Self-supervised contrastive learning for integrative single cell RNA-seq data analysis

Abstract

Single-cell RNA-sequencing (scRNA-seq) has become a powerful tool to reveal the complex biological diversity and heterogeneity among cell populations. However, the technical noise and bias of the technology still have negative impacts on the downstream analysis. Here, we present a self-supervised Contrastive LEArning framework for scRNA-seq (CLEAR) profile representation and the downstream analysis. CLEAR overcomes the heterogeneity of the experimental data with a specifically designed representation learning task and thus can handle batch effects and dropout events. In the task, the deep learning model learns to pull together the representations of similar cells while pushing apart distinct cells, without manual labeling. It achieves superior performance on a broad range of fundamental tasks, including clustering, visualization, dropout correction, batch effect removal, and pseudo-time inference. The proposed method successfully identifies and illustrates inflammatory-related mechanisms in a COVID-19 disease study with 43,695 single cells from peripheral blood mononuclear cells. Further experiments to process a million-scale single-cell dataset demonstrate the scalability of CLEAR. This scalable method generates effective scRNA-seq data representation while eliminating technical noise, and it will serve as a general computational framework for single-cell data analysis.

HiC-LDNet: A general and robust deep learning framework for accurate chromatin loop detection in genome-wide contact maps

“…Before feeding the data to the deep neural network, we first apply various data augmentation techniques to the training data sets [35, 36], including flipping, centered cropping, and adding random noise. During every epoch in the training process, the samples are flipped along their main diagonals with a probability of 0.5, while the original data set remains unmodified.…”

Contrastive Cycle Adversarial Autoencoders for Single-cell Multi-omics Alignment and Integration

“…The cell type labels could refer to biological cell types or the labels of data batches collected from different times or platforms. Following the idea of contrastive learning (31, 32), we employ a contrastive loss in embedding space. It enforces smaller In-Batch distance and larger Between-Batch distance.…”

A scalable sparse neural network framework for rare cell type annotation of single-cell transcriptome data

“…Typically, cell type annotation involves two steps: (1) clustering the cells into different subgroups and (2) labeling each group a specific type manually based on the prior-known marker genes. A number of unsupervised machine learning algorithms have been developed, including classical machine learning based methods such as Seurat 7 and Scanpy 8 , and newly published deep learning based methods, such as scDHA 9 and CLEAR 10 . However, these methods can be time-consuming and burdensome.…”