Hao Sixi, Li Cai-Yan, Hu Xiuzhen, Feng Zhenxing, Zhang Gaimei, Yang Caiyun, Hu Huimin
College of Sciences, Inner Mongolia University of Technology, Hohhot, China.
School of Mathematics and Statistics, Xinyang College, Xinyang, China.
Front Genet. 2025 Jan 6;15:1513201. doi: 10.3389/fgene.2024.1513201. eCollection 2024.
The realization of many protein functions requires binding with ligands. As a significant protein-binding ligand, ATP plays a crucial role in various biological processes. Currently, the precise prediction of ATP binding residues remains challenging.
Based on the sequence information, this paper introduces a method called S-DCNN for predicting ATP binding residues, utilizing a deep convolutional neural network (DCNN) enhanced with the synthetic minority over-sampling technique (SMOTE).
The incorporation of additional feature parameters such as dihedral angles, energy, and propensity factors into the standard parameter set resulted in a significant enhancement in prediction accuracy on the ATP-289 dataset. The S-DCNN achieved the highest Matthews correlation coefficient value of 0.5031 and an accuracy rate of 97.06% on an independent test set. Furthermore, when applied to the ATP-221 and ATP-388 datasets for validation, the S-DCNN outperformed existing methods on ATP-221 and performed comparably to other methods on ATP-388 during independent testing.
Our experimental results underscore the efficacy of the S-DCNN in accurately predicting ATP binding residues, establishing it as a potent tool in the prediction of ATP binding residues.
许多蛋白质功能的实现需要与配体结合。作为一种重要的蛋白质结合配体，ATP在各种生物过程中起着关键作用。目前，精确预测ATP结合残基仍然具有挑战性。
基于序列信息，本文介绍了一种名为S-DCNN的预测ATP结合残基的方法，该方法利用深度卷积神经网络（DCNN）并结合合成少数类过采样技术（SMOTE）进行增强。
在标准参数集中纳入诸如二面角、能量和倾向因子等额外特征参数，使得在ATP-289数据集上的预测准确率有显著提高。S-DCNN在独立测试集上的马修斯相关系数最高达到0.5031，准确率为97.06%。此外，当应用于ATP-221和ATP-388数据集进行验证时，S-DCNN在ATP-221上优于现有方法，在ATP-388的独立测试中与其他方法表现相当。
我们的实验结果强调了S-DCNN在准确预测ATP结合残基方面的有效性，使其成为预测ATP结合残基的有力工具。
