Dissecting the cis -regulatory syntax of transcription initiation with deep learning.

Despite extensive characterization of mammalian Pol II transcription, the DNA sequence determinants of transcription initiation at a third of human promoters and most enhancers remain poorly understood. We trained and interpreted a neural network called ProCapNet that accurately models base-resolution initiation profiles from PRO-cap experiments using local DNA sequence. ProCapNet learns sequence motifs with distinct effects on initiation rates and TSS positioning and uncovers context-specific cryptic initiator elements intertwined within other TF motifs. ProCapNet annotates predictive motifs in nearly all actively transcribed regulatory elements across multiple cell-lines, revealing a shared cis -regulatory logic across promoters and enhancers and a highly epistatic sequence syntax of cooperative and competitive motif interactions. ProCapNet models of steady-state RAMPAGE profiles distill initiation signals on par with models trained directly on PRO-cap profiles. ProCapNet learns a largely cell-type-agnostic cis -regulatory code of initiation complementing sequence drivers of cell-type-specific chromatin state critical for accurate prediction of cell-type-specific transcription initiation.
Competing Interests: Competing Interests A.K. is on the scientific advisory board of SerImmune, AINovo, TensorBio and OpenTargets. A.K. was a scientific co-founder of RavelBio, a paid consultant with Illumina, was on the SAB of PatchBio and owns shares in DeepGenomics, Immunai, Freenome, and Illumina. K.C. is a paid consultant with ImmunoVec and owns shares in Inceptive Nucleics. J.S. is a paid consultant for Talus Bioscience and ImmunoVec. All other authors have no competing interests to declare.