PROVEAN

PROVEAN predicts the functional impact of protein sequence variants—including single amino-acid substitutions, in-frame insertions, deletions, and multiple amino-acid changes—to prioritize variants likely to alter protein function.

Key Features:

• Alignment-based scoring: Quantifies the change in sequence similarity between a variant-containing query protein and a set of homologous protein sequences.
• Support for multiple variant types: Evaluates single amino-acid substitutions, in-frame insertions, deletions, and multiple amino-acid changes.
• Variant prioritization: Separates potentially disease-associated variants from common polymorphisms using its similarity-change score.
• Reported predictive performance: Achieves a reported area under the ROC curve (AUC) of ~0.85 on human and non-human protein variation benchmarks.
• Wide applicability: Supports variant prioritization across diverse datasets, including large-scale studies aimed at narrowing candidate causal variants underlying disease phenotypes and interrogating protein function.

Scientific Applications:

• Variant prioritization in genomics and proteomics: Prioritizes protein-coding variants from next-generation sequencing and proteomics datasets that may affect biological function.
• Pathogenicity identification: Identifies potentially pathogenic variants for downstream investigation.
• Genotype–phenotype interpretation and hypothesis generation: Aids interpretation of genotype–phenotype relationships and generates hypotheses for functional validation and therapeutic targeting.

Methodology:

Computes an alignment-based score by measuring the change in sequence similarity between the variant-containing query protein and a set of homologous protein sequences.