AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptides
Abstract Aging is a natural phenomenon characterized by the loss of normal morphology and physiological functioning of the body, causing wrinkles on the skin, loss of hair, and compromised immune systems. Peptide therapies have emerged as a promising approach in aging studies because of their excell...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-12759-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849235449747341312 |
|---|---|
| author | Saptashwa Datta Jen-Chieh Yu Yi-Hsiang Lin Yun-Chen Cheng Ching-Tai Chen |
| author_facet | Saptashwa Datta Jen-Chieh Yu Yi-Hsiang Lin Yun-Chen Cheng Ching-Tai Chen |
| author_sort | Saptashwa Datta |
| collection | DOAJ |
| description | Abstract Aging is a natural phenomenon characterized by the loss of normal morphology and physiological functioning of the body, causing wrinkles on the skin, loss of hair, and compromised immune systems. Peptide therapies have emerged as a promising approach in aging studies because of their excellent tolerability, low immunogenicity, and high specificity. Computational methods can significantly expedite wet lab-based anti-aging peptide discovery by predicting potential candidates with high specificity and efficacy. We propose AAGP, an anti-aging peptide predictor based on diverse physicochemical and compositional features. Two datasets were constructed, both shared anti-aging peptides as positives, with the first using antimicrobial peptides as negatives and the second using random peptides as negatives. Peptides were encoded using 4,305 features, followed by adaptive feature selection with a heuristic algorithm on both datasets. Nine machine learning models were used for cross-validation and independent tests. AAGP achieves reasonably accurate prediction performance, with MCCs of 0.692 and 0.580 and AUCs of 0.963 and 0.808 on the two independent test datasets, respectively. Our feature importance analysis shows that physicochemical features are more crucial for the first dataset, whereas compositional features hold greater importance for the second. The source code of AAGP is available at https://github.com/saptawtf/AAGP . |
| format | Article |
| id | doaj-art-3cd5d825635842fdbc7610efeee5a01e |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-3cd5d825635842fdbc7610efeee5a01e2025-08-20T04:02:46ZengNature PortfolioScientific Reports2045-23222025-08-0115111310.1038/s41598-025-12759-0AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptidesSaptashwa Datta0Jen-Chieh Yu1Yi-Hsiang Lin2Yun-Chen Cheng3Ching-Tai Chen4Department of Bioinformatics and Medical Engineering, Asia UniversityGraduate Institute of Genomics and Bioinformatics, National Chung Hsing UniversityDepartment of Bioinformatics and Medical Engineering, Asia UniversityDepartment of Bioinformatics and Medical Engineering, Asia UniversityDepartment of Computer Science, University of TaipeiAbstract Aging is a natural phenomenon characterized by the loss of normal morphology and physiological functioning of the body, causing wrinkles on the skin, loss of hair, and compromised immune systems. Peptide therapies have emerged as a promising approach in aging studies because of their excellent tolerability, low immunogenicity, and high specificity. Computational methods can significantly expedite wet lab-based anti-aging peptide discovery by predicting potential candidates with high specificity and efficacy. We propose AAGP, an anti-aging peptide predictor based on diverse physicochemical and compositional features. Two datasets were constructed, both shared anti-aging peptides as positives, with the first using antimicrobial peptides as negatives and the second using random peptides as negatives. Peptides were encoded using 4,305 features, followed by adaptive feature selection with a heuristic algorithm on both datasets. Nine machine learning models were used for cross-validation and independent tests. AAGP achieves reasonably accurate prediction performance, with MCCs of 0.692 and 0.580 and AUCs of 0.963 and 0.808 on the two independent test datasets, respectively. Our feature importance analysis shows that physicochemical features are more crucial for the first dataset, whereas compositional features hold greater importance for the second. The source code of AAGP is available at https://github.com/saptawtf/AAGP .https://doi.org/10.1038/s41598-025-12759-0Anti-aging peptideMachine learning modelsSkin agingPeptidesCosmetics |
| spellingShingle | Saptashwa Datta Jen-Chieh Yu Yi-Hsiang Lin Yun-Chen Cheng Ching-Tai Chen AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptides Scientific Reports Anti-aging peptide Machine learning models Skin aging Peptides Cosmetics |
| title | AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptides |
| title_full | AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptides |
| title_fullStr | AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptides |
| title_full_unstemmed | AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptides |
| title_short | AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptides |
| title_sort | aagp integrates physicochemical and compositional features for machine learning based prediction of anti aging peptides |
| topic | Anti-aging peptide Machine learning models Skin aging Peptides Cosmetics |
| url | https://doi.org/10.1038/s41598-025-12759-0 |
| work_keys_str_mv | AT saptashwadatta aagpintegratesphysicochemicalandcompositionalfeaturesformachinelearningbasedpredictionofantiagingpeptides AT jenchiehyu aagpintegratesphysicochemicalandcompositionalfeaturesformachinelearningbasedpredictionofantiagingpeptides AT yihsianglin aagpintegratesphysicochemicalandcompositionalfeaturesformachinelearningbasedpredictionofantiagingpeptides AT yunchencheng aagpintegratesphysicochemicalandcompositionalfeaturesformachinelearningbasedpredictionofantiagingpeptides AT chingtaichen aagpintegratesphysicochemicalandcompositionalfeaturesformachinelearningbasedpredictionofantiagingpeptides |