AnOxPePred

AnOxPePred predicts the antioxidative properties of peptides using convolutional neural networks (CNNs) to identify sequences with free-radical scavenging and metal ion-chelating activities.

Key Features:

• Deep Learning Approach: Convolutional neural network trained on a curated dataset of experimentally validated antioxidative and non-antioxidative peptides.
• Activity Prediction: Assesses peptide activities including free-radical scavenging and metal ion chelation.
• Performance Metrics: Demonstrates superior predictive performance compared to k-nearest neighbors (k-NN) sequence identity-based methods.
• Sequence Pattern Recognition: Utilizes CNNs to capture complex patterns within peptide sequences that correlate with antioxidative potential.

Scientific Applications:

• Food Industry: Aids identification of peptide-based natural preservatives by predicting antioxidative properties that could replace synthetic additives.
• Healthcare Research: Supports discovery of peptides with antioxidant capabilities for research into mitigating oxidative stress-related conditions.

Methodology:

A convolutional neural network was trained on a dataset of experimentally tested antioxidative and non-antioxidative peptides, and model performance was evaluated against k-nearest neighbors (k-NN) sequence identity-based methods.