School of Mathematics and Physics, China University of Geosciences, Wuhan 430074, China.
Brief Bioinform. 2024 Sep 23;25(6). doi: 10.1093/bib/bbae538.
The integration of single-cell RNA sequencing (scRNA-seq) data from multiple experimental batches enables more comprehensive characterizations of cell states. Given that existing methods disregard the structural information between cells and genes, we proposed a structure-preserved scRNA-seq data integration approach using heterogeneous graph neural network (scHetG). By establishing a heterogeneous graph that represents the interactions between multiple batches of cells and genes, and combining a heterogeneous graph neural network with contrastive learning, scHetG concurrently obtained cell and gene embeddings with structural information. A comprehensive assessment covering different species, tissues and scales indicated that scHetG is an efficacious method for eliminating batch effects while preserving the structural information of cells and genes, including batch-specific cell types and cell-type specific gene co-expression patterns.
单细胞 RNA 测序（scRNA-seq）数据的整合来自多个实验批次，可以更全面地描述细胞状态。鉴于现有方法忽略了细胞和基因之间的结构信息，我们提出了一种使用异质图神经网络（scHetG）保留结构的 scRNA-seq 数据整合方法。通过建立一个表示多个批次的细胞和基因之间相互作用的异质图，并结合异质图神经网络和对比学习，scHetG 同时获得了具有结构信息的细胞和基因嵌入。涵盖不同物种、组织和规模的综合评估表明，scHetG 是一种有效的方法，可以消除批次效应，同时保留细胞和基因的结构信息，包括批次特异性细胞类型和细胞类型特异性基因共表达模式。
