Online t-SNE for single-cell RNA-seq

TL;DR

This paper introduces online t-SNE, an incremental visualization method for sequential single-cell RNA-seq data that updates embeddings in real-time, enabling continuous discovery and visualization of evolving data structures.

Contribution

The paper presents online t-SNE, a novel method that updates t-SNE embeddings incrementally for sequential scRNA-seq data, overcoming limitations of static offline visualization.

Findings

Enables real-time visualization of evolving scRNA-seq data

Maintains high-quality embeddings without retraining from scratch

Demonstrates effective visualization across diverse datasets

Abstract

Due to the sequential sample arrival, changing experiment conditions, and evolution of knowledge, the demand to continually visualize evolving structures of sequential and diverse single-cell RNA-sequencing (scRNA-seq) data becomes indispensable. However, as one of the state-of-the-art visualization and analysis methods for scRNA-seq, t-distributed stochastic neighbor embedding (t-SNE) merely visualizes static scRNA-seq data offline and fails to meet the demand well. To address these challenges, we introduce online t-SNE to seamlessly integrate sequential scRNA-seq data. Online t-SNE achieves this by leveraging the embedding space of old samples, exploring the embedding space of new samples, and aligning the two embedding spaces on the fly. Consequently, online t-SNE dramatically enables the continual discovery of new structures and high-quality visualization of new scRNA-seq data without retraining from scratch. We showcase the formidable visualization capabilities of online t-SNE across diverse sequential scRNA-seq datasets.