返回
An order-preserving batch-effect correction method based on a monotonic deep learning framework
DOI:10.1093/bib/bbaf247.png)
摘要
En 中文
单细胞RNA测序显著加深了我们对细胞异质性和基因调控的理解。批次效应校正对于实现稳健的数据集成至关重要。已开发多种方法以解决此问题,特别是涉及锚定或深度学习等组件的流程方法,已取得显著成功。然而,作为一项重要特征,顺序保持性在流程方法中大多被忽视。基于单调深度学习网络,我们开发了一种具有顺序保持特性的校正方法。通过与现有方法比较,我们证明了该方法有效提升了聚类性能,更好地保留了原始基因间相关性及差异表达信息。
Keyword:
scRNA-sequencing
batch effect
order-preserving
monotonic deep learning network
inter-gene correlation
differential expression consistency
期刊
IF:
7.7
论文数:
5.6K
被引数:
2.7W
机构
引用论文
Single-Cell Transcriptome Profiling of Human Pancreatic Islets in Health and Type 2 Diabetes健康和2型糖尿病中人胰岛的单细胞转录组图谱
CELL METABOLISM
IF30.9
Single-cell RNA-seq reveals new types of human blood dendritic cells, monocytes, and progenitors单细胞rna-seq揭示了新型的人血树突状细胞,单核细胞和祖细胞
Science
IF0
From Louvain to Leiden: guaranteeing well-connected communities从鲁汶到莱顿: 保证良好连接的社区
SCIENTIFIC REPORTS
IF3.9
Construction of developmental lineage relationships in the mouse mammary gland by single-cell RNA profiling
NATURE COMMUNICATIONS
IF15.7

