Prediction of protein-ATP binding residues using multi-view feature learning via contextual-based co-attention network

• Published in: Computers in biology and medicine 2024-04, Vol.172, p.108227, Article 108227
• Main Authors: Wu, Jia-Shun, Liu, Yan, Ge, Fang, Yu, Dong-Jun
• Format: Article
• Language: English
• Subjects: Adenosine Triphosphate; Algorithms; Amino Acid Sequence; Annotations; ATP; Binding; Context; Contextual-based co-attention network; Datasets; Deep learning; Deep learning model; Embedding; Experimental methods; Harnesses; Language; Neural networks; Performance evaluation; Pre-trained protein language; Predictions; Protein Binding; Protein-ATP binding residues prediction; Proteins; Proteins - chemistry; Research methodology; Residues; Semantics; Signal transduction
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108227

Accurately predicting protein-ATP binding residues is critical for protein function annotation and drug discovery. Computational methods dedicated to the prediction of binding residues based on protein sequence information have exhibited notable advancements in predictive accuracy. Nevertheless, these methods continue to grapple with several formidable challenges, including limited means of extracting more discriminative features and inadequate algorithms for integrating protein and residue information. To address the problems, we propose ATP-Deep, a novel protein-ATP binding residues predictor. ATP-Deep harnesses the capabilities of unsupervised pre-trained language models and incorporates domain-specific evolutionary context information from homologous sequences. It further refines the embedding at the residue level through integration with corresponding protein-level information and employs a contextual-based co-attention mechanism to adeptly fuse multiple sources of features. The performance evaluation results on the benchmark datasets reveal that ATP-Deep achieves an AUC of 0.954 and 0.951, respectively, surpassing the performance of the state-of-the-art model. These findings underscore the effectiveness of assimilating protein-level information and deploying a contextual-based co-attention mechanism grounded in context to bolster the prediction performance of protein-ATP binding residues. •We developed ATP-Deep, a novel deep learning-based method for predicting protein-ATP binding residues.•ATP-Deep employs pre-trained protein language models and task-specific evolutionary context for feature embedding.•The contextual-based co-attention network facilitates the learning of multi-view features.