Dataset Information

Pattern recognition of topologically associating domains using deep learning.

ABSTRACT:

Background

Recent increasing evidence indicates that three-dimensional chromosome structure plays an important role in genomic function. Topologically associating domains (TADs) are self-interacting regions that have been shown to be a chromosomal structural unit. During evolution, these are conserved based on checking synteny block cross species. Are there common TAD patterns across species or cell lines?

Results

To address the above question, we propose a novel task-TAD recognition-as opposed to traditional TAD identification. Specifically, we treat Hi-C maps as images, thus re-casting TAD recognition as image pattern recognition, for which we use a convolutional neural network and a residual neural network. In addition, we propose an elegant way to generate non-TAD data for binary classification. We demonstrate deep learning performance which is quite promising, AUC > 0.80, through cross-species and cell-type validation.

Conclusions

TADs have been shown to be conserved during evolution. Interestingly, our results confirm that the TAD recognition model is practical across species, which indicates that TADs between human and mouse show common patterns from an image classification point of view. Our approach could be a new way to identify TAD variations or patterns among Hi-C maps. For example, TADs of two Hi-C maps are conserved if the two classification models are exchangeable.

SUBMITTER: Yang JY

PROVIDER: S-EPMC9732975 | biostudies-literature | 2022 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Pattern recognition of topologically associating domains using deep learning.

Yang Jhen Yuan JY Chang Jia-Ming JM

BMC bioinformatics 20221208 Suppl 10

<h4>Background</h4>Recent increasing evidence indicates that three-dimensional chromosome structure plays an important role in genomic function. Topologically associating domains (TADs) are self-interacting regions that have been shown to be a chromosomal structural unit. During evolution, these are conserved based on checking synteny block cross species. Are there common TAD patterns across species or cell lines?<h4>Results</h4>To address the above question, we propose a novel task-TAD recognit ...[more]

PMID: 36482308

Similar Datasets

Project description:Chromatin is a polymer complex of DNA and proteins that regulates gene expression. The three-dimensional (3D) structure and organization of chromatin controls DNA transcription and replication. High-throughput chromatin conformation capture techniques generate Hi-C maps that can provide insight into the 3D structure of chromatin. Hi-C maps can be represented as a symmetric matrix [Formula: see text], where each element represents the average contact probability or number of contacts between chromatin loci i and j. Previous studies have detected topologically associating domains (TADs), or self-interacting regions in [Formula: see text] within which the contact probability is greater than that outside the region. Many algorithms have been developed to identify TADs within Hi-C maps. However, most TAD identification algorithms are unable to identify nested or overlapping TADs and for a given Hi-C map there is significant variation in the location and number of TADs identified by different methods. We develop a novel method to identify TADs, KerTAD, using a kernel-based technique from computer vision and image processing that is able to accurately identify nested and overlapping TADs. We benchmark this method against state-of-the-art TAD identification methods on both synthetic and experimental data sets. We find that the new method consistently has higher true positive rates (TPR) and lower false discovery rates (FDR) than all tested methods for both synthetic and manually annotated experimental Hi-C maps. The TPR for KerTAD is also largely insensitive to increasing noise and sparsity, in contrast to the other methods. We also find that KerTAD is consistent in the number and size of TADs identified across replicate experimental Hi-C maps for several organisms. Thus, KerTAD will improve automated TAD identification and enable researchers to better correlate changes in TADs to biological phenomena, such as enhancer-promoter interactions and disease states.

Project description:Experiments based on chromosome conformation capture have shown that mammalian genomes are partitioned into topologically associating domains (TADs), within which the chromatin fiber preferentially interacts. TADs may provide three-dimensional scaffolds allowing genes to contact their appropriate distal regulatory DNA sequences (e.g., enhancers) and thus to be properly regulated. Understanding the cell-to-cell and temporal variability of the chromatin fiber within TADs, and what determines them, is thus of great importance to better understand transcriptional regulation. We recently described an equilibrium polymer model that can accurately predict cell-to-cell variation of chromosome conformation within single TADs, from chromosome conformation capture-based data. Here we further analyze the conformational and energetic properties of our model. We show that the chromatin fiber within TADs can easily fluctuate between several conformational states, which are hierarchically organized and are not separated by important free energy barriers, and that this is facilitated by the fact that the chromatin fiber within TADs is close to the onset of the coil-globule transition. We further show that in this dynamic state the properties of the chromatin fiber, and its contact probabilities in particular, are determined in a nontrivial manner not only by site-specific interactions between strongly interacting loci along the fiber, but also by nonlocal correlations between pairs of contacts. Finally, we use live-cell experiments to measure the dynamics of the chromatin fiber in mouse embryonic stem cells, in combination with dynamical simulations, and predict that conformational changes within one TAD are likely to occur on timescales that are much shorter than the duration of one cell cycle. This suggests that genes and their regulatory elements may come together and disassociate several times during a cell cycle. These results have important implications for transcriptional regulation as they support the concept of highly dynamic interactions driven by a complex interplay between site-specific interactions and the intrinsic biophysical properties of the chromatin fiber.

Project description:Eukaryotic genomes are structurally organized via the formation of multiple loops that create gene expression regulatory units called topologically associating domains (TADs). Here we revealed the KSHV TAD structure at 500 bp resolution and constructed a 3D KSHV genomic structural model with 2 kb binning. The latent KSHV genome formed very similar genomic architectures in three different naturally infected PEL cell lines and in an experimentally infected epithelial cell line. The majority of the TAD boundaries were occupied by structural maintenance of chromosomes (SMC1) cohesin complex and CCCTC-binding factor (CTCF), and the KSHV transactivator was recruited to those sites during reactivation. Triggering KSHV gene expression decreased prewired genomic loops within the regulatory unit, while contacts extending outside of regulatory borders increased, leading to formation of a larger regulatory unit with a shift from repressive to active compartments (B to A). The 3D genomic structural model proposes that the immediate early promoter region is localized on the periphery of the 3D viral genome during latency, while highly inducible noncoding RNA regions moved toward the inner space of the structure, resembling the configuration of a "bird cage" during reactivation. The compartment-like properties of viral episomal chromatin structure and its reorganization during the transition from latency may help facilitate viral gene transcription. IMPORTANCE The 3D architecture of chromatin allows for efficient arrangement, expression, and replication of genetic material. The genomes of all organisms studied to date have been found to be organized through some form of tiered domain structures. However, the architectural framework of the genomes of large double-stranded DNA viruses such as the herpesvirus family has not been reported. Prior studies with Kaposi's sarcoma-associated herpesvirus (KSHV) have indicated that the viral chromatin shares many biological properties exhibited by the host cell genome, essentially behaving as a mini human chromosome. Thus, we hypothesized that the KSHV genome may be organized in a similar manner. In this report, we describe the domain structure of the latent and lytic KSHV genome at 500 bp resolution and present a 3D genomic structural model for KSHV under each condition. These results add new insights into the complex regulation of the viral life cycle.

Project description:Eukaryotic chromosomes replicate in a temporal order known as the replication-timing program. In mammals, replication timing is cell-type-specific with at least half the genome switching replication timing during development, primarily in units of 400-800 kilobases ('replication domains'), whose positions are preserved in different cell types, conserved between species, and appear to confine long-range effects of chromosome rearrangements. Early and late replication correlate, respectively, with open and closed three-dimensional chromatin compartments identified by high-resolution chromosome conformation capture (Hi-C), and, to a lesser extent, late replication correlates with lamina-associated domains (LADs). Recent Hi-C mapping has unveiled substructure within chromatin compartments called topologically associating domains (TADs) that are largely conserved in their positions between cell types and are similar in size to replication domains. However, TADs can be further sub-stratified into smaller domains, challenging the significance of structures at any particular scale. Moreover, attempts to reconcile TADs and LADs to replication-timing data have not revealed a common, underlying domain structure. Here we localize boundaries of replication domains to the early-replicating border of replication-timing transitions and map their positions in 18 human and 13 mouse cell types. We demonstrate that, collectively, replication domain boundaries share a near one-to-one correlation with TAD boundaries, whereas within a cell type, adjacent TADs that replicate at similar times obscure replication domain boundaries, largely accounting for the previously reported lack of alignment. Moreover, cell-type-specific replication timing of TADs partitions the genome into two large-scale sub-nuclear compartments revealing that replication-timing transitions are indistinguishable from late-replicating regions in chromatin composition and lamina association and accounting for the reduced correlation of replication timing to LADs and heterochromatin. Our results reconcile cell-type-specific sub-nuclear compartmentalization and replication timing with developmentally stable structural domains and offer a unified model for large-scale chromosome structure and function.

Dataset Information

Pattern recognition of topologically associating domains using deep learning.

Background

Results

Conclusions

Publications

Pattern recognition of topologically associating domains using deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets