Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Trimetazidine attenuates high-altitude fatigue and cardiorespiratory fitness impairment: A randomized double-blinded placebo-controlled clinical trial.

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapieĀ·2019
Same author

TNF-Ī±-induced Tim-3 expression marks the dysfunction of infiltrating natural killer cells in human esophageal cancer.

Journal of translational medicineĀ·2019
Same author

First Community-Wide, Comparative Cross-Linking Mass Spectrometry Study.

Analytical chemistryĀ·2019
Same author

In vivo assembly and trafficking of olfactory Ionotropic Receptors.

BMC biologyĀ·2019
Same author

Plinabulin, an inhibitor of tubulin polymerization, targets KRAS signaling through disruption of endosomal recycling.

Biomedical reportsĀ·2019
Same author

PACS2 is required for ox-LDL-induced endothelial cell apoptosis by regulating mitochondria-associated ER membrane formation and mitochondrial Ca<sup>2+</sup> elevation.

Experimental cell researchĀ·2019

Related Experiment Video

Updated: Jun 28, 2025

Identifying Transcription Factor Olig2 Genomic Binding Sites in Acutely Purified PDGFR&#945;+ Cells by Low-cell Chromatin Immunoprecipitation Sequencing Analysis
12:29

Identifying Transcription Factor Olig2 Genomic Binding Sites in Acutely Purified PDGFRα+ Cells by Low-cell Chromatin Immunoprecipitation Sequencing Analysis

Published on: April 16, 2018

9.3K

MMGAT: a graph attention network framework for ATAC-seq motifs finding.

Xiaotian Wu1,2, Wenju Hou1, Ziqi Zhao1

  • 1Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun, 130012, China.

BMC Bioinformatics
|April 20, 2024
PubMed
Summary

This study introduces MMGAT, a novel graph attention network for identifying transcription factor binding sites in ATAC-seq data. MMGAT accurately finds multiple motifs of varying lengths, outperforming existing tools on human and mouse datasets.

Keywords:
ATAC-seqCoexisting probabilitiesGraph attention networkMotif findingTFBSs prediction

More Related Videos

ATAC-seq Assay with Low Mitochondrial DNA Contamination from Primary Human CD4+ T Lymphocytes
08:36

ATAC-seq Assay with Low Mitochondrial DNA Contamination from Primary Human CD4+ T Lymphocytes

Published on: March 22, 2019

12.7K
ATAC-Seq Optimization for Cancer Epigenetics Research
07:13

ATAC-Seq Optimization for Cancer Epigenetics Research

Published on: June 30, 2022

4.3K

Related Experiment Videos

Last Updated: Jun 28, 2025

Identifying Transcription Factor Olig2 Genomic Binding Sites in Acutely Purified PDGFR&#945;+ Cells by Low-cell Chromatin Immunoprecipitation Sequencing Analysis
12:29

Identifying Transcription Factor Olig2 Genomic Binding Sites in Acutely Purified PDGFRα+ Cells by Low-cell Chromatin Immunoprecipitation Sequencing Analysis

Published on: April 16, 2018

9.3K
ATAC-seq Assay with Low Mitochondrial DNA Contamination from Primary Human CD4+ T Lymphocytes
08:36

ATAC-seq Assay with Low Mitochondrial DNA Contamination from Primary Human CD4+ T Lymphocytes

Published on: March 22, 2019

12.7K
ATAC-Seq Optimization for Cancer Epigenetics Research
07:13

ATAC-Seq Optimization for Cancer Epigenetics Research

Published on: June 30, 2022

4.3K

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Motif finding in Assay for Transposase-Accessible Chromatin using sequencing (ATAC-seq) data is crucial for understanding gene regulation.
  • Current deep learning methods like CNNs and GNNs have limitations in identifying ATAC-seq motifs of varying lengths and efficiently aggregating node information.

Purpose of the Study:

  • To develop an advanced deep learning framework for accurate ATAC-seq motif discovery.
  • To overcome limitations of existing CNN and GNN approaches in motif finding.

Main Methods:

  • Developed MMGAT, a novel graph attention network framework utilizing an attention mechanism.
  • MMGAT leverages attention coefficients of sequence and k-mer nodes, along with k-mer co-occurrence probabilities.
  • A user-friendly web server, MMGAT-S, was created to host the method and results.

Main Results:

  • MMGAT demonstrated superior performance on human ATAC-seq datasets, achieving top scores in precision, recall, F1_score, ACC, AUC, and PRC.
  • Identified 389 higher-quality motifs in human datasets and 356 in mouse datasets.
  • Achieved highest scores on six metrics for mouse ATAC-seq data, confirming multi-species validation.

Conclusions:

  • MMGAT offers a robust tool for ATAC-seq motif identification, significantly advancing genomics research.
  • The MMGAT-S web server enhances accessibility for researchers.
  • Open-source code and the web server are available for public use.