Abstract
BackgroundTranscription factor (TF) binding specificity is determined via a complex interplay between the transcription factor’s DNA binding preference and cell type-specific chromatin environments. The chromatin features that correlate with transcription factor binding in a given cell type have been well characterized. For instance, the binding sites for a majority of transcription factors display concurrent chromatin accessibility. However, concurrent chromatin features reflect the binding activities of the transcription factor itself and thus provide limited insight into how genome-wide TF-DNA binding patterns became established in the first place. To understand the determinants of transcription factor binding specificity, we therefore need to examine how newly activated transcription factors interact with sequence and preexisting chromatin landscapes.ResultsHere, we investigate the sequence and preexisting chromatin predictors of TF-DNA binding by examining the genome-wide occupancy of transcription factors that have been induced in well-characterized chromatin environments. We develop Bichrom, a bimodal neural network that jointly models sequence and preexisting chromatin data to interpret the genome-wide binding patterns of induced transcription factors. We find that the preexisting chromatin landscape is a differential global predictor of TF-DNA binding; incorporating preexisting chromatin features improves our ability to explain the binding specificity of some transcription factors substantially, but not others. Furthermore, by analyzing site-level predictors, we show that transcription factor binding in previously inaccessible chromatin tends to correspond to the presence of more favorable cognate DNA sequences.ConclusionsBichrom thus provides a framework for modeling, interpreting, and visualizing the joint sequence and chromatin landscapes that determine TF-DNA binding dynamics.
Highlights
Transcription factor (TF) binding specificity is determined via a complex interplay between the transcription factor’s DNA binding preference and cell type-specific chromatin environments
A bimodal neural network integrates DNA sequence and preexisting chromatin data to characterize TF binding predictors Bichrom’s bimodal neural network is composed of two sub-networks: one that operates only on DNA sequence features (BichromSEQ), and one that operates on chromatin features derived from ATAC-seq and ChIP-seq specific for histone modifications (BichromCHR)
Bichrom trains on binding labels for a TF that has become activated in a given cell type, using input features from DNA sequence and chromatin data profiled before the targeted TF has become active
Summary
Transcription factor (TF) binding specificity is determined via a complex interplay between the transcription factor’s DNA binding preference and cell type-specific chromatin environments. TFs typically bind a small fraction of their potential target motif instances in a given cell type, and the cohort of sites which are bound can vary greatly across cell types [6,7,8] These observations suggest that cell type-specific TF selectivity is governed by cell type-specific chromatin environments [5, 7, 9, 10]. Even pioneer TFs, which are characterized by their ability to bind target motifs in relatively inaccessible chromatin, bind DNA in cell type-specific patterns that can be modulated by other TFs [20,21,22,23]. It remains unclear how DNA sequence, chromatin structure, and interactions with other regulators act in concert to determine cell typespecific TF binding patterns
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
