MV-MLCF: A Semi-Supervised Self-training Method for Peptide Function Prediction Based on Multi-View and Multi-Label Co-Forest.

Abstract

Peptides, as biologically active molecules, have gained significant attention due to their therapeutic potential in treating various diseases, including metabolic disorders, cancers, and infectious diseases. However, the identification and functional annotation of multifunctional therapeutic peptides (MTPs) still remain challenging due to the limitations of traditional experimental costs and the scarcity of high-quality labeled data. To address these issues, we propose a novel semi-supervised self-training method called MV-MLCF (Multi-View and Multi-Label Co-Forest). MV-MLCF leverages multi-view feature representation techniques to comprehensively represent peptide sequences and employs a co-forest framework to iteratively label unannotated instances with a small set of high-quality labeled samples. By integrating multi-label learning, MV-MLCF effectively captures the multifunctional nature of peptides and lowers dependency on extensive labeled datasets. Extensive experiments across three benchmark datasets demonstrate the robustness and generalization of MV-MLCF across multiple base classifiers, including logistic regression, naive Bayes, and extreme learning machines. The results show that the proposed MV MLCF method significantly improves prediction accuracy and outperforms comparison algorithms, highlighting its potential in accelerating peptide-based drug discovery and reducing experimental costs. This study provides a new perspective and methodology for peptide function prediction, and offers a scalable and efficient solution to overcome data scarcity and enhance prediction performance in computational biology and bioinformatics.