PDL1Binder

PDL1Binder predicts and prioritizes PD-L1-binding peptides by analyzing Next-Generation Phage Display (NGPD) deep-sequencing data with machine learning.

Key Features:

• Integration of Next-Generation Phage Display (NGPD): Leverages NGPD biopanning and deep sequencing to isolate candidate PD-L1 binding peptides.
• Machine Learning-Based Predictive Models: Uses diverse peptide descriptors and feature selection methods to train predictive models on NGPD deep-sequencing data to identify high-affinity PD-L1 binders.
• Ensemble Computational Model: Employs an ensemble of multiple machine learning algorithms to improve prediction accuracy and reliability for selecting peptide candidates as alternatives or complements to monoclonal antibody therapies.

Scientific Applications:

• Cancer immunotherapy discovery: Enables discovery of peptide inhibitors targeting the PD-1/PD-L1 pathway.
• Therapeutic candidate prioritization: Prioritizes PD-L1-binding peptide candidates for development as alternatives or complements to monoclonal antibody therapies.
• Immune response enhancement research: Supports identification of peptides that may enhance anti-tumor immune responses.

Methodology:

Computational analysis applies machine learning-based predictive models using diverse peptide descriptors and feature selection, and integrates predictions via an ensemble of machine learning algorithms on deep-sequencing data from NGPD experiments.