TL;DR
RGTBind, a graph transformer that combines multi-scale radial basis function distance encoding with a learnable threshold-gating mechanism to model spatially informative residue interactions, achieved the best F1, AUC, and MCC among the compared methods.
DeepPNI is a deep learning regression model that integrates sequence- and structure-based features to estimate mutation-induced changes in binding free energy in protein–nucleic acid complexes, developed using a comprehensive dataset of 1754 mutations spanning protein–DNA and protein–RNA complexes.
An innovative two-stage deep learning framework that combines residue-level graph representation learning with protein-level regression to achieve a thorough modeling of protein interactions and gives a better understanding of the structural processes that control PPI.
Accurate protein function prediction (PFP) is essential for understanding biological systems. However, structure-based graph neural networks often rely on fixed-distance contact maps, which may inadequately capture continuous, multi-scale spatial topologies, while the long-tail distribution of Gene Ontology (GO) labels may bias prediction toward frequent functions. We propose DHST, a deep hybrid structure–topology framework that integrates sequence semantics from a pretrained protein language model with local structural information learned by a residual graph convolutional network. DHST further introduces site-specific persistent homology to encode multi-scale topological invariants and a topology-guided residue-wise gated fusion module to modulate structure–semantics representations using local topological embeddings. The fused residue features are aggregated through dual-path pooling, and a weighted binary cross-entropy loss is used to mitigate the adverse effects of label imbalance. On the PDB dataset, DHST achieved area under the precision–recall curve (AUPR) scores of 0.779, 0.481, and 0.557 for molecular function (MF), biological process (BP), and cellular component (CC), respectively; on the AF2 dataset, the corresponding scores were 0.729, 0.390, and 0.459. The model also demonstrated robust generalization to low-homology proteins and maintained strong predictive performance across GO terms with different levels of functional specificity. Ablation results supported the contributions of the main components.
Abstract Accurate predictions of DNA-binding residues (DBRs) in protein sequences facilitate decoding molecular-level mechanisms underlying cellular functions that involve protein–DNA interactions. While dozens of these predictors have been released, they target either structured or intrinsically disordered regions (IDRs), and the latter were trained to predict less detailed DNA-binding IDRs rather than DBRs. Given this dichotomy, the structure-trained methods underperform on disordered proteins, and vice versa. Moreover, they suffer from high cross-prediction rates, incorrectly labeling many residues that interact with non-DNA ligands as DBRs. We address these issues by introducing DNAreader, the first predictor specifically designed to predict DBRs in the structured and disordered sequence regions. DNAreader relies on an innovative stacked transformer encoder network that combines batch training and contrastive learning, which substantially boosts predictive performance. Using two low-similarity test datasets, we demonstrate that DNAreader statistically outperforms existing tools, performs well for structured and disordered regions, and produces very few cross-predictions. We also developed the DNAreaderDBIDR module, which accurately predicts DNA-binding IDRs, providing flexibility to identify DBRs within IDRs or to predict entire disordered DNA-binding regions. We release DNAreader as a user-friendly web server at http://biomine.cs.vcu.edu/servers/DNAreader/, with the corresponding source code at https://github.com/jianzhang-xynu/DNAreader.
Protein function prediction is one of the core challenges in bioinformatics, which plays a key role in resolving cellular mechanisms and driving drug discovery. A core challenge in this field is that protein function depends on both local structural motifs and long-range spatial interactions, and traditional Graph neural networks (GNNS) are limited by fixed receptive fields, which are difficult to comprehensively model these two features in different protein structures. To overcome this limitation, we propose ARF-GNN, an adaptive receptive field graph neural network tailored for protein function prediction. Our approach dynamically models structural context via hierarchical multi-hop neighborhood aggregation and introduces a dual-branch meta-learning framework: the Task branch performs multi-label functional annotation, while the Meta branch jointly learns sample-specific optimal receptive field sizes, thus thereby enabling structure-aware, input-adaptive information integration and mitigating noise and redundancy inherent in static neighborhood definitions. Empirical evaluation shows that ARF-GNN has significant improvements over the existing best benchmark models: in the PDBch benchmark test set, it has significant enhancements in the AUPR, Fmax, and Smin evaluation metrics. Ablation and interpretability analyses further confirm that the adaptive mechanism robustly captures functionally relevant multi-scale structural patterns, establishing a principled paradigm that unifies expressive structural representation with data-driven neighborhood adaptation.