EpiXFormer: a cross-attention neural network for predicting cell type-specific transcription factor binding sites

Transcription factors (TFs) bind to specific sequences in the genome to regulate gene expression and specify cell states. TF binding sites (TFBSs) are cell type-specific, which can be attributed to epigenomic contexts. Comprehensive profiling of TFBSs across various cell types through experimental approaches is neither practical nor cost-friendly. Accurately identifying cell type-specific TFBSs through computational approaches remains challenging. Here, we develop EpiXFormer, a novel transformer-based neural network for cell type-specific TFBS prediction. EpiXFormer achieves exceptional performance in predicting binding sites of DNA-binding proteins (DBPs) across a diverse collection of cell types. It models the effects of proximal and distal epigenomic information on DBP binding and learns the identified motifs of the examined TFs and their potential co-occurring proteins. Moreover, we demonstrate that EpiXFormer can infer pioneer factors during cell type transition and delineate the cell type-specific regulatory functions of TFs. Overall, EpiXFormer enables cell type-specific TFBS prediction in the examined cell lines and is readily applied to other cell types of interest. It provides a robust, scalable framework for characterizing and interpreting multimodal genomic data.