DeepRCI: predicting RNA-chromatin interactions via deep learning with multi-omics data

Abstract

Background: Chromatin-associated RNA (caRNA) acts as a ubiquitous epigenetic layer in eukaryotes, and has been reported to be essential in various biological processes, including gene transcription, chromatin remodeling and cellular differentiation. Recently, numerous experimental techniques have been developed to characterize genome-wide RNA-chromatin interactions to understand their underlying biological functions. However, these experimental methods are generally expensive, time-consuming, and limited in identifying all potential sites, while most of the existing computational methods are restricted to detecting only specific types of RNAs interacting with chromatin.

Methods: Here, we propose a highly interpretable computational framework, named DeepRCI, to identify the interactions between various types of RNAs and chromatin. In this framework, we introduce a novel deep learning component called variformer and integrate multi-omics data to capture intrinsic genomic features at both RNA and DNA levels.

Results: Extensive experiments demonstrate that DeepRCI can detect RNA-chromatin interactions more accurately when compared to the state-of-the-art baseline prediction methods. Furthermore, the sequence features extracted by DeepRCI can be well matched to known critical gene regulatory components, indicating that our model can provide useful biological insights into understanding the underlying mechanisms of RNA-chromatin interactions. In addition, based on the prediction results, we further delineate the relationships between RNA-chromatin interactions and cellular functions, including gene expression and the modulation of cell states.

Conclusions: In summary, DeepRCI can serve as a useful tool for characterizing RNA-chromatin interactions and studying the underlying gene regulatory code.

Author summary

Chromatin-associated RNA (caRNA) acts as a ubiquitous epigenetic layer in eukaryotes, and has been reported to be essential in various biological processes. Here, we propose a highly interpretable computational framework, named DeepRCI, to identify the interactions between various types of RNAs and chromatin. DeepRCI can serve as a useful tool for characterizing RNA-chromatin interactions and studying the underlying gene regulatory code.

Graphical abstract

Keywords

deep learning / multi-omics data / RNA-chromatin

References

[1] Bell,J. C., Jukam,D., Teran,N. A., Risca,V. I., Smith,O. K., Johnson,W. L., Skotheim,J. M., Greenleaf,W. J. Straight,A. (2018). Chromatin-associated RNA sequencing (ChAR-seq) maps genome-wide RNA-to-DNA contacts. eLife, 7: e27024

[2] Calandrelli,R., Xu,L., Luo,Y., Wu,W., Fan,X., Nguyen,T., Chen,C. Sriram,K., Tang,X., Burns,A. B. . (2020). Stress-induced RNA-chromatin interactions promote endothelial dysfunction. Nat. Commun., 11: 5211

[3] Li,X. Fu,X. (2019). Chromatin-associated RNAs as facilitators of functional genomic interactions. Nat. Rev. Genet., 20: 503–519

[4] Bonetti,A., Agostini,F., Suzuki,A. M., Hashimoto,K., Pascarella,G., Gimenez,J., Roos,L., Nash,A. J., Ghilotti,M., Cameron,C. J. F. . (2020). RADICL-seq identifies general and cell type-specific principles of genome-wide RNA-chromatin interactions. Nat. Commun., 11: 1018

[5] Antonov,I. Medvedeva,Y. (2018). Purine-rich low complexity regions are potential RNA binding hubs in the human genome. F1000 Res., 7: 76

[6] Kato,M. (2020). Genome-wide technologies to study RNA–chromatin interactions. Noncoding RNA, 6: 20

[7] Watanabe,T., Tomizawa,S., Mitsuya,K., Totoki,Y., Yamamoto,Y., Kuramochi-Miyagawa,S., Iida,N., Hoki,Y., Murphy,P. J., Toyoda,A. . (2011). Role for piRNAs and noncoding RNA in de novo DNA methylation of the imprinted mouse Rasgrf1 locus. Science, 332: 848–852

[8] Miao,Y., Ajami,N. E., Huang,T. Lin,F. Lou,C. Wang,Y. Li,S., Kang,J., Munkacsi,H., Maurya,M. R. . (2018). Enhancer-associated long non-coding RNA LEENE regulates endothelial nitric oxide synthase and endothelial function. Nat. Commun., 9: 292

[9] Rinn,M. Kertesz,J. K. Wang,S. L. Squazzo,X. Xu,S. A. Brugmann,L. H. Goodnough,J. A. Helms,P. J. Farnham,E. . (2007). Functional demarcation of active and silent chromatin domains in human HOX loci by noncoding RNAs. Cell, 129: 1311–1323

[10] Kalwa,M., nzelmann,S., Otto,S., Kuo,C. Franzen,J., Joussen,S., Fernandez-Rebollo,E., Rath,B., Koch,C., Hofmann,A. . (2016). The lncRNA HOTAIR impacts on mesenchymal stem cells via triple helix formation. Nucleic Acids Res., 44: 10631–10643

[11] Wang,S., Ke,H., Zhang,H., Ma,Y., Ao,L., Zou,L., Yang,Q., Zhu,H., Nie,J., Wu,C. . (2018). LncRNA MIR100HG promotes cell proliferation in triple-negative breast cancer through triplex formation with p27 loci. Cell Death Dis., 9: 805

[12] Leary,V. B., Ovsepian,S. V., Carrascosa,L. G., Buske,F. A., Radulovic,V., Niyazi,M., Moertl,S., Trau,M., Atkinson,M. J. (2015). Particle, a triplex-forming long ncRNA, regulates locus-specific methylation in response to low-dose irradiation. Cell Rep., 11: 474–485

[13] Simon,M. (2013). Capture hybridization analysis of RNA targets (CHART). Curr. Protoc. Mol. Biol., 101: 21–25

[14] ChuC.Chang H.. (2016) Understanding RNA-chromatin interactions using chromatin isolation by RNA purification (chirp). In: Polycomb Group Proteins, pp. 115–123. New York: Springer

[15] EngreitzJ.,Lander E. S.. (2015) RNA antisense purification (rap) for mapping RNA interactions with chromatin. In: Nuclear Bodies and Noncoding RNAs, pp. 183–197. New York: Springer

[16] Wu,W., Yan,Z., Nguyen,T. C., Bouman Chen,Z., Chien,S. (2019). Mapping RNA-chromatin interactions by sequencing with iMARGI. Nat. Protoc., 14: 3243–3272

[17] Sridhar,B., Rivas-Astroza,M., Nguyen,T. C., Chen,W., Yan,Z., Cao,X., Hebert,L. (2017). Systematic mapping of RNA-chromatin interactions in vivo. Curr. Biol., 27: 602–609

[18] Zhou,B., Li,X., Luo,D., Lim,D. Zhou,Y. Fu,X. (2019). GRID-seq for comprehensive analysis of global RNA-chromatin interactions. Nat. Protoc., 14: 2036–2068

[19] Kuo,C. nzelmann,S., rk Cetin,N., Frank,S., Zajzon,B., Derks,J. Akhade,V. S., Ahuja,G., Kanduri,C., Grummt,I. . (2019). Detection of RNA-DNA binding sites in long noncoding RNAs. Nucleic Acids Res., 47: e32

[20] Buske,F. A., Bauer,D. C., Mattick,J. S. Bailey,T. (2013). Triplex-inspector: an analysis tool for triplex-mediated targeting of genomic loci. Bioinformatics, 29: 1895–1897

[21] He,S., Zhang,H., Liu,H. (2015). LongTarget: a tool to predict lncRNA DNA-binding motifs and binding sites via Hoogsteen base-pairing analysis. Bioinformatics, 31: 178–186

[22] Zhang,Y., Long,Y. Kwoh,C. (2020). Deep learning based DNA: RNA triplex forming potential prediction. BMC Bioinformatics, 21: 522

[23] ller,A. T., Hiss,J. A. (2018). Recurrent neural network model for constructive peptide design. J. Chem. Inf. Model., 58: 472–479

[24] Sureyya Rifaioglu,A., an,T., Jesus Martin,M., Cetin-Atalay,R. (2019). Deepred: automated protein function prediction with multi-task feed-forward deep neural networks. Sci. Rep., 9: 1–16

[25] Zeng,Y., Chen,X., Luo,Y., Li,X. (2021). Deep drug-target binding affinity prediction with multiple attention blocks. Brief. Bioinform., 22: bbab117

[26] Lopez-Del Rio,A., Martin,M., Perera-Lluna,A. (2020). Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction. Sci. Rep., 10: 14634

[27] Schubert,T., Pusch,M. C., Diermeier,S., Benes,V., Kremmer,E., Imhof,A. (2012). Df31 protein and snoRNAs maintain accessible higher-order structures of chromatin. Mol. Cell, 48: 434–444

[28] Schubert,T. (2013). Changes in higher order structures of chromatin by RNP complexes. RNA Biol., 10: 175–179

[29] Sen,S., Cheng,Z., Sheu,K. M., Chen,Y. H. (2020). Gene regulatory strategies that decode the duration of NFκB dynamics contribute to LPS-versus TNF-specific gene expression. Cell Syst., 10: 169–182.e5

[30] LanchantinJ.,SinghR.,WangB.. (2017) Deep motif dashboard: visualizing and understanding genomic sequences using deep neural networks. In: Pacific Symposium on Biocomputing 2017, pp. 254–265. Singapore: World Scientific

[31] Kelley,D. R., Snoek,J. Rinn,J. (2016). Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome Res., 26: 990–999

[32] Lambert,S. A., Jolma,A., Campitelli,L. F., Das,P. K., Yin,Y., Albu,M., Chen,X., Taipale,J., Hughes,T. R. Weirauch,M. (2018). The human transcription factors. Cell, 172: 650–665

[33] Gupta,S., Stamatoyannopoulos,J. A., Bailey,T. L. Noble,W. (2007). Quantifying similarity between motifs. Genome Biol., 8: R24

[34] Zhao,X., Li,D., Pu,J., Mei,H., Yang,D., Xiang,X., Qu,H., Huang,K., Zheng,L. (2016). CTCF cooperates with noncoding RNA MYCNOS to promote neuroblastoma progression through facilitating MYCN expression. Oncogene, 35: 3565–3576

[35] Guttman,M. Rinn,J. (2012). Modular regulatory principles of large non-coding RNAs. Nature, 482: 339–346

[36] Wang,I. X., Grunseich,C., Fox,J., Burdick,J., Zhu,Z., Ravazian,N., Hafner,M. Cheung,V. (2018). Human proteins that interact with RNA/DNA hybrids. Genome Res., 28: 1405–1414

[37] Engreitz,J. M., Ollikainen,N. (2016). Long non-coding RNAs: spatial amplifiers that control nuclear structure and gene expression. Nat. Rev. Mol. Cell Biol., 17: 756–770

[38] Iyengar,B. R., Choudhary,A., Sarangdhar,M. A., Venkatesh,K. V., Gadgil,C. J. (2014). Non-coding RNA interact to regulate neuronal development and function. Front. Cell. Neurosci., 8: 47

[39] Li,L., Luo,H., Lim,D. Han,L., Li,Y., Fu,X. (2021). Global profiling of RNA-chromatin interactions reveals co-regulatory gene expression networks in Arabidopsis. Nat. Plants, 7: 1364–1378

[40] Chen,X., Sun,Y., Cai,R., Wang,G., Shu,X. (2018). Long noncoding RNA: multiple players in gene expression. BMB Rep., 51: 280–289

[41] Mishra,K. (2019). Understanding long noncoding RNA and chromatin interactions: what we know so far. Noncoding RNA, 5: 54

[42] Antonov,I. V., Mazurov,E., Borodovsky,M. Medvedeva,Y. (2019). Prediction of lncRNAs and their interactions with nucleic acids: benchmarking bioinformatics tools. Brief. Bioinform., 20: 551–564

[43] Quinodoz,S. A., Jachowicz,J. W., Bhat,P., Ollikainen,N., Banerjee,A. K., Goronzy,I. N., Blanco,M. R., Chovanec,P., Chow,A., Markaki,Y. . (2021). RNA promotes the formation of spatial compartments in the nucleus. Cell, 184: 5775–5790.e30

[44] Hu,M., Deng,K., Selvaraj,S., Qin,Z., Ren,B. Liu,J. (2012). HiCNorm: removing biases in Hi-C data via Poisson regression. Bioinformatics, 28: 3131–3133

[45] Fu,L., Niu,B., Zhu,Z., Wu,S. (2012). CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics, 28: 3150–3152

[46] RibeiroL. S. F.,BuiT.,Collomosse J.. (2020) Sketchformer: transformer-based representation for sketched structure. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14153–14162

[47] VaswaniA.,Shazeer N.,ParmarN.,UszkoreitJ.,JonesL., GomezA. N.,. (2017) Attention is all you need. In: Advances in neural information processing systems, pp. 5998–6008

[48] IoffeS.. (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp. 448–456

[49] Hu,H., Xiao,A., Zhang,S., Li,Y., Shi,X., Jiang,T., Zhang,L., Zhang,L. (2019). DeepHINT: understanding HIV-1 integration via deep learning with attention. Bioinformatics, 35: 1660–1667

[50] Almagro Armenteros,J. J., nderby,C. K., nderby,S. K., Nielsen,H. (2017). DeepLoc: prediction of protein subcellular localization using deep learning. Bioinformatics, 33: 3387–3395

AVAILABILITY

github website (mlcb-thu/DeepRCI).

SUPPLEMENTARY MATERIALS

The supplementary materials can be found online with this article at https://doi.org/10.15302/J-QB-022-0316.

ACKNOWLEDGEMENTS

The authors would like to thank BioRender for the creation of the Bayesian network shown in Fig.1. They thank Mr. Xingang Peng and Mr. Hantao Shu for the helpful discussions and suggestions on the manuscript. This work was supported in part by the National Natural Science Foundation of China (61872216, T2125007 to JZ, 31900862 to DZ), the National Key Research and Development Program of China (2018YFC0910404, 2021YFF1201300), the Turing AI Institute of Nanjing, the Tsinghua-Toyota Joint Research Fund and the US National Institute of Health grant (1R01NS125018).

COMPLIANCE WITH ETHICS GUIDELINES

The authors Yuanpeng Xiong, Xuan He, Dan Zhao, Tao Jiang, and Jianyang Zeng declare that they have no conflict of interest or financial conflicts to disclose.

This article does not contain any studies with human or animal materials performed by any of the authors

OPEN ACCESS

This article is licensed by the CC By under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

RIGHTS & PERMISSIONS

2023 The Author(s). Published by Higher Education Press.