Abstract
BackgroundDNA inside eukaryotic cells wraps around histones to form the 11nm chromatin fiber that can further fold into higher-order DNA loops, which may depend on the binding of architectural factors. Predicting how the DNA will fold given a distribution of bound factors, here viewed as a type of sequence, is currently an unsolved problem and several heterogeneous polymer models have shown that many features of the measured structure can be reproduced from simulations. However a model that determines the optimal connection between sequence and structure and that can rapidly assess the effects of varying either one is still lacking.ResultsHere we train a dense neural network to solve for the local folding of chromatin, connecting structure, represented as a contact map, to a sequence of bound chromatin factors. The network includes a convolutional filter that compresses the large number of bound chromatin factors into a single 1D sequence representation that is optimized for predicting structure. We also train a network to solve the inverse problem, namely given only structural information in the form of a contact map, predict the likely sequence of chromatin states that generated it.ConclusionsBy carrying out sensitivity analysis on both networks, we are able to highlight the importance of chromatin contexts and neighborhoods for regulating long-range contacts, along with critical alterations that affect contact formation. Our analysis shows that the networks have learned physical insights that are informative and intuitive about this complex polymer problem.
Highlights
DNA inside eukaryotic cells wraps around histones to form the 11nm chromatin fiber that can further fold into higher-order DNA loops, which may depend on the binding of architectural factors
The chromatin states that were used as inputs were based on an unsupervised clustering of bound chromatin factors that did not take into account any structural information [30]
We take as sequence data the enrichment of each site for a given bound protein that is associated with the folding of chromatin. (For the results that follow here, we use Hi-C data collected from Drosophila Melanogaster embryos at a resolution of 10 kbp for structure and we use the genome-wide distribution of 50 different bound chromatin-associated factors as sequence.) Our aim is to train the neural networks to make predictions at the intra-chromosomal scale, i.e. using sequence data for a region of a chromosome predict the corresponding sub-region of the Hi-C contact map
Summary
DNA inside eukaryotic cells wraps around histones to form the 11nm chromatin fiber that can further fold into higher-order DNA loops, which may depend on the binding of architectural factors. The condensation of the DNA into the spatial arrangement of bound chromatin factors along chromatin fibers that fold into specific 3D structures the DNA strongly influences the probability of chromatin brings distant sites of the genome into spatial proxim- contacts between distant genomic regions [6]. It is unlikely that this classification constitutes the best 1D description of the sequence that determines chromatin structure and one may expect to achieve better predictive power by generating a conformation-specific annotation of the sequence of chromatin states. Methods that integrate both chromatin structure and sequence into a unified framework that can rapidly predict the respective contributions of changing sequence or structure are needed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
