Calibrated confidence layer for variant-effect pathogenicity (AlphaMissense/ESM-1v/EVE)
-
Updated
Jul 18, 2026 - Python
Calibrated confidence layer for variant-effect pathogenicity (AlphaMissense/ESM-1v/EVE)
CLI tool that batch-scores VCF variants against AlphaGenome and generates interpretable multi-modal effect reports.
Score DNA variants from a VCF with Evo 2 (via NVIDIA’s hosted API). Exploratory, research use only.
Calibrates six MaveDB assay score sets against ClinVar labels: pre-registered AUCs and OddsPath evidence strength with bootstrap intervals.
MCP server for MaveDB: quantitative variant-effect scores from Multiplexed Assays of Variant Effect (MAVE) and deep mutational scanning — functional evidence as typed tools for LLM agents.
To associate your repository with the variant-effect topic, visit your repo's landing page and select "manage topics."