Gene knockout inference with variational graph autoencoder learning single-cell gene regulatory networks

Abstract In this paper, we introduce Gene Knockout Inference (GenKI), a virtual knockout (KO) tool for gene function prediction using single-cell RNA sequencing (scRNA-seq) data in the absence of KO samples when only wild-type (WT) samples are available. Without using any information from real KO sa...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Nucleic acids research Ročník 51; číslo 13; s. 6578 - 6592
Hlavní autoři:	Yang, Yongjian, Li, Guanxun, Zhong, Yan, Xu, Qian, Chen, Bo-Jia, Lin, Yu-Te, Chapkin, Robert S, Cai, James J
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	England Oxford University Press 21.07.2023
Témata:	Animals Computational Biology Gene Expression Profiling Gene Expression Regulation Gene Knockout Techniques Gene Regulatory Networks Sequence Analysis, RNA Single-Cell Analysis
ISSN:	0305-1048, 1362-4962, 1362-4962
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Abstract In this paper, we introduce Gene Knockout Inference (GenKI), a virtual knockout (KO) tool for gene function prediction using single-cell RNA sequencing (scRNA-seq) data in the absence of KO samples when only wild-type (WT) samples are available. Without using any information from real KO samples, GenKI is designed to capture shifting patterns in gene regulation caused by the KO perturbation in an unsupervised manner and provide a robust and scalable framework for gene function studies. To achieve this goal, GenKI adapts a variational graph autoencoder (VGAE) model to learn latent representations of genes and interactions between genes from the input WT scRNA-seq data and a derived single-cell gene regulatory network (scGRN). The virtual KO data is then generated by computationally removing all edges of the KO gene—the gene to be knocked out for functional study—from the scGRN. The differences between WT and virtual KO data are discerned by using their corresponding latent parameters derived from the trained VGAE model. Our simulations show that GenKI accurately approximates the perturbation profiles upon gene KO and outperforms the state-of-the-art under a series of evaluation conditions. Using publicly available scRNA-seq data sets, we demonstrate that GenKI recapitulates discoveries of real-animal KO experiments and accurately predicts cell type-specific functions of KO genes. Thus, GenKI provides an in-silico alternative to KO experiments that may partially replace the need for genetically modified animals or other genetically perturbed systems. Graphical Abstract Graphical Abstract
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0305-1048 1362-4962 1362-4962
DOI:	10.1093/nar/gkad450