TPpred-ATMV: therapeutic peptide prediction by adaptive multi-view tensor learning model.

Area of Science:

• Computational biology
• Drug discovery
• Bioinformatics

Background:

• Therapeutic peptide prediction is crucial for drug development, but existing computational methods often fail to predict comprehensive peptide types.
• Predicting therapeutic peptides using diverse properties remains a significant challenge in the field.

Purpose of the Study:

• To propose an advanced computational framework, TPpred-ATMV, for the accurate prediction of diverse therapeutic peptide types.
• To overcome the limitations of current methods in comprehensively identifying therapeutic peptides.

Main Methods:

• Developed TPpred-ATMV, an adaptive multi-view tensor learning framework.
• Integrated various sequence features to construct class and probability information.
• Utilized latent subspace and auto-weighted multi-view tensor learning to leverage high correlations among multi-view features.

Main Results:

• TPpred-ATMV demonstrated superior or comparable performance against state-of-the-art methods.
• The framework successfully predicted eight distinct types of therapeutic peptides.
• Experimental validation confirmed the efficacy of the proposed multi-view tensor learning approach.

Conclusions:

• TPpred-ATMV offers a robust and effective solution for comprehensive therapeutic peptide prediction.
• The developed method advances the capabilities in identifying therapeutic peptides for drug development.
• The framework's ability to integrate multi-view features provides a novel approach to peptide prediction.