MFP-MFL: Leveraging Graph Attention and Multi-Feature Integration for Superior Multifunctional Bioactive Peptide Prediction

Bioactive peptides, composed of amino acid chains, are fundamental to a wide range of biological functions. Their inherent multifunctionality, however, complicates accurate classification and prediction. To address these challenges, we present MFP-MFL, an advanced multi-feature, multi-label learning framework that integrates Graph Attention Networks (GAT) with leading protein language models, including ESM-2, ProtT5, and RoBERTa. By employing an ensemble learning strategy, MFP-MFL effectively utilizes deep sequence features and complex functional dependencies, ensuring highly accurate and robust predictions of multifunctional peptides. Comparative experiments demonstrate that MFP-MFL achieves precision, coverage, and accuracy scores of 0.799, 0.821, and 0.786, respectively. Additionally, it attains an Absolute true of 0.737 while maintaining a low Absolute false of 0.086. A comprehensive case study involving 86,970 mutations further highlights the model's ability to predict functional changes resulting from sequence variations. These results establish MFP-MFL as a powerful tool for the discovery and application of multifunctional peptides, offering significant potential to advance research and biomedical applications.