AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Big Data Mining and Analytics Article
PDF (2.2 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation

Qiaozhen Meng1, Yinuo Lyu2, Xiaoqing Peng3, Junhai Xu1( ), Jijun Tang4( ), Fei Guo5( )
School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin 300350, China
Aeronautical Information Service Center of the Civil Aviation Administration of China (AISC.ATMB.CAAC), Beijing 100015, China
Center for Medical Genetics & Hunan Key Laboratory of Medical Genetics, School of Life Sciences, Central South University, Changsha 410038, China
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, China
School of Computer Science and Engineering, Central South University, Changsha 410083, China
Show Author Information

Abstract

Prediction of enhancer-promoter interactions (EPIs) is key to regulating gene expression and diagnosing genetic diseases. Due to limited resolution, biological experiments perform not as well as expected while precisely identifying specific interactions, giving rise to computational biology approaches. Many EPI predictors have been developed, but their prediction accuracy still needs to be enhanced. Here, we design a new model named EPIMR to identify enhancer-promoter interactions. First, Hilbert Curve is utilized to represent sequences to images to preserve the position and spatial information. Second, a multi-scale residual neural network (ResNet) is used to learn the distinguishing features of different abstraction levels. Finally, matching heuristics are adopted to concatenate the learned features of enhancers and promoters, which pays attention to their potential interaction information. Experimental results on six cell lines indicate that EPIMR performs better than existing methods, with higher area under the precision-recall curve (AUPR) and area under the receiver operating characteristic (AUROC) results on benchmark and under-sampling datasets. Furthermore, our model is pre-trained on all cell lines, which improves not only the transferability of cross-cell line prediction, but also cell line-specific prediction ability. In conclusion, our method serves as a valuable technical tool for predicting enhancer-promoter interactions, contributing to the understanding of gene transcription mechanisms. Our code and results are available at https://github.com/guofei-tju/EPIMR.

Keywords

Hilbert Curveenhancer-promoter interactionsmulti-scale residual neural network (ResNet)

References

[1]

Y. Lyu, Z. Zhang, J. Li, W. He, Y. Ding, and F. Guo, iEnhancer-KL: A novel two-layer predictor for identifying enhancers by position specific of nucleotide composition, IEEE/ACM Trans. Comput. Biol. Bioinform., vol. 18, no. 6, pp. 2809–2815, 2021.
Crossref Google Scholar
[2]

Y. Lyu, W. He, S. Li, Q. Zou, and F. Guo, iPro2L-PSTKNC: A two-layer predictor for discovering various types of promoters by position specific of nucleotide composition, IEEE J. Biomed. Health Inform., vol. 25, no. 6, pp. 2329–2337, 2021.
Crossref Google Scholar
[3]
J. Jin, Y. Yu, R. Wang, X. Zeng, C. Pang, Y. Jiang, Z. Li, Y. Dai, R. Su, Q. Zou, et al., iDNA-ABF: Multi-scale deep biological language learning model for the interpretable prediction of DNA methylations, Genome Biol., vol. 23, no. 1, p. 219, 2022.
Crossref
[4]

K. Monfils and T. S. Barakat, Models behind the mystery of establishing enhancer-promoter interactions, Eur. J. Cell Biol., vol. 100, nos. 5&6, p. 151170, 2021.
Crossref Google Scholar
[5]

D. T. Bergman, T. R. Jones, V. Liu, J. Ray, E. Jagoda, L. Siraj, H. Y. Kang, J. Nasser, M. Kane, A. Rios, et al., Compatibility rules of human enhancer and promoter sequences, Nature, vol. 607, no. 7917, pp. 176–184, 2022.
Crossref Google Scholar
[6]

L. Liu, L. R. Zhang, F. Y. Dao, Y. C. Yang, and H. Lin, A computational framework for identifying the transcription factors involved in enhancer-promoter loop formation, Mol. Ther. Nucleic Acids, vol. 23, pp. 347–354, 2020.
Crossref Google Scholar
[7]

H. Lv, F. Y. Dao, H. Zulfiqar, W. Su, H. Ding, L. Liu, and H. Lin, A sequence-based deep learning approach to predict CTCF-mediated chromatin loop, Brief. Bioinform., vol. 22, no. 5, p. bbab031, 2021.
Crossref Google Scholar
[8]

O. Kyrchanova and P. Georgiev, Mechanisms of enhancer-promoter interactions in higher eukaryotes, Int. J. Mol. Sci., vol. 22, no. 2, p. 671, 2021.
Crossref Google Scholar
[9]

N. V. N. Carullo and J. J. Day, Genomic enhancers in brain health and disease, Genes, vol. 10, no. 1, p. 43, 2019.
Crossref Google Scholar
[10]

K. Hamamoto and T. Fukaya, Molecular architecture of enhancer-promoter interaction, Curr. Opin. Cell Biol., vol. 74, pp. 62–70, 2022.
Crossref Google Scholar
[11]
C. Cao, J. Wang, D. Kwok, F. Cui, Z. Zhang, D. Zhao, M. J. Li, and Q. Zou, webTWAS: A resource for disease candidate susceptibility genes identified by transcriptome-wide association study, Nucleic Acids Res., vol. 50, no. D1, pp. D1123–D1130, 2022.
Crossref
[12]

L. Yu, K. Yang, X. He, M. Li, L. Gao, and Y. Zha, Repositioning linifanib as a potent anti-necroptosis agent for sepsis, Cell Death Discov., vol. 9, no. 1, p. 57, 2023.
Crossref Google Scholar
[13]
W. He, J. Tang, Q. Zou, and F. Guo, MMFGRN: A multi-source multi-model fusion method for gene regulatory network reconstruction, Brief. Bioinform., vol. 22, no. 6, p. bbab166, 2021.
Crossref
[14]

M. Zhao, W. He, J. Tang, Q. Zou, and F. Guo, A comprehensive overview and critical evaluation of gene regulatory network inference technologies, Brief. Bioinform., vol. 22, no. 5, p. bbab009, 2021.
Crossref Google Scholar
[15]

M. Zhao, W. He, J. Tang, Q. Zou, and F. Guo, A hybrid deep learning framework for gene regulatory network inference from single-cell transcriptomic data, Brief. Bioinform., vol. 23, no. 2, p. bbab568, 2022.
Crossref Google Scholar
[16]

J. Wang, Y. Chen, and Q. Zou, Inferring gene regulatory network from single-cell transcriptomes with graph autoencoder model, PLoS Genet., vol. 19, no. 9, p. e1010942, 2023.
Crossref Google Scholar
[17]
T. Borggrefe and B. D. Giaimo, Enhancers and Promoters. New York, NY, USA: Humana, 2021.
Crossref
[18]

R. Wang, Y. Jiang, J. Jin, C. Yin, H. Yu, F. Wang, J. Feng, R. Su, K. Nakai, Q. Zou, et al., DeepBIO: An automated and interpretable deep-learning platform for high-throughput biological sequence prediction, functional annotation and visualization analysis, Nucleic Acids Res., vol. 51, no. 7, pp. 3017–3029, 2023.
Crossref Google Scholar
[19]

B. M. Javierre, O. S. Burren, S. P. Wilder, R. Kreuzhuber, S. M. Hill, S. Sewitz, J. Cairns, S. W. Wingett, C. Várnai, M. J. Thiecke, et al., Lineage-specific genome architecture links enhancers and non-coding disease variants to target gene promoters, Cell, vol. 167, no. 5, pp. 1369–1384, 2016.
Crossref Google Scholar
[20]

E. E. M. Furlong and M. Levine, Developmental enhancers and chromosome topology, Science, vol. 361, no. 6409, pp. 1341–1345, 2018.
Crossref Google Scholar
[21]

M. Osterwalder, I. Barozzi, V. Tissières, Y. Fukuda-Yuzawa, B. J. Mannion, S. Y. Afzal, E. A. Lee, Y. Zhu, I. Plajzer-Frick, C. S. Pickle, et al., Enhancer redundancy provides phenotypic robustness in mammalian development, Nature, vol. 554, no. 7691, pp. 239–243, 2018.
Crossref Google Scholar
[22]

F. Jing, S. W. Zhang, and S. Zhang, Prediction of enhancer-promoter interactions using the cross-cell type information and domain adversarial neural network, BMC Bioinformatics, vol. 21, no. 1, p. 507, 2020.
Crossref Google Scholar
[23]

H. Ray-Jones and M. Spivakov, Transcriptional enhancers and their communication with gene promoters, Cell. Mol. Life Sci., vol. 78, nos. 19&20, pp. 6453–6485, 2021.
Crossref Google Scholar
[24]
S. S. Rao, M. H. Huntley, N. C. Durand, E. K. Stamenova, I. D. Bochkov, J. T. Robinson, A. L. Sanborn, I. Machol, A. D. Omer, E. S. Lander, et al., A 3D map of the human genome at kilobase resolution reveals principles of chromatin looping, Cell, vol. 159, no. 7, pp. 1665–1680, 2014.
Crossref
[25]

J. Dekker, K. Rippe, M. Dekker, and N. Kleckner, Capturing chromosome conformation, Science, vol. 295, no. 5558, pp. 1306–1311, 2002.
Crossref Google Scholar
[26]

J. Dostie, T. A. Richmond, R. A. Arnaout, R. R. Selzer, W. L. Lee, T. A. Honan, E. D. Rubio, A. Krumm, J. Lamb, C. Nusbaum, et al., Chromosome Conformation Capture Carbon Copy (5C): A massively parallel solution for mapping interactions between genomic elements, Genome Res., vol. 16, no. 10, pp. 1299–1309, 2006.
Crossref Google Scholar
[27]

E. Lieberman-Aiden, N. L. van Berkum, L. Williams, M. Imakaev, T. Ragoczy, A. Telling, I. Amit, B. R. Lajoie, P. J. Sabo, M. O. Dorschner, et al., Comprehensive mapping of long-range interactions reveals folding principles of the human genome, Science, vol. 326, no. 5950, pp. 289–293, 2009.
Crossref Google Scholar
[28]

M. Simonis, P. Klous, E. Splinter, Y. Moshkin, R. Willemsen, E. de Wit, B. van Steensel, and W. de Laat, Nuclear organization of active and inactive chromatin domains uncovered by chromosome conformation capture–on-chip (4C), Nat. Genet., vol. 38, pp. 1348–1354, 2006.
Crossref Google Scholar
[29]

L. Lu, X. Liu, W. K. Huang, P. Giusti-Rodríguez, J. Cui, S. Zhang, W. Xu, Z. Wen, S. Ma, J. D. Rosen, et al., Robust Hi-C maps of enhancer-promoter interactions reveal the function of non-coding genome in neural development and diseases, Mol. Cell, vol. 79, no. 3, pp. 521–534, 2020.
Crossref Google Scholar
[30]

J. C. Birkhoff, R. W. W. Brouwer, P. Kolovos, A. L. Korporaal, A. Bermejo-Santos, I. Boltsis, K. Nowosad, M. C. G. N. van den Hout, F. G. Grosveld, W. F. J. van IJcken, et al., Targeted chromatin conformation analysis identifies novel distal neural enhancers of ZEB2 in pluripotent stem cell differentiation, Hum. Mol. Genet., vol. 29, no. 15, pp. 2535–2550, 2020.
Crossref Google Scholar
[31]

B. Mifsud, F. Tavares-Cadete, A. N. Young, R. Sugar, S. Schoenfelder, L. Ferreira, S. W. Wingett, S. Andrews, W. Grey, P. A. Ewels, et al., Mapping long-range promoter contacts in human cells with high-resolution capture Hi-C, Nat. Genet., vol. 47, no. 6, pp. 598–606, 2015.
Crossref Google Scholar
[32]

Y. B. Zouari, A. M. Molitor, N. Sikorska, V. Pancaldi, and T. Sexton, ChiCMaxima: A robust and simple pipeline for detection and visualization of chromatin looping in Capture Hi-C, Genome Biol., vol. 20, no. 1, p. 102, 2019.
Crossref Google Scholar
[33]

M. J. Fullwood, M. H. Liu, Y. F. Pan, J. Liu, H. Xu, Y. Bin Mohamed, Y. L. Orlov, S. Velkov, A. Ho, P. H. Mei, et al., An oestrogen-receptor-α-bound human chromatin interactome, Nature, vol. 462, no. 7269, pp. 58–64, 2009.
Crossref Google Scholar
[34]

M. R. Mumbach, A. J. Rubin, R. A. Flynn, C. Dai, P. A. Khavari, W. J. Greenleaf, and H. Y. Chang, HiChIP: Efficient and sensitive analysis of protein-directed genome architecture, Nat. Meth., vol. 13, no. 11, pp. 919–922, 2016.
Crossref Google Scholar
[35]

S. Roy, A. F. Siahpirani, D. Chasman, S. Knaack, F. Ay, R. Stewart, M. Wilson, and R. Sridharan, A predictive modeling approach for cell line-specific long-range regulatory interactions, Nucleic Acids Res., vol. 43, no. 18, pp. 8694–8712, 2015.
Crossref Google Scholar
[36]

S. Whalen, R. M. Truty, and K. S. Pollard, Enhancer-promoter interactions are encoded by complex genomic signatures on looping chromatin, Nat. Genet., vol. 48, no. 5, pp. 488–496, 2016.
Crossref Google Scholar
[37]

S. Singh, Y. Yang, B. Póczos, and J. Ma, Predicting enhancer-promoter interaction from genomic sequence with deep neural networks, Quant. Biol., vol. 7, no. 2, pp. 122–137, 2019.
Crossref Google Scholar
[38]

Z. Zhuang, X. Shen, and W. Pan, A simple convolutional neural network for prediction of enhancer–promoter interactions with DNA sequence data, Bioinformatics, vol. 35, no. 17, pp. 2899–2906, 2019.
Crossref Google Scholar
[39]
W. Mao, D. Kostka, and M. Chikina, Modeling enhancer-promoter interactions with attention-based neural networks, https://www.biorxiv.org/content/10.1101/219667v1, 2017.
Crossref
[40]

W. Zeng, M. Wu, and R. Jiang, Prediction of enhancer-promoter interactions via natural language processing, BMC Genomics, vol. 19, no. Suppl2, p. 84, 2018.
Crossref Google Scholar
[41]

Y. Yang, R. Zhang, S. Singh, and J. Ma, Exploiting sequence-based features for predicting enhancer-promoter interactions, Bioinformatics, vol. 33, no. 14, pp. i252–i260, 2017.
Crossref Google Scholar
[42]

Z. Hong, X. Zeng, L. Wei, and X. Liu, Identifying enhancer-promoter interactions with neural network based on pre-trained DNA vectors and attention mechanism, Bioinformatics, vol. 36, no. 4, pp. 1037–1043, 2020.
Crossref Google Scholar
[43]

X. Min, C. Ye, X. Liu, and X. Zeng, Predicting enhancer-promoter interactions by deep learning and matching heuristic, Brief. Bioinform., vol. 22, no. 4, p. bbaa254, 2021.
Crossref Google Scholar
[44]
S. Liu, X. Xu, Z. Yang, X. Zhao, S. Liu, and W. Zhang, EPIHC: Improving enhancer-promoter interaction prediction by using hybrid features and communicative learning, IEEE/ACM Trans. Comput. Biol. Bioinform., vol. 19, no. 6, pp. 3435–3443, 2022.
Crossref
[45]
Z. Wang, L. Zhou, S. Jiang, and W. Huang, EPnet: A general network to predict enhancer-promoter interactions, in Proc. 11th Int. Conf. Information Science and Technology (ICIST), Chengdu, China, 2021, pp. 119–124.
Crossref
[46]
P. Ng, dna2vec: Consistent vector representations of variable-length k-mers, arXiv preprint arXiv: 1701.06279, 2017.
[47]
M. Zhang, Y. Hu, and M. Zhu, EPIsHilbert: Prediction of enhancer-promoter interactions via Hilbert Curve encoding and transfer learning, Genes, vol. 12, no. 9, p. 1385, 2021.
Crossref
[48]
B. Yin, M. Balvert, D. Zambrano, A. Schönhuth, and S. Bohte, An image representation based convolutional network for DNA classification, arXiv preprint arXiv: 1806.04931, 2018.
[49]

ENCODE Project Consortium, An integrated encyclopedia of DNA elements in the human genome, Nature, vol. 489, no. 7414, pp. 57–74, 2012.
Crossref Google Scholar
[50]

Roadmap Epigenomics Consortium, A. Kundaje, W. Meuleman, J. Ernst, M. Bilenky, A. Yen, A. Heravi-Moussavi, P. Kheradpour, Z. Zhang, J. Wang, et al., Integrative analysis of 111 reference human epigenomes, Nature, vol. 518, no. 7539, pp. 317–330, 2015.
Crossref Google Scholar
[51]

A. Krizhevsky, I. Sutskever, and G. E. Hinton, Imagenet classification with deep convolutional neural networks, Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017.
Crossref Google Scholar
[52]
M. D. Zeiler and R. Fergus, Visualizing and understanding convolutional networks, in Computer Vision—ECCV 2014, D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, eds. Cham, Switzerland: Springer International Publishing, 2014, pp. 818–833.
Crossref
[53]

H. L. Li, Y. H. Pang, and B. Liu, BioSeq-BLM: A platform for analyzing DNA, RNA and protein sequences based on biological language models, Nucleic Acids Res., vol. 49, no. 22, p. e129, 2021.
Crossref Google Scholar
[54]
K. Yan, H. Lv, Y. Guo, W. Peng, and B. Liu, sAMPpred-GAT: Prediction of antimicrobial peptide by graph attention network and predicted peptide structure, Bioinformatics, vol. 39, no. 1, p. btac715, 2023.
Crossref
[55]
Y. J. Tang, Y. H. Pang, and B. Liu, IDP-Seq2Seq: Identification of intrinsically disordered regions based on sequence to sequence learning, Bioinformatics, vol. 36, no. 21, pp. 5177–5186, 2021.
Crossref
[56]
K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770–778.
Crossref
[57]
L. Liu, Z. Qiu, G. Li, S. Liu, W. Ouyang, and L. Lin, Crowd counting with deep structured scale integration network, in Proc. IEEE/CVF Int. Conf. Computer Vision (ICCV), Seoul, Republic of Korea, 2019, pp. 1774–1783.
Crossref
[58]

Z. Deng, H. Sun, S. Zhou, J. Zhao, L. Lei, and H. Zou, Multi-scale object detection in remote sensing imagery with convolutional neural networks, ISPRS J. Photogramm. Remote. Sens., vol. 145, pp. 3–22, 2018.
Crossref Google Scholar
[59]
E. Rumetshofer, M. Hofmarcher, C. Röhrl, S. Hochreiter, and G. Klambauer, Human-level protein localization with convolutional neural networks, presented at the Int. Conf. Learn. Represent. (ICLR), Vancouver, Canada, 2018.
[60]
Y. Liu, C. Sun, L. Lin, and X. Wang, Learning natural language inference using bidirectional LSTM model and inner-attention, arXiv preprint arXiv: 1605.09090, 2016.
[61]
L. Mou, R. Men, G. Li, Y. Xu, L. Zhang, R. Yan, and Z. Jin, Natural language inference by tree-based convolution and heuristic matching, arXiv preprint arXiv: 1512.08422, 2015.
Crossref
[62]
Y. Nie and M. Bansal, Shortcut-stacked sentence encoders for multi-domain inference, arXiv preprint arXiv: 1708.02312, 2017.
Crossref
[63]
C. Ao, X. Ye, T. Sakurai, Q. Zou, and L. Yu, m5U-SVM: Identification of RNA 5-methyluridine modification sites based on multi-view features of physicochemical features and distributed representation, BMC Biol., vol. 21, no. 1, p. 93, 2023.
Crossref
[64]

H. Li and B. Liu, BioSeq-Diabolo: Biological sequence similarity analysis using Diabolo, PLoS Comput. Biol., vol. 19, no. 6, p. e1011214, 2023.
Crossref Google Scholar
[65]

X. Zeng, F. Wang, Y. Luo, S. G. Kang, J. Tang, F. C. Lightstone, E. F. Fang, W. Cornell, R. Nussinov, and F. Cheng, Deep generative molecular design reshapes drug discovery, Cell Rep. Med., vol. 3, no. 12, p. 100794, 2022.
Crossref Google Scholar
[66]
J. Davis and M. Goadrich, The relationship between Precision-Recall and ROC curves, in Proc. 23rd Int. Conf. Machine learning, Pittsburgh, PA, USA, 2006, pp. 233–240.
Crossref
[67]

J. A. Hanley and B. J. McNeil, The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology, vol. 143, no. 1, pp. 29–36, 1982.
Crossref Google Scholar
[68]

F. Cao and M. J. Fullwood, Inflated performance measures in enhancer-promoter interaction-prediction methods, Nat. Genet., vol. 51, no. 8, pp. 1196–1198, 2019.
Crossref Google Scholar
[69]

S. Whalen and K. S. Pollard, Reply to ‘Inflated performance measures in enhancer-promoter interaction-prediction methods’, Nat. Genet., vol. 51, no. 8, pp. 1198–1200, 2019.
Crossref Google Scholar
[70]
L. McInnes, J. Healy, and J. Melville, UMAP: Uniform manifold approximation and projection for dimension reduction, arXiv preprint arXiv: 1802.03426, 2018.
Crossref
Big Data Mining and Analytics
Volume 7 Issue 3,
September 2024
Pages 668-681
DOI: 10.26599/BDMA.2024.9020018
Cite this article:
Meng Q, Lyu Y, Peng X, et al. EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation. Big Data Mining and Analytics, 2024, 7(3): 668-681. https://doi.org/10.26599/BDMA.2024.9020018

107

Views

11

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 28 December 2023
Revised: 01 February 2024
Accepted: 18 March 2024
Published: 28 August 2024
© The author(s) 2024.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Return