MultiK: An Automated Tool to Infer Optimal Cluster Numbers in Single-Cell RNA Sequencing Data

This paper proposes MultiK, a data-driven tool for objective selection of multiple insightful numbers of clusters (K) from single-cell RNA-seq data. MultiK combines multiple clustering resolution solutions together through a consensus approach, and is capable of identifying robust and reproducible groups across multiple datasets.本文提出MultiK这一数据驱动工具，可从单细胞RNA测序（single-cell RNA-seq）数据中客观选取多个具有生物学洞察价值的簇数（K）。MultiK通过共识整合策略将多种聚类分辨率方案进行融合，能够在多组数据集间识别出稳健且可重复的细胞群。