If you have not registered yet, once-off registration is required https://uni-sydney.zoom.us/meeting/register/tJMuc-yupzgqG9wuIVJI7qB8lAOGUreWpvP4 Single-cell transcriptomics profiling with single-cell RNA-seq (scRNA-seq) has provided unprecedented resolution in charatersing cell identities, cell functions across diverse tissues and conditions. Recent advances in measuring multiple modalities of single cells, such as single-cell ATAC sequencing (scATAC-seq), further enable characterisation of cells from different aspects. While scATAC-seq data provides the epigenomics profiling of cells, its extreme sparsity leads to its lack of the power of cell type identification. Therefore, integrative analysis of scRNA-seq and scATAC-seq allows not only cell type label transferring but also better understanding of the cellular phenotypes. We develop an end-to-end transfer learning algorithm, scJoint, to integrate scRNA-seq and scATAC-seq data. By building an integrative framework with neural network based dimension reduction and semi-supervised cell type prediction model, our algorithm is able to transfer labels from scRNA-seq to scATAC-seq data and construct a joint embedding for the two modalities. We illustrate our algorithm with two mouse cell atlas data from scRNA-seq and scATAC-seq data. We found that our algorithm outperforms the existing methods by a large margin in both joint visualisation of two modalities and cell type prediction.