Deep learning-based identification of N6-methyladenine sites via hybrid feature fusion and SHAP-driven feature selection
4 affiliations
- 1Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, 11451, Saudi Arabia
- 2Department of Computer Science, Abdul Wali Khan University, Mardan, KPK, Pakistan
- 3Department of Computer Science & Engineering, Sejong University, Seoul, 05006, South Korea
- 4Department of Computer Science, Khurasan University, Jalalabad, Afghanistan. [email protected]
Abstract
N6-methyladenine (6 mA) is a critical epigenetic modification involved in gene regulation, genome stability, and cellular adaptation. Accurate computational identification of 6 mA sites is essential for elucidating epigenetic mechanisms and advancing disease-related research. However, existing methods are often constrained by limited feature representations and poor interpretability, hindering predictive performance and generalisation across diverse genomic contexts. To address these challenges, we propose a novel deep neural network (DNN)-based framework that integrates optimal hybrid features for robust and interpretable 6 mA site identification. The proposed framework employs a comprehensive multi-feature extraction strategy to capture complex sequence-level patterns in DNA, which are subsequently fused into a unified hybrid representation. To enhance model efficiency and interpretability, SHapley Additive exPlanations (SHAP) are applied for feature importance analysis, enabling the selection of the most discriminative features for downstream classification. The optimised feature set is then fed into a DNN classifier for accurate 6 mA site prediction. Evaluated using 5-fold cross-validation, the proposed model achieved training accuracies of 97.95% and 96.15% on the F. vesca and R. chinensis datasets, respectively. On independent test datasets, the model achieved accuracies of 97.10% (F. vesca) and 95.32% (R. chinensis), demonstrating strong generalisation. These results establish the proposed framework as an accurate, reliable, and interpretable computational tool for genome-wide identification of 6 mA sites, with broad applicability to epigenetic research and beyond.
Related
- Wrapshap a high dimension feature selection framework to explore biological systems through machine learning explanations
- CAMELLIA: an alignment-free pipeline integrating k-mer feature selection and supervised classification for genomic sequence subtyping.
- Enhancing Linear B-Cell Epitope Prediction via Evolutionary Scale Modeling (ESM-2) and Hybrid Feature Integration
- A Leakage-Controlled Benchmark of Metaheuristic Multi-Omics Feature Selection for Reconstructing TCGA Molecular Subtypes in Endometrial Cancer
- From conservation scores to language models: a feature engineering perspective on machine learning for genetic variant interpretation
BibTeX
@article{alzamel2026deep,
title = {{Deep learning-based identification of N6-methyladenine sites via hybrid feature fusion and SHAP-driven feature selection}},
author = {Mai Alzamel and Islam Uddin and Salman Khan and Naqqash Dilshad and Nijad Ahmad},
journal = {Scientific Reports},
year = {2026},
month = may,
doi = {10.1038/s41598-026-50667-z},
url = {https://doi.org/10.1038/s41598-026-50667-z},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Deep learning-based identification of N6-methyladenine sites via hybrid feature fusion and SHAP-driven feature selection
AU - Mai Alzamel
AU - Islam Uddin
AU - Salman Khan
AU - Naqqash Dilshad
AU - Nijad Ahmad
PY - 2026
DA - 2026/05/18
JO - Scientific Reports
DO - 10.1038/s41598-026-50667-z
UR - https://doi.org/10.1038/s41598-026-50667-z
AB - N6-methyladenine (6 mA) is a critical epigenetic modification involved in gene regulation, genome stability, and cellular adaptation. Accurate computational identification of 6 mA sites is essential for elucidating epigenetic mechanisms and advancing disease-related research. However, existing methods are often constrained by limited feature representations and poor interpretability, hindering predictive performance and generalisation across diverse genomic contexts. To address these challenges, we propose a novel deep neural network (DNN)-based framework that integrates optimal hybrid features for robust and interpretable 6 mA site identification. The proposed framework employs a comprehensive multi-feature extraction strategy to capture complex sequence-level patterns in DNA, which are subsequently fused into a unified hybrid representation. To enhance model efficiency and interpretability, SHapley Additive exPlanations (SHAP) are applied for feature importance analysis, enabling the selection of the most discriminative features for downstream classification. The optimised feature set is then fed into a DNN classifier for accurate 6 mA site prediction. Evaluated using 5-fold cross-validation, the proposed model achieved training accuracies of 97.95% and 96.15% on the F. vesca and R. chinensis datasets, respectively. On independent test datasets, the model achieved accuracies of 97.10% (F. vesca) and 95.32% (R. chinensis), demonstrating strong generalisation. These results establish the proposed framework as an accurate, reliable, and interpretable computational tool for genome-wide identification of 6 mA sites, with broad applicability to epigenetic research and beyond.
SN - 2045-2322
ER -