Literature DB >> 33516170

Self-organizing maps with variable neighborhoods facilitate learning of chromatin accessibility signal shapes associated with regulatory elements.

Tara Eicher1,2,3, Jany Chan1, Han Luu1, Raghu Machiraju4,5,6,7, Ewy A Mathé8,9.   

Abstract

BACKGROUND: Assigning chromatin states genome-wide (e.g. promoters, enhancers, etc.) is commonly performed to improve functional interpretation of these states. However, computational methods to assign chromatin state suffer from the following drawbacks: they typically require data from multiple assays, which may not be practically feasible to obtain, and they depend on peak calling algorithms, which require careful parameterization and often exclude the majority of the genome. To address these drawbacks, we propose a novel learning technique built upon the Self-Organizing Map (SOM), Self-Organizing Map with Variable Neighborhoods (SOM-VN), to learn a set of representative shapes from a single, genome-wide, chromatin accessibility dataset to associate with a chromatin state assignment in which a particular RE is prevalent. These shapes can then be used to assign chromatin state using our workflow.
RESULTS: We validate the performance of the SOM-VN workflow on 14 different samples of varying quality, namely one assay each of A549 and GM12878 cell lines and two each of H1 and HeLa cell lines, primary B-cells, and brain, heart, and stomach tissue. We show that SOM-VN learns shapes that are (1) non-random, (2) associated with known chromatin states, (3) generalizable across sets of chromosomes, and (4) associated with magnitude and multimodality. We compare the accuracy of SOM-VN chromatin states against the Clustering Aggregation Tool (CAGT), an unsupervised method that learns chromatin accessibility signal shapes but does not associate these shapes with REs, and we show that overall precision and recall is increased when learning shapes using SOM-VN as compared to CAGT. We further compare enhancer state assignments from SOM-VN in signals above a set threshold to enhancer state assignments from Predicting Enhancers from ATAC-seq Data (PEAS), a deep learning method that assigns enhancer chromatin states to peaks. We show that the precision-recall area under the curve for the assignment of enhancer states is comparable to PEAS.
CONCLUSIONS: Our work shows that the SOM-VN workflow can learn relationships between REs and chromatin accessibility signal shape, which is an important step toward the goal of assigning and comparing enhancer state across multiple experiments and phenotypic states.

Entities:  

Keywords:  ATAC-seq; Chromatin accessibility; Chromatin state assignment; DNase-seq; Enhancers; Machine learning; Promoters; RPKM signal shape; Regulatory elements; Self-organizing maps

Year:  2021        PMID: 33516170      PMCID: PMC7847148          DOI: 10.1186/s12859-021-03976-1

Source DB:  PubMed          Journal:  BMC Bioinformatics        ISSN: 1471-2105            Impact factor:   3.169


  5 in total

1.  MUSIC: identification of enriched regions in ChIP-Seq experiments using a mappability-corrected multiscale signal processing framework.

Authors:  Arif Harmanci; Joel Rozowsky; Mark Gerstein
Journal:  Genome Biol       Date:  2014       Impact factor: 13.583

2.  Association of COX-2 Promoter Polymorphisms -765G/C and -1195A/G with Migraine.

Authors:  Elahe Mozaffari; Abbas Doosti; Asghar Arshi; Mostafa Faghani
Journal:  Iran J Public Health       Date:  2016-12       Impact factor: 1.429

3.  Familial analysis reveals rare risk variants for migraine in regulatory regions.

Authors:  Tanya Ramdal Techlo; Andreas Høiberg Rasmussen; Peter L Møller; Morten Bøttcher; Simon Winther; Olafur B Davidsson; Isa A Olofsson; Mona Ameri Chalmer; Lisette J A Kogelman; Mette Nyegaard; Jes Olesen; Thomas Folkmann Hansen
Journal:  Neurogenetics       Date:  2020-02-19       Impact factor: 2.660

4.  Classifying human promoters by occupancy patterns identifies recurring sequence elements, combinatorial binding, and spatial interactions.

Authors:  Xinyi Yang; Martin Vingron
Journal:  BMC Biol       Date:  2018-11-15       Impact factor: 7.431

5.  A comparison of peak callers used for DNase-Seq data.

Authors:  Hashem Koohy; Thomas A Down; Mikhail Spivakov; Tim Hubbard
Journal:  PLoS One       Date:  2014-05-08       Impact factor: 3.240

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.