scDFC: A deep fusion clustering method for single-cell RNA-seq data

Clustering methods have been widely used in single-cell RNA-seq data for investigating tumor heterogeneity. Since traditional clustering methods fail to capture the high-dimension methods, deep clustering methods have drawn increasing attention these years due to their promising strengths on the task. However, existing methods consider either the attribute information of each cell or the structure information between different cells. In other words, they cannot sufficiently make use of all of this information simultaneously. To this end, we propose a novel single-cell deep fusion clustering model, which contains two modules, i.e. an attributed feature clustering module and a structure-attention feature clustering module. More concretely, two elegantly designed autoencoders are built to handle both features regardless of their data types. Experiments have demonstrated the validity of the proposed approach, showing that it is efficient to fuse attributes, structure, and attention information on single-cell RNA-seq data. This work will be further beneficial for investigating cell subpopulations and tumor microenvironment. The Python implementation of our work is now freely available at .

Automated summary

Clustering methods in single-cell RNA-seq data have been widely used for investigating tumor heterogeneity. Deep clustering methods, which have the strength to capture high-dimensional information, are gaining increasing attention. However, existing methods cannot effectively utilize attribute and structure information simultaneously. In this study, we propose a novel single-cell deep fusion clustering model that combines attributed and structure-attention features. Experimental results demonstrate the effectiveness of our approach in fusing attributes, structure, and attention information in single-cell RNA-seq data. This work has important implications for studying cell subpopulations and tumor microenvironment.