Related Experiment Video
Updated: May 22, 2025
06:50
Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
Published on: January 26, 2024
1.0K
Prediction of Chemically Modified Antimicrobial Peptides and Their Sub-functional Activities Using Hybrid Features
Yujie Yao1, Daijun Zhang1, Henghui Fan1
1Information Materials and Intelligent Sensing Laboratory of Anhui Province, Institutes of Physical Science and Information Technology, Anhui University, Hefei, 230601, Anhui, China.
Probiotics and Antimicrobial Proteins
|May 21, 2025
Summary
Chemically modified antimicrobial peptides (cmAMPs) show promise against resistant pathogens. A new computational model, iCMAMP, accurately identifies cmAMPs and predicts their functions, offering improved prediction over existing methods.
Area of Science:
- Biochemistry and Molecular Biology
- Computational Biology and Bioinformatics
- Drug Discovery and Development
Background:
- Antimicrobial peptides (AMPs) are crucial in combating pathogens and antimicrobial resistance.
- Chemically modified AMPs (cmAMPs) offer reduced toxicity and enhanced efficacy.
- Existing computational tools lack specialized prediction capabilities for cmAMPs and their sub-functions.
Purpose of the Study:
- To develop a novel computational model, iCMAMP, for identifying cmAMPs.
- To predict the sub-functional activities of cmAMPs.
- To provide an improved computational approach for cmAMP analysis.
Main Methods:
- A two-layer prediction model, iCMAMP, was proposed.
- The first layer (iCMAMP-1L) utilized an ensemble method integrating seven feature categories for cmAMP identification.
- The second layer (iCMAMP-2L) employed multi-label classification with dipeptide composition for sub-function prediction.
Main Results:
- iCMAMP-1L achieved 0.934 accuracy and 0.868 MCC, outperforming the existing AntiMPmod method.
- Comparative analysis showed chemical modifications reduce AMP-induced hemolysis and toxicity.
- iCMAMP-2L demonstrated accuracy of 0.390 and absolute true of 0.621 for sub-function prediction.
Conclusions:
- The iCMAMP model provides an effective computational framework for cmAMP identification and sub-function prediction.
- Chemical modification of AMPs can significantly mitigate adverse effects while preserving antimicrobial activity.
- The study highlights the potential of sequence-based features in determining peptide function.
