iLBE

iLBE predicts linear B-cell epitopes by integrating sequence and evolutionary features to support epitope identification for vaccine design, immunodiagnostics, and antibody development.

Key Features:

• Integration of Sequence and Evolutionary Features: Leverages primary amino acid sequence features together with evolutionary conservation patterns to represent candidate epitopes.
• Optimization with Wilcoxon-rank Sum Test: Uses the Wilcoxon-rank sum test to select and optimize feature vectors by identifying statistically significant features.
• Random Forest Algorithm: Applies a Random Forest (RF) classifier to predict linear B-cell epitopes from the optimized feature vectors.
• Logistic Regression Integration: Combines RF scores using logistic regression to model the probability of epitope presence and refine predictions.
• Performance Metrics: Reported an area under the curve (AUC) of 0.809 on the training dataset and outperformed other models on an independent dataset.

Scientific Applications:

• Vaccine Design: Identification of potential linear B-cell epitopes for inclusion in vaccine candidates.
• Immunodiagnostic Tests: Selection of epitope biomarkers for disease detection assays.
• Antibody Production: Identification of target regions for antibody generation and therapeutic development.

Methodology:

Integrates evolutionary and sequence-based features, optimizes features with the Wilcoxon-rank sum test, trains a Random Forest classifier, and combines RF scores via logistic regression.