Infection with human T cell leukaemia/lymphoma virus type I in patients attending an antenatal clinic in London.

There is an increasing need for single cell omics data to be integrated across sources, types, and features of data. We present a deep clustering algorithm that learns discriminative representation for single-cell data via maximizing mutual information, SMILE (Single-cell Mutual Information Learning). SMILE successfully integrates multi-source single-cell transcriptome data and can also integrate single-cell ATAC-seq, RNA-seq, DNA methylation, and Hi-C data generated by the latest joint profiling technologies.