Abstract
Clustering is a critical step in single cell-based studies. Most existing methods support unsupervised clustering without the a priori exploitation of any domain knowledge. When confronted by the high dimensionality and pervasive dropout events of scRNA-Seq data, purely unsupervised clustering methods may not produce biologically interpretable clusters, which complicates cell type assignment. In such cases, the only recourse is for the user to manually and repeatedly tweak clustering parameters until acceptable clusters are found. Consequently, the path to obtaining biologically meaningful clusters can be ad hoc and laborious. Here we report a principled clustering method named scDCC, that integrates domain knowledge into the clustering step. Experiments on various scRNA-seq datasets from thousands to tens of thousands of cells show that scDCC can significantly improve clustering performance, facilitating the interpretability of clusters and downstream analyses, such as cell type assignment.
Highlights
Clustering is a critical step in single cell-based studies
RNA-seq or microarray, due to the extreme sparsity caused by dropouts and high variability in gene expression levels, traditional clustering approaches tend to deliver suboptimal results on scRNA-seq data sets[3,11]
DendroSplit[13] applies “split” and “merge” operations on the dendrogram obtained from hierarchical clustering, which iteratively groups cells based on their pairwise distances, to uncover multiple levels of biologically meaningful populations with interpretable hyperparameters
Summary
Clustering is a critical step in single cell-based studies. Most existing methods support unsupervised clustering without the a priori exploitation of any domain knowledge. We apply scDCC with pairwise constraints to the scRNA-seq datasets of various sizes (from thousands to tens of thousands of cells). In the context of scRNA-seq studies, pairwise constraints can be constructed based on the cell distance computed using marker genes, cell sorting using flow cytometry, or other methods depending on real application scenarios.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
