School of Computer Science and Technology, Hainan University, Haikou 570228, China.
International Business School, Hainan University, Haikou 570228, China.
Bioinformatics. 2024 Nov 1;40(11). doi: 10.1093/bioinformatics/btae625.
The modification of N4-acetylcytidine (ac4C) in RNA is a conserved epigenetic mark that plays a crucial role in post-transcriptional regulation, mRNA stability, and translation efficiency. Traditional methods for detecting ac4C modifications are laborious and costly, necessitating the development of efficient computational approaches for accurate identification of ac4C sites in mRNA.
We present DPNN-ac4C, a dual-path neural network with a self-attention mechanism for the identification of ac4C sites in mRNA. Our model integrates embedding modules, bidirectional GRU networks, convolutional neural networks, and self-attention to capture both local and global features of RNA sequences. Extensive evaluations demonstrate that DPNN-ac4C outperforms existing models, achieving an AUROC of 91.03%, accuracy of 82.78%, MCC of 65.78%, and specificity of 84.78% on an independent test set. Moreover, DPNN-ac4C exhibits robustness under the Fast Gradient Method attack, maintaining a high level of accuracy in practical applications.
The model code and dataset are publicly available on GitHub (https://github.com/shock1ng/DPNN-ac4C).
N4-乙酰胞苷（ac4C）在 RNA 中的修饰是一种保守的表观遗传标记，在转录后调控、mRNA 稳定性和翻译效率中起着关键作用。检测 ac4C 修饰的传统方法既繁琐又昂贵，因此需要开发有效的计算方法来准确识别 mRNA 中的 ac4C 位点。
我们提出了 DPNN-ac4C，这是一种具有自注意力机制的双路径神经网络，用于识别 mRNA 中的 ac4C 位点。我们的模型集成了嵌入模块、双向 GRU 网络、卷积神经网络和自注意力，以捕获 RNA 序列的局部和全局特征。广泛的评估表明，DPNN-ac4C 优于现有模型，在独立测试集上的 AUROC 为 91.03%，准确性为 82.78%，MCC 为 65.78%，特异性为 84.78%。此外，DPNN-ac4C 在 Fast Gradient Method 攻击下具有鲁棒性，在实际应用中保持了较高的准确性。
模型代码和数据集可在 GitHub（https://github.com/shock1ng/DPNN-ac4C）上公开获取。
