Can this skill help with ACMG/AMP guidelines?

Yes, it provides standardized mapping of ClinVar terminology to ACMG/AMP classifications such as Pathogenic, Likely Pathogenic, and Uncertain Significance (VUS).

How are conflicting variant interpretations handled?

It implements a resolution strategy that prioritizes expert panel reviews (star ratings) and recent submission dates to help identify the most reliable clinical classification.

Does this skill require an NCBI API key?

An API key is not strictly required but highly recommended. The skill provides guidance on using keys to increase your rate limit from 3 to 10 requests per second.

How does this skill handle different genomic coordinates?

The skill supports both GRCh37 and GRCh38 builds, providing specific patterns for downloading and annotating variants in standard VCF formats for both assemblies.

Can I use this for bulk data analysis instead of single queries?

Yes, the skill includes optimized workflows for handling multi-GB XML releases and tab-delimited summaries directly from the NCBI FTP server using pandas and command-line tools.

ClinVar Database Integration

Name: ClinVar Database Integration
Author: ricable

byricable

•

数据科学与机器学习

Queries NCBI ClinVar to retrieve and interpret clinical significance data for human genetic variants.

关于

This skill provides a specialized interface for interacting with NCBI's ClinVar database, the primary archive for human genetic variation and its relationship to health. It enables researchers and developers to programmatically search variants via E-utilities API, process bulk datasets from FTP servers, and annotate VCF files with clinical pathogenicity classifications. By automating the interpretation of ACMG/AMP guidelines and star-rated evidence levels, it streamlines genomic medicine workflows and helps resolve conflicting variant interpretations within bioinformatics pipelines.

主要功能

Automated interpretation of pathogenicity classifications and star-rated review status
Heuristics for resolving conflicting variant interpretations and tracking classification updates
VCF file annotation and filtering integration with bcftools and Python
1 GitHub stars
Programmatic access to NCBI E-utilities API for searching and fetching records
Bulk data processing from FTP in XML, VCF, and tab-delimited formats

使用场景

Automating the retrieval of pathogenic variants for specific genes like BRCA1 or CFTR
Annotating genomic variant call sets (VCF) with clinical significance data for diagnostic research
Building and maintaining local bioinformatics databases by parsing monthly ClinVar XML releases

关于

主要功能

Automated interpretation of pathogenicity classifications and star-rated review status
Heuristics for resolving conflicting variant interpretations and tracking classification updates
VCF file annotation and filtering integration with bcftools and Python
1 GitHub stars
Programmatic access to NCBI E-utilities API for searching and fetching records
Bulk data processing from FTP in XML, VCF, and tab-delimited formats

使用场景

Automating the retrieval of pathogenic variants for specific genes like BRCA1 or CFTR
Annotating genomic variant call sets (VCF) with clinical significance data for diagnostic research
Building and maintaining local bioinformatics databases by parsing monthly ClinVar XML releases