The gene regulatory structure of cells involves not only the regulatory relationship between two genes, but also the cooperative associations of multiple genes. However, most gene regulatory network inference methods for single cell only focus on and infer the regulatory relationships of pairs of genes, ignoring the global regulatory structure which is crucial to identify the regulations in the complex biological systems. Here, we proposed a graph-based Deep learning model for Regulatory networks Inference among Genes (DeepRIG) from single-cell RNA-seq data. To learn the global regulatory structure, DeepRIG builds a prior regulatory graph by transforming the gene expression of data into the co-expression mode. Then it utilizes a graph autoencoder model to embed the global regulatory information contained in the graph into gene latent embeddings and to reconstruct the gene regulatory network. Extensive benchmarking results demonstrate that DeepRIG can accurately reconstruct the gene regulatory networks and outperform existing methods on multiple simulated networks and real-cell regulatory networks. Additionally, we applied DeepRIG to the samples of human peripheral blood mononuclear cells and triple-negative breast cancer, and presented that DeepRIG can provide accurate cell-type-specific gene regulatory networks inference and identify novel regulators of progression and inhibition.

中文翻译：

---

使用图自动编码器模型从单细胞转录组推断基因调控网络。

细胞的基因调控结构不仅涉及两个基因之间的调控关系，还涉及多个基因的协同关联。然而，大多数单细胞基因调控网络推理方法仅关注和推断基因对的调控关系，而忽略了对于识别复杂生物系统中的调控至关重要的全局调控结构。在这里，我们提出了一种基于图的深度学习模型，用于根据单细胞 RNA-seq 数据进行基因间调控网络推理 (DeepRIG)。为了学习全局调控结构，DeepRIG 通过将数据的基因表达转化为共表达模式来构建先验调控图。然后，它利用图自动编码器模型将图中包含的全局调控信息嵌入到基因潜在嵌入中并重建基因调控网络。大量的基准测试结果表明，DeepRIG 可以准确地重建基因调控网络，并在多个模拟网络和真实细胞调控网络上优于现有方法。此外，我们将 DeepRIG 应用到人外周血单核细胞和三阴性乳腺癌样本中，发现 DeepRIG 可以提供准确的细胞类型特异性基因调控网络推断，并识别新的进展和抑制调节因子。