Interpretable deep learning reveals the sequence rules of Hippo signaling (ChIP-Seq)

How specific cells respond to signaling pathways is largely encoded in the DNA sequence. However, the sequence rules result from complex interactions between signaling and cell-type-specific transcription factors and are considered intractable by traditional methods. Here, we leverage interpretable deep learning on high-resolution data and extensive validation experiments to identify the sequence rules for the Hippo pathway in mouse trophoblast stem cells. We show that Tead4 and Yap1 engage in two types of cooperativity. First, their binding is enhanced by cell-type-specific transcription factors, including Tfap2c, in a distance-dependent manner. Second, a strictly-spaced Tead double motif is a canonical Hippo pathway element that mediates strong Tead4 cooperativity through transient protein-protein interactions on DNA. These mechanisms occur genome-wide and allow us to predict how small sequence changes alter the activity of enhancers in vivo. This illustrates the power of interpretable deep learning to decode canonical and cell type-specific sequence rules of signaling pathways. Chromatin immunoprecipitation DNA-sequencing (ChIP-nexus) for Tead4, Yap1, Tfap2c, Cdx2, Gata3 and Pol II Factors, as well as H3K27ac ChIP-seq experiment, in wild-type mouse trophoblast stem cells (Singh and Gerton 2021). ChIP-nexus for Tead4,Pol II and ChIP-seq H3K27ac in CRISPR mutatated cell lines at genomic region of chr12:102,261,820-102,262,484 (putative enhancer for Rin3 gene consisting Tfap2c and Tead motifs) & chr17:6,827,739-6,828,394 (putative enhancer for Ezrin gene consisting for Tead double motif) Chromatin immunoprecipitation DNA-sequencing (ChIP-nexus) for Tead4, in wild-type mouse embryonic stem cells (R1-ESCs).