In recent years, with the rapid development of single-cell sequencing technology, this brings new opportunities and challenges to reconstruct gene regulatory networks. On the one hand, scRNA-seq data reveal statistical information of gene expression at single-cell resolution, which is beneficial to construct gene expression regulatory networks. On the other hand, the noise and dropout of single-cell data bring great difficulties to the analysis of scRNA-seq data, resulting in lower accuracy of gene regulatory networks reconstructed by traditional methods. In this article, we propose a novel supervised convolutional neural network (CNNSE), which can extract gene expression information from 2D co-expression matrices of gene doublets and identify interactions between genes. Our method can avoid the loss of extreme point interference by constructing a 2D co-expression matrix of gene pairs and significantly improve the regulation precision between gene pairs. And the CNNSE model is able to obtain detailed and high-level semantic information from the 2D co-expression matrix. Our method achieves satisfactory results on simulated data [accuracy (ACC): 0.712, F1: 0.724]. On two real scRNA-seq datasets, our method exhibits higher stability and accuracy in inference tasks compared with other existing gene regulatory network inference algorithms.

中文翻译：

---

使用来自 scRNA-seq 数据的卷积神经网络进行基因调控网络推断。

近年来，随着单细胞测序技术的快速发展，这为重构基因调控网络带来了新的机遇和挑战。一方面，scRNA-seq数据揭示了单细胞分辨率下基因表达的统计信息，有利于构建基因表达调控网络。另一方面，单细胞数据的噪声和dropout给scRNA-seq数据的分析带来了很大的困难，导致传统方法重建的基因调控网络的准确性较低。在这篇文章中，我们提出了一种新型的监督卷积神经网络 (CNNSE)，它可以从基因双联体的二维共表达矩阵中提取基因表达信息，并识别基因之间的相互作用。我们的方法可以通过构建基因对的二维共表达矩阵来避免极值点干扰的损失，显着提高基因对之间的调控精度。CNNSE 模型能够从二维共表达矩阵中获取详细的高级语义信息。我们的方法在模拟数据上取得了令人满意的结果 [准确度 (ACC)：0.712，F1：0.724]。在两个真实的 scRNA-seq 数据集上，与其他现有的基因调控网络推理算法相比，我们的方法在推理任务中表现出更高的稳定性和准确性。我们的方法在模拟数据上取得了令人满意的结果 [准确度 (ACC)：0.712，F1：0.724]。在两个真实的 scRNA-seq 数据集上，与其他现有的基因调控网络推理算法相比，我们的方法在推理任务中表现出更高的稳定性和准确性。我们的方法在模拟数据上取得了令人满意的结果 [准确度 (ACC)：0.712，F1：0.724]。在两个真实的 scRNA-seq 数据集上，与其他现有的基因调控网络推理算法相比，我们的方法在推理任务中表现出更高的稳定性和准确性。