ACMG variant classification software
ACMG variant classification software for clinical genomics
Folklore turns germline VCF data into annotated, five-tier ACMG/AMP classification proposals with criterion-level evidence prepared for qualified professional review.
Ensembl VEP annotation and governed population, clinical, computational, and gene-level evidence feed deterministic ACMG/AMP rules. AI-generated text does not determine the class, and the software does not provide a diagnosis.
What is ACMG variant classification software?
ACMG variant classification software helps genetics teams apply the ACMG/AMP framework consistently by assembling relevant evidence, proposing eligible criterion codes and strengths, and recording how a five-tier result was reached. It supports, but does not replace, professional interpretation or clinical sign-out.
Core Capabilities
Move from VCF analysis to a reviewable classification proposal without separating annotation, rule evaluation, and evidence provenance across different tools.
VCF Processing
Process VCF inputs from whole-genome, whole-exome, and targeted-panel workflows while retaining the variant and quality context needed for analysis.
Multi-Source Annotation
Use Ensembl VEP for consequence annotation and combine governed evidence from ClinVar, gnomAD, ClinGen, dbNSFP, and supported computational predictors with source provenance.
Rule-Based ACMG/AMP Classification
Evaluate eligible ACMG/AMP criteria under the deployed rule set and produce one of five classes. Criteria that depend on family, functional, segregation, or other reviewed evidence are not assigned automatically.
Audit Trail
Record each proposed criterion with its evidence source, strength, safeguards, and classifier version so a qualified reviewer can confirm or change it with a rationale.
Technical Foundation
The classification pipeline queries the genomic and clinical resources listed below for each variant.
Ensembl VEP
Variant effect prediction, consequence, protein impact
ClinVar
Clinical variant interpretations and review status
gnomAD
Population allele frequencies (global and population-specific)
ClinGen
Gene-disease validity and dosage sensitivity
dbNSFP
Aggregated functional predictions across 12+ tools
AlphaMissense
Missense pathogenicity prediction (DeepMind)
SpliceAI
Splice site impact prediction
BayesDel
Meta-predictor with ClinGen SVI-calibrated thresholds
GERP++ / PhyloP / PhastCons
Evolutionary conservation
pLI / LOEUF / o/e
Gene-level constraint metrics
ACMG/AMP evidence framework
The groups below summarize the 2015 ACMG/AMP evidence framework. Folklore proposes only criteria supported by the available governed evidence and deployed safeguards; review-dependent criteria require qualified assessment.
PVS1
Very Strong Pathogenic
- PVS1, Null variant in gene with established LOF mechanism
PS1–PS4
Strong Pathogenic
- PS1, Same amino acid change as established pathogenic
- PS2, De novo (paternity and maternity confirmed)
- PS3, Functional studies showing damaging effect
- PS4, Significantly increased prevalence in affected individuals
PM1–PM6
Moderate Pathogenic
- PM1, Mutational hot spot or critical functional domain
- PM2, Absent or extremely low frequency in population databases
- PM3, Detected in trans with a pathogenic variant (recessive)
- PM4, Protein length changes (in-frame indels, stop-loss)
- PM5, Novel missense at residue with different pathogenic change
- PM6, Assumed de novo without confirmation of paternity/maternity
PP1–PP5
Supporting Pathogenic
- PP1, Cosegregation with disease in multiple affected family members
- PP2, Missense in gene with low rate of benign missense variants
- PP3, Multiple computational lines of evidence support deleterious effect
- PP4, Patient phenotype highly specific for the gene
- PP5, Reputable source reports as pathogenic
BA1
Stand-alone Benign
- BA1, Allele frequency above 5% in population databases
BS1–BS4
Strong Benign
- BS1, Allele frequency greater than expected for disease
- BS2, Observed in healthy adults (recessive, dominant, X-linked)
- BS3, Functional studies showing no damaging effect
- BS4, Lack of segregation in affected family members
BP1–BP7
Supporting Benign
- BP1, Missense in gene where only truncating cause disease
- BP2, Observed in trans with pathogenic (dominant) or in cis
- BP3, In-frame indel in repetitive region without known function
- BP4, Multiple computational lines of evidence suggest no impact
- BP5, Variant found in case with alternate molecular basis
- BP6, Reputable source reports as benign
- BP7, Synonymous with no predicted splice impact and conserved
What You Receive
The output keeps the proposed class, criterion-level evidence, and review context together. It supports interpretation and prioritization but does not replace diagnosis or clinical sign-out.
Classified Variant Table
Supported variants receive a five-tier ACMG/AMP classification proposal with an explicit list of the criteria and strengths used.
Evidence Detail Per Variant
Review population frequencies, ClinVar assertions, computational predictions, conservation, and gene constraint alongside their source context.
Criteria Audit Trail
Inspect the evidence, threshold, strength, and safeguards behind each proposed criterion, including strength-modified codes such as PM2 Supporting.
Confidence Scoring
A confidence indicator can help order review. It is not a probability of pathogenicity and does not replace assessment of the underlying evidence.
Classify and review variant evidence
Create an account for case-based VCF analysis, or search one public GRCh38 germline variant without entering patient or case information. Review a worked ACMG/AMP example with dated public evidence.