Single-cell transcriptomic heterogeneity between conduit and resistance mesenteric arteries in rats

AGImpute: imputation of scRNA-seq data based on a hybrid GAN with dropouts identification

MOTIVATION

Dropout events bring challenges in analyzing single-cell RNA sequencing data as they introduce noise and distort the true distributions of gene expression profiles. Recent studies focus on estimating dropout probability and imputing dropout events by leveraging information from similar cells or genes. However, the number of dropout events differs in different cells, due to the complex factors, such as different sequencing protocols, cell types, and batch effects. The dropout event differences are not fully considered in assessing the similarities between cells and genes, which compromises the reliability of downstream analysis.

RESULTS

This work proposes a hybrid Generative Adversarial Network with dropouts identification to impute single-cell RNA sequencing data, named AGImpute. First, the numbers of dropout events in different cells in scRNA-seq data are differentially estimated by using a dynamic threshold estimation strategy. Next, the identified dropout events are imputed by a hybrid deep learning model, combining Autoencoder with a Generative Adversarial Network. To validate the efficiency of the AGImpute, it is compared with seven state-of-the-art dropout imputation methods on two simulated datasets and seven real single-cell RNA sequencing datasets. The results show that AGImpute imputes the least number of dropout events than other methods. Moreover, AGImpute enhances the performance of downstream analysis, including clustering performance, identifying cell-specific marker genes, and inferring trajectory in the time-course dataset.

AVAILABILITY AND IMPLEMENTATION

The source code can be obtained from https://github.com/xszhu-lab/AGImpute.

Endothelin-1 in Health and Disease

Discovered almost 40 years ago, the potent vasoconstrictor peptide endothelin-1 (ET-1) has a wide range of roles both physiologically and pathologically. In recent years, there has been a focus on the contribution of ET-1 to disease. This has led to the development of various ET receptor antagonists, some of which are approved for the treatment of pulmonary arterial hypertension, while clinical trials for other diseases have been numerous yet, for the most part, unsuccessful. However, given the vast physiological impact of ET-1, it is both surprising and disappointing that therapeutics targeting the ET-1 pathway remain limited. Strategies aimed at the pathways influencing the synthesis and release of ET-1 could provide new therapeutic avenues, yet research using cultured cells in vitro has had little follow up in intact ex vivo and in vivo preparations. This article summarises what is currently known about the synthesis, storage and release of ET-1 as well as the role of ET-1 in several diseases including cardiovascular diseases, COVID-19 and chronic pain. Unravelling the ET-1 pathway and identifying therapeutic targets has the potential to treat many diseases whether through disease prevention, slowing disease progression or reversing pathology.