AggreRATE-Pred

AggreRATE-Pred predicts changes in protein aggregation rates caused by single-point amino acid mutations using a linear regression model trained on experimentally measured aggregation data.

Key Features:

• Mutation-Induced Aggregation Prediction: Estimates changes in protein aggregation rates resulting from single amino acid substitutions.
• Linear Regression Model: Implements a statistical model to correlate sequence mutations with experimentally observed aggregation rate changes.
• Experimentally Derived Training Data: Uses a dataset of 183 unique single-point mutations across 23 polypeptides and proteins for model development.
• Refined Predictive Model: Improves prediction accuracy by filtering training data based on protein length and conformational characteristics at mutation sites.

Scientific Applications:

• Protein Aggregation Studies: Evaluates the impact of amino acid substitutions on protein aggregation propensity.
• Disease Mechanism Research: Supports investigation of aggregation-related diseases including Alzheimer's disease, Parkinson's disease, Huntington's disease, type II diabetes, and corneal dystrophy.
• Protein Engineering: Assesses mutation effects on aggregation in recombinant proteins, monoclonal antibodies, industrial enzymes, and vaccines.

Methodology:

AggreRATE-Pred applies a linear regression model trained on experimentally measured aggregation-rate changes from 183 single-point mutations across 23 proteins and refines predictions using protein length and conformational characteristics at mutation sites.