E-CLEAP: An ensemble learning model for efficient and accurate identification of antimicrobial peptides

Area of Science:

• Biotechnology
• Computational Biology
• Drug Discovery

Background:

• Antimicrobial drug resistance is a growing global health threat.
• Antimicrobial peptides offer a promising alternative due to broad-spectrum activity and low resistance risk.
• Traditional screening methods for antimicrobial peptides are inefficient.

Purpose of the Study:

• To develop an efficient ensemble learning model for identifying antimicrobial peptides.
• To improve the accuracy and generalization of antimicrobial peptide identification.
• To address the limitations of traditional screening methods.

Main Methods:

• Developed an ensemble learning model named E-CLEAP, utilizing the Multilayer Perceptron Classifier.
• Incorporated features such as amino acid composition (AAC) and pseudo amino acid composition (PseAAC).
• Validated the model using five-fold cross-validation and comparison with existing methods.

Main Results:

• E-CLEAP achieved high accuracy: 97.33% for AAC and 84% for PseAAC on an independent test set.
• The model demonstrated superior performance across all evaluation metrics compared to other methods.
• Experimental results confirm the model's effectiveness in antimicrobial peptide identification.

Conclusions:

• The E-CLEAP model significantly enhances the efficiency and accuracy of antimicrobial peptide screening.
• Findings have substantial implications for drug development, disease treatment, and biotechnology.
• Future work includes incorporating more features and validating on larger, real-world datasets.