NetDiseaseSNP

NetDiseaseSNP predicts the pathogenic potential of non-synonymous single nucleotide polymorphisms (nsSNPs) by integrating sequence conservation and structural features to classify and prioritize variants, including discrimination of cancer driver versus passenger mutations.

Key Features:

• Sequence conservation-based prediction: Uses the SIFT algorithm's alignment generation capabilities to identify homologous sequences across species and assess evolutionary conservation of nsSNP positions.
• Feature integration: Integrates 31 distinct features evaluating sequence conservation and predicted surface accessibility to generate evidence for each variant.
• Ranking system: Combines the integrated features into a single score to rank nsSNPs by likelihood of being disease-causing.
• Cancer mutation discrimination: Distinguishes cancer driver mutations from passenger mutations to prioritize oncogenic variants.
• Performance benchmarking: Benchmarked against other state-of-the-art methods and reported superior performance on disease/neutral nsSNP and cancer driver/passenger mutation datasets.

Scientific Applications:

• Genetic disease research: Identifies nsSNPs with potential pathogenicity to support discovery of disease-associated variants.
• Cancer genomics: Highlights mutations likely to act as cancer drivers for tumorigenesis studies.
• Personalized medicine: Prioritizes nsSNPs for downstream validation to inform individualized therapeutic strategies.

Methodology:

Generates SIFT alignments to assess conservation, computes 31 features including predicted surface accessibility, and integrates them into a single score used to classify and rank nsSNPs and to discriminate cancer driver versus passenger mutations.