Predicting functional consequences of mutations using molecular interaction network features.

Area of Science:

• Genomics
• Computational Biology
• Bioinformatics

Background:

• Interpreting missense variants is crucial for precision medicine but challenging.
• Existing tools focus on protein sequence and structure, neglecting cellular context.

Purpose of the Study:

• To develop and evaluate network-based annotations for missense variant interpretation.
• To improve in silico variant effect prediction by integrating protein structure and interaction data.

Main Methods:

• Developed 16 novel network-based annotations for missense mutations.
• Integrated protein structure and interaction data.
• Evaluated annotations using a machine-learning framework on benchmark datasets.

Main Results:

• Network features provided orthogonal information to traditional variant prioritization methods.
• The approach significantly improved variant classification accuracy.
• Somatic mutations showed larger performance gains than germline variants.

Conclusions:

• Modeling variant potential to perturb context-specific interactome networks is a promising strategy.
• Network-based approaches enhance in silico variant effect prediction for precision medicine.
• Understanding cellular constraints is key for interpreting variant effects.