Machine learning polymer models of three-dimensional chromatin organization in human lymphoblastoid cells

Bkhetan, Ziad Al; Kadlof, Michal; Kraft, Agnieszka; Plewczynski, Dariusz

doi:10.1016/j.ymeth.2019.03.002

Cited by 9 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RAD21 and the insulator-binding protein CTCF bind to highly conserved promoters and distal enhancers, contributing to transcriptional regulation ( Whalen et al, 2016 ; Liu et al, 2021 ). Numerous studies have shown that distance is a useful factor for studying EPI ( Bianco et al, 2018 ; Al Bkhetan et al, 2019 ). The distance feature has an essential contribution to many models ( Moore et al, 2020 ; Ao et al, 2022b ).…”

Section: Resultsmentioning

confidence: 99%

Predicting enhancer-promoter interaction based on epigenomic signals

et al. 2023

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Predicting enhancer-promoter interaction based on epigenomic signals

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Bkhetan et al . [ 75 ] proposed a pipeline that integrates an improved version of 3DEpiLoop and the spring model to construct visualized 3D chromatin structures based on molecular mechanics.…”

Section: Computational Methods For the Prediction Of 3d Chromatin Organizationmentioning

confidence: 99%

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

Huan

et al. 2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

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.

show abstract

“…Applying to much interactions on short region of chromatin will lead to collapsing model (see fig 3). Contacts may be derived from great variety types of experiment, e.g, ChIA-PET, Hi-C, single-cell Hi-C or even ChIP-Seq processed by machine learning techniques [19].…”

Section: From Experimental Data To Set Of Interaction 160mentioning

confidence: 99%

“…To check the consistency of our approach with ChIA-PET experiment data, we generated 10 000 models starting from SARW and randomly choosing interactions with In [19] we showed that there is a possibility of predicting ChIA-PET interactions from data from cheaper experiments like ChIP-Seq, and in many cases, the interaction pattern is analogous to similarities between 3D structures. 310 We also found out that in some cases it is easy to radically change the structure by simply removing one key long range contact; whilst in other some contacts seems to be redundant because even if they are missing other neighborhood interactions keep structure folded.…”

mentioning

confidence: 99%

Spring Model – chromatin modeling tool based on OpenMM

Kadlof

Rozycka

Plewczynski

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Chromatin structures modelling is a rapidly developing field. Parallel to the enormous growth of available experimental data, there is a growing need of building and visualizing 3D structures of nuclei, chromosomes, chromatin domains, and single loops associated with particular genes locus. Here we present a tool for chromatin domain modeling. It is available as a webserver and standalone python script. Our tool is based on molecular mechanics. It uses OpenMM engine for building models. In this method, the user has to provide contacts and will obtain 3D structure that satisfies these contacts. Additional extra parameters allow controlling fibre stiffness, type of initial structure, resolution. There are also options for structure refinement, and modelling in a spherical container. A user may provide contacts using beads indices, or paste interactions in genome coordinates from BEDPE file. After modelling user is able to download the structure in Protein Data Bank (PDB) file format for further analysis.We dedicate this tool for all who are interested in chromatin structures. It is suitable for quick visualization of datasets, studying the impact of structural variants (SVs), inspecting the effects of adding and removing particular contacts, measuring features like maximum distances between certain sites (e.g. promotor-enhancer) or local density of chromatin.

show abstract

Machine learning polymer models of three-dimensional chromatin organization in human lymphoblastoid cells

Cited by 9 publications

References 24 publications

Predicting enhancer-promoter interaction based on epigenomic signals

Predicting enhancer-promoter interaction based on epigenomic signals

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

Spring Model – chromatin modeling tool based on OpenMM

Contact Info

Product

Resources

About