ClinVar Database Integration

소개

This skill enables developers and bioinformaticians to interface seamlessly with the NCBI ClinVar database, a central archive for relationships between human genetic variants and phenotypes. It provides comprehensive guidance for searching variants by gene or condition, interpreting standardized pathogenicity classifications (such as Pathogenic, Benign, or VUS), and accessing data via the E-utilities API or bulk FTP downloads. Whether you are annotating VCF files for clinical pipelines or resolving conflicting variant interpretations using star-rating review statuses, this skill streamlines complex genomic data workflows within Claude.

주요 기능

• Conflict resolution strategies based on review status and expert panel ratings
• Programmatic access via NCBI E-utilities API (esearch, esummary, efetch)
• Bulk data processing support for XML, VCF, and tab-delimited formats
• Standardized pathogenicity interpretation using ACMG/AMP guidelines
• Automated VCF annotation and filtering using bcftools integration
• 81 GitHub stars

사용 사례

• Annotating genomic variant call sets with clinical significance and review status
• Building local bioinformatics pipelines for variant discovery and validation
• Automating the retrieval of pathogenic variants for specific hereditary conditions