Quantitative prediction of enhancer-promoter interactions

Identifying promoter and enhancer sequences by graph convolutional networks

Identification of promoters, enhancers, and their interactions helps understand genetic regulation. This study proposes a graph-based semi-supervised learning model (GCN4EPI) for the enhancer-promoter classification problem. We adopt a graph convolutional network (GCN) architecture to integrate interaction information with sequence features. Nodes of the constructed graph hold word embeddings of DNA sequences while edges hold the Enhancer-Promoter Interaction (EPI) information. By means of semi-supervised learning, much less data (16%) and time are needed in model training. Comparisons on a benchmark dataset of six human cell lines show that the proposed approach outperforms the state-of-the-art methods by a large margin (10% higher F1 score) and has the fastest training time (up to 3 times). Moreover, GCN4EPI's performance on cross-cell line data is also better than the baselines (3% higher F1 score). Our qualitative analyses with graph explainability models prove that GCN4EPI learns from both text and graph structure. The results suggest that integrating interaction information with sequence features improves predictive performance and compensates for the number of training instances.

Structural variants in the Epb41l4a locus: TAD disruption and Nrep gene misregulation as hypothetical drivers of neurodevelopmental outcomes

Structural variations are a pervasive feature of human genomes, and there is growing recognition of their role in disease development through their impact on spatial chromatin architecture. This understanding has led us to investigate the clinical significance of CNVs in noncoding regions that influence TAD structures. In this study, we focused on the Epb41l4a locus, which contains a highly conserved TAD boundary present in both human chromosome 5 and mouse chromosome 18, and its association with neurodevelopmental phenotypes. Analysis of human data from the DECIPHER database indicates that CNVs within this locus, including both deletions and duplications, are often observed alongside neurological abnormalities, such as dyslexia and intellectual disability, although there is not enough evidence of a direct correlation or causative relationship. To investigate these possible associations, we generated mouse models with deletion and inversion mutations at this locus and carried out RNA-seq analysis to elucidate gene expression changes. We found that modifications in the Epb41l4a TAD boundary led to dysregulation of the Nrep gene, which plays a crucial role in nervous system development. These findings underscore the potential pathogenicity of these CNVs and highlight the crucial role of spatial genome architecture in gene expression regulation.

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.

Hi-BDiSCO: folding 3D mesoscale genome structures from Hi-C data using brownian dynamics

The structure and dynamics of the eukaryotic genome are intimately linked to gene regulation and transcriptional activity. Many chromosome conformation capture experiments like Hi-C have been developed to detect genome-wide contact frequencies and quantify loop/compartment structures for different cellular contexts and time-dependent processes. However, a full understanding of these events requires explicit descriptions of representative chromatin and chromosome configurations. With the exponentially growing amount of data from Hi-C experiments, many methods for deriving 3D structures from contact frequency data have been developed. Yet, most reconstruction methods use polymer models with low resolution to predict overall genome structure. Here we present a Brownian Dynamics (BD) approach termed Hi-BDiSCO for producing 3D genome structures from Hi-C and Micro-C data using our mesoscale-resolution chromatin model based on the Discrete Surface Charge Optimization (DiSCO) model. Our approach integrates reconstruction with chromatin simulations at nucleosome resolution with appropriate biophysical parameters. Following a description of our protocol, we present applications to the NXN, HOXC, HOXA and Fbn2 mouse genes ranging in size from 50 to 100 kb. Such nucleosome-resolution genome structures pave the way for pursuing many biomedical applications related to the epigenomic regulation of chromatin and control of human disease.

ChIPr: accurate prediction of cohesin-mediated 3D genome organization from 2D chromatin features

The three-dimensional genome organization influences diverse nuclear processes. Here we present Chromatin Interaction Predictor (ChIPr), a suite of regression models based on deep neural networks, random forest, and gradient boosting to predict cohesin-mediated chromatin interaction strength between any two loci in the genome. The predictions of ChIPr correlate well with ChIA-PET data in four cell lines. The standard ChIPr model requires three experimental inputs: ChIP-Seq signals for RAD21, H3K27ac, and H3K27me3 but works well with just RAD21 signal. Integrative analysis reveals novel insights into the role of CTCF motif, its orientation, and CTCF binding on cohesin-mediated chromatin interactions.

Enhancer target prediction: state-of-the-art approaches and future prospects

Enhancers are genomic regions that regulate gene transcription and are located far away from the transcription start sites of their target genes. Enhancers are highly enriched in disease-associated variants and thus deciphering the interactions between enhancers and genes is crucial to understanding the molecular basis of genetic predispositions to diseases. Experimental validations of enhancer targets can be laborious. Computational methods have thus emerged as a valuable alternative for studying enhancer-gene interactions. A variety of computational methods have been developed to predict enhancer targets by incorporating genomic features (e.g. conservation, distance, and sequence), epigenomic features (e.g. histone marks and chromatin contacts) and activity measurements (e.g. covariations of enhancer activity and gene expression). With the recent advances in genome perturbation and chromatin conformation capture technologies, data on experimentally validated enhancer targets are becoming available for supervised training of these methods and evaluation of their performance. In this review, we categorize enhancer target prediction methods based on their rationales and approaches. Then we discuss their merits and limitations and highlight the future directions for enhancer targets prediction.

Techniques for and challenges in reconstructing 3D genome structures from 2D chromosome conformation capture data

Chromosome conformation capture technologies that provide frequency information for contacts between genomic regions have been crucial for increasing our understanding of genome folding and regulation. However, such data do not provide direct evidence of the spatial 3D organization of chromatin. In this opinion article, we discuss the development and application of computational methods to reconstruct chromatin 3D structures from experimental 2D contact data, highlighting how such modeling provides biological insights and can suggest mechanisms anchored to experimental data. By applying different reconstruction methods to the same contact data, we illustrate some state-of-the-art of these techniques and discuss our gene resolution approach based on Brownian dynamics and Monte Carlo sampling.

Cell-type-specific prediction of 3D chromatin organization enables high-throughput in silico genetic screening

Investigating how chromatin organization determines cell-type-specific gene expression remains challenging. Experimental methods for measuring three-dimensional chromatin organization, such as Hi-C, are costly and have technical limitations, restricting their broad application particularly in high-throughput genetic perturbations. We present C.Origami, a multimodal deep neural network that performs de novo prediction of cell-type-specific chromatin organization using DNA sequence and two cell-type-specific genomic features-CTCF binding and chromatin accessibility. C.Origami enables in silico experiments to examine the impact of genetic changes on chromatin interactions. We further developed an in silico genetic screening approach to assess how individual DNA elements may contribute to chromatin organization and to identify putative cell-type-specific trans-acting regulators that collectively determine chromatin architecture. Applying this approach to leukemia cells and normal T cells, we demonstrate that cell-type-specific in silico genetic screening, enabled by C.Origami, can be used to systematically discover novel chromatin regulation circuits in both normal and disease-related biological systems.

Leveraging epigenomes and three-dimensional genome organization for interpreting regulatory variation

Understanding the impact of regulatory variants on complex phenotypes is a significant challenge because the genes and pathways that are targeted by such variants and the cell type context in which regulatory variants operate are typically unknown. Cell-type-specific long-range regulatory interactions that occur between a distal regulatory sequence and a gene offer a powerful framework for examining the impact of regulatory variants on complex phenotypes. However, high-resolution maps of such long-range interactions are available only for a handful of cell types. Furthermore, identifying specific gene subnetworks or pathways that are targeted by a set of variants is a significant challenge. We have developed L-HiC-Reg, a Random Forests regression method to predict high-resolution contact counts in new cell types, and a network-based framework to identify candidate cell-type-specific gene networks targeted by a set of variants from a genome-wide association study (GWAS). We applied our approach to predict interactions in 55 Roadmap Epigenomics Mapping Consortium cell types, which we used to interpret regulatory single nucleotide polymorphisms (SNPs) in the NHGRI-EBI GWAS catalogue. Using our approach, we performed an in-depth characterization of fifteen different phenotypes including schizophrenia, coronary artery disease (CAD) and Crohn's disease. We found differentially wired subnetworks consisting of known as well as novel gene targets of regulatory SNPs. Taken together, our compendium of interactions and the associated network-based analysis pipeline leverages long-range regulatory interactions to examine the context-specific impact of regulatory variation in complex phenotypes.

Function and Evolution of the Loop Extrusion Machinery in Animals

Structural maintenance of chromosomes (SMC) complexes are essential proteins found in genomes of all cellular organisms. Essential functions of these proteins, such as mitotic chromosome formation and sister chromatid cohesion, were discovered a long time ago. Recent advances in chromatin biology showed that SMC proteins are involved in many other genomic processes, acting as active motors extruding DNA, which leads to the formation of chromatin loops. Some loops formed by SMC proteins are highly cell type and developmental stage specific, such as SMC-mediated DNA loops required for VDJ recombination in B-cell progenitors, or dosage compensation in Caenorhabditis elegans and X-chromosome inactivation in mice. In this review, we focus on the extrusion-based mechanisms that are common for multiple cell types and species. We will first describe an anatomy of SMC complexes and their accessory proteins. Next, we provide biochemical details of the extrusion process. We follow this by the sections describing the role of SMC complexes in gene regulation, DNA repair, and chromatin topology.

Profiling human pathogenic repeat expansion regions by synergistic and multi-level impacts on molecular connections

Whilst DNA repeat expansions cause numerous heritable human disorders, their origins and underlying pathological mechanisms are often unclear. We collated a dataset comprising 224 human repeat expansions encompassing 203 different genes, and performed a systematic analysis with respect to key topological features at the DNA, RNA and protein levels. Comparison with controls without known pathogenicity and genomic regions lacking repeats, allowed the construction of the first tool to discriminate repeat regions harboring pathogenic repeat expansions (DPREx). At the DNA level, pathogenic repeat expansions exhibited stronger signals for DNA regulatory factors (e.g. H3K4me3, transcription factor-binding sites) in exons, promoters, 5'UTRs and 5'genes but were not significantly different from controls in introns, 3'UTRs and 3'genes. Additionally, pathogenic repeat expansions were also found to be enriched in non-B DNA structures. At the RNA level, pathogenic repeat expansions were characterized by lower free energy for forming RNA secondary structure and were closer to splice sites in introns, exons, promoters and 5'genes than controls. At the protein level, pathogenic repeat expansions exhibited a preference to form coil rather than other types of secondary structure, and tended to encode surface-located protein domains. Guided by these features, DPREx ( http://biomed.nscc-gz.cn/zhaolab/geneprediction/# ) achieved an Area Under the Curve (AUC) value of 0.88 in a test on an independent dataset. Pathogenic repeat expansions are thus located such that they exert a synergistic influence on the gene expression pathway involving inter-molecular connections at the DNA, RNA and protein levels.

ChromLoops: a comprehensive database for specific protein-mediated chromatin loops in diverse organisms

Chromatin loops (or chromatin interactions) are important elements of chromatin structures. Disruption of chromatin loops is associated with many diseases, such as cancer and polydactyly. A few methods, including ChIA-PET, HiChIP and PLAC-Seq, have been proposed to detect high-resolution, specific protein-mediated chromatin loops. With rapid progress in 3D genomic research, ChIA-PET, HiChIP and PLAC-Seq datasets continue to accumulate, and effective collection and processing for these datasets are urgently needed. Here, we developed a comprehensive, multispecies and specific protein-mediated chromatin loop database (ChromLoops, https://3dgenomics.hzau.edu.cn/chromloops), which integrated 1030 ChIA-PET, HiChIP and PLAC-Seq datasets from 13 species, and documented 1 491 416 813 high-quality chromatin loops. We annotated genes and regions overlapping with chromatin loop anchors with rich functional annotations, such as regulatory elements (enhancers, super-enhancers and silencers), variations (common SNPs, somatic SNPs and eQTLs), and transcription factor binding sites. Moreover, we identified genes with high-frequency chromatin interactions in the collected species. In particular, we identified genes with high-frequency interactions in cancer samples. We hope that ChromLoops will provide a new platform for studying chromatin interaction regulation in relation to biological processes and disease.

Enhancer/gene relationships: Need for more reliable genome-wide reference sets

Differences in cells' functions arise from differential activity of regulatory elements, including enhancers. Enhancers are cis-regulatory elements that cooperate with promoters through transcription factors to activate the expression of one or several genes by getting physically close to them in the 3D space of the nucleus. There is increasing evidence that genetic variants associated with common diseases are enriched in enhancers active in cell types relevant to these diseases. Identifying the enhancers associated with genes and conversely, the sets of genes activated by each enhancer (the so-called enhancer/gene or E/G relationships) across cell types, can help understanding the genetic mechanisms underlying human diseases. There are three broad approaches for the genome-wide identification of E/G relationships in a cell type: 1) genetic link methods or eQTL, 2) functional link methods based on 1D functional data such as open chromatin, histone mark or gene expression and 3) spatial link methods based on 3D data such as HiC. Since 1) and 3) are costly, the current strategy is to develop functional link methods and to use data from 1) and 3) as reference to evaluate them. However, there is still no consensus on the best functional link method to date, and method comparison remain seldom. Here, we compared the relative performances of three recent methods for the identification of enhancer-gene links, TargetFinder, Average-Rank, and the ABC model, using the three latest benchmarks from the field: a reference that combines 3D and eQTL data, called BENGI, and two genetic screening references, called CRiFF and CRiSPRi. Overall, none of the three methods performed best on the three references. CRiFF and CRISPRi reference sets are likely more reliable, but CRiFF is not genome-wide and CRiFF and CRISPRi are mostly available on the K562 cancer cell line. The BENGI reference set is genome-wide but likely contains many false positives. This study therefore calls for new reliable and genome-wide E/G reference data rather than new functional link E/G identification methods.

Predicting Chromatin Interactions from DNA Sequence Using DeepC

The genome 3D structure is central to understanding how disease-associated genetic variants in the noncoding genome regulate their target genes. Genome architecture spans large-scale structures determined by fine-grained regulatory elements, making it challenging to predict the effects of sequence and structural variants. Experimental approaches for chromatin interaction mapping remain costly and time-consuming, limiting their use for interrogating changes of chromatin architecture associated with genomic variation at scale. Computational models to predict chromatin interactions have either interpreted chromatin at coarse resolution or failed to capture the long-range dependencies of larger sequence contexts. To bridge this gap, we previously developed deepC, a deep neural network approach to predict chromatin interactions from DNA sequence at megabase scale. deepC employs dilated convolutional layers to achieve simultaneously a large sequence context while interpreting the DNA sequence at single base pair resolution. Using transfer learning of convolutional weights trained to predict a compendium of chromatin features across cell types allows deepC to predict cell type-specific chromatin interactions from DNA sequence alone. Here, we present a detailed workflow to predict chromatin interactions with deepC. We detail the necessary data pre-processing steps, guide through deepC model training, and demonstrate how to employ trained models to predict chromatin interactions and the effect of sequence variations on genome architecture.

Integrating extrusion complex-associated pattern to predict cell type-specific long-range chromatin loops

The chromatin loop plays a critical role in the study of gene expression and disease. Supervised learning-based algorithms to predict the chromatin loops require large priori information to satisfy the model construction, while the prediction sensitivity of unsupervised learning-based algorithms is still unsatisfactory. Therefore, we propose an unsupervised algorithm, Ecomap-loop. It takes advantage of extrusion complex-associated patterns, including CTCF, RAD21, and SMC enrichments, as well as the orientation distribution of CTCF motif of loops to build feature matrices; then the eigen decomposition model is employed to obtain the cell type-specific loops. We compare the performance of Ecomap-loop with the state-of-the-art unsupervised algorithm using Hi-C, ChIA-PET, expression quantitative trait locus (eQTL), and CRISPR interference (CRISPRi) screen data; the results show that Ecomap-loop achieves the best in four cell types. In addition, the functional analysis reveals the ability of Ecomap-loop to predict active functionality-related and cell type-specific loops.

EPIHC: Improving Enhancer-Promoter Interaction Prediction by Using Hybrid Features and Communicative Learning

Enhancer-promoter interactions (EPIs) regulate the expression of specific genes in cells, which help facilitate understanding of gene regulation, cell differentiation and disease mechanisms. EPI identification approaches through wet experiments are often costly and time-consuming, leading to the design of high-efficiency computational methods is in demand. In this paper, we propose a deep neural network-based method named EPIHC to predict Enhancer-Promoter Interactions with Hybrid features and Communicative learning. EPIHC extracts enhancer and promoter sequence-derived features using convolutional neural networks (CNN), and then we design a communicative learning module to capture the communicative information between enhancer and promoter sequences. Besides, EPIHC takes the genomic features of enhancers and promoters into account, incorporating with the sequence-derived features to predict EPIs. The computational experiments show that EPIHC outperforms the existing state-of-the-art EPI prediction methods on the benchmark datasets and chromosome-split datasets, and the study reveals that the communicative learning module can bring explicit information about EPIs, which is ignored by CNN, and provide explainability about EPIs to some degree. Moreover, we consider two strategies to improve the performances of EPIHC in the cross-cell line prediction, and experimental results show that EPIHC constructed on some cell lines can exhibit good performances for other cell lines. The codes and data are available at https://github.com/BioMedicalBigDataMiningLab/EPIHC.

GenomicKB: a knowledge graph for the human genome

Genomic Knowledgebase (GenomicKB) is a graph database for researchers to explore and investigate human genome, epigenome, transcriptome, and 4D nucleome with simple and efficient queries. The database uses a knowledge graph to consolidate genomic datasets and annotations from over 30 consortia and portals, including 347 million genomic entities, 1.36 billion relations, and 3.9 billion entity and relation properties. GenomicKB is equipped with a web-based query system (https://gkb.dcmb.med.umich.edu/) which allows users to query the knowledge graph with customized graph patterns and specific constraints on entities and relations. Compared with traditional tabular-structured data stored in separate data portals, GenomicKB emphasizes the relations among genomic entities, intuitively connects isolated data matrices, and supports efficient queries for scientific discoveries. GenomicKB transforms complicated analysis among multiple genomic entities and relations into coding-free queries, and facilitates data-driven genomic discoveries in the future.

3DGenBench: a web-server to benchmark computational models for 3D Genomics

Modeling 3D genome organisation has been booming in the last years thanks to the availability of experimental datasets of genomic contacts. However, the field is currently missing the standardisation of methods and metrics to compare predictions and experiments. We present 3DGenBench, a web server available at https://inc-cost.eu/benchmarking/, that allows benchmarking computational models of 3D Genomics. The benchmark is performed using a manually curated dataset of 39 capture Hi-C profiles in wild type and genome-edited mouse cells, and five genome-wide Hi-C profiles in human, mouse, and Drosophila cells. 3DGenBench performs two kinds of analysis, each supplied with a specific scoring module that compares predictions of a computational method to experimental data using several metrics. With 3DGenBench, the user obtains model performance scores, allowing an unbiased comparison with other models. 3DGenBench aims to become a reference web server to test new 3D genomics models and is conceived as an evolving platform where new types of analysis will be implemented in the future.

EPIXplorer: A web server for prediction, analysis and visualization of enhancer-promoter interactions

Long distance enhancers can physically interact with promoters to regulate gene expression through formation of enhancer-promoter (E-P) interactions. Identification of E-P interactions is also important for profound understanding of normal developmental and disease-associated risk variants. Although the state-of-art predictive computation methods facilitate the identification of E-P interactions to a certain extent, currently there is no efficient method that can meet various requirements of usage. Here we developed EPIXplorer, a user-friendly web server for efficient prediction, analysis and visualization of E-P interactions. EPIXplorer integrates 9 robust predictive algorithms, supports multiple types of 3D contact data and multi-omics data as input. The output from EPIXplorer is scored, fully annotated by regulatory elements and risk single-nucleotide polymorphisms (SNPs). In addition, the Visualization and Downstream module provide further functional analysis, all the output files and high-quality images are available for download. Together, EPIXplorer provides a user-friendly interface to predict the E-P interactions in an acceptable time, as well as understand how the genome-wide association study (GWAS) variants influence disease pathology by altering DNA looping between enhancers and the target gene promoters. EPIXplorer is available at https://www.csuligroup.com/EPIXplorer.

Computational Approaches for Understanding Sequence Variation Effects on the 3D Genome Architecture

Decoding how genomic sequence and its variations affect 3D genome architecture is indispensable for understanding the genetic architecture of various traits and diseases. The 3D genome organization can be significantly altered by genome variations and in turn impact the function of the genomic sequence. Techniques for measuring the 3D genome architecture across spatial scales have opened up new possibilities for understanding how the 3D genome depends upon the genomic sequence and how it can be altered by sequence variations. Computational methods have become instrumental in analyzing and modeling the sequence effects on 3D genome architecture, and recent development in deep learning sequence models have opened up new opportunities for studying the interplay between sequence variations and the 3D genome. In this review, we focus on computational approaches for both the detection and modeling of sequence variation effects on the 3D genome, and we discuss the opportunities presented by these approaches. Expected final online publication date for the Annual Review of Biomedical Data Science, Volume 5 is August 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Anopheles mosquitoes reveal new principles of 3D genome organization in insects

Chromosomes are hierarchically folded within cell nuclei into territories, domains and subdomains, but the functional importance and evolutionary dynamics of these hierarchies are poorly defined. Here, we comprehensively profile genome organizations of five Anopheles mosquito species and show how different levels of chromatin architecture influence each other. Patterns observed on Hi-C maps are associated with known cytological structures, epigenetic profiles, and gene expression levels. Evolutionary analysis reveals conservation of chromatin architecture within synteny blocks for tens of millions of years and enrichment of synteny breakpoints in regions with increased genomic insulation. However, in-depth analysis shows a confounding effect of gene density on both insulation and distribution of synteny breakpoints, suggesting limited causal relationship between breakpoints and regions with increased genomic insulation. At the level of individual loci, we identify specific, extremely long-ranged looping interactions, conserved for ~100 million years. We demonstrate that the mechanisms underlying these looping contacts differ from previously described Polycomb-dependent interactions and clustering of active chromatin.

Anopheles mosquitoes are vectors of human malaria, and better understanding of them has implications for public health. Here, the authors apply Hi-C, FISH, RNA-seq, and ChIP-seq techniques to comprehensively characterize chromatin architecture and its evolutionary dynamics in five Anopheles species.

TADreg: a versatile regression framework for TAD identification, differential analysis and rearranged 3D genome prediction

Background/Aim

In higher eukaryotes, the three-dimensional (3D) organization of the genome is intimately related to numerous key biological functions including gene expression, DNA repair and DNA replication regulations. Alteration of 3D organization, in particular topologically associating domains (TADs), is detrimental to the organism and can give rise to a broad range of diseases such as cancers.

Methods

Here, we propose a versatile regression framework which not only identifies TADs in a fast and accurate manner, but also detects differential TAD borders across conditions for which few methods exist, and predicts 3D genome reorganization after chromosomal rearrangement. Moreover, the framework is biologically meaningful, has an intuitive interpretation and is easy to visualize.

Result and conclusion

The novel regression ranks among top TAD callers. Moreover, it identifies new features of the genome we called TAD facilitators, and that are enriched with specific transcription factors. It also unveils the importance of cell-type specific transcription factors in establishing novel TAD borders during neuronal differentiation. Lastly, it compares favorably with the state-of-the-art method for predicting rearranged 3D genome.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04614-0.

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.

Capturing large genomic contexts for accurately predicting enhancer-promoter interactions

Enhancer-promoter interaction (EPI) is a key mechanism underlying gene regulation. EPI prediction has always been a challenging task because enhancers could regulate promoters of distant target genes. Although many machine learning models have been developed, they leverage only the features in enhancers and promoters, or simply add the average genomic signals in the regions between enhancers and promoters, without utilizing detailed features between or outside enhancers and promoters. Due to a lack of large-scale features, existing methods could achieve only moderate performance, especially for predicting EPIs in different cell types. Here, we present a Transformer-based model, TransEPI, for EPI prediction by capturing large genomic contexts. TransEPI was developed based on EPI datasets derived from Hi-C or ChIA-PET data in six cell lines. To avoid over-fitting, we evaluated the TransEPI model by testing it on independent test datasets where the cell line and chromosome are different from the training data. TransEPI not only achieved consistent performance across the cross-validation and test datasets from different cell types but also outperformed the state-of-the-art machine learning and deep learning models. In addition, we found that the improved performance of TransEPI was attributed to the integration of large genomic contexts. Lastly, TransEPI was extended to study the non-coding mutations associated with brain disorders or neural diseases, and we found that TransEPI was also useful for predicting the target genes of non-coding mutations.

Multi-omics mapping of human papillomavirus integration sites illuminates novel cervical cancer target genes

BACKGROUND

Integration of human papillomavirus (HPV) into the host genome is a dominant feature of invasive cervical cancer (ICC), yet the tumorigenicity of cis genomic changes at integration sites remains largely understudied.

METHODS

Combining multi-omics data from The Cancer Genome Atlas with patient-matched long-read sequencing of HPV integration sites, we developed a strategy for using HPV integration events to identify and prioritise novel candidate ICC target genes (integration-detected genes (IDGs)). Four IDGs were then chosen for in vitro functional studies employing small interfering RNA-mediated knockdown in cell migration, proliferation and colony formation assays.

RESULTS

PacBio data revealed 267 unique human-HPV breakpoints comprising 87 total integration events in eight tumours. Candidate IDGs were filtered based on the following criteria: (1) proximity to integration site, (2) clonal representation of integration event, (3) tumour-specific expression (Z-score) and (4) association with ICC survival. Four candidates prioritised based on their unknown function in ICC (BNC1, RSBN1, USP36 and TAOK3) exhibited oncogenic properties in cervical cancer cell lines. Further, annotation of integration events provided clues regarding potential mechanisms underlying altered IDG expression in both integrated and non-integrated ICC tumours.

CONCLUSIONS

HPV integration events can guide the identification of novel IDGs for further study in cervical carcinogenesis and as putative therapeutic targets.

Single-cell Hi-C data analysis: safety in numbers

Over the past decade, genome-wide assays for chromatin interactions in single cells have enabled the study of individual nuclei at unprecedented resolution and throughput. Current chromosome conformation capture techniques survey contacts for up to tens of thousands of individual cells, improving our understanding of genome function in 3D. However, these methods recover a small fraction of all contacts in single cells, requiring specialised processing of sparse interactome data. In this review, we highlight recent advances in methods for the interpretation of single-cell genomic contacts. After discussing the strengths and limitations of these methods, we outline frontiers for future development in this rapidly moving field.

Disease-associated genetic variants in the regulatory regions of human genes: mechanisms of action on transcription and genomic resources for dissecting these mechanisms

Whole genome and whole exome sequencing technologies play a very important role in the studies of the genetic aspects of the pathogenesis of various diseases. The ample use of genome-wide and exome-wide association study methodology (GWAS and EWAS) made it possible to identify a large number of genetic variants associated with diseases. This information is accumulated in the databases like GWAS central, GWAS catalog, OMIM, ClinVar, etc. Most of the variants identified by the GWAS technique are located in the noncoding regions of the human genome. According to the ENCODE project, the fraction of regions in the human genome potentially involved in transcriptional control is many times greater than the fraction of coding regions. Thus, genetic variation in noncoding regions of the genome can increase the susceptibility to diseases by disrupting various regulatory elements (promoters, enhancers, silencers, insulator regions, etc.). However, identification of the mechanisms of influence of pathogenic genetic variants on the diseases risk is difficult due to a wide variety of regulatory elements. The present review focuses on the molecular genetic mechanisms by which pathogenic genetic variants affect gene expression. At the same time, attention is concentrated on the transcriptional level of regulation as an initial step in the expression of any gene. A triggering event mediating the effect of a pathogenic genetic variant on the level of gene expression can be, for example, a change in the functional activity of transcription factor binding sites (TFBSs) or DNA methylation change, which, in turn, affects the functional activity of promoters or enhancers. Dissecting the regulatory roles of polymorphic loci have been impossible without close integration of modern experimental approaches with computer analysis of a growing wealth of genetic and biological data obtained using omics technologies. The review provides a brief description of a number of the most well-known public genomic information resources containing data obtained using omics technologies, including (1) resources that accumulate data on the chromatin states and the regions of transcription factor binding derived from ChIP-seq experiments; (2) resources containing data on genomic loci, for which allele-specific transcription factor binding was revealed based on ChIP-seq technology; (3) resources containing in silico predicted data on the potential impact of genetic variants on the transcription factor binding sites

Understanding 3D genome organization by multidisciplinary methods

Understanding how chromatin is folded in the nucleus is fundamental to understanding its function. Although 3D genome organization has been historically difficult to study owing to a lack of relevant methodologies, major technological breakthroughs in genome-wide mapping of chromatin contacts and advances in imaging technologies in the twenty-first century considerably improved our understanding of chromosome conformation and nuclear architecture. In this Review, we discuss methods of 3D genome organization analysis, including sequencing-based techniques, such as Hi-C and its derivatives, Micro-C, DamID and others; microscopy-based techniques, such as super-resolution imaging coupled with fluorescence in situ hybridization (FISH), multiplex FISH, in situ genome sequencing and live microscopy methods; and computational and modelling approaches. We describe the most commonly used techniques and their contribution to our current knowledge of nuclear architecture and, finally, we provide a perspective on up-and-coming methods that open possibilities for future major discoveries.

Methods for ChIP-seq analysis: A practical workflow and advanced applications

Chromatin immunoprecipitation followed by sequencing (ChIP-seq) is a central method in epigenomic research. Genome-wide analysis of histone modifications, such as enhancer analysis and genome-wide chromatin state annotation, enables systematic analysis of how the epigenomic landscape contributes to cell identity, development, lineage specification, and disease. In this review, we first present a typical ChIP-seq analysis workflow, from quality assessment to chromatin-state annotation. We focus on practical, rather than theoretical, approaches for biological studies. Next, we outline various advanced ChIP-seq applications and introduce several state-of-the-art methods, including prediction of gene expression level and chromatin loops from epigenome data and data imputation. Finally, we discuss recently developed single-cell ChIP-seq analysis methodologies that elucidate the cellular diversity within complex tissues and cancers.

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.

A machine learning framework for the prediction of chromatin folding in Drosophila using epigenetic features

Technological advances have lead to the creation of large epigenetic datasets, including information about DNA binding proteins and DNA spatial structure. Hi-C experiments have revealed that chromosomes are subdivided into sets of self-interacting domains called Topologically Associating Domains (TADs). TADs are involved in the regulation of gene expression activity, but the mechanisms of their formation are not yet fully understood. Here, we focus on machine learning methods to characterize DNA folding patterns in Drosophila based on chromatin marks across three cell lines. We present linear regression models with four types of regularization, gradient boosting, and recurrent neural networks (RNN) as tools to study chromatin folding characteristics associated with TADs given epigenetic chromatin immunoprecipitation data. The bidirectional long short-term memory RNN architecture produced the best prediction scores and identified biologically relevant features. Distribution of protein Chriz (Chromator) and histone modification H3K4me3 were selected as the most informative features for the prediction of TADs characteristics. This approach may be adapted to any similar biological dataset of chromatin features across various cell lines and species. The code for the implemented pipeline, Hi-ChiP-ML, is publicly available: https://github.com/MichalRozenwald/Hi-ChIP-ML.

Predicting unrecognized enhancer-mediated genome topology by an ensemble machine learning model

Transcriptional enhancers commonly work over long genomic distances to precisely regulate spatiotemporal gene expression patterns. Dissecting the promoters physically contacted by these distal regulatory elements is essential for understanding developmental processes as well as the role of disease-associated risk variants. Modern proximity-ligation assays, like HiChIP and ChIA-PET, facilitate the accurate identification of long-range contacts between enhancers and promoters. However, these assays are technically challenging, expensive, and time-consuming, making it difficult to investigate enhancer topologies, especially in uncharacterized cell types. To overcome these shortcomings, we therefore designed LoopPredictor, an ensemble machine learning model, to predict genome topology for cell types which lack long-range contact maps. To enrich for functional enhancer-promoter loops over common structural genomic contacts, we trained LoopPredictor with both H3K27ac and YY1 HiChIP data. Moreover, the integration of several related multi-omics features facilitated identifying and annotating the predicted loops. LoopPredictor is able to efficiently identify cell type–specific enhancer-mediated loops, and promoter–promoter interactions, with a modest feature input requirement. Comparable to experimentally generated H3K27ac HiChIP data, we found that LoopPredictor was able to identify functional enhancer loops. Furthermore, to explore the cross-species prediction capability of LoopPredictor, we fed mouse multi-omics features into a model trained on human data and found that the predicted enhancer loops outputs were highly conserved. LoopPredictor enables the dissection of cell type–specific long-range gene regulation and can accelerate the identification of distal disease-associated risk variants.

Predicting 3D genome folding from DNA sequence with Akita

In interphase, the human genome sequence folds in three dimensions into a rich variety of locus-specific contact patterns. Cohesin and CTCF (CCCTC-binding factor) are key regulators; perturbing the levels of either greatly disrupts genome-wide folding as assayed by chromosome conformation capture methods. Still, how a given DNA sequence encodes a particular locus-specific folding pattern remains unknown. Here we present a convolutional neural network, Akita, that accurately predicts genome folding from DNA sequence alone. Representations learned by Akita underscore the importance of an orientation-specific grammar for CTCF binding sites. Akita learns predictive nucleotide-level features of genome folding, revealing effects of nucleotides beyond the core CTCF motif. Once trained, Akita enables rapid in silico predictions. Accounting for this, we demonstrate how Akita can be used to perform in silico saturation mutagenesis, interpret eQTLs, make predictions for structural variants and probe species-specific genome folding. Collectively, these results enable decoding genome function from sequence through structure.

Predicting 3D genome folding from DNA sequence with Akita

In interphase, the human genome sequence folds in three dimensions into a rich variety of locus-specific contact patterns. Cohesin and CTCF (CCCTC-binding factor) are key regulators; perturbing the levels of either greatly disrupts genome-wide folding as assayed by chromosome conformation capture methods. Still, how a given DNA sequence encodes a particular locus-specific folding pattern remains unknown. Here we present a convolutional neural network, Akita, that accurately predicts genome folding from DNA sequence alone. Representations learned by Akita underscore the importance of an orientation-specific grammar for CTCF binding sites. Akita learns predictive nucleotide-level features of genome folding, revealing effects of nucleotides beyond the core CTCF motif. Once trained, Akita enables rapid in silico predictions. Accounting for this, we demonstrate how Akita can be used to perform in silico saturation mutagenesis, interpret eQTLs, make predictions for structural variants and probe species-specific genome folding. Collectively, these results enable decoding genome function from sequence through structure.

DeepC: predicting 3D genome folding using megabase-scale transfer learning

Predicting the impact of noncoding genetic variation requires interpreting it in the context of three-dimensional genome architecture. We have developed deepC, a transfer-learning-based deep neural network that accurately predicts genome folding from megabase-scale DNA sequence. DeepC predicts domain boundaries at high resolution, learns the sequence determinants of genome folding and predicts the impact of both large-scale structural and single base-pair variations.

Data integration for inferring context-specific gene regulatory networks

Transcriptional regulatory networks control context-specific gene expression patterns and play important roles in normal and disease processes. Advances in genomics are rapidly increasing our ability to measure different components of the regulation machinery at the single-cell and bulk population level. An important challenge is to combine different types of regulatory genomic measurements to construct a more complete picture of gene regulatory networks across different disease, environmental, and developmental contexts. In this review, we focus on recent computational methods that integrate regulatory genomic data sets to infer context specificity and dynamics in regulatory networks.

Exploring 3D chromatin contacts in gene regulation: The evolution of approaches for the identification of functional enhancer-promoter interaction

Mechanisms underlying gene regulation are key to understand how multicellular organisms with various cell types develop from the same genetic blueprint. Dynamic interactions between enhancers and genes are revealed to play central roles in controlling gene transcription, but the determinants to link functional enhancer-promoter pairs remain elusive. A major challenge is the lack of reliable approach to detect and verify functional enhancer-promoter interactions (EPIs). In this review, we summarized the current methods for detecting EPIs and described how developing techniques facilitate the identification of EPI through assessing the merits and drawbacks of these methods. We also reviewed recent state-of-art EPI prediction methods in terms of their rationale, data usage and characterization. Furthermore, we briefly discussed the evolved strategies for validating functional EPIs.