CNV-Hub: an integrated web-based platform for CNV classification and interpretation using multi-algorithm consensus

Area of Science:

• Genomic Medicine
• Molecular Cytogenetics
• Bioinformatics

Background:

• Copy number variations (CNVs) are significant causes of rare genetic diseases.
• Interpreting CNVs involves complex analysis of gene content, regulatory elements, and syndrome associations, often requiring consultation of multiple databases and guidelines.
• Existing interpretation methods are time-consuming and require specialized expertise.

Purpose of the Study:

• To develop a streamlined, web-based platform, CNV-Hub, for efficient and accurate classification and interpretation of CNVs.
• To integrate diverse analytical approaches, including established guidelines and machine learning, into a single tool.
• To reduce the time and complexity associated with CNV analysis in clinical settings.

Main Methods:

• Development of CNV-Hub, a web-based platform integrating five CNV analysis algorithms.
• Inclusion of algorithms based on American College of Medical Genetics (ACMG) recommendations (AnnotSV, ClassifyCNV).
• Integration of machine learning algorithms (X-CNV, ISV) and a custom algorithm based on French guidelines.
• Provision of automated pathogenicity predictions, gene dosage sensitivity scores (pHaplo, pTriplo), syndrome associations, and links to external databases (OMIM, PubMed).

Main Results:

• CNV-Hub provides automated pathogenicity predictions and comprehensive annotations for CNVs.
• The platform integrates multiple algorithms, including machine learning, to enhance the interpretation of uncertain variants.
• User-friendly interface facilitates rapid, evidence-based evaluation of CNVs.

Conclusions:

• CNV-Hub significantly reduces the time required for CNV analysis while maintaining accuracy and reliability.
• The platform supports geneticists in clinical decision-making by providing a comprehensive and efficient tool for CNV interpretation.
• CNV-Hub represents a substantial advancement in molecular cytogenetics, improving the diagnostic yield for rare genetic diseases caused by CNVs.