Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Epiphany: predicting Hi-C contact maps from 1D epigenomic signals

ABSTRACT: Recent deep learning models that predict the Hi-C contact map from DNA sequence achieve promising accuracy but cannot generalize to new cell types and or even capture differences among training cell types. We propose Epiphany, a neural network to predict cell-type-specific Hi-C contact maps from widely available epigenomic tracks. Epiphany uses bidirectional long short-term memory layers to capture long-range dependencies and optionally a generative adversarial network architecture to encourage contact map realism. Epiphany shows excellent generalization to held-out chromosomes within and across cell types, yields accurate TAD and interaction calls, and predicts structural changes caused by perturbations of epigenomic signals.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13059-023-02934-9.

SUBMITTER: Yang R

PROVIDER: S-EPMC10242996 | biostudies-literature | 2023 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Predicting enhancer-promoter interaction based on epigenomic signals.

Project description:Introduction: The physical interactions between enhancers and promoters are often involved in gene transcriptional regulation. High tissue-specific enhancer-promoter interactions (EPIs) are responsible for the differential expression of genes. Experimental methods are time-consuming and labor-intensive in measuring EPIs. An alternative approach, machine learning, has been widely used to predict EPIs. However, most existing machine learning methods require a large number of functional genomic and epigenomic features as input, which limits the application to different cell lines. Methods: In this paper, we developed a random forest model, HARD (H3K27ac, ATAC-seq, RAD21, and Distance), to predict EPI using only four types of features. Results: Independent tests on a benchmark dataset showed that HARD outperforms other models with the fewest features. Discussion: Our results revealed that chromatin accessibility and the binding of cohesin are important for cell-line-specific EPIs. Furthermore, we trained the HARD model in the GM12878 cell line and performed testing in the HeLa cell line. The cross-cell-lines prediction also performs well, suggesting it has the potential to be applied to other cell lines.

| S-EPMC10151517 | biostudies-literature

EpiMCI: Predicting Multi-Way Chromatin Interactions from Epigenomic Signals.

Project description:The recently emerging high-throughput Pore-C (HiPore-C) can identify whole-genome high-order chromatin multi-way interactions with an ultra-high output, contributing to deciphering three-dimensional (3D) genome organization. However, it also brings new challenges to relevant data analysis. To alleviate this problem, we proposed the EpiMCI, a model for multi-way chromatin interaction prediction based on a hypergraph neural network with epigenomic signals as the input. The EpiMCI integrated separate hyperedge representations with coupling hyperedge information and obtained AUCs of 0.981 and 0.984 in the GM12878 and K562 datasets, respectively, which outperformed the current available method. Moreover, the EpiMCI can be applied to denoise the HiPore-C data and improve the data quality efficiently. Furthermore, the vertex embeddings extracted from the EpiMCI reflected the global chromatin architecture accurately. The principal component analysis suggested that it was well aligned with the activities of genomic regions at the chromatin compartment level. Taken together, the EpiMCI can accurately predict multi-way chromatin interactions and can be applied to studies relying on chromatin architecture.

| S-EPMC10525350 | biostudies-literature

Species-level deconvolution of metagenome assemblies with Hi-C-based contact probability maps.

Project description:Microbial communities consist of mixed populations of organisms, including unknown species in unknown abundances. These communities are often studied through metagenomic shotgun sequencing, but standard library construction methods remove long-range contiguity information; thus, shotgun sequencing and de novo assembly of a metagenome typically yield a collection of contigs that cannot readily be grouped by species. Methods for generating chromatin-level contact probability maps, e.g., as generated by the Hi-C method, provide a signal of contiguity that is completely intracellular and contains both intrachromosomal and interchromosomal information. Here, we demonstrate how this signal can be exploited to reconstruct the individual genomes of microbial species present within a mixed sample. We apply this approach to two synthetic metagenome samples, successfully clustering the genome content of fungal, bacterial, and archaeal species with more than 99% agreement with published reference genomes. We also show that the Hi-C signal can secondarily be used to create scaffolded genome assemblies of individual eukaryotic species present within the microbial community, with higher levels of contiguity than some of the species' published reference genomes.

| S-EPMC4455782 | biostudies-literature

EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework.

Project description:MotivationThe high-throughput chromosome conformation capture (Hi-C) technique has enabled genome-wide mapping of chromatin interactions. However, high-resolution Hi-C data requires costly, deep sequencing; therefore, it has only been achieved for a limited number of cell types. Machine learning models based on neural networks have been developed as a remedy to this problem.ResultsIn this work, we propose a novel method, EnHiC, for predicting high-resolution Hi-C matrices from low-resolution input data based on a generative adversarial network (GAN) framework. Inspired by non-negative matrix factorization, our model fully exploits the unique properties of Hi-C matrices and extracts rank-1 features from multi-scale low-resolution matrices to enhance the resolution. Using three human Hi-C datasets, we demonstrated that EnHiC accurately and reliably enhanced the resolution of Hi-C matrices and outperformed other GAN-based models. Moreover, EnHiC-predicted high-resolution matrices facilitated the accurate detection of topologically associated domains and fine-scale chromatin interactions.Availability and implementationEnHiC is publicly available at https://github.com/wmalab/EnHiC.Supplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC8382278 | biostudies-literature

Juicebox Provides a Visualization System for Hi-C Contact Maps with Unlimited Zoom.

Project description:Hi-C experiments study how genomes fold in 3D, generating contact maps containing features as small as 20 bp and as large as 200 Mb. Here we introduce Juicebox, a tool for exploring Hi-C and other contact map data. Juicebox allows users to zoom in and out of Hi-C maps interactively, just as a user of Google Earth might zoom in and out of a geographic map. Maps can be compared to one another, or to 1D tracks or 2D feature sets.

| S-EPMC5596920 | biostudies-literature

HiCBin: binning metagenomic contigs and recovering metagenome-assembled genomes using Hi-C contact maps.

Project description:Recovering high-quality metagenome-assembled genomes (MAGs) from complex microbial ecosystems remains challenging. Recently, high-throughput chromosome conformation capture (Hi-C) has been applied to simultaneously study multiple genomes in natural microbial communities. We develop HiCBin, a novel open-source pipeline, to resolve high-quality MAGs utilizing Hi-C contact maps. HiCBin employs the HiCzin normalization method and the Leiden clustering algorithm and includes the spurious contact detection into binning pipelines for the first time. HiCBin is validated on one synthetic and two real metagenomic samples and is shown to outperform the existing Hi-C-based binning methods. HiCBin is available at https://github.com/dyxstat/HiCBin .

| S-EPMC8883645 | biostudies-literature

HiC-spector: a matrix library for spectral and reproducibility analysis of Hi-C contact maps.

Project description:SummaryGenome-wide proximity ligation based assays like Hi-C have opened a window to the 3D organization of the genome. In so doing, they present data structures that are different from conventional 1D signal tracks. To exploit the 2D nature of Hi-C contact maps, matrix techniques like spectral analysis are particularly useful. Here, we present HiC-spector, a collection of matrix-related functions for analyzing Hi-C contact maps. In particular, we introduce a novel reproducibility metric for quantifying the similarity between contact maps based on spectral decomposition. The metric successfully separates contact maps mapped from Hi-C data coming from biological replicates, pseudo-replicates and different cell types.Availability and implementationSource code in Julia and Python, and detailed documentation is available at https://github.com/gersteinlab/HiC-spector .Contactkoonkiu.yan@gmail.com or mark@gersteinlab.org.Supplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC5870694 | biostudies-literature

Predicting Designability of Small Proteins from Graph Features of Contact Maps.

Project description:Highly designable structures can be distinguished based on certain geometric graphical features of the interactions, confirming the fact that the topology of a protein structure and its residue-residue interaction network are important determinants of its designability. The most designable structures and least designable structures obtained for sets of proteins having the same number of residues are compared. It is shown that the most designable structures predicted by the graph features of the contact diagrams are more densely packed, whereas the poorly designable structures are more open structures or structures that are loosely packed. Interestingly enough, it can also be seen that the highly designable identified are also common structural motifs found in nature.

| S-EPMC4876523 | biostudies-literature

Constructing 3D interaction maps from 1D epigenomes.

Project description:The human genome is tightly packaged into chromatin whose functional output depends on both one-dimensional (1D) local chromatin states and three-dimensional (3D) genome organization. Currently, chromatin modifications and 3D genome organization are measured by distinct assays. An emerging question is whether it is possible to deduce 3D interactions by integrative analysis of 1D epigenomic data and associate 3D contacts to functionality of the interacting loci. Here we present EpiTensor, an algorithm to identify 3D spatial associations within topologically associating domains (TADs) from 1D maps of histone modifications, chromatin accessibility and RNA-seq. We demonstrate that active promoter-promoter, promoter-enhancer and enhancer-enhancer associations identified by EpiTensor are highly concordant with those detected by Hi-C, ChIA-PET and eQTL analyses at 200 bp resolution. Moreover, EpiTensor has identified a set of interaction hotspots, characterized by higher chromatin and transcriptional activity as well as enriched TF and ncRNA binding across diverse cell types, which may be critical for stabilizing the local 3D interactions.

| S-EPMC4792925 | biostudies-literature

Multi-head attention-based U-Nets for predicting protein domain boundaries using 1D sequence features and 2D distance maps.

Project description:The information about the domain architecture of proteins is useful for studying protein structure and function. However, accurate prediction of protein domain boundaries (i.e., sequence regions separating two domains) from sequence remains a significant challenge. In this work, we develop a deep learning method based on multi-head U-Nets (called DistDom) to predict protein domain boundaries utilizing 1D sequence features and predicted 2D inter-residue distance map as input. The 1D features contain the evolutionary and physicochemical information of protein sequences, whereas the 2D distance map includes the structural information of proteins that was rarely used in domain boundary prediction before. The 1D and 2D features are processed by the 1D and 2D U-Nets respectively to generate hidden features. The hidden features are then used by the multi-head attention to predict the probability of each residue of a protein being in a domain boundary, leveraging both local and global information in the features. The residue-level domain boundary predictions can be used to classify proteins as single-domain or multi-domain proteins. It classifies the CASP14 single-domain and multi-domain targets at the accuracy of 75.9%, 13.28% more accurate than the state-of-the-art method. Tested on the CASP14 multi-domain protein targets with expert annotated domain boundaries, the average per-target F1 measure score of the domain boundary prediction by DistDom is 0.263, 29.56% higher than the state-of-the-art method.

| S-EPMC9295499 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data