Hierarchical novel class discovery for single-cell transcriptomic profiles

TL;DR

This paper introduces hierarchical clustering methods tailored for single-cell transcriptomic data, enabling simultaneous discovery of novel cell types and their annotation by leveraging the data's hierarchical structure.

Contribution

It proposes extensions of k-Means and GMM clustering algorithms specifically designed for hierarchical single-cell data, addressing the novel class discovery challenge.

Findings

Effective clustering of artificial and experimental datasets

Improved annotation accuracy for novel cell types

Leveraging hierarchical structure enhances discovery

Abstract

One of the major challenges arising from single-cell transcriptomics experiments is the question of how to annotate the associated single-cell transcriptomic profiles. Because of the large size and the high dimensionality of the data, automated methods for annotation are needed. We focus here on datasets obtained in the context of developmental biology, where the differentiation process leads to a hierarchical structure. We consider a frequent setting where both labeled and unlabeled data are available at training time, but the sets of the labels of labeled data on one side and of the unlabeled data on the other side, are disjoint. It is an instance of the Novel Class Discovery problem. The goal is to achieve two objectives, clustering the data and mapping the clusters with labels. We propose extensions of k-Means and GMM clustering methods for solving the problem and report comparative results on artificial and experimental transcriptomic datasets. Our approaches take advantage of the hierarchical nature of the data.