Residual–capsule deep learning network for accurate prediction of deoxyribonucleic acid–binding proteins using global protein transformer embeddings

Deoxyribonucleic acid–binding proteins (DBPs) are integral to gene regulation and cellular processes, making their accurate identification essential for understanding biological functions and disease mechanisms. Experimental methods for DBP identification are time-consuming and costly, driving the need for efficient computational prediction techniques. In this study, we propose a deep learning framework, ResCap-DBP, that combines a residual learning-based encoder with a one-dimensional Capsule Network (1D-CapsNet) to predict DBPs directly from raw protein sequences. Our architecture incorporates dilated convolutions within residual blocks to extract rich sequence features, while capsule layers with dynamic routing capture hierarchical relationships in the learned feature space. We conducted comprehensive ablation studies comparing global and local embeddings from ProteinBERT and conventional one-hot encoding. Results show that ProteinBERT embeddings substantially outperform other representations on large datasets. Although one-hot encoding showed marginal advantages on smaller datasets, such as PDB186, it struggled to scale effectively. Extensive evaluations on four pairs of publicly available benchmark datasets demonstrate that our model achieves strong and competitive performance across benchmark datasets. It achieved AUC scores of 98.0% and 89.50% on PDB14189 and PDB1075, respectively. On independent test sets PDB2272 and PDB186, the model attained top AUCs of 83.2% and 83.3%, while maintaining competitive performance on larger datasets such as PDB20000. Notably, the model maintains a well-balanced sensitivity and specificity across datasets. These findings support the effectiveness of integrating global protein representations with a residual-capsule architecture for sequence-based DBP prediction across multiple benchmark datasets. • Introduced ResCap-DBP for accurate DNA-binding protein prediction. • Combined residual blocks with 1D Capsule Networks for feature extraction. • Used global ProteinBERT embeddings for enhanced sequence representation. • Achieved SOTA performance across eight benchmark DBP datasets. • Model is lightweight with fast inference suitable for real-time use.