scINSIGHT for interpreting single-cell gene expression from biologically heterogeneous data

Qian, Kun; Fu, Shiwei; Li, Hongwei; Li, Wei Vivian

The increasing number of scRNA-seq data emphasizes the need for integrative analysis to interpret similarities and differences between single-cell samples. Even though different batch effect removal methods have been developed, none of the existing methods is suitable for het-erogeneous single-cell samples coming from multiple biological conditions. To address this challenge, we propose a method named scINSIGHT to learn coordinated gene expression patterns that are common among or specific to different biological conditions, offering a unique chance to identify cellular identities and key biological processes across single-cell samples. We have evaluated scINSIGHT in comparison with state-of-the-art methods using simulated and real data, which consistently demonstrate its improved performance. In addition, our results show the applicability of scINSIGHT in diverse biomedical and clinical problems.