Tensor-Decomposition-Based Unsupervised Feature Extraction in Single-Cell Multiomics Data Analysis

Analysis of single-cell multiomics datasets is a novel topic and is considerably challenging because such datasets contain a large number of features with numerous missing values. In this study, we implemented a recently proposed tensor-decomposition (TD)-based unsupervised feature extraction (FE) technique to address this difficult problem. The technique can successfully integrate single-cell multiomics data composed of gene expression, DNA methylation, and accessibility. Although the last two have large dimensions, as many as ten million, containing only a few percentage of nonzero values, TD-based unsupervised FE can integrate three omics datasets without filling in missing values. Together with UMAP, which is used frequently when embedding single-cell measurements into two-dimensional space, TD-based unsupervised FE can produce two-dimensional embedding coincident with classification when integrating single-cell omics datasets. Genes selected based on TD-based unsupervised FE are also significantly related to reasonable biological roles.

Automated summary

This study applied a tensor-decomposition-based unsupervised feature extraction technique to integrate single-cell multiomics datasets, including gene expression, DNA methylation, and accessibility data. The method successfully handled high-dimensional datasets without filling in missing values, and in combination with UMAP, produced two-dimensional embeddings consistent with classification. Genes selected based on this technique were found to be significantly related to biological roles.