Single-Cell Multiomics Integration by SCOT
Single-Cell Multiomics Integration by SCOT
复制标题
DOI：
10.1089/cmb.2021.0477
复制
发表时间：
2022-01-05
影响因子：
1.7
通讯作者：
Singh, Ritambhara
中科院分区：
文献类型：
--
作者：
Demetci, Pinar;Santorella, Rebecca;Singh, Ritambhara
尽管各种测序技术的可用性使我们能够以单细胞分辨率捕获不同的基因组特性，但除了少数共测定技术之外，在同一个单细胞上应用不同的测序测定是不可能的。使用最佳传输的单细胞对齐（SCOT）是一种无监督算法，通过使用最佳传输来对齐单细胞多组学数据来解决这一限制。首先，它通过为每个数据集（或域）构建k-最近邻（k-NN）图来捕获域内距离，从而保留局部几何形状。然后，SCOT找到一个概率耦合矩阵，使域内距离矩阵之间的差异最小化。最后，利用耦合矩阵，通过重心投影将一个单细胞数据集投影到另一个单细胞数据集上，从而将它们对齐。SCOT只需要调整两个超参数，并且对选择一个超参数具有鲁棒性。此外，该算法中的Gromov-Wasserstein距离可以指导SCOT的超参数调整在一个完全无监督的设置时，没有正交对齐信息是可用的。因此，SCOT是一种快速准确的对齐方法，它为现实世界中无监督单单元数据对齐场景中的超参数选择提供了启发式方法。我们为SCOT提供了一个教程，并在GitHub上公开了其源代码。
Although the availability of various sequencing technologies allows us to capture different genome properties at single-cell resolution, with the exception of a few co-assaying technologies, applying different sequencing assays on the same single cell is impossible. Single-cell alignment using optimal transport (SCOT) is an unsupervised algorithm that addresses this limitation by using optimal transport to align single-cell multiomics data. First, it preserves the local geometry by constructing a k-nearest neighbor (k-NN) graph for each data set (or domain) to capture the intra-domain distances. SCOT then finds a probabilistic coupling matrix that minimizes the discrepancy between the intra-domain distance matrices. Finally, it uses the coupling matrix to project one single-cell data set onto another through barycentric projection, thus aligning them. SCOT requires tuning only two hyperparameters and is robust to the choice of one. Furthermore, the Gromov-Wasserstein distance in the algorithm can guide SCOT's hyperparameter tuning in a fully unsupervised setting when no orthogonal alignment information is available. Thus, SCOT is a fast and accurate alignment method that provides a heuristic for hyperparameter selection in a real-world unsupervised single-cell data alignment scenario. We provide a tutorial for SCOT and make its source code publicly available on GitHub.