docs/DATASETS.md

Dataset Library

Generated — do not edit by hand.

protein_controls

• Category: protein
• Type: curated · date 2026-01-15 · version 1
• Records: 3
• Description: Curated positive/negative control proteins for BLAST and interpretation engines.
• Citation: UniProt curated annotations (2026_01 release); verified manually for BioNexus demos.

clinical_variants

• Category: genomics
• Type: curated · date 2026-01-20 · version 1
• Records: 4
• Description: Small curated variant interpretation set (HGVS) for NGS/evidence engine truth checks.
• Citation: HGMD/ClinVar curated examples (pathogenic/benign anchors); simplified for demonstration.