GNNMF: a Multi-view Graph Neural Network for ATAC-seq Motif Finding

Overview

Journal BMC Genomics

Publisher Biomed Central

Specialty Genetics

Date 2024 Mar 22

PMID 38515040

Authors

Shuangquan Zhang

Xiaotian Wu

Zhichao Lian

Chunman Zuo

Yan Wang

Affiliations

Soon will be listed here.

Abstract

Background: The Assay for Transposase-Accessible Chromatin using sequencing (ATAC-seq) utilizes the Transposase Tn5 to probe open chromatic, which simultaneously reveals multiple transcription factor binding sites (TFBSs) compared to traditional technologies. Deep learning (DL) technology, including convolutional neural networks (CNNs), has successfully found motifs from ATAC-seq data. Due to the limitation of the width of convolutional kernels, the existing models only find motifs with fixed lengths. A Graph neural network (GNN) can work on non-Euclidean data, which has the potential to find ATAC-seq motifs with different lengths. However, the existing GNN models ignored the relationships among ATAC-seq sequences, and their parameter settings should be improved.

Results: In this study, we proposed a novel GNN model named GNNMF to find ATAC-seq motifs via GNN and background coexisting probability. Our experiment has been conducted on 200 human datasets and 80 mouse datasets, demonstrated that GNNMF has improved the area of eight metrics radar scores of 4.92% and 6.81% respectively, and found more motifs than did the existing models.

Conclusions: In this study, we developed a novel model named GNNMF for finding multiple ATAC-seq motifs. GNNMF built a multi-view heterogeneous graph by using ATAC-seq sequences, and utilized background coexisting probability and the iterloss to find different lengths of ATAC-seq motifs and optimize the parameter sets. Compared to existing models, GNNMF achieved the best performance on TFBS prediction and ATAC-seq motif finding, which demonstrates that our improvement is available for ATAC-seq motif finding.

References

Li Z, Schulz M, Look T, Begemann M, Zenke M, Costa I . Identification of transcription factor binding sites using ATAC-seq. Genome Biol. 2019; 20(1):45. PMC: 6391789. DOI: 10.1186/s13059-019-1642-2. View

Vishnoi K, Viswakarma N, Rana A, Rana B . Transcription Factors in Cancer Development and Therapy. Cancers (Basel). 2020; 12(8). PMC: 7464564. DOI: 10.3390/cancers12082296. View

Quang D, Xie X . FactorNet: A deep learning framework for predicting cell type specific transcription factor binding from nucleotide-resolution sequential data. Methods. 2019; 166:40-47. PMC: 6708499. DOI: 10.1016/j.ymeth.2019.03.020. View

Bajic M, Maher K, Deal R . Identification of Open Chromatin Regions in Plant Genomes Using ATAC-Seq. Methods Mol Biol. 2017; 1675:183-201. PMC: 5693289. DOI: 10.1007/978-1-4939-7318-7_12. View

Zhang S, Ma A, Zhao J, Xu D, Ma Q, Wang Y . Assessing deep learning methods in cis-regulatory motif finding based on genomic sequencing data. Brief Bioinform. 2021; 23(1). PMC: 8769700. DOI: 10.1093/bib/bbab374. View

Youn A, Marquez E, Lawlor N, Stitzel M, Ucar D . BiFET: sequencing Bias-free transcription factor Footprint Enrichment Test. Nucleic Acids Res. 2018; 47(2):e11. PMC: 6344870. DOI: 10.1093/nar/gky1117. View

Babu M, Teichmann S . Evolution of transcription factors and the gene regulatory network in Escherichia coli. Nucleic Acids Res. 2003; 31(4):1234-44. PMC: 150228. DOI: 10.1093/nar/gkg210. View

Zhang S, Yang L, Wu X, Sheng N, Fu Y, Ma A . MMGraph: a multiple motif predictor based on graph neural network and coexisting probability for ATAC-seq data. Bioinformatics. 2022; 38(19):4636-4638. PMC: 9524997. DOI: 10.1093/bioinformatics/btac572. View

Quinlan A, Hall I . BEDTools: a flexible suite of utilities for comparing genomic features. Bioinformatics. 2010; 26(6):841-2. PMC: 2832824. DOI: 10.1093/bioinformatics/btq033. View

10.

Nie Y, Shu C, Sun X . Cooperative binding of transcription factors in the human genome. Genomics. 2020; 112(5):3427-3434. DOI: 10.1016/j.ygeno.2020.06.029. View

11.

Wang Y, Zhang S, Yang L, Yang S, Tian Y, Ma Q . Measurement of Conditional Relatedness Between Genes Using Fully Convolutional Neural Network. Front Genet. 2019; 10:1009. PMC: 6818468. DOI: 10.3389/fgene.2019.01009. View

12.

Joaquin M, Watson R . Cell cycle regulation by the B-Myb transcription factor. Cell Mol Life Sci. 2003; 60(11):2389-401. PMC: 11138814. DOI: 10.1007/s00018-003-3037-4. View

13.

Ouyang N, Boyle A . TRACE: transcription factor footprinting using chromatin accessibility data and DNA sequence. Genome Res. 2020; 30(7):1040-1046. PMC: 7397869. DOI: 10.1101/gr.258228.119. View

14.

Sun Y, Miao N, Sun T . Detect accessible chromatin using ATAC-sequencing, from principle to applications. Hereditas. 2019; 156:29. PMC: 6696680. DOI: 10.1186/s41065-019-0105-9. View

15.

Fang R, Preissl S, Li Y, Hou X, Lucero J, Wang X . Comprehensive analysis of single cell ATAC-seq data with SnapATAC. Nat Commun. 2021; 12(1):1337. PMC: 7910485. DOI: 10.1038/s41467-021-21583-9. View

16.

Sinha S . On counting position weight matrix matches in a sequence, with application to discriminative motif finding. Bioinformatics. 2006; 22(14):e454-63. DOI: 10.1093/bioinformatics/btl227. View

17.

Alipanahi B, Delong A, Weirauch M, Frey B . Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat Biotechnol. 2015; 33(8):831-8. DOI: 10.1038/nbt.3300. View

18.

Ma S, Zhang Y . Profiling chromatin regulatory landscape: insights into the development of ChIP-seq and ATAC-seq. Mol Biomed. 2021; 1(1):9. PMC: 7546943. DOI: 10.1186/s43556-020-00009-w. View

19.

Fu L, Zhang L, Dollinger E, Peng Q, Nie Q, Xie X . Predicting transcription factor binding in single cells through deep learning. Sci Adv. 2020; 6(51). PMC: 11206197. DOI: 10.1126/sciadv.aba9031. View

20.

Mancini A, Vito L, Marcelli E, Piangerelli M, De Leone R, Pucciarelli S . Machine learning models predicting multidrug resistant urinary tract infections using "DsaaS". BMC Bioinformatics. 2020; 21(Suppl 10):347. PMC: 7446147. DOI: 10.1186/s12859-020-03566-7. View