KRATOS: Context-Aware Cell Type Classification and Interpretation using Joint Dimensionality Reduction and Clustering
KRATOS: Context-Aware Cell Type Classification and Interpretation using Joint Dimensionality Reduction and Clustering
复制标题
DOI：
10.1145/3534678.3539455
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Zihan Zhou;Zijia Du;S. Chaterji
中科院分区：
文献类型：
--
作者：
Zihan Zhou;Zijia Du;S. Chaterji
单细胞 RNA 测序 (sc-RNA-seq) 数据分析的常见工作流程是编排一个三步管道。首先，对输入的细胞轮廓矩阵进行降维；其次，将细胞聚集在潜在空间中；第三，提取将某个簇与其他簇区分开来的“基因组”。该工作流程的主要缺点是三个步骤是独立执行的，忽略了步骤之间以及标记基因或基因组之间的依赖性。在我们的系统 KRATOS 中，我们将三步工作流程改为两步工作流程，联合优化前两步并添加第三步（可解释性）以形成集成的 sc-RNA-seq 分析流程。我们展示了 KRATOS 更紧凑的工作流程提取的标记基因可以更好地区分目标簇，提炼指导簇成员资格的潜在机制。在此过程中，KRATOS 明显优于我们比较的两个 SOTA 基线，特别是比全局反事实解释 (GCE) [ICML-20] 优越 5.62%，比对抗聚类解释 (ACE) [ICML-21] 优越 3.31%（通过内核 SVM 分类器的 AUROC 测量）。我们在这里开源代码和数据集：https://github.com/icanforce/single-cell-genomics-kratos。
A common workflow for single-cell RNA-sequencing (sc-RNA-seq) data analysis is to orchestrate a three-step pipeline. First, conduct a dimension reduction of the input cell profile matrix; second, cluster the cells in the latent space; and third, extract the "gene panels" that distinguish a certain cluster from others. This workflow has the primary drawback that the three steps are performed independently, neglecting the dependencies among the steps and among the marker genes or gene panels. In our system, KRATOS, we alter the three-step workflow to a two-step one, where we jointly optimize the first two steps and add the third (interpretability) step to form an integrated sc-RNA-seq analysis pipeline. We show that the more compact workflow of KRATOS extracts marker genes that can better discriminate the target cluster, distilling underlying mechanisms guiding cluster membership. In doing so, KRATOS is significantly better than the two SOTA baselines we compare against, specifically 5.62% superior to Global Counterfactual Explanation (GCE) [ICML-20], and 3.31% better than Adversarial Clustering Explanation (ACE) [ICML-21], measured by the AUROC of a kernel-SVM classifier. We opensource our code and datasets here: https://github.com/icanforce/single-cell-genomics-kratos.