Transfer learning of multicellular organization via single-cell and spatial transcriptomics.

Journal: PLoS computational biology
PMID:

Abstract

Biological tissues exhibit complex gene expression and multicellular patterns that are valuable to dissect. Single-cell RNA sequencing (scRNA-seq) provides full coverages of genes, but lacks spatial information, whereas spatial transcriptomics (ST) measures spatial locations of individual or group of cells, with more restrictions on gene information. Here we show a transfer learning method named iSORT to decipher spatial organization of cells by integrating scRNA-seq and ST data. iSORT trains a neural network that maps gene expressions to spatial locations. iSORT can find spatial patterns at single-cell scale, identify spatial-organizing genes (SOGs) that drive the patterning, and infer pseudo-growth trajectories using a concept of SpaRNA velocity. Benchmarking on a range of biological systems, such as human cortex, mouse embryo, mouse brain, Drosophila embryo, and human developmental heart, demonstrates iSORT's accuracy and practicality in reconstructing multicellular organization. We further conducted scRNA-seq and ST sequencing from normal and atherosclerotic arteries, and the functional enrichment analysis shows that SOGs found by iSORT are strongly associated with vascular structural anomalies.

Authors

  • Yecheng Tan
    Research Institute of Intelligent Complex Systems, Fudan University, Shanghai, China.
  • Ai Wang
    Department of Radiology, Shanghai General Hospital, Jiading Branch, #800, Huangjiahuayuan Rd, Shanghai, China.
  • Zezhou Wang
    Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, China.
  • Wei Lin
    Department of Geriatric Rehabilitation, Jiangbin Hospital, Nanning, China.
  • Yan Yan
    Department of Biomedical Engineering, Wayne State University, Detroit, Michigan, USA.
  • Qing Nie
    Department of Mathematics, University of California, Irvine, Irvine, CA USA.
  • Jifan Shi
    Research Institute of Intelligent Complex Systems, Fudan University, Shanghai, China.