Motivation
Single-cell RNA-sequencing (scRNA-seq) is widely used to reveal cellular heterogeneity, complex disease mechanisms, and cell differentiation processes. Due to high sparsity and complex gene expression patterns, scRNA-seq data presents a large number of dropout events, affecting downstream tasks such as cell clustering and pseudo-time analysis. Restoring the expression levels of genes is essential for reducing technical noise and facilitating downstream analysis. However, Existing scRNA-seq data imputation methods ignore the topological structure information of scRNA-seq data and cannot comprehensively utilize the relationships between cells.
Results
Here, we propose a single-cell Graph Contrastive Learning method for scRNA-seq data imputation, named scGCL, which integrates graph contrastive learning and Zero-inflated Negative Binomial (ZINB) distribution to estimate dropout values. scGCL summarizes global and local semantic information through contrastive learning and selects positive samples to enhance the representation of target nodes. To capture the global probability distribution, scGCL introduces an autoencoder based on the ZINB distribution, which reconstructs the scRNA-seq data based on the prior distribution. Through extensive experiments, we verify that scGCL outperforms existing state-of-the-art imputation methods in clustering performance and gene imputation on 14 scRNA-seq datasets. Further, we find that scGCL can enhance the expression patterns of specific genes in Alzheimer’s disease datasets.
Availability
https://github.com/zehaoxiong123/scGCL
Supplementary information
Supplementary data are available at Bioinformatics online.
Motivation
Cell-type annotation plays a crucial role in single-cell RNA-seq (scRNA-seq) data analysis. As more and more well-annotated scRNA-seq reference data is publicly available, automatical label transference algorithms are gaining popularity over manual marker gene-based annotation methods. However, most existing methods fail to unify cell-type annotation with dimensionality reduction, and are unable to generate deep latent representation from the perspective of data generation.
Results
In this article, we propose scSemiGAN, a semi-supervised cell-type annotation and dimensionality reduction framework based on generative adversarial network, to overcome these challenges, modeling scRNA-seq data from the aspect of data generation. Our proposed scSemiGAN is capable of performing deep latent representation learning and cell-type label prediction simultaneously. Through extensive comparison with four state-of-the-art annotation methods on diverse simulated and real scRNA-seq datasets, scSemiGAN achieves competitive or superior performance in multiple downstream tasks including cell-type annotation, latent representation visualization, confounding factor removal and enrichment analysis.
Availability
The code of scSemiGAN is available on GitHub: https://github.com/rafa-nadal/scSemiGAN.
Supplementary information
Supplementary data are available at Bioinformatics online.
Logistic regression is the industry standard in credit risk modeling. However, when the model is deployed, the lack of negative samples affects the accuracy of the model, and the nonlinear characteristics of the data itself cannot be learned. In this paper, a residual neural network combined with Gan is applied to the lending club public data set to predict credit default. Among them, the number of bad users is very small, which leads to sample imbalance, and then affects the effect of the model. For this problem, we use Gan (general adverse networks) to produce bad user samples, so that the proportion of good user samples and bad user samples reaches 1:1. Finally, the residual neural network is used to predict credit default, and the accuracy is improved by about 5% compared with logistic regression.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.