返回
Imputing missing values in single-cell RNA-sequencing data: a statistical and machine learning-based approach
DOI:10.1093/bib/bbag072.png)
摘要
En 中文
单细胞RNA测序(scRNA-seq)为捕获单个细胞内的基因表达模式提供了有力工具。然而,由于细胞内RNA含量有限,存在dropout事件,导致单细胞表达矩阵中出现大量零计数。为解决此问题,我们提出了一种名为单细胞dropout检测与插补(scDDI)的新方法。该方法利用泊松-负二项混合模型识别dropout事件,并随后使用决策树回归模型对缺失值进行插补。我们在模拟和真实scRNA-seq数据集上评估了scDDI的性能,证明了其优于现有的单细胞插补技术。值得注意的是,scDDI显著提高了dropout检测能力,从而在基因表达恢复、细胞聚类和细胞亚群识别等下游分析任务中表现出更优的性能。
Keyword:
single-cell RNA-sequencing
dropout
imputation
regression
clustering
downstream analysis
期刊
IF:
7.7
论文数:
5.8K
被引数:
2.7W
机构
引用论文
Single-cell RNA-Seq profiling of human preimplantation embryos and embryonic stem cells人植入前胚胎和胚胎干细胞的单细胞rna-seq谱
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
Best practices on the differential expression analysis of multi-species RNA-seq多物种rna-seq差异表达分析的最佳实践
GENOME BIOLOGY
IF9.4
scGNN is a novel graph neural network framework for single-cell RNA-Seq analysesscGNN是一种用于单细胞rna-seq分析的新型图形神经网络框架
NATURE COMMUNICATIONS
IF15.7
Rare Cell Detection by Single-Cell RNA Sequencing as Guided by Single-Molecule RNA FISH
CELL SYSTEMS
IF7.7

