DeepPNI: Language- and graph-based model for mutation-driven protein-nucleic acid energetics

2025-11-27

AI Summary

This study addresses the challenge of accurately predicting the impact of amino acid mutations on binding free energy changes (ΔΔG) in protein–DNA/RNA complexes. Existing methods suffer from limited generalizability and fail to jointly leverage structural and evolutionary sequence information. To overcome these limitations, we propose the first unified deep learning framework: a coupled edge-aware relational graph convolutional network (RGCN) to model 3D interaction structures, integrated with ESM-2 for extracting evolutionarily conserved protein sequence representations. Evaluated on a large-scale dataset of 1,951 mutations via five-fold cross-validation, our model achieves a mean Pearson correlation coefficient of 0.76. In external benchmarking, it significantly outperforms state-of-the-art tools and demonstrates strong generalization across diverse complex types and experimental temperatures. The framework establishes a new paradigm for computational prediction of mutation effects on nucleic acid–protein binding affinity.

Technology Category

• Machine Learning: Evolutionary Learning
• Search and Optimization: Evolutionary Computation
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The interaction between proteins and nucleic acids is crucial for processes that sustain cellular function, including DNA maintenance and the regulation of gene expression and translation. Amino acid mutations in protein-nucleic acid complexes often lead to vital diseases. Experimental techniques have their own specific limitations in predicting mutational effects in protein-nucleic acid complexes. In this study, we compiled a large dataset of 1951 mutations including both protein-DNA and protein-RNA complexes and integrated structural and sequential features to build a deep learning-based regression model named DeepPNI. This model estimates mutation-induced binding free energy changes in protein-nucleic acid complexes. The structural features are encoded via edge-aware RGCN and the sequential features are extracted using protein language model ESM-2. We have achieved a high average Pearson correlation coefficient (PCC) of 0.76 in the large dataset via five-fold cross-validation. Consistent performance across individual dataset of protein-DNA, protein-RNA complexes, and different experimental temperature split dataset make the model generalizable. Our model showed good performance in complex-based five-fold cross-validation, which proved its robustness. In addition, DeepPNI outperformed in external dataset validation, and comparison with existing tools

Problem

• Predicts mutation effects on protein-nucleic acid binding energy
• Integrates structural and sequential features via deep learning
• Addresses experimental limitations in studying protein-DNA/RNA complexes

Innovation

• Integrates structural and sequential features via deep learning
• Encodes structural features using edge-aware RGCN
• Extracts sequential features with protein language model ESM-2