AAVC: An automated framework for high-accuracy ACMG-based variant classification

Area of Science:

• Genomics
• Bioinformatics
• Medical Genetics

Background:

• Accurate classification of DNA sequence variants is crucial for clinical diagnostics and research.
• Existing automated tools often lack robust and up-to-date methodologies for variant classification according to ACMG standards.
• There is a need for advanced computational tools to interpret human germline sequence diversity.

Purpose of the Study:

• To develop and evaluate a novel automated tool, the Automated ACMG-based Variant Classifier (AAVC).
• To assess the performance of AAVC for both diagnostic and research purposes in classifying DNA sequence variants.
• To provide a more accurate and up-to-date platform for sequence variant interpretation.

Main Methods:

• The Automated ACMG-based Variant Classifier (AAVC) was developed to computationally analyze sequence variants.
• AAVC utilizes the American College of Medical Genetics and Genomics (ACMG) guidelines, ClinGen specifications, and a novel framework.
• The tool integrates large public databases and in silico prediction tools for variant analysis.

Main Results:

• AAVC achieved high concordance (94.39%) with FDA-recognized variant classifications, surpassing current tools.
• The tool successfully reclassified 55% of variants of uncertain significance (VUS) in ClinVar into clinically significant categories.
• Novel pathogenic, likely pathogenic, or VUS-high variants were identified in the Turkish Variome, with 1 in 10 individuals carrying actionable genotypes.

Conclusions:

• AAVC provides a robust framework for the accurate classification of human germline sequence diversity.
• The tool offers a highly accurate, rapid, and up-to-date platform for automated sequence variant interpretation.
• AAVC is a valuable resource for clinical laboratories and research groups engaged in genetic variant analysis.