scMASKGAN

Single-cell RNA sequencing (scRNA-seq) enables high-resolution analysis of cellular heterogeneity, but dropout events, where gene expression is undetected in individual cells, present a significant challenge. We propose \textbf{scMASKGAN}, which transforms matrix imputation into a pixel restoration task to improve the recovery of missing gene expression data.  Specifically, we integrate masking, convolutional neural networks (CNNs), attention mechanisms, and residual networks (ResNets) to effectively address dropout events in scRNA-seq data. The masking mechanism ensures the preservation of complete cellular information, while convolution and attention mechanisms are employed to capture both global and local features. Residual networks augment feature representation and effectively mitigate the risk of model overfitting. Additionally, cell-type labels are incorporated as constraints to guide the methods in learning more accurate cellular features. Finally, multiple experiments were conducted to evaluate methods performance using seven different data types and scRNA-seq data from ten neuroblastoma samples. The results demonstrate that the data imputed by scMASKGAN not only perform excellently across various evaluation metrics but also significantly enhance the effectiveness of downstream analyses, enabling a more comprehensive exploration of underlying biological information.

单细胞RNA测序（scRNA-seq）可实现细胞异质性的高分辨率分析，但缺失事件（即单个细胞中基因表达未被检测到的情况）构成了重大挑战。我们提出**scMASKGAN**方法，将矩阵插补转化为像素恢复任务，以改善缺失基因表达数据的恢复效果。具体而言，我们整合了掩蔽机制、卷积神经网络（CNNs）、注意力机制和残差网络（ResNets），有效解决scRNA-seq数据中的缺失事件。掩蔽机制确保完整细胞信息的保留，而卷积和注意力机制则用于捕获全局和局部特征。残差网络增强特征表示并有效降低模型过拟合风险。此外，细胞类型标签被纳入作为约束条件，以引导方法学习更准确的细胞特征。最后，我们使用七种不同数据类型和来自十个神经母细胞瘤样本的scRNA-seq数据进行了多项实验来评估方法性能。结果表明，scMASKGAN插补的数据不仅在各种评估指标上表现优异，还显著提升下游分析的有效性，从而能够更全面地探索潜在生物学信息。