Folklore

Folklore automates ACMG/AMP 2015 variant classification using a deterministic, rule-based Bayesian point-based framework with BayesDel ClinGen SVI-calibrated thresholds for clinical genetics laboratories.

Key Features:

• Bayesian Classification Framework: Implements the Tavtigian et al. 2018 Bayesian point-based framework with Pejaver et al. 2022 BayesDel ClinGen SVI-calibrated thresholds for deterministic variant interpretation.
• Multi-Database Integration: Integrates 8 reference databases including gnomAD v4.1, ClinVar, dbNSFP 4.9c, SpliceAI, gnomAD Constraint, HPO, ClinGen, and Ensembl VEP.
• Comprehensive Variant Analysis: Analyzes nuclear and mitochondrial DNA variants, structural variants, and copy-number variants (SV/CNV) with trio/family and cohort analysis capabilities.
• Phenotype and Literature Integration: Supports HPO-based phenotype matching and biomedical literature mining across 2M+ PubMed publications.
• Structured Reporting: Generates structured clinical reports with AI-assisted evidence synthesis without AI making final classification decisions.
• Public MCP Adapter: Provides a read-only Model Context Protocol adapter giving AI clients structured access to public germline variant evidence, automated ACMG/AMP decision support, provenance, and related literature without patient, phenotype, family, or case context.

Scientific Applications:

• Clinical Variant Interpretation: Automates germline variant classification in clinical genetics laboratories following ACMG/AMP 2015 guidelines.
• Multimodal Variant Assessment: Supports interpretation of single nucleotide variants, indels, structural variants, and copy-number variants across nuclear and mitochondrial genomes.
• Family-Based Analysis: Enables trio and family-based variant interpretation for inheritance pattern assessment.
• Cohort Analysis: Supports analysis across patient cohorts for research and diagnostic applications.
• AI-Assisted Evidence Review: Facilitates literature mining and evidence synthesis to support human classification decisions.

Methodology:

Deterministic rule-based interpretation using a Bayesian point-based framework with BayesDel ClinGen SVI-calibrated thresholds; integrates evidence from 8 reference databases and biomedical literature mining across 2M+ PubMed publications.