SSEL ‐ CPP : A SHAP ‐based feature‐selection ensemble learning framework identifies molecular properties of cell‐penetrating peptides
Protein Science · 2026-08 · 35 (8)
DOI: 10.1002/pro.70704 ↗At a glance
Journal article in Protein Science, published online on 2026-07-10. Written by Chan Woo Kwon and 5 co-authors. Institution: Ajou University School of Medicine, Suwon, South Korea. Major MEDLINE topics: Cell-Penetrating Peptides, Machine Learning. Cited 1 times so far (Crossref); 60 references. The full text is freely available (open access, CC BY-NC 4.0). Funded by: Ministry of Science and ICT, South Korea.
Abstract (original language)
Cell‐penetrating peptides (CPPs) facilitate the intracellular delivery of therapeutic molecules. However, their accurate identification and design remain challenging because of the complexity of their structural and physicochemical characteristics. This study aimed to develop an interpretable predictive model that enables reliable CPP discovery and provides interpretable descriptors suggestive of the molecular properties underlying their activity. Peptide samples were represented using two‐dimensional descriptors generated by Mordred. A novel two‐stage feature selection method was introduced, combining a correlation‐based filter with Shapley Additive exPlanations (SHAP). The model was trained on the CPP1708 dataset and built using an ensemble learning strategy integrating multiple machine learning algorithms. The ensemble framework, combining Extreme Gradient Boosting and Light Gradient Boosting Machine, identified five Mordred descriptors—5‐ordered bonding information content (BIC5), Extended Topochemical Atom epsilon 5 (ETA_epsilon_5), averaged and centered Moreau‐Broto autocorrelation of lag 0 weighted by ionization potential (AATSC0i), centered Moreau‐Broto autocorrelation of lag 2 weighted by mass (ATSC2m), and first highest eigenvalue of Burden matrix weighted by gasteiger charge (BCUTc‐1h)—as critical features for CPP prediction. The model achieved an accuracy of 82.0% and an area under the curve of 87.5% on the CPP1708 test set, outperforming existing predictors. This interpretable, high‐performing prediction model supports the rational design of CPPs and advances peptide‐based drug development. The SHAP‐guided feature selection framework improves both efficiency and interpretability, with potential applications across diverse peptide classes. Furthermore, the identification of five mechanistic descriptors offers deeper insight into the structural, electronic, and physicochemical properties underpinning CPP activity.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Ajou University School of Medicine, Suwon, South Korea.
- Department of Physiology, Ajou University School of Medicine, Suwon, South Korea.
- Molecular Science and Technology Research Center, Ajou University, Suwon, South Korea.
- Department of Molecular Science and Technology, Ajou University, Suwon, South Korea.
ORCID profiles: Sampa Misra, Gwang Lee
Funding
- Ministry of Science and ICT, South Korea
Cite
APA
Kwon, C. W., Kwon, M., Basith, S., Misra, S., Jang, Y. E., & Lee, G. (2026). SSEL ‐ CPP : A SHAP ‐based feature‐selection ensemble learning framework identifies molecular properties of cell‐penetrating peptides. Protein Science, 35(8). https://doi.org/10.1002/pro.70704
Vancouver
Kwon CW, Kwon M, Basith S, Misra S, Jang YE, Lee G. SSEL ‐ CPP : A SHAP ‐based feature‐selection ensemble learning framework identifies molecular properties of cell‐penetrating peptides. Protein Science. 2026;35(8). doi:10.1002/pro.70704
BibTeX
@article{Kwon2026,
author = {Kwon, Chan Woo and Kwon, Minjun and Basith, Shaherin and Misra, Sampa and Jang, Yong Eun and Lee, Gwang},
title = {SSEL ‐ CPP : A SHAP ‐based feature‐selection ensemble learning framework identifies molecular properties of cell‐penetrating peptides},
journal = {Protein Science},
year = {2026},
volume = {35},
number = {8},
doi = {10.1002/pro.70704}
}
EUVIMED