Forest Fire Clustering for Single-cell Sequencing with Iterative Label Propagation and Parallelized Monte Carlo Simulation

TL;DR

Forest Fire Clustering is a scalable, interpretable, non-parametric method for cell-type discovery in single-cell sequencing data, providing confidence measures and insights into developmental trajectories, outperforming existing methods.

Contribution

Introduces Forest Fire Clustering, a novel non-parametric, scalable clustering method with confidence estimation for large-scale single-cell data analysis.

Findings

Outperforms state-of-the-art clustering methods on benchmarks.

Provides robust, online, inductive inferences.

Enables detection of rare cell types and developmental trajectories.

Abstract

In the era of single-cell sequencing, there is a growing need to extract insights from data with clustering methods. Here, we introduce Forest Fire Clustering, an efficient and interpretable method for cell-type discovery from single-cell data. Forest Fire Clustering makes minimal prior assumptions and, different from current approaches, calculates a non-parametric posterior probability that each cell is assigned a cell-type label. These posterior distributions allow for the evaluation of a label confidence for each cell and enable the computation of "label entropies," highlighting transitions along developmental trajectories. Furthermore, we show that Forest Fire Clustering can make robust, inductive inferences in an online-learning context and can readily scale to millions of cells. Finally, we demonstrate that our method outperforms state-of-the-art clustering approaches on diverse benchmarks of simulated and experimental data. Overall, Forest Fire Clustering is a useful tool for rare cell type discovery in large-scale single-cell analysis.