Predicting CTCF-mediated chromatin interactions by integrating genomic and epigenomic features

Regulatory landscape enrichment analysis (RLEA): a computational toolkit for non-coding variant enrichment and cell type prioritization

BACKGROUND

As genomic studies continue to implicate non-coding sequences in disease, testing the roles of these variants requires insights into the cell type(s) in which they are likely to be mediating their effects. Prior methods for associating non-coding variants with cell types have involved approaches using linkage disequilibrium or ontological associations, incurring significant processing requirements. GaiaAssociation is a freely available, open-source software that enables thousands of genomic loci implicated in a phenotype to be tested for enrichment at regulatory loci of multiple cell types in minutes, permitting insights into the cell type(s) mediating the studied phenotype.

RESULTS

In this work, we present Regulatory Landscape Enrichment Analysis (RLEA) by GaiaAssociation and demonstrate its capability to test the enrichment of 12,133 variants across the cis-regulatory regions of 44 cell types. This analysis was completed in 134.0 ± 2.3 s, highlighting the efficient processing provided by GaiaAssociation. The intuitive interface requires only four inputs, offers a collection of customizable functions, and visualizes variant enrichment in cell-type regulatory regions through a heatmap matrix. GaiaAssociation is available on PyPi for download as a command line tool or Python package and the source code can also be installed from GitHub at https://github.com/GreallyLab/gaiaAssociation .

CONCLUSIONS

GaiaAssociation is a novel package that provides an intuitive and efficient resource to understand the enrichment of non-coding variants across the cis-regulatory regions of different cells, empowering studies seeking to identify disease-mediating cell types.

CD-Loop: a chromatin loop detection method based on the diffusion model

Motivation

In recent years, there have been significant advances in various chromatin conformation capture techniques, and annotating the topological structure from Hi-C contact maps has become crucial for studying the three-dimensional structure of chromosomes. However, the structure and function of chromatin loops are highly dynamic and diverse, influenced by multiple factors. Therefore, obtaining the three-dimensional structure of the genome remains a challenging task. Among many chromatin loop prediction methods, it is difficult to fully extract features from the contact map and make accurate predictions at low sequencing depths.

Results

In this study, we put forward a deep learning framework based on the diffusion model called CD-Loop for predicting accurate chromatin loops. First, by pre-training the input data, we obtain prior probabilities for predicting the classification of the Hi-C contact map. Then, by combining the denoising process based on the diffusion model and the prior probability obtained by pre-training, candidate loops were predicted from the input Hi-C contact map. Finally, CD-Loop uses a density-based clustering algorithm to cluster the candidate chromatin loops and predict the final chromatin loops. We compared CD-Loop with the currently popular methods, such as Peakachu, Chromosight, and Mustache, and found that in different cell types, species, and sequencing depths, CD-Loop outperforms other methods in loop annotation. We conclude that CD-Loop can accurately predict chromatin loops and reveal cell-type specificity. The code is available at https://github.com/wangyang199897/CD-Loop.

A systematic analyses of different bioinformatics pipelines for genomic data and its impact on deep learning models for chromatin loop prediction

Genomic data analysis has witnessed a surge in complexity and volume, primarily driven by the advent of high-throughput technologies. In particular, studying chromatin loops and structures has become pivotal in understanding gene regulation and genome organization. This systematic investigation explores the realm of specialized bioinformatics pipelines designed specifically for the analysis of chromatin loops and structures. Our investigation incorporates two protein (CTCF and Cohesin) factor-specific loop interaction datasets from six distinct pipelines, amassing a comprehensive collection of 36 diverse datasets. Through a meticulous review of existing literature, we offer a holistic perspective on the methodologies, tools and algorithms underpinning the analysis of this multifaceted genomic feature. We illuminate the vast array of approaches deployed, encompassing pivotal aspects such as data preparation pipeline, preprocessing, statistical features and modelling techniques. Beyond this, we rigorously assess the strengths and limitations inherent in these bioinformatics pipelines, shedding light on the interplay between data quality and the performance of deep learning models, ultimately advancing our comprehension of genomic intricacies.

Machine and deep learning methods for predicting 3D genome organization

Three-Dimensional (3D) chromatin interactions, such as enhancer-promoter interactions (EPIs), loops, Topologically Associating Domains (TADs), and A/B compartments play critical roles in a wide range of cellular processes by regulating gene expression. Recent development of chromatin conformation capture technologies has enabled genome-wide profiling of various 3D structures, even with single cells. However, current catalogs of 3D structures remain incomplete and unreliable due to differences in technology, tools, and low data resolution. Machine learning methods have emerged as an alternative to obtain missing 3D interactions and/or improve resolution. Such methods frequently use genome annotation data (ChIP-seq, DNAse-seq, etc.), DNA sequencing information (k-mers, Transcription Factor Binding Site (TFBS) motifs), and other genomic properties to learn the associations between genomic features and chromatin interactions. In this review, we discuss computational tools for predicting three types of 3D interactions (EPIs, chromatin interactions, TAD boundaries) and analyze their pros and cons. We also point out obstacles of computational prediction of 3D interactions and suggest future research directions.

SpecLoop predicts cell type-specific chromatin loop via transcription factor cooperation

Cell-type-Specific Chromatin Loops (CSCLs) are crucial for gene regulation and cell fate determination. However, the mechanisms governing their establishment remain elusive. Here, we present SpecLoop, a network regularization-based machine learning framework, to investigate the role of transcription factors (TFs) cooperation in CSCL formation. SpecLoop integrates multi-omics data, including gene expression, chromatin accessibility, sequence, protein-protein interaction, and TF binding motif data, to predict CSCLs and identify TF cooperations. Using high resolution Hi-C data as the gold standard, SpecLoop accurately predicts CSCL in GM12878, IMR90, HeLa-S3, K562, HUVEC, HMEC, and NHEK seven cell types, with the AUROC values ranging from 0.8645 to 0.9852 and AUPR values ranging from 0.8654 to 0.9734. Notably SpecLoop demonstrates improved accuracy in predicting long-distance CSCLs and identifies TF complexes with strong predictive ability. Our study systematically explores the TFs and TF pairs associated with CSCL through effective integration of diverse omics data. SpecLoop is freely available at https://github.com/AMSSwanglab/SpecLoop.

Computational methods for analysing multiscale 3D genome organization

Recent progress in whole-genome mapping and imaging technologies has enabled the characterization of the spatial organization and folding of the genome in the nucleus. In parallel, advanced computational methods have been developed to leverage these mapping data to reveal multiscale three-dimensional (3D) genome features and to provide a more complete view of genome structure and its connections to genome functions such as transcription. Here, we discuss how recently developed computational tools, including machine-learning-based methods and integrative structure-modelling frameworks, have led to a systematic, multiscale delineation of the connections among different scales of 3D genome organization, genomic and epigenomic features, functional nuclear components and genome function. However, approaches that more comprehensively integrate a wide variety of genomic and imaging datasets are still needed to uncover the functional role of 3D genome structure in defining cellular phenotypes in health and disease.

IChrom-Deep: An Attention-Based Deep Learning Model for Identifying Chromatin Interactions

Identification of chromatin interactions is crucial for advancing our knowledge of gene regulation. However, due to the limitations of high-throughput experimental techniques, there is an urgent need to develop computational methods for predicting chromatin interactions. In this study, we propose a novel attention-based deep learning model, termed IChrom-Deep, to identify chromatin interactions using sequence features and genomic features. The experimental results based on the datasets of three cell lines demonstrate that the IChrom-Deep achieves satisfactory performance and is superior to the previous methods. We also investigate the effect of DNA sequence and associated features and genomic features on chromatin interactions, and highlight the applicable scenarios of some features, such as sequence conservation and distance. Moreover, we identify a few genomic features that are extremely important across different cell lines, and IChrom-Deep achieves comparable performance with only these significant genomic features versus using all genomic features. It is believed that IChrom-Deep can serve as a useful tool for future studies that seek to identify chromatin interactions.

Inferring CTCF-binding patterns and anchored loops across human tissues and cell types

CCCTC-binding factor (CTCF) is a transcription regulator with a complex role in gene regulation. The recognition and effects of CTCF on DNA sequences, chromosome barriers, and enhancer blocking are not well understood. Existing computational tools struggle to assess the regulatory potential of CTCF-binding sites and their impact on chromatin loop formation. Here we have developed a deep-learning model, DeepAnchor, to accurately characterize CTCF binding using high-resolution genomic/epigenomic features. This has revealed distinct chromatin and sequence patterns for CTCF-mediated insulation and looping. An optimized implementation of a previous loop model based on DeepAnchor score excels in predicting CTCF-anchored loops. We have established a compendium of CTCF-anchored loops across 52 human tissue/cell types, and this suggests that genomic disruption of these loops could be a general mechanism of disease pathogenesis. These computational models and resources can help investigate how CTCF-mediated cis-regulatory elements shape context-specific gene regulation in cell development and disease progression.

DeepChIA-PET: Accurately predicting ChIA-PET from Hi-C and ChIP-seq with deep dilated networks

Chromatin interaction analysis by paired-end tag sequencing (ChIA-PET) can capture genome-wide chromatin interactions mediated by a specific DNA-associated protein. The ChIA-PET experiments have been applied to explore the key roles of different protein factors in chromatin folding and transcription regulation. However, compared with widely available Hi-C and ChIP-seq data, there are not many ChIA-PET datasets available in the literature. A computational method for accurately predicting ChIA-PET interactions from Hi-C and ChIP-seq data is needed that can save the efforts of performing wet-lab experiments. Here we present DeepChIA-PET, a supervised deep learning approach that can accurately predict ChIA-PET interactions by learning the latent relationships between ChIA-PET and two widely used data types: Hi-C and ChIP-seq. We trained our deep models with CTCF-mediated ChIA-PET of GM12878 as ground truth, and the deep network contains 40 dilated residual convolutional blocks. We first showed that DeepChIA-PET with only Hi-C as input significantly outperforms Peakachu, another computational method for predicting ChIA-PET from Hi-C but using random forests. We next proved that adding ChIP-seq as one extra input does improve the classification performance of DeepChIA-PET, but Hi-C plays a more prominent role in DeepChIA-PET than ChIP-seq. Our evaluation results indicate that our learned models can accurately predict not only CTCF-mediated ChIA-ET in GM12878 and HeLa but also non-CTCF ChIA-PET interactions, including RNA polymerase II (RNAPII) ChIA-PET of GM12878, RAD21 ChIA-PET of GM12878, and RAD21 ChIA-PET of K562. In total, DeepChIA-PET is an accurate tool for predicting the ChIA-PET interactions mediated by various chromatin-associated proteins from different cell types.

Benefiting from the intrinsic role of epigenetics to predict patterns of CTCF binding

Motivation

One of the most relevant mechanisms involved in the determination of chromatin structure is the formation of structural loops that are also related with the conservation of chromatin states. Many of these loops are stabilized by CCCTC-binding factor (CTCF) proteins at their base. Despite the relevance of chromatin structure and the key role of CTCF, the role of the epigenetic factors that are involved in the regulation of CTCF binding, and thus, in the formation of structural loops in the chromatin, is not thoroughly understood.

Results

Here we describe a CTCF binding predictor based on Random Forest that employs different epigenetic data and genomic features. Importantly, given the ability of Random Forests to determine the relevance of features for the prediction, our approach also shows how the different types of descriptors impact the binding of CTCF, confirming previous knowledge on the relevance of chromatin accessibility and DNA methylation, but demonstrating the effect of epigenetic modifications on the activity of CTCF. We compared our approach against other predictors and found improved performance in terms of areas under PR and ROC curves (PRAUC-ROCAUC), outperforming current state-of-the-art methods.

Prediction of CTCF loop anchor based on machine learning

Introduction: Various activities in biological cells are affected by three-dimensional genome structure. The insulators play an important role in the organization of higher-order structure. CTCF is a representative of mammalian insulators, which can produce barriers to prevent the continuous extrusion of chromatin loop. As a multifunctional protein, CTCF has tens of thousands of binding sites in the genome, but only a portion of them can be used as anchors of chromatin loops. It is still unclear how cells select the anchor in the process of chromatin looping.

Methods: In this paper, a comparative analysis is performed to investigate the sequence preference and binding strength of anchor and non-anchor CTCF binding sites. Furthermore, a machine learning model based on the CTCF binding intensity and DNA sequence is proposed to predict which CTCF sites can form chromatin loop anchors.

Results: The accuracy of the machine learning model that we constructed for predicting the anchor of the chromatin loop mediated by CTCF reached 0.8646. And we find that the formation of loop anchor is mainly influenced by the CTCF binding strength and binding pattern (which can be interpreted as the binding of different zinc fingers).

Discussion: In conclusion, our results suggest that The CTCF core motif and it’s flanking sequence may be responsible for the binding specificity. This work contributes to understanding the mechanism of loop anchor selection and provides a reference for the prediction of CTCF-mediated chromatin loops.

Regulation of loop extrusion on the interphase genome

In the human cell nucleus, dynamically organized chromatin is the substrate for gene regulation, DNA replication, and repair. A central mechanism of DNA loop formation is an ATPase motor cohesin-mediated loop extrusion. The cohesin complexes load and unload onto the chromosome under the control of other regulators that physically interact and affect motor activity. Regulation of the dynamic loading cycle of cohesin influences not only the chromatin structure but also genome-associated human disorders and aging. This review focuses on the recently spotlighted genome organizing factors and the mechanism by which their dynamic interactions shape the genome architecture in interphase.

The Interplay of Transcription and Genome Topology Programs T Cell Development and Differentiation

T cells are essential for mounting defense against various pathogens and malignantly transformed cells. Thymic development and peripheral T cell differentiation are highly orchestrated biological processes that require precise gene regulation. Higher-order genome organization on multiple scales, in the form of chromatin loops, topologically associating domains and compartments, provides pivotal control of T cell gene expression. CTCF and the cohesin machinery are ubiquitously expressed architectural proteins responsible for establishing chromatin structures. Recent studies indicate that transcription factors, such as T lineage-defining Tcf1 and TCR-induced Batf, may have intrinsic ability and/or engage CTCF to shape chromatin architecture. In this article, we summarize current knowledge on the dynamic changes in genome topology that underlie normal or leukemic T cell development, CD4+ helper T cell differentiation, and CD8+ cytotoxic T cell functions. The knowledge lays a solid foundation for elucidating the causative link of spatial chromatin configuration to transcriptional and functional output in T cells.

DLoopCaller: A deep learning approach for predicting genome-wide chromatin loops by integrating accessible chromatin landscapes

In recent years, major advances have been made in various chromosome conformation capture technologies to further satisfy the needs of researchers for high-quality, high-resolution contact interactions. Discriminating the loops from genome-wide contact interactions is crucial for dissecting three-dimensional(3D) genome structure and function. Here, we present a deep learning method to predict genome-wide chromatin loops, called DLoopCaller, by combining accessible chromatin landscapes and raw Hi-C contact maps. Some available orthogonal data ChIA-PET/HiChIP and Capture Hi-C were used to generate positive samples with a wider contact matrix which provides the possibility to find more potential genome-wide chromatin loops. The experimental results demonstrate that DLoopCaller effectively improves the accuracy of predicting genome-wide chromatin loops compared to the state-of-the-art method Peakachu. Moreover, compared to two of most popular loop callers, such as HiCCUPS and Fit-Hi-C, DLoopCaller identifies some unique interactions. We conclude that a combination of chromatin landscapes on the one-dimensional genome contributes to understanding the 3D genome organization, and the identified chromatin loops reveal cell-type specificity and transcription factor motif co-enrichment across different cell lines and species.

CLNN-loop: a deep learning model to predict CTCF-mediated chromatin loops in the different cell lines and CTCF-binding sites (CBS) pair types

MOTIVATION

Three-dimensional (3D) genome organization is of vital importance in gene regulation and disease mechanisms. Previous studies have shown that CTCF-mediated chromatin loops are crucial to studying the 3D structure of cells. Although various experimental techniques have been developed to detect chromatin loops, they have been found to be time-consuming and costly. Nowadays, various sequence-based computational methods can capture significant features of 3D genome organization and help predict chromatin loops. However, these methods have low performance and poor generalization ability in predicting chromatin loops.

RESULTS

Here, we propose a novel deep learning model, called CLNN-loop, to predict chromatin loops in different cell lines and CTCF-binding sites (CBS) pair types by fusing multiple sequence-based features. The analysis of a series of examinations based on the datasets in the previous study shows that CLNN-loop has satisfactory performance and is superior to the existing methods in terms of predicting chromatin loops. In addition, we apply the SHAP framework to interpret the predictions of different models, and find that CTCF motif and sequence conservation are important signs of chromatin loops in different cell lines and CBS pair types.

AVAILABILITY AND IMPLEMENTATION

The source code of CLNN-loop is freely available at https://github.com/HaoWuLab-Bioinformatics/CLNN-loop and the webserver of CLNN-loop is freely available at http://hwclnn.sdu.edu.cn.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Machine Learning Methods for Exploring Sequence Determinants of 3D Genome Organization

In higher eukaryotic cells, chromosomes are folded inside the nucleus. Recent advances in whole-genome mapping technologies have revealed the multiscale features of 3D genome organization that are intertwined with fundamental genome functions. However, DNA sequence determinants that modulate the formation of 3D genome organization remain poorly characterized. In the past few years, predicting 3D genome organization based on DNA sequence features has become an active area of research. Here, we review the recent progress in computational approaches to unraveling important sequence elements for 3D genome organization. In particular, we discuss the rapid development of machine learning-based methods that facilitate the connections between DNA sequence features and 3D genome architectures at different scales. While much progress has been made in developing predictive models for revealing important sequence features for 3D genome organization, new research is urgently needed to incorporate multi-omic data and enhance model interpretability, further advancing our understanding of gene regulation mechanisms through the lens of 3D genome organization.

Recommendations for clinical interpretation of variants found in non-coding regions of the genome

BACKGROUND

The majority of clinical genetic testing focuses almost exclusively on regions of the genome that directly encode proteins. The important role of variants in non-coding regions in penetrant disease is, however, increasingly being demonstrated, and the use of whole genome sequencing in clinical diagnostic settings is rising across a large range of genetic disorders. Despite this, there is no existing guidance on how current guidelines designed primarily for variants in protein-coding regions should be adapted for variants identified in other genomic contexts.

METHODS

We convened a panel of nine clinical and research scientists with wide-ranging expertise in clinical variant interpretation, with specific experience in variants within non-coding regions. This panel discussed and refined an initial draft of the guidelines which were then extensively tested and reviewed by external groups.

RESULTS

We discuss considerations specifically for variants in non-coding regions of the genome. We outline how to define candidate regulatory elements, highlight examples of mechanisms through which non-coding region variants can lead to penetrant monogenic disease, and outline how existing guidelines can be adapted for the interpretation of these variants.

CONCLUSIONS

These recommendations aim to increase the number and range of non-coding region variants that can be clinically interpreted, which, together with a compatible phenotype, can lead to new diagnoses and catalyse the discovery of novel disease mechanisms.

DeepLUCIA: predicting tissue-specific chromatin loops using Deep Learning-based Universal Chromatin Interaction Annotator

MOTIVATION

The importance of chromatin loops in gene regulation is broadly accepted. There are mainly two approaches to predict chromatin loops: transcription factor (TF) binding-dependent approach and genomic variation-based approach. However, neither of these approaches provides an adequate understanding of gene regulation in human tissues. To address this issue, we developed a deep learning-based chromatin loop prediction model called DeepLUCIA (Deep Learning-based Universal Chromatin Interaction Annotator).

RESULTS

Although DeepLUCIA does not use TF binding profile data which previous TF binding-dependent methods critically rely on, its prediction accuracies are comparable to those of the previous TF binding-dependent methods. More importantly, DeepLUCIA enables the tissue-specific chromatin loop predictions from tissue-specific epigenomes that cannot be handled by genomic variation-based approach. We demonstrated the utility of the DeepLUCIA by predicting several novel target genes of SNPs identified in genome-wide association studies targeting Brugada syndrome, COVID-19 severity, and age-related macular degeneration.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

InsuLock: A Weakly Supervised Learning Approach for Accurate Insulator Prediction, and Variant Impact Quantification

Mapping chromatin insulator loops is crucial to investigating genome evolution, elucidating critical biological functions, and ultimately quantifying variant impact in diseases. However, chromatin conformation profiling assays are usually expensive, time-consuming, and may report fuzzy insulator annotations with low resolution. Therefore, we propose a weakly supervised deep learning method, InsuLock, to address these challenges. Specifically, InsuLock first utilizes a Siamese neural network to predict the existence of insulators within a given region (up to 2000 bp). Then, it uses an object detection module for precise insulator boundary localization via gradient-weighted class activation mapping (~40 bp resolution). Finally, it quantifies variant impacts by comparing the insulator score differences between the wild-type and mutant alleles. We applied InsuLock on various bulk and single-cell datasets for performance testing and benchmarking. We showed that it outperformed existing methods with an AUROC of ~0.96 and condensed insulator annotations to ~2.5% of their original size while still demonstrating higher conservation scores and better motif enrichments. Finally, we utilized InsuLock to make cell-type-specific variant impacts from brain scATAC-seq data and identified a schizophrenia GWAS variant disrupting an insulator loop proximal to a known risk gene, indicating a possible new mechanism of action for the disease.

CharID: a two-step model for universal prediction of interactions between chromatin accessible regions

Open chromatin regions (OCRs) allow direct interaction between cis-regulatory elements and trans-acting factors. Therefore, predicting all potential OCR-mediated loops is essential for deciphering the regulation mechanism of gene expression. However, existing loop prediction tools are restricted to specific anchor types. Here, we present CharID (Chromatin Accessible Region Interaction Detector), a two-step model that combines neural network and ensemble learning to predict OCR-mediated loops. In the first step, CharID-Anchor, an attention-based hybrid CNN-BiGRU network is constructed to discriminate between the anchor and nonanchor OCRs. In the second step, CharID-Loop uses gradient boosting decision tree with chromosome-split strategy to predict the interactions between anchor OCRs. The performance was assessed in three human cell lines, and CharID showed superior prediction performance compared with other algorithms. In contrast to the methods designed to predict a particular type of loops, CharID can detect varieties of chromatin loops not limited to enhancer-promoter loops or architectural protein-mediated loops. We constructed the OCR-mediated interaction network using the predicted loops and identified hub anchors, which are highlighted by their proximity to housekeeping genes. By analyzing loops containing SNPs associated with cardiovascular disease, we identified an SNP-gene loop indicating the regulation mechanism of the GFOD1. Taken together, CharID universally predicts diverse chromatin loops beyond other state-of-the-art methods, which are limited by anchor types, and experimental techniques, which are limited by sensitivities drastically decaying with the genomic distance of anchors. Finally, we hosted Peaksniffer, a user-friendly web server that provides online prediction, query and visualization of OCRs and associated loops.

preciseTAD: a transfer learning framework for 3D domain boundary prediction at base-pair resolution

MOTIVATION

Chromosome conformation capture technologies (Hi-C) revealed extensive DNA folding into discrete 3D domains, such as Topologically Associating Domains and chromatin loops. The correct binding of CTCF and cohesin at domain boundaries is integral in maintaining the proper structure and function of these 3D domains. 3D domains have been mapped at the resolutions of 1 kilobase and above. However, it has not been possible to define their boundaries at the resolution of boundary-forming proteins.

RESULTS

To predict domain boundaries at base-pair resolution, we developed preciseTAD, an optimized transfer learning framework trained on high-resolution genome annotation data. In contrast to current TAD/loop callers, preciseTAD-predicted boundaries are strongly supported by experimental evidence. Importantly, this approach can accurately delineate boundaries in cells without Hi-C data. preciseTAD provides a powerful framework to improve our understanding of how genomic regulators are shaping the 3D structure of the genome at base-pair resolution.

AVAILABILITY AND IMPLEMENTATION

preciseTAD is an R/Bioconductor package available at https://bioconductor.org/packages/preciseTAD/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Mapping the evolving landscape of super-enhancers during cell differentiation

Background

Super-enhancers are clusters of enhancer elements that play critical roles in the maintenance of cell identity. Current investigations on super-enhancers are centered on the established ones in static cell types. How super-enhancers are established during cell differentiation remains obscure.

Results

Here, by developing an unbiased approach to systematically analyze the evolving landscape of super-enhancers during cell differentiation in multiple lineages, we discover a general trend where super-enhancers emerge through three distinct temporal patterns: conserved, temporally hierarchical, and de novo. The three types of super-enhancers differ further in association patterns in target gene expression, functional enrichment, and 3D chromatin organization, suggesting they may represent distinct structural and functional subtypes. Furthermore, we dissect the enhancer repertoire within temporally hierarchical super-enhancers, and find enhancers that emerge at early and late stages are enriched with distinct transcription factors, suggesting that the temporal order of establishment of elements within super-enhancers may be directed by underlying DNA sequence. CRISPR-mediated deletion of individual enhancers in differentiated cells shows that both the early- and late-emerged enhancers are indispensable for target gene expression, while in undifferentiated cells early enhancers are involved in the regulation of target genes.

Conclusions

In summary, our analysis highlights the heterogeneity of the super-enhancer population and provides new insights to enhancer functions within super-enhancers.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13059-021-02485-x.

CCIP: Predicting CTCF-mediated chromatin loops with transitivity

Motivation

CTCF-mediated chromatin loops underlie the formation of topological associating domains and serve as the structural basis for transcriptional regulation. However, the formation mechanism of these loops remains unclear, and the genome-wide mapping of these loops is costly and difficult. Motivated by the recent studies on the formation mechanism of CTCF-mediated loops, we studied the possibility of making use of transitivity-related information of interacting CTCF anchors to predict CTCF loops computationally. In this context, transitivity arises when two CTCF anchors interact with the same third anchor by the loop extrusion mechanism and bring themselves close to each other spatially to form an indirect loop.

Results

To determine whether transitivity is informative for predicting CTCF loops and to obtain an accurate and low-cost predicting method, we proposed a two-stage random-forest-based machine learning method, CTCF-mediated Chromatin Interaction Prediction (CCIP), to predict CTCF-mediated chromatin loops. Our two-stage learning approach makes it possible for us to train a prediction model by taking advantage of transitivity-related information as well as functional genome data and genomic data. Experimental studies showed that our method predicts CTCF-mediated loops more accurately than other methods and that transitivity, when used as a properly defined attribute, is informative for predicting CTCF loops. Furthermore, we found that transitivity explains the formation of tandem CTCF loops and facilitates enhancer–promoter interactions. Our work contributes to the understanding of the formation mechanism and function of CTCF-mediated chromatin loops.

Availability and implementation

The source code of CCIP can be accessed at: https://github.com/GaoLabXDU/CCIP.

Supplementary information

Supplementary data are available at Bioinformatics online.

A sequence-based deep learning approach to predict CTCF-mediated chromatin loop

Three-dimensional (3D) architecture of the chromosomes is of crucial importance for transcription regulation and DNA replication. Various high-throughput chromosome conformation capture-based methods have revealed that CTCF-mediated chromatin loops are a major component of 3D architecture. However, CTCF-mediated chromatin loops are cell type specific, and most chromatin interaction capture techniques are time-consuming and labor-intensive, which restricts their usage on a very large number of cell types. Genomic sequence-based computational models are sophisticated enough to capture important features of chromatin architecture and help to identify chromatin loops. In this work, we develop Deep-loop, a convolutional neural network model, to integrate k-tuple nucleotide frequency component, nucleotide pair spectrum encoding, position conservation, position scoring function and natural vector features for the prediction of chromatin loops. By a series of examination based on cross-validation, Deep-loop shows excellent performance in the identification of the chromatin loops from different cell types. The source code of Deep-loop is freely available at the repository https://github.com/linDing-group/Deep-loop.

Loop competition and extrusion model predicts CTCF interaction specificity

Three-dimensional chromatin looping interactions play an important role in constraining enhancer–promoter interactions and mediating transcriptional gene regulation. CTCF is thought to play a critical role in the formation of these loops, but the specificity of which CTCF binding events form loops and which do not is difficult to predict. Loops often have convergent CTCF binding site motif orientation, but this constraint alone is only weakly predictive of genome-wide interaction data. Here we present an easily interpretable and simple mathematical model of CTCF mediated loop formation which is consistent with Cohesin extrusion and can predict ChIA-PET CTCF looping interaction measurements with high accuracy. Competition between overlapping loops is a critical determinant of loop specificity. We show that this model is consistent with observed chromatin interaction frequency changes induced by CTCF binding site deletion, inversion, and mutation, and is also consistent with observed constraints on validated enhancer–promoter interactions.

Boundaries of topologically associated domains in genomes are marked by CTCF and cohesin binding. Here the authors predict CTCF interaction specificity by building a simple mathematical model with features including loop competition and extrusion.

Identification and analysis of consensus RNA motifs binding to the genome regulator CTCF

CCCTC-binding factor (CTCF) is a key regulator of 3D genome organization and gene expression. Recent studies suggest that RNA transcripts, mostly long non-coding RNAs (lncRNAs), can serve as locus-specific factors to bind and recruit CTCF to the chromatin. However, it remains unclear whether specific sequence patterns are shared by the CTCF-binding RNA sites, and no RNA motif has been reported so far for CTCF binding. In this study, we have developed DeepLncCTCF, a new deep learning model based on a convolutional neural network and a bidirectional long short-term memory network, to discover the RNA recognition patterns of CTCF and identify candidate lncRNAs binding to CTCF. When evaluated on two different datasets, human U2OS dataset and mouse ESC dataset, DeepLncCTCF was shown to be able to accurately predict CTCF-binding RNA sites from nucleotide sequence. By examining the sequence features learned by DeepLncCTCF, we discovered a novel RNA motif with the consensus sequence, AGAUNGGA, for potential CTCF binding in humans. Furthermore, the applicability of DeepLncCTCF was demonstrated by identifying nearly 5000 candidate lncRNAs that might bind to CTCF in the nucleus. Our results provide useful information for understanding the molecular mechanisms of CTCF function in 3D genome organization.

Predicting Genome Architecture: Challenges and Solutions

Genome architecture plays a pivotal role in gene regulation. The use of high-throughput methods for chromatin profiling and 3-D interaction mapping provide rich experimental data sets describing genome organization and dynamics. These data challenge development of new models and algorithms connecting genome architecture with epigenetic marks. In this review, we describe how chromatin architecture could be reconstructed from epigenetic data using biophysical or statistical approaches. We discuss the applicability and limitations of these methods for understanding the mechanisms of chromatin organization. We also highlight the emergence of new predictive approaches for scoring effects of structural variations in human cells.

Computational methods for the prediction of chromatin interaction and organization using sequence and epigenomic profiles

The exploration of three-dimensional chromatin interaction and organization provides insight into mechanisms underlying gene regulation, cell differentiation and disease development. Advances in chromosome conformation capture technologies, such as high-throughput chromosome conformation capture (Hi-C) and chromatin interaction analysis by paired-end tag (ChIA-PET), have enabled the exploration of chromatin interaction and organization. However, high-resolution Hi-C and ChIA-PET data are only available for a limited number of cell lines, and their acquisition is costly, time consuming, laborious and affected by theoretical limitations. Increasing evidence shows that DNA sequence and epigenomic features are informative predictors of regulatory interaction and chromatin architecture. Based on these features, numerous computational methods have been developed for the prediction of chromatin interaction and organization, whereas they are not extensively applied in biomedical study. A systematical study to summarize and evaluate such methods is still needed to facilitate their application. Here, we summarize 48 computational methods for the prediction of chromatin interaction and organization using sequence and epigenomic profiles, categorize them and compare their performance. Besides, we provide a comprehensive guideline for the selection of suitable methods to predict chromatin interaction and organization based on available data and biological question of interest.

DeepYY1: a deep learning approach to identify YY1-mediated chromatin loops

The protein Yin Yang 1 (YY1) could form dimers that facilitate the interaction between active enhancers and promoter-proximal elements. YY1-mediated enhancer-promoter interaction is the general feature of mammalian gene control. Recently, some computational methods have been developed to characterize the interactions between DNA elements by elucidating important features of chromatin folding; however, no computational methods have been developed for identifying the YY1-mediated chromatin loops. In this study, we developed a deep learning algorithm named DeepYY1 based on word2vec to determine whether a pair of YY1 motifs would form a loop. The proposed models showed a high prediction performance (AUCs$\ge$0.93) on both training datasets and testing datasets in different cell types, demonstrating that DeepYY1 has an excellent performance in the identification of the YY1-mediated chromatin loops. Our study also suggested that sequences play an important role in the formation of YY1-mediated chromatin loops. Furthermore, we briefly discussed the distribution of the replication origin site in the loops. Finally, a user-friendly web server was established, and it can be freely accessed at http://lin-group.cn/server/DeepYY1.

A Comparative Study of Supervised Machine Learning Algorithms for the Prediction of Long-Range Chromatin Interactions

The role of three-dimensional genome organization as a critical regulator of gene expression has become increasingly clear over the last decade. Most of our understanding of this association comes from the study of long range chromatin interaction maps provided by Chromatin Conformation Capture-based techniques, which have greatly improved in recent years. Since these procedures are experimentally laborious and expensive, in silico prediction has emerged as an alternative strategy to generate virtual maps in cell types and conditions for which experimental data of chromatin interactions is not available. Several methods have been based on predictive models trained on one-dimensional (1D) sequencing features, yielding promising results. However, different approaches vary both in the way they model chromatin interactions and in the machine learning-based strategy they rely on, making it challenging to carry out performance comparison of existing methods. In this study, we use publicly available 1D sequencing signals to model cohesin-mediated chromatin interactions in two human cell lines and evaluate the prediction performance of six popular machine learning algorithms: decision trees, random forests, gradient boosting, support vector machines, multi-layer perceptron and deep learning. Our approach accurately predicts long-range interactions and reveals that gradient boosting significantly outperforms the other five methods, yielding accuracies of about 95%. We show that chromatin features in close genomic proximity to the anchors cover most of the predictive information, as has been previously reported. Moreover, we demonstrate that gradient boosting models trained with different subsets of chromatin features, unlike the other methods tested, are able to produce accurate predictions. In this regard, and besides architectural proteins, transcription factors are shown to be highly informative. Our study provides a framework for the systematic prediction of long-range chromatin interactions, identifies gradient boosting as the best suited algorithm for this task and highlights cell-type specific binding of transcription factors at the anchors as important determinants of chromatin wiring mediated by cohesin.

MATCHA: Probing multi-way chromatin interaction with hypergraph representation learning

Recent advances in ligation-free, genome-wide chromatin interaction mapping such as SPRITE and ChIA-Drop have enabled the identification of simultaneous interactions involving multiple genomic loci within the same nuclei, which are informative to delineate higher-order genome organization and gene regulation mechanisms at single-nucleus resolution. Unfortunately, computational methods for analyzing multi-way chromatin interaction data are significantly underexplored. Here we develop an algorithm, called MATCHA, based on hypergraph representation learning where multi-way chromatin interactions are represented as hyperedges. Applications to SPRITE and ChIA-Drop data suggest that MATCHA is effective to denoise the data and make de novo predictions, which greatly enhances the data quality for analyzing the properties of multi-way chromatin interactions. MATCHA provides a promising framework to significantly improve the analysis of multi-way chromatin interaction data and has the potential to offer unique insights into higher-order chromosome organization and function. MATCHA is freely available for download here: https://github.com/ma-compbio/MATCHA.

DeepMILO: a deep learning approach to predict the impact of non-coding sequence variants on 3D chromatin structure

Non-coding variants have been shown to be related to disease by alteration of 3D genome structures. We propose a deep learning method, DeepMILO, to predict the effects of variants on CTCF/cohesin-mediated insulator loops. Application of DeepMILO on variants from whole-genome sequences of 1834 patients of twelve cancer types revealed 672 insulator loops disrupted in at least 10% of patients. Our results show mutations at loop anchors are associated with upregulation of the cancer driver genes BCL2 and MYC in malignant lymphoma thus pointing to a possible new mechanism for their dysregulation via alteration of insulator loops.

Three-dimensional genome: developmental technologies and applications in precision medicine

In the 20th century, our familiar structure of DNA was the double helix. Due to technical limitations, we do not have a good way to understand the finer structure of the genome, let alone its transcriptional regulation. Until the advent of 3C technologies, we were no longer blind to this one. Three-dimensional (3D) genomics is a new subject, which mainly studies the 3D structure and transcriptional regulation of eukaryotic genomes. Now, this field mainly has Hi-C series and CHIA-PET series technologies. Through 3D genomics, we can understand the basic structure of DNA, understand the growth and development of organisms and the occurrence of diseases, so as to promote human medical and health undertakings. The review introduces the main research techniques of 3D genomics and their characteristics, the latest development of 3D genome structure, the relationship between diseases and 3D genome structure, the applications of 3D genome in precision medicine, and the development of the 4D nucleome project.

Quantitative prediction of enhancer-promoter interactions

Recent experimental and computational efforts have provided large data sets describing three-dimensional organization of mouse and human genomes and showed the interconnection between the expression profile, epigenetic state, and spatial interactions of loci. These interconnections were utilized to infer the spatial organization of chromatin, including enhancer–promoter contacts, from one-dimensional epigenetic marks. Here, we show that the predictive power of some of these algorithms is overestimated due to peculiar properties of the biological data. We propose an alternative approach, which provides high-quality predictions of chromatin interactions using information on gene expression and CTCF-binding alone. Using multiple metrics, we confirmed that our algorithm could efficiently predict the three-dimensional architecture of both normal and rearranged genomes.

Comparison of computational methods for 3D genome analysis at single-cell Hi-C level

Hi-C is a high-throughput chromosome conformation capture technology that is becoming routine in the literature. Although the price of sequencing has been dropping dramatically, high-resolution Hi-C data are not always an option for many studies, such as in single cells. However, the performance of current computational methods based on Hi-C at the ultra-sparse data condition has yet to be fully assessed. Therefore, in this paper, after briefly surveying the primary computational methods for Hi-C data analysis, we assess the performance of representative methods on data normalization, identification of compartments, Topologically Associating Domains (TADs) and chromatin loops under the condition of ultra-low resolution. We showed that most state-of-the-art methods do not work properly for that condition. Then, we applied the three best-performing methods on real single-cell Hi-C data, and their performance indicates that compartments may be a statistical feature emerging from the cell population, while TADs and chromatin loops may dynamically exist in single cells.

Large-scale chromatin organisation in interphase, mitosis and meiosis

The spatial configuration of chromatin is fundamental to ensure any given cell can fulfil its functional duties, from gene expression to specialised cellular division. Significant technological innovations have facilitated further insights into the structure, function and regulation of three-dimensional chromatin organisation. To date, the vast majority of investigations into chromatin organisation have been conducted in interphase and mitotic cells leaving meiotic chromatin relatively unexplored. In combination, cytological and genome-wide contact frequency analyses in mammalian germ cells have recently demonstrated that large-scale chromatin structures in meiotic prophase I are reminiscent of the sequential loop arrays found in mitotic cells, although interphase-like segmentation of transcriptionally active and inactive regions are also evident along the length of chromosomes. Here, we discuss the similarities and differences of such large-scale chromatin architecture, between interphase, mitotic and meiotic cells, as well as their functional relevance and the proposed modulatory mechanisms which underlie them.

Cut-C: cleavage under tethered nuclease for conformational capture

BACKGROUND

Deciphering the 3D structure of the genome is essential for elucidating the regulatory mechanisms of gene expression in detail. Existing methods, such as chromosome conformation capture (3C) and Hi-C have enabled the identification of novel aspects of chromatin structure. Further identification of protein-centric chromatin conformation is enabled by coupling the Hi-C procedure with a conventional chromatin immunoprecipitation assay. However, these methods are time-consuming and require independent methods for validation.

RESULTS

To simultaneously identify protein-centric chromatin conformation and target protein localization, we have developed Cut-C, a method that combines antibody-mediated cleavage by tethered nuclease with chromosome conformation capture to identify chromatin interactions mediated by a protein of interest. Applying Cut-C to H3K4me3, a histone modification enriched at active gene promoters, we have successfully identified chromatin loops mediated by H3K4me3 along with the genome-wide distribution of H3K4me3. Cut-C also identified chromatin loops mediated by CTCF, validating the general applicability of the method.

CONCLUSIONS

Cut-C identifies protein-centric chromatin conformations along with the genome-wide distribution of target proteins using simple procedures. The simplified protocol will improve the efficiency of analysing chromatin conformation using precious materials, such as clinical samples.

Predicting three-dimensional genome organization with chromatin states

We introduce a computational model to simulate chromatin structure and dynamics. Starting from one-dimensional genomics and epigenomics data that are available for hundreds of cell types, this model enables de novo prediction of chromatin structures at five-kilo-base resolution. Simulated chromatin structures recapitulate known features of genome organization, including the formation of chromatin loops, topologically associating domains (TADs) and compartments, and are in quantitative agreement with chromosome conformation capture experiments and super-resolution microscopy measurements. Detailed characterization of the predicted structural ensemble reveals the dynamical flexibility of chromatin loops and the presence of cross-talk among neighboring TADs. Analysis of the model's energy function uncovers distinct mechanisms for chromatin folding at various length scales and suggests a need to go beyond simple A/B compartment types to predict specific contacts between regulatory elements using polymer simulations.