DeepTACT: predicting 3D chromatin contacts via bootstrapping deep learning

Longitudinal analysis of epigenome-wide DNA methylation reveals novel loci associated with BMI change in East Asians

BACKGROUND

Obesity is a global public health concern linked to chronic diseases such as cardiovascular disease and type 2 diabetes (T2D). Emerging evidence suggests that epigenetic modifications, particularly DNA methylation, may contribute to obesity. However, the molecular mechanism underlying the longitudinal change of BMI has not been well-explored, especially in East Asian populations.

METHODS

This study performed a longitudinal epigenome-wide association analysis of DNA methylation to uncover novel loci associated with BMI change in 533 individuals across two Chinese cohorts with repeated DNA methylation and BMI measurements over four years.

RESULTS

We identified three novel CpG sites (cg14671384, cg25540824, and cg10848724) significantly associated with BMI change. Two of the identified CpG sites were located in regions previously associated with body shape and basal metabolic rate. Annotation of the top 20 BMI change-associated CpGs revealed strong connections to obesity and T2D. Notably, these CpGs exhibited active regulatory roles and located in genes with high expression in the liver and digestive tract, suggesting a potential regulatory pathway from genome to phenotypes of energy metabolism and absorption via DNA methylation. Cross-sectional and longitudinal EWAS comparisons indicated different mechanisms between CpGs related to BMI and BMI change.

CONCLUSION

This study enhances our understanding of the epigenetic dynamics underlying BMI change and emphasizes the value of longitudinal analyses in deciphering the complex interplay between epigenetics and obesity.

Probabilistic association of differentially expressed genes with cis-regulatory elements

Differential gene expression in response to perturbations is mediated at least in part by changes in binding of transcription factors (TFs) and other proteins at specific genomic regions. Association of these cis-regulatory elements (CREs) with their target genes is a challenging task that is essential to address many biological and mechanistic questions. Many current approaches rely on chromatin conformation capture techniques or single-cell correlational methods to establish CRE-to-gene associations. These methods can be effective but have limitations, including resolution, gaps in detectable association distances, and cost. As an alternative, we have developed DegCre, a nonparametric method that evaluates correlations between measurements of perturbation-induced differential gene expression and differential regulatory signal at CREs to score possible CRE-to-gene associations. It has several unique features, including the ability to use any type of CRE activity measurement, yield probabilistic scores for CRE-to-gene pairs, and assess CRE-to-gene pairings across a wide range of sequence distances. We apply DegCre to six data sets, each using different perturbations and containing a variety of regulatory signal measurements, including chromatin openness, histone modifications, and TF occupancy. To test their efficacy, we compare DegCre associations to Hi-C loop calls and CRISPR-validated CRE-to-gene associations, establishing good performance by DegCre that is comparable or superior to competing methods. DegCre is a novel approach to the association of CREs to genes from a perturbation-differential perspective, with strengths that are complementary to existing approaches and allow for new insights into gene regulation.

Targeting the chromatin structural changes of antitumor immunity

Epigenomic imbalance drives abnormal transcriptional processes, promoting the onset and progression of cancer. Although defective gene regulation generally affects carcinogenesis and tumor suppression networks, tumor immunogenicity and immune cells involved in antitumor responses may also be affected by epigenomic changes, which may have significant implications for the development and application of epigenetic therapy, cancer immunotherapy, and their combinations. Herein, we focus on the impact of epigenetic regulation on tumor immune cell function and the role of key abnormal epigenetic processes, DNA methylation, histone post-translational modification, and chromatin structure in tumor immunogenicity, and introduce these epigenetic research methods. We emphasize the value of small-molecule inhibitors of epigenetic modulators in enhancing antitumor immune responses and discuss the challenges of developing treatment plans that combine epigenetic therapy and immunotherapy through the complex interaction between cancer epigenetics and cancer immunology.

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.

EpiGePT: a Pretrained Transformer model for epigenomics

The inherent similarities between natural language and biological sequences have given rise to great interest in adapting the transformer-based large language models (LLMs) underlying recent breakthroughs in natural language processing (references), for applications in genomics. However, current LLMs for genomics suffer from several limitations such as the inability to include chromatin interactions in the training data, and the inability to make prediction in new cellular contexts not represented in the training data. To mitigate these problems, we propose EpiGePT, a transformer-based pretrained language model for predicting context-specific epigenomic signals and chromatin contacts. By taking the context-specific activities of transcription factors (TFs) and 3D genome interactions into consideration, EpiGePT offers wider applicability and deeper biological insights than models trained on DNA sequence only. In a series of experiments, EpiGePT demonstrates superior performance in a diverse set of epigenomic signals prediction tasks when compared to existing methods. In particular, our model enables cross-cell-type prediction of long-range interactions and offers insight on the functional impact of genetic variants under different cellular contexts. These new capabilities will enhance the usefulness of LLM in the study of gene regulatory mechanisms. We provide free online prediction service of EpiGePT through http://health.tsinghua.edu.cn/epigept/.

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.

CREaTor: zero-shot cis-regulatory pattern modeling with attention mechanisms

Linking cis-regulatory sequences to target genes has been a long-standing challenge. In this study, we introduce CREaTor, an attention-based deep neural network designed to model cis-regulatory patterns for genomic elements up to 2 Mb from target genes. Coupled with a training strategy that predicts gene expression from flanking candidate cis-regulatory elements (cCREs), CREaTor can model cell type-specific cis-regulatory patterns in new cell types without prior knowledge of cCRE-gene interactions or additional training. The zero-shot modeling capability, combined with the use of only RNA-seq and ChIP-seq data, allows for the ready generalization of CREaTor to a broad range of cell types.

Integrative approaches based on genomic techniques in the functional studies on enhancers

With the development of sequencing technology and the dramatic drop in sequencing cost, the functions of noncoding genes are being characterized in a wide variety of fields (e.g. biomedicine). Enhancers are noncoding DNA elements with vital transcription regulation functions. Tens of thousands of enhancers have been identified in the human genome; however, the location, function, target genes and regulatory mechanisms of most enhancers have not been elucidated thus far. As high-throughput sequencing techniques have leapt forwards, omics approaches have been extensively employed in enhancer research. Multidimensional genomic data integration enables the full exploration of the data and provides novel perspectives for screening, identification and characterization of the function and regulatory mechanisms of unknown enhancers. However, multidimensional genomic data are still difficult to integrate genome wide due to complex varieties, massive amounts, high rarity, etc. To facilitate the appropriate methods for studying enhancers with high efficacy, we delineate the principles, data processing modes and progress of various omics approaches to study enhancers and summarize the applications of traditional machine learning and deep learning in multi-omics integration in the enhancer field. In addition, the challenges encountered during the integration of multiple omics data are addressed. Overall, this review provides a comprehensive foundation for enhancer analysis.

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.

Nucleotide-level prediction of CircRNA-protein binding based on fully convolutional neural network

Introduction: CircRNA-protein binding plays a critical role in complex biological activity and disease. Various deep learning-based algorithms have been proposed to identify CircRNA-protein binding sites. These methods predict whether the CircRNA sequence includes protein binding sites from the sequence level, and primarily concentrate on analysing the sequence specificity of CircRNA-protein binding. For model performance, these methods are unsatisfactory in accurately predicting motif sites that have special functions in gene expression. Methods: In this study, based on the deep learning models that implement pixel-level binary classification prediction in computer vision, we viewed the CircRNA-protein binding sites prediction as a nucleotide-level binary classification task, and use a fully convolutional neural networks to identify CircRNA-protein binding motif sites (CPBFCN). Results: CPBFCN provides a new path to predict CircRNA motifs. Based on the MEME tool, the existing CircRNA-related and protein-related database, we analysed the motif functions discovered by CPBFCN. We also investigated the correlation between CircRNA sponge and motif distribution. Furthermore, by comparing the motif distribution with different input sequence lengths, we found that some motifs in the flanking sequences of CircRNA-protein binding region may contribute to CircRNA-protein binding. Conclusion: This study contributes to identify circRNA-protein binding and provides help in understanding the role of circRNA-protein binding in gene expression regulation.

Epromoters are new players in the regulatory landscape with potential pleiotropic roles

Precise spatiotemporal control of gene expression during normal development and cell differentiation is achieved by the combined action of proximal (promoters) and distal (enhancers) cis-regulatory elements. Recent studies have reported that a subset of promoters, termed Epromoters, works also as enhancers to regulate distal genes. This new paradigm opened novel questions regarding the complexity of our genome and raises the possibility that genetic variation within Epromoters has pleiotropic effects on various physiological and pathological traits by differentially impacting multiple proximal and distal genes. Here, we discuss the different observations pointing to an important role of Epromoters in the regulatory landscape and summarize the evidence supporting a pleiotropic impact of these elements in disease. We further hypothesize that Epromoter might represent a major contributor to phenotypic variation 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.

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.

A survey on algorithms to characterize transcription factor binding sites

Transcription factors (TFs) are key regulatory proteins that control the transcriptional rate of cells by binding short DNA sequences called transcription factor binding sites (TFBS) or motifs. Identifying and characterizing TFBS is fundamental to understanding the regulatory mechanisms governing the transcriptional state of cells. During the last decades, several experimental methods have been developed to recover DNA sequences containing TFBS. In parallel, computational methods have been proposed to discover and identify TFBS motifs based on these DNA sequences. This is one of the most widely investigated problems in bioinformatics and is referred to as the motif discovery problem. In this manuscript, we review classical and novel experimental and computational methods developed to discover and characterize TFBS motifs in DNA sequences, highlighting their advantages and drawbacks. We also discuss open challenges and future perspectives that could fill the remaining gaps in the field.

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.

The Neural Metric Factorization for Computational Drug Repositioning

Computational drug repositioning aims to discover new therapeutic diseases for marketed drugs and has the advantages of low cost, short development cycle, and high controllability compared to traditional drug development. The matrix factorization model has become the cornerstone technique for computational drug repositioning due to its ease of implementation and excellent scalability. However, the matrix factorization model uses the inner product operation to represent the association between drugs and diseases, which is lacking in expressive ability. Moreover, the degree of similarity of drugs or diseases could not be implied on their respective latent factor vectors, which is not satisfy the common sense of drug discovery. Therefore, a neural metric factorization model for computational drug repositioning (NMFDR) is proposed in this work. We novelly consider the latent factor vector of drugs and diseases as a point in the high-dimensional coordinate system and propose a generalized euclidean distance to represent the association between drugs and diseases to compensate for the shortcomings of the inner product operation. Furthermore, by embedding multiple drug (disease) metrics information into the encoding space of the latent factor vector, the information about the similarity between drugs (diseases) can be reflected in the distance between latent factor vectors. Finally, we conduct wide analysis experiments on three real datasets to demonstrate the effectiveness of the above improvement points and the superiority of the NMFDR model.

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.

DeepPHiC: predicting promoter-centered chromatin interactions using a novel deep learning approach

MOTIVATION

Promoter-centered chromatin interactions, which include promoter-enhancer (PE) and promoter-promoter (PP) interactions, are important to decipher gene regulation and disease mechanisms. The development of next-generation sequencing technologies such as promoter capture Hi-C (pcHi-C) leads to the discovery of promoter-centered chromatin interactions. However, pcHi-C experiments are expensive and thus may be unavailable for tissues/cell types of interest. In addition, these experiments may be underpowered due to insufficient sequencing depth or various artifacts, which results in a limited finding of interactions. Most existing computational methods for predicting chromatin interactions are based on in situ Hi-C and can detect chromatin interactions across the entire genome. However, they may not be optimal for predicting promoter-centered chromatin interactions.

RESULTS

We develop a supervised multi-modal deep learning model, which utilizes a comprehensive set of features such as genomic sequence, epigenetic signal, anchor distance, evolutionary features and DNA structural features to predict tissue/cell type-specific PE and PP interactions. We further extend the deep learning model in a multi-task learning and a transfer learning framework and demonstrate that the proposed approach outperforms state-of-the-art deep learning methods. Moreover, the proposed approach can achieve comparable prediction performance using predefined biologically relevant tissues/cell types compared to using all tissues/cell types in the pretraining especially for predicting PE interactions. The prediction performance can be further improved by using computationally inferred biologically relevant tissues/cell types in the pretraining, which are defined based on the common genes in the proximity of two anchors in the chromatin interactions.

AVAILABILITY AND IMPLEMENTATION

https://github.com/lichen-lab/DeepPHiC.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

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.

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.

Modeling chromatin state from sequence across angiosperms using recurrent convolutional neural networks

Accessible chromatin regions are critical components of gene regulation but modeling them directly from sequence remains challenging, especially within plants, whose mechanisms of chromatin remodeling are less understood than in animals. We trained an existing deep-learning architecture, DanQ, on data from 12 angiosperm species to predict the chromatin accessibility in leaf of sequence windows within and across species. We also trained DanQ on DNA methylation data from 10 angiosperms because unmethylated regions have been shown to overlap significantly with ACRs in some plants. The across-species models have comparable or even superior performance to a model trained within species, suggesting strong conservation of chromatin mechanisms across angiosperms. Testing a maize (Zea mays L.) held-out model on a multi-tissue chromatin accessibility panel revealed our models are best at predicting constitutively accessible chromatin regions, with diminishing performance as cell-type specificity increases. Using a combination of interpretation methods, we ranked JASPAR motifs by their importance to each model and saw that the TCP and AP2/ERF transcription factor (TF) families consistently ranked highly. We embedded the top three JASPAR motifs for each model at all possible positions on both strands in our sequence window and observed position- and strand-specific patterns in their importance to the model. With our publicly available across-species 'a2z' model it is now feasible to predict the chromatin accessibility and methylation landscape of any angiosperm genome.

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.

A review of deep learning applications in human genomics using next-generation sequencing data

Genomics is advancing towards data-driven science. Through the advent of high-throughput data generating technologies in human genomics, we are overwhelmed with the heap of genomic data. To extract knowledge and pattern out of this genomic data, artificial intelligence especially deep learning methods has been instrumental. In the current review, we address development and application of deep learning methods/models in different subarea of human genomics. We assessed over- and under-charted area of genomics by deep learning techniques. Deep learning algorithms underlying the genomic tools have been discussed briefly in later part of this review. Finally, we discussed briefly about the late application of deep learning tools in genomic. Conclusively, this review is timely for biotechnology or genomic scientists in order to guide them why, when and how to use deep learning methods to analyse human genomic data.

Learning representations of chromatin contacts using a recurrent neural network identifies genomic drivers of conformation

Despite the availability of chromatin conformation capture experiments, discerning the relationship between the 1D genome and 3D conformation remains a challenge, which limits our understanding of their affect on gene expression and disease. We propose Hi-C-LSTM, a method that produces low-dimensional latent representations that summarize intra-chromosomal Hi-C contacts via a recurrent long short-term memory neural network model. We find that these representations contain all the information needed to recreate the observed Hi-C matrix with high accuracy, outperforming existing methods. These representations enable the identification of a variety of conformation-defining genomic elements, including nuclear compartments and conformation-related transcription factors. They furthermore enable in-silico perturbation experiments that measure the influence of cis-regulatory elements on conformation.

DeepCAGE: Incorporating Transcription Factors in Genome-wide Prediction of Chromatin Accessibility

Although computational approaches have been complementing high-throughput biological experiments for the identification of functional regions in the human genome, it remains a great challenge to systematically decipher interactions between transcription factors (TFs) and regulatory elements to achieve interpretable annotations of chromatin accessibility across diverse cellular contexts. To solve this problem, we propose DeepCAGE, a deep learning framework that integrates sequence information and binding statuses of TFs, for the accurate prediction of chromatin accessible regions at a genome-wide scale in a variety of cell types. DeepCAGE takes advantage of a densely connected deep convolutional neural network architecture to automatically learn sequence signatures of known chromatin accessible regions and then incorporates such features with expression levels and binding activities of human core TFs to predict novel chromatin accessible regions. In a series of systematic comparisons with existing methods, DeepCAGE exhibits superior performance in not only the classification but also the regression of chromatin accessibility signals. In a detailed analysis of TF activities, DeepCAGE successfully extracts novel binding motifs and measures the contribution of a TF to the regulation with respect to a specific locus in a certain cell type. When applied to whole-genome sequencing data analysis, our method successfully prioritizes putative deleterious variants underlying a human complex trait and thus provides insights into the understanding of disease-associated genetic variants. DeepCAGE can be downloaded from https://github.com/kimmo1019/DeepCAGE.

Predicting 3D chromatin interactions from DNA sequence using Deep Learning

Gene regulation in eukaryotes is profoundly shaped by the 3D organization of chromatin within the cell nucleus. Distal regulatory interactions between enhancers and their target genes are widespread and many causal loci underlying heritable agricultural or clinical traits have been mapped to distal cis-regulatory elements. Dissecting the sequence features that mediate such distal interactions is key to understanding their underlying biology. Deep Learning (DL) models coupled with genome-wide 3C-based sequencing data have emerged as powerful tools to infer the DNA sequence grammar underlying such distal interactions. In this review we show that most DL models have remarkably high prediction accuracy, which indicates that DNA sequence features are important determinants of chromatin looping. However, DL model training has so far been limited to a small set of human cell lines, raising questions about the generalization of these predictions to other tissue-types and species. Furthermore, we find that the model architecture seems less relevant for model performance than the training strategy and the data preparation step. Transfer learning, coupled with functionally curated interactions, appear to be the most promising approach to learn cell-type specific and possibly species- specific sequence features in future applications.

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.

Integrating convolution and self-attention improves language model of human genome for interpreting non-coding regions at base-resolution

Interpretation of non-coding genome remains an unsolved challenge in human genetics due to impracticality of exhaustively annotating biochemically active elements in all conditions. Deep learning based computational approaches emerge recently to help interpret non-coding regions. Here, we present LOGO (Language of Genome), a self-attention based contextualized pre-trained language model containing only two self-attention layers with 1 million parameters as a substantially light architecture that applies self-supervision techniques to learn bidirectional representations of the unlabelled human reference genome. LOGO is then fine-tuned for sequence labelling task, and further extended to variant prioritization task via a special input encoding scheme of alternative alleles followed by adding a convolutional module. Experiments show that LOGO achieves 15% absolute improvement for promoter identification and up to 4.5% absolute improvement for enhancer-promoter interaction prediction. LOGO exhibits state-of-the-art multi-task predictive power on thousands of chromatin features with only 3% parameterization benchmarking against the fully supervised model, DeepSEA and 1% parameterization against a recent BERT-based DNA language model. For allelic-effect prediction, locality introduced by one dimensional convolution shows improved sensitivity and specificity for prioritizing non-coding variants associated with human diseases. In addition, we apply LOGO to interpret type 2 diabetes (T2D) GWAS signals and infer underlying regulatory mechanisms. We make a conceptual analogy between natural language and human genome and demonstrate LOGO is an accurate, fast, scalable, and robust framework to interpret non-coding regions for global sequence labeling as well as for variant prioritization at base-resolution.

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.

Connecting high-resolution 3D chromatin organization with epigenomics

The resolution of chromatin conformation capture technologies keeps increasing, and the recent nucleosome resolution chromatin contact maps allow us to explore how fine-scale 3D chromatin organization is related to epigenomic states in human cells. Using publicly available Micro-C datasets, we develop a deep learning model, CAESAR, to learn a mapping function from epigenomic features to 3D chromatin organization. The model accurately predicts fine-scale structures, such as short-range chromatin loops and stripes, that Hi-C fails to detect. With existing epigenomic datasets from ENCODE and Roadmap Epigenomics Project, we successfully impute high-resolution 3D chromatin contact maps for 91 human tissues and cell lines. In the imputed high-resolution contact maps, we identify the spatial interactions between genes and their experimentally validated regulatory elements, demonstrating CAESAR's potential in coupling transcriptional regulation with 3D chromatin organization at high resolution.

MOMA: a multi-task attention learning algorithm for multi-omics data interpretation and classification

MOTIVATION

Accurate diagnostic classification and biological interpretation are important in biology and medicine, which are data-rich sciences. Thus, integration of different data types is necessary for the high predictive accuracy of clinical phenotypes, and more comprehensive analyses for predicting the prognosis of complex diseases are required.

RESULTS

Here, we propose a novel multi-task attention learning algorithm for multi-omics data, termed MOMA, which captures important biological processes for high diagnostic performance and interpretability. MOMA vectorizes features and modules using a geometric approach and focuses on important modules in multi-omics data via an attention mechanism. Experiments using public data on Alzheimer's disease and cancer with various classification tasks demonstrated the superior performance of this approach. The utility of MOMA was also verified using a comparison experiment with an attention mechanism that was turned on or off and biological analysis.

AVAILABILITY AND IMPLEMENTATION

The source codes are available at https://github.com/dmcb-gist/MOMA.

SUPPLEMENTARY INFORMATION

Supplementary materials are available at Bioinformatics online.

ProbC: joint modeling of epigenome and transcriptome effects in 3D genome

Background

Hi-C and its high nucleosome resolution variant Micro-C provide a window into the spatial packing of a genome in 3D within the cell. Even though both techniques do not directly depend on the binding of specific antibodies, previous work has revealed enriched interactions and domain structures around multiple chromatin marks; epigenetic modifications and transcription factor binding sites. However, the joint impact of chromatin marks in Hi-C and Micro-C interactions have not been globally characterized, which limits our understanding of 3D genome characteristics. An emerging question is whether it is possible to deduce 3D genome characteristics and interactions by integrative analysis of multiple chromatin marks and associate interactions to functionality of the interacting loci.

Result

We come up with a probabilistic method ProbC to decompose Hi-C and Micro-C interactions by known chromatin marks. ProbC is based on convex likelihood optimization, which can directly take into account both interaction existence and nonexistence. Through ProbC, we discover histone modifications (H3K27ac, H3K9me3, H3K4me3, H3K4me1) and CTCF as particularly predictive of Hi-C and Micro-C contacts across cell types and species. Moreover, histone modifications are more effective than transcription factor binding sites in explaining the genome’s 3D shape through these interactions. ProbC can successfully predict Hi-C and Micro-C interactions in given species, while it is trained on different cell types or species. For instance, it can predict missing nucleosome resolution Micro-C interactions in human ES cells trained on mouse ES cells only from these 5 chromatin marks with above 0.75 AUC. Additionally, ProbC outperforms the existing methods in predicting interactions across almost all chromosomes.

Conclusion

Via our proposed method, we optimally decompose Hi-C interactions in terms of these chromatin marks at genome and chromosome levels. We find a subset of histone modifications and transcription factor binding sites to be predictive of both Hi-C and Micro-C interactions and TADs across human, mouse, and different cell types. Through learned models, we can predict interactions on species just from chromatin marks for which Hi-C data may be limited.

scGraph: a graph neural network-based approach to automatically identify cell types

MOTIVATION

Single cell technologies play a crucial role in revolutionizing biological research over the past decade, which strengthens our understanding in cell differentiation, development, and regulation from a single-cell level perspective. Single-cell RNA sequencing (scRNA-seq) is one of the most common single cell technologies, which enables probing transcriptional states in thousands of cells in one experiment. Identification of cell types from scRNA-seq measurements is a fundamental and crucial question to answer. Most previous studies directly take gene expression as input while ignoring the comprehensive gene-gene interactions.

RESULTS

We propose scGraph, an automatic cell identification algorithm leveraging gene interaction relationships to enhance the performance of the cell type identification. ScGraph is based on a graph neural network to aggregate the information of interacting genes. In a series of experiments, we demonstrate that scGraph is accurate and outperforms eight comparison methods in the task of cell type identification. Moreover, scGraph automatically learns the gene interaction relationships from biological data and the pathway enrichment analysis shows consistent findings with previous analysis, providing insights on the analysis of regulatory mechanism.

AVAILABILITY

scGraph is freely available at https://github.com/QijinYin/scGraph and https://figshare.com/articles/software/scGraph/17157743.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

An efficient curriculum learning-based strategy for molecular graph learning

Computational methods have been widely applied to resolve various core issues in drug discovery, such as molecular property prediction. In recent years, a data-driven computational method-deep learning had achieved a number of impressive successes in various domains. In drug discovery, graph neural networks (GNNs) take molecular graph data as input and learn graph-level representations in non-Euclidean space. An enormous amount of well-performed GNNs have been proposed for molecular graph learning. Meanwhile, efficient use of molecular data during training process, however, has not been paid enough attention. Curriculum learning (CL) is proposed as a training strategy by rearranging training queue based on calculated samples' difficulties, yet the effectiveness of CL method has not been determined in molecular graph learning. In this study, inspired by chemical domain knowledge and task prior information, we proposed a novel CL-based training strategy to improve the training efficiency of molecular graph learning, called CurrMG. Consisting of a difficulty measurer and a training scheduler, CurrMG is designed as a plug-and-play module, which is model-independent and easy-to-use on molecular data. Extensive experiments demonstrated that molecular graph learning models could benefit from CurrMG and gain noticeable improvement on five GNN models and eight molecular property prediction tasks (overall improvement is 4.08%). We further observed CurrMG’s encouraging potential in resource-constrained molecular property prediction. These results indicate that CurrMG can be used as a reliable and efficient training strategy for molecular graph learning.

Availability: The source code is available in https://github.com/gu-yaowen/CurrMG.

Multi-omics research in sarcopenia: Current progress and future prospects

Sarcopenia is a systemic disease with progressive and generalized skeletal muscle dysfunction defined by age-related low muscle mass, high content of muscle slow fibers, and low muscle function. Muscle phenotypes and sarcopenia risk are heritable; however, the genetic architecture and molecular mechanisms underlying sarcopenia remain largely unclear. In recent years, significant progress has been made in determining susceptibility loci using genome-wide association studies. In addition, recent advances in omics techniques, including genomics, epigenomics, transcriptomics, proteomics, and metabolomics, offer new opportunities to identify novel targets to help us understand the pathophysiology of sarcopenia. However, each individual technology cannot capture the entire view of the biological complexity of this disorder, while integrative multi-omics analyses may be able to reveal new insights. Here, we review the latest findings of multi-omics studies for sarcopenia and provide an in-depth summary of our current understanding of sarcopenia pathogenesis. Leveraging multi-omics data could give us a holistic understanding of sarcopenia etiology that may lead to new clinical applications. This review offers guidance and recommendations for fundamental research, innovative perspectives, and preventative and therapeutic interventions for sarcopenia.

CT-FOCS: a novel method for inferring cell type-specific enhancer–promoter maps

Spatiotemporal gene expression patterns are governed to a large extent by the activity of enhancer elements, which engage in physical contacts with their target genes. Identification of enhancer–promoter (EP) links that are functional only in a specific subset of cell types is a key challenge in understanding gene regulation. We introduce CT-FOCS (cell type FOCS), a statistical inference method that uses linear mixed effect models to infer EP links that show marked activity only in a single or a small subset of cell types out of a large panel of probed cell types. Analyzing 808 samples from FANTOM5, covering 472 cell lines, primary cells and tissues, CT-FOCS inferred such EP links more accurately than recent state-of-the-art methods. Furthermore, we show that strictly cell type-specific EP links are very uncommon in the human genome.

Air Pollution and Perinatal Health in the Eastern Mediterranean Region: Challenges, Limitations, and the Potential of Epigenetics

PURPOSE OF REVIEW

Even though the burden of disease attributable to air pollution is high in the Eastern Mediterranean Region (EMR), the number of studies linking environmental exposures to negative health outcomes remains scarce and limited in scope. This review aims to assess the literature on exposure to air pollutants and perinatal health in the EMR and to explain the potential of epigenetics in exploring the processes behind adverse birth outcomes.

RECENT FINDINGS

In the last three decades, hundreds of studies and publications tackled the health effects of air pollution on birth outcomes and early life development, but only a small number of these studies was conducted in the EMR. The existing literature is concentrated in specific geographic locations and is focused on a limited number of exposures and outcomes. Main limitations include inconsistent and poorly funded air quality monitoring, inappropriate study designs, imprecise and/or unreliable assessments of exposures, and outcomes. Even though the studies establish associations between air pollutants and adverse birth outcomes, the mechanisms through which these processes take place are yet to be fully understood. A likely candidate to explain these processes is epigenetics; however, epigenetics research on the impact of air pollution in EMR is still in its infancy. This review highlights the need for future research examining perinatal health and air pollutants, especially the epigenetic processes that underlie the adverse birth outcomes, to better understand them and to develop effective recommendations and intervention strategies.

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.

PDGNet: Predicting Disease Genes Using a Deep Neural Network With Multi-View Features

The knowledge of phenotype-genotype associations is crucial for the understanding of disease mechanisms. Numerous studies have focused on developing efficient and accurate computing approaches to predict disease genes. However, owing to the sparseness and complexity of medical data, developing an efficient deep neural network model to identify disease genes remains a huge challenge. Therefore, we develop a novel deep neural network model that fuses the multi-view features of phenotypes and genotypes to identify disease genes (termed PDGNet). Our model integrated the multi-view features of diseases and genes and leveraged the feedback information of training samples to optimize the parameters of deep neural network and obtain the deep vector features of diseases and genes. The evaluation experiments on a large data set indicated that PDGNet obtained higher performance than the state-of-the-art method (precision and recall improved by 9.55 and 9.63 percent). The analysis results for the candidate genes indicated that the predicted genes have strong functional homogeneity and dense interactions with known genes. We validated the top predicted genes of Parkinson's disease based on external curated data and published medical literatures, which indicated that the candidate genes have a huge potential to guide the selection of causal genes in the 'wet experiment'. The source codes and the data of PDGNet are available at https://github.com/yangkuoone/PDGNet.

3D genome organization links non-coding disease-associated variants to genes

Genome sequencing has revealed over 300 million genetic variations in human populations. Over 90% of variants are single nucleotide polymorphisms (SNPs), the remainder include short deletions or insertions, and small numbers of structural variants. Hundreds of thousands of these variants have been associated with specific phenotypic traits and diseases through genome wide association studies which link significant differences in variant frequencies with specific phenotypes among large groups of individuals. Only 5% of disease-associated SNPs are located in gene coding sequences, with the potential to disrupt gene expression or alter of the function of encoded proteins. The remaining 95% of disease-associated SNPs are located in non-coding DNA sequences which make up 98% of the genome. The role of non-coding, disease-associated SNPs, many of which are located at considerable distances from any gene, was at first a mystery until the discovery that gene promoters regularly interact with distal regulatory elements to control gene expression. Disease-associated SNPs are enriched at the millions of gene regulatory elements that are dispersed throughout the non-coding sequences of the genome, suggesting they function as gene regulation variants. Assigning specific regulatory elements to the genes they control is not straightforward since they can be millions of base pairs apart. In this review we describe how understanding 3D genome organization can identify specific interactions between gene promoters and distal regulatory elements and how 3D genomics can link disease-associated SNPs to their target genes. Understanding which gene or genes contribute to a specific disease is the first step in designing rational therapeutic interventions.

Epromoters function as a hub to recruit key transcription factors required for the inflammatory response

Gene expression is controlled by the involvement of gene-proximal (promoters) and distal (enhancers) regulatory elements. Our previous results demonstrated that a subset of gene promoters, termed Epromoters, work as bona fide enhancers and regulate distal gene expression. Here, we hypothesized that Epromoters play a key role in the coordination of rapid gene induction during the inflammatory response. Using a high-throughput reporter assay we explored the function of Epromoters in response to type I interferon. We find that clusters of IFNa-induced genes are frequently associated with Epromoters and that these regulatory elements preferentially recruit the STAT1/2 and IRF transcription factors and distally regulate the activation of interferon-response genes. Consistently, we identified and validated the involvement of Epromoter-containing clusters in the regulation of LPS-stimulated macrophages. Our findings suggest that Epromoters function as a local hub recruiting the key TFs required for coordinated regulation of gene clusters during the inflammatory response.

Machine learning meets omics: applications and perspectives

The innovation of biotechnologies has allowed the accumulation of omics data at an alarming rate, thus introducing the era of 'big data'. Extracting inherent valuable knowledge from various omics data remains a daunting problem in bioinformatics. Better solutions often need some kind of more innovative methods for efficient handlings and effective results. Recent advancements in integrated analysis and computational modeling of multi-omics data helped address such needs in an increasingly harmonious manner. The development and application of machine learning have largely advanced our insights into biology and biomedicine and greatly promoted the development of therapeutic strategies, especially for precision medicine. Here, we propose a comprehensive survey and discussion on what happened, is happening and will happen when machine learning meets omics. Specifically, we describe how artificial intelligence can be applied to omics studies and review recent advancements at the interface between machine learning and the ever-widest range of omics including genomics, transcriptomics, proteomics, metabolomics, radiomics, as well as those at the single-cell resolution. We also discuss and provide a synthesis of ideas, new insights, current challenges and perspectives of machine learning in omics.

Improving Chromatin-Interaction Prediction Using Single-Cell Open-Chromatin Profiles and Making Insight Into the Cis-Regulatory Landscape of the Human Brain

Single-cell open-chromatin profiles have the potential to reveal the pattern of chromatin-interaction in a cell type. However, currently available cis-regulatory network prediction methods using single-cell open-chromatin profiles focus more on local chromatin interactions despite the fact that long-range interactions among genomic sites play a significant role in gene regulation. Here, we propose a method that predicts both short and long-range interactions among genomic sites using single-cell open chromatin profiles. Our method, termed as single-cell epigenome based chromatin-interaction analysis (scEChIA) exploits signal imputation and refined L1 regularization. For a few single-cell open-chromatin profiles, scEChIA outperformed other tools even in terms of accuracy of prediction. Using scEChIA, we predicted almost 0.7 million interactions among genomic sites across seven cell types in the human brain. Further analysis revealed cell type for connection between genes and expression quantitative trait locus (eQTL) in the human brain and making insight about target genes of human-accelerated-elements and disease-associated mutations. Our analysis enabled by scEChIA also hints about the possible action of a few transcription factors (TFs), especially through long-range interaction in brain endothelial cells.

Leveraging three-dimensional chromatin architecture for effective reconstruction of enhancer-target gene regulatory interactions

A growing amount of evidence in literature suggests that germline sequence variants and somatic mutations in non-coding distal regulatory elements may be crucial for defining disease risk and prognostic stratification of patients, in genetic disorders as well as in cancer. Their functional interpretation is challenging because genome-wide enhancer-target gene (ETG) pairing is an open problem in genomics. The solutions proposed so far do not account for the hierarchy of structural domains which define chromatin three-dimensional (3D) architecture. Here we introduce a change of perspective based on the definition of multi-scale structural chromatin domains, integrated in a statistical framework to define ETG pairs. In this work (i) we develop a computational and statistical framework to reconstruct a comprehensive map of ETG pairs leveraging functional genomics data; (ii) we demonstrate that the incorporation of chromatin 3D architecture information improves ETG pairing accuracy and (iii) we use multiple experimental datasets to extensively benchmark our method against previous solutions for the genome-wide reconstruction of ETG pairs. This solution will facilitate the annotation and interpretation of sequence variants in distal non-coding regulatory elements. We expect this to be especially helpful in clinically oriented applications of whole genome sequencing in cancer and undiagnosed genetic diseases research.

Chromatin interaction neural network (ChINN): a machine learning-based method for predicting chromatin interactions from DNA sequences

Chromatin interactions play important roles in regulating gene expression. However, the availability of genome-wide chromatin interaction data is limited. We develop a computational method, chromatin interaction neural network (ChINN), to predict chromatin interactions between open chromatin regions using only DNA sequences. ChINN predicts CTCF- and RNA polymerase II-associated and Hi-C chromatin interactions. ChINN shows good across-sample performances and captures various sequence features for chromatin interaction prediction. We apply ChINN to 6 chronic lymphocytic leukemia (CLL) patient samples and a published cohort of 84 CLL open chromatin samples. Our results demonstrate extensive heterogeneity in chromatin interactions among CLL patient samples.

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.

OpenAnnotate: a web server to annotate the chromatin accessibility of genomic regions

Chromatin accessibility, as a powerful marker of active DNA regulatory elements, provides valuable information for understanding regulatory mechanisms. The revolution in high-throughput methods has accumulated massive chromatin accessibility profiles in public repositories. Nevertheless, utilization of these data is hampered by cumbersome collection, time-consuming processing, and manual chromatin accessibility (openness) annotation of genomic regions. To fill this gap, we developed OpenAnnotate (http://health.tsinghua.edu.cn/openannotate/) as the first web server for efficiently annotating openness of massive genomic regions across various biosample types, tissues, and biological systems. In addition to the annotation resource from 2729 comprehensive profiles of 614 biosample types of human and mouse, OpenAnnotate provides user-friendly functionalities, ultra-efficient calculation, real-time browsing, intuitive visualization, and elaborate application notebooks. We show its unique advantages compared to existing databases and toolkits by effectively revealing cell type-specificity, identifying regulatory elements and 3D chromatin contacts, deciphering gene functional relationships, inferring functions of transcription factors, and unprecedentedly promoting single-cell data analyses. We anticipate OpenAnnotate will provide a promising avenue for researchers to construct a more holistic perspective to understand regulatory mechanisms.