Secuer: ultrafast, scalable and accurate clustering of single-cell RNA-seq data

TL;DR

Secuer is a highly scalable and efficient clustering algorithm for single-cell RNA-seq data that significantly reduces runtime and memory usage while maintaining or improving accuracy, suitable for datasets with millions of cells.

Contribution

Introduces Secuer, a novel spectral clustering algorithm that is ultra-fast, scalable, and accurate for large-scale single-cell RNA-seq data, and extends it with a consensus clustering framework.

Findings

Secuer reduces runtime and memory usage by orders of magnitude.

Secuer achieves comparable or better accuracy than existing methods.

Secuer can be integrated into consensus clustering to improve scalability and maintain accuracy.

Abstract

Identifying cell clusters is a critical step for single-cell transcriptomics study. Despite the numerous clustering tools developed recently, the rapid growth of scRNA-seq volumes prompts for a more (computationally) efficient clustering method. Here, we introduce Secuer, a Scalable and Efficient speCtral clUstERing algorithm for scRNA-seq data. By employing an anchor-based bipartite graph representation algorithm, Secuer enjoys reduced runtime and memory usage by orders of magnitude, especially for ultra-large datasets profiling over 1 or even 10 million cells. Meanwhile, Secuer also achieves better or comparable accuracy than competing methods in small and moderate benchmark datasets. Furthermore, we showcase that Secuer can also serve as a building block for a new consensus clustering method, Secuer-consensus, which again greatly improves the runtime and scalability of state-of-the-art consensus clustering methods while also maintaining the accuracy. Overall, Secuer is a versatile, accurate, and scalable clustering framework suitable for small to ultra-large single-cell clustering tasks.