MOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST/Department of Automation, Tsinghua University, Beijing 100084, China.
School of Statistics and Data Science, Nankai University, Tianjin 300071, China.
Cells. 2023 Feb 13;12(4):604. doi: 10.3390/cells12040604.
Recent advances in spatial transcriptomics have revolutionized the understanding of tissue organization. The identification of spatially variable genes (SVGs) is an essential step for downstream spatial domain characterization. Although several methods have been proposed for identifying SVGs, inadequate ability to decipher spatial domains, poor efficiency, and insufficient interoperability with existing standard analysis workflows still impede the applications of these methods. Here we propose SINFONIA, a scalable method for identifying spatially variable genes via ensemble strategies. Implemented in Python, SINFONIA can be seamlessly integrated into existing analysis workflows. Using 15 spatial transcriptomic datasets generated with different protocols and with different sizes, dimensions and qualities, we show the advantage of SINFONIA over three baseline methods and two variants via systematic evaluation of spatial clustering, domain resolution, latent representation, spatial visualization, and computational efficiency with 21 quantitative metrics. Additionally, SINFONIA is robust relative to the choice of the number of SVGs. We anticipate SINFONIA will facilitate the analysis of spatial transcriptomics.
近年来，空间转录组学的发展极大地推动了人们对组织架构的理解。识别空间变异基因（SVGs）是下游空间域特征描述的重要步骤。尽管已经提出了几种识别 SVGs 的方法，但这些方法在破译空间域方面的能力不足、效率低下以及与现有标准分析工作流程的互操作性不足，仍然限制了这些方法的应用。在这里，我们提出了 SINFONIA，这是一种通过集成策略识别空间变异基因的可扩展方法。SINFONIA 是用 Python 实现的，可以无缝集成到现有的分析工作流程中。我们使用了 15 个具有不同协议、不同大小、维度和质量的空间转录组数据集，通过对 21 个定量指标的空间聚类、域分辨率、潜在表示、空间可视化和计算效率的系统评估，展示了 SINFONIA 相对于三种基线方法和两种变体的优势。此外，SINFONIA 相对于选择的 SVGs 数量具有鲁棒性。我们预计 SINFONIA 将促进空间转录组学的分析。
