Prediction of enhancer-promoter interactions via natural language processing
Open accessAbstract
BACKGROUND: Precise identification of three-dimensional genome organization, especially enhancer-promoter interactions (EPIs), is important to deciphering gene regulation, cell differentiation and disease mechanisms. Currently, it is a challenging task to distinguish true interactions from other nearby non-interacting ones since the power of traditional experimental methods is limited due to low resolution or low throughput. RESULTS: We propose a novel computational framework EP2vec to assay three-dimensional genomic interactions. We first extract sequence embedding features, defined as fixed-length vector representations learned from variable-length sequences using an unsupervised deep learning method in natural language processing. Then, we train a classifier to predict EPIs using the learned representations in supervised way. Experimental results demonstrate that EP2vec obtains F1 scores ranging from 0.841~ 0.933 on different datasets, which outperforms existing methods. We prove the robustness of sequence embedding features by carrying out sensitivity analysis. Besides, we identify motifs that represent cell line-specific information through analysis of the learned sequence embedding features by adopting attention mechanism. Last, we show that even superior performance with F1 scores 0.889~ 0.940 can be achieved by combining sequence embedding features and experimental features. CONCLUSIONS: EP2vec sheds light on feature extraction for DNA sequences of arbitrary lengths and provides a powerful approach for EPIs identification.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Machine learning strategies to predict enhancer-gene links on the basis of 1D and 3D biochemical annotations are already advancing beyond the simple 'nearest gene' approach.
“For example, machine learning strategies to predict enhancer–gene links on the basis of 1D and 3D biochemical annotations are already advancing beyond the simple ‘nearest gene’ approach134,209,222.”
From Towards a comprehensive catalogue of validated and target-linked human enhancers (2020) · cites this paper as [222]
The Background describes computational methods that use 1D chromatin-state data to predict 3D enhancer–promoter interactions, and the Methods > Datasets section studies distal interactions rather than assigning enhancers to the nearest promoter. But the paper does not establish that its own model uses both 1D and 3D biochemical annotations as predictors: it describes its model as sequence-based and uses Hi-C data to label interactions. No page numbers are available in our copy. (LLM, conf=0.83)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892 · cited 1× · see citing works
“The N sentence vectors and 4 k word vectors were trained using stochastic gradient descent (SGD) together with the softmax parameters U and b , where the gradient was obtained via back propagation [33].”
MethodSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1× · see citing works
“Paragraph Vector [22] successfully solves the problem by mapping texts into a unified vector representation, and generates embedding representation which can be further used for different applications [23], such as machine translation [24], sentiment analysis [22], and information retrieval [25].”
BackgroundAdvances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653 · see citing works
Distributed Representations of Sentences and DocumentsPreprint
Le, Q. V., & Mikolov, T. (2014) · International Conference on Machine Learning · doi:10.48550/arxiv.1405.4053 · Cited by 10,307 · cited 1× · see citing works
“Paragraph Vector [22] successfully solves the problem by mapping texts into a unified vector representation, and generates embedding representation which can be further used for different applications [23], such as machine translation [24], sentiment analysis [22], and information retrieval [25].”
BackgroundA 3D Map of the Human Genome at Kilobase Resolution Reveals Principles of Chromatin Looping
Rao, S. S. P., Huntley, M. H., Durand, N. C., Stamenova, E. K., Bochkov, I. D., Robinson, J. T., Sanborn, A. L., Machol, I., Omer, A. D., Lander, E. S., et al. (2014) · Cell · doi:10.1016/j.cell.2014.11.021 · Cited by 9,212 · cited 1× · see citing works
“Positive EPIs were annotated using high-resolution genome-wide Hi-C data [32].”
MethodComprehensive Mapping of Long-Range Interactions Reveals Folding Principles of the Human Genome
Lieberman-Aiden, E., van Berkum, N. L., Williams, L., Imakaev, M., Ragoczy, T., Telling, A., Amit, I., Lajoie, B. R., Sabo, P. J., Dorschner, M. O., et al. (2009) · Science · doi:10.1126/science.1181369 · Cited by 8,898 · cited 1× · see citing works
“The method of Hi-C [11] allows the genome-wide detections of interactions but its current resolution is not high enough (~ 10 kb) to capture individual EPIs.”
MethodNon-coding RNAs in human disease
Esteller, M. (2011) · Nature Reviews Genetics · doi:10.1038/nrg3074 · Cited by 4,825 · cited 1× · see citing works
“On the contrary, they fulfill a wide variety of crucial biological roles involving regulatory and signaling functions [1].”
BackgroundGENCODE: The reference human genome annotation for The ENCODE Project
Harrow, J., Frankish, A., Gonzalez, J. M., Tapanari, E., Diekhans, M., Kokocinski, F., Aken, B. L., Barrell, D., Zadissa, A., Searle, S., et al. (2012) · Genome Research · doi:10.1101/gr.135350.111 · Cited by 4,585 · cited 1× · see citing works
“Using GENCODE [29] version 19 annotations and RNA-seq data from ENCODE, promoters were reserved if actively transcribed (mean FPKM > 0.3 [30] with irreproducible discovery rate 0.1 [31]) in each cell line.”
MethodInfluentialSoftware Framework for Topic Modelling with Large Corpora
Rek, R. R. U., & Sojka, P. (2010) · doi:10.13140/2.1.2393.1847 · Cited by 3,766 · see citing works
Capturing Chromosome Conformation
Dekker, J., Rippe, K., Dekker, M., & Kleckner, N. (2002) · Science · doi:10.1126/science.1067799 · Cited by 3,652 · cited 1× · see citing works
“Chromosome conformation capture-based (3C) methods [7], including 4C [8] and 5C [9] have been developed to detect physical contacts in the 3D space but fail to capture whole genome interactions.”
MethodPredicting the sequence specificities of DNA- and RNA-binding proteins by deep learning
Alipanahi, B., Delong, A., Weirauch, M. T., & Frey, B. J. (2015) · Nature Biotechnology · doi:10.1038/nbt.3300 · Cited by 2,873 · cited 1× · see citing works
“…including gkmSVM for enhancer prediction [19], DeepSEA for epigenomic state prediction [20] and DeepBind for DNA/RNA-binding proteins prediction [21], which extract sequence features and yield high performance. gkmSVM transforms variable-length sequences to fixed-length k -mer features to…”
BackgroundAn atlas of active enhancers across human cell types and tissues
The FANTOM Consortium, Andersson, R., Gebhard, C., Miguel-Escalada, I., Hoof, I., Bornholdt, J., Boyd, M., Chen, Y., Zhao, X., Schmidl, C., et al. (2014) · Nature · doi:10.1038/nature12787 · Cited by 2,550 · cited 2× · see citing works
“Recent studies have shown that noncoding single nucleotide polymorphisms (SNPs) that are associated with risk for numerous common diseases through genome-wide association studies (GWAS), frequently lie in cell line-specific enhancers [3, 4].”
BackgroundMethodChromHMM: automating chromatin-state discovery and characterization
Ernst, J., & Kellis, M. (2012) · Nature Methods · doi:10.1038/nmeth.1906 · Cited by 2,489 · cited 1× · see citing works
“Promoter and enhancer regions were identified using ENCODE Segway [26] and ChromHMM [27] annotations for K562, GM12878, HeLa-S3, and HUVEC cell lines, and using Roadmap [28] Epige-nomics ChromHMM annotations for NHEK and IMR90 cell lines.”
MethodPredicting effects of noncoding variants with deep learning–based sequence model
Zhou, J., & Troyanskaya, O. G. (2015) · Nature Methods · doi:10.1038/nmeth.3547 · Cited by 2,338 · cited 1× · see citing works
“…methods for 1D chromatin states prediction [17, 18], including gkmSVM for enhancer prediction [19], DeepSEA for epigenomic state prediction [20] and DeepBind for DNA/RNA-binding proteins prediction [21], which extract sequence features and yield high performance. gkmSVM transforms…”
MethodLearning deep structured semantic models for web search using clickthrough data
Huang, P.-S., He, X., Gao, J., Deng, L., Acero, A., & Heck, L. P. (2013) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2505515.2505665 · Cited by 2,054 · cited 1× · see citing works
“Paragraph Vector [22] successfully solves the problem by mapping texts into a unified vector representation, and generates embedding representation which can be further used for different applications [23], such as machine translation [24], sentiment analysis [22], and information retrieval [25].”
BackgroundThe NIH Roadmap Epigenomics Mapping Consortium
Bernstein, B. E., Stamatoyannopoulos, J. A., Costello, J. F., Ren, B., Milosavljevic, A., Meissner, A., Kellis, M., Marra, M. A., Beaudet, A. L., Ecker, J. R., et al. (2010) · Nature Biotechnology · doi:10.1038/nbt1010-1045 · Cited by 1,892 · cited 1× · see citing works
“Promoter and enhancer regions were identified using ENCODE Segway [26] and ChromHMM [27] annotations for K562, GM12878, HeLa-S3, and HUVEC cell lines, and using Roadmap [28] Epige-nomics ChromHMM annotations for NHEK and IMR90 cell lines.”
MethodAn oestrogen-receptor-α-bound human chromatin interactome
Fullwood, M. J., Liu, M. H., Pan, Y. F., Liu, J., Han, X., Mohamed, Y. B., Orlov, Y. L., Velkov, S., Ho, A., Poh, H. M., et al. (2009) · Nature · doi:10.1038/nature08497 · Cited by 1,728 · see citing works
Simonis, M., Klous, P., Splinter, E., Moshkin, Y., Willemsen, R., de Wit, E., van Steensel, B., & de Laat, W. (2006) · Nature Genetics · doi:10.1038/ng1896 · Cited by 1,386 · see citing works
Transcriptional enhancers: from properties to genome-wide predictions
Shlyueva, D., Stampfel, G., & Stark, A. (2014) · Nature Reviews Genetics · doi:10.1038/nrg3682 · Cited by 1,356 · see citing works
Dostie, J., Richmond, T., Arnaout, R., Selzer, R. R., Lee, W. L., Honan, T., Rubio, E. D., Krumm, A., Lamb, J., Nusbaum, C., et al. (2006) · Genome Research · doi:10.1101/gr.5571506 · Cited by 1,182 · cited 1× · see citing works
“Chromosome conformation capture-based (3C) methods [7], including 4C [8] and 5C [9] have been developed to detect physical contacts in the 3D space but fail to capture whole genome interactions.”
MethodMeasuring reproducibility of high-throughput experiments
Li, Q., Brown, J. B., Huang, H., & Bickel, P. J. (2011) · The Annals of Applied Statistics · doi:10.1214/11-aoas466 · Cited by 1,008 · cited 1× · see citing works
“Using GENCODE [29] version 19 annotations and RNA-seq data from ENCODE, promoters were reserved if actively transcribed (mean FPKM > 0.3 [30] with irreproducible discovery rate 0.1 [31]) in each cell line.”
MethodInfluentialMeasuring reproducibility of high-throughput experiments
Li, Q., Brown, J. B., Huang, H., & Bickel, P. J. (2010) · UC Berkeley · Cited by 915 · see citing works
A Scalable Hierarchical Distributed Language Model
Mnih, A., & Hinton, G. E. (2008) · Cited by 843 · see citing works
(2005) · Cited by 823 · see citing works
An Abundance of Ubiquitously Expressed Genes Revealed by Tissue Transcriptome Sequence Data
Ramsköld, D., Wang, E. T., Burge, C. B., & Sandberg, R. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000598 · Cited by 820 · cited 1× · see citing works
“Using GENCODE [29] version 19 annotations and RNA-seq data from ENCODE, promoters were reserved if actively transcribed (mean FPKM > 0.3 [30] with irreproducible discovery rate 0.1 [31]) in each cell line.”
MethodInfluentialMYB function in normal and cancer cells
Ramsay, R. G., & Gonda, T. J. (2008) · Nature reviews. Cancer · doi:10.1038/nrc2439 · Cited by 619 · cited 1× · see citing works
“MYB may be aberrantly expressed or rear-ranged or undergo translocation in leukemias and lymphomas, and is considered to be an oncogene [41].”
BackgroundUnsupervised pattern discovery in human chromatin structure through genomic segmentation
Hoffman, M. M., Buske, O. J., Wang, J., Weng, Z., Bilmes, J., & Noble, W. S. (2012) · Nature Methods · doi:10.1038/nmeth.1937 · Cited by 566 · cited 1× · see citing works
“Promoter and enhancer regions were identified using ENCODE Segway [26] and ChromHMM [27] annotations for K562, GM12878, HeLa-S3, and HUVEC cell lines, and using Roadmap [28] Epige-nomics ChromHMM annotations for NHEK and IMR90 cell lines.”
MethodGfi-1 restricts proliferation and preserves functional integrity of haematopoietic stem cells
Hock, H., Hamblen, M. J., Rooke, H. M., Schindler, J. W., Saleque, S., Fujiwara, Y., & Orkin, S. H. (2004) · Nature · doi:10.1038/nature02994 · Cited by 541 · cited 1× · see citing works
“It functions as part of a complex along with other cofactors to control histone modifications that lead to silencing of the target gene promoters [42].”
BackgroundEnhanced Regulatory Sequence Prediction Using Gapped k-mer Features
Ghandi, M., Lee, D., Mohammad-Noori, M., & Beer, M. A. (2014) · PLoS Comput. Biol. · doi:10.1371/journal.pcbi.1003711 · Cited by 514 · cited 1× · see citing works
“At the meantime, there are many inspiring methods for 1D chromatin states prediction [17, 18], including gkmSVM for enhancer prediction [19], DeepSEA for epigenomic state prediction [20] and DeepBind for DNA/RNA-binding proteins prediction [21], which extract sequence features and yield high…”
MethodInferring direct DNA binding from ChIP-seq
Bailey, T. L., & Machanick, P. (2012) · Nucleic Acids Research · doi:10.1093/nar/gks433 · Cited by 472 · cited 1× · see citing works
“Then we performed motif enrichment analysis using CentriMo [38] to compare these words against known motifs in the HOCOMOCO v9 dataset [39], and drew out top enriched motifs with sequence logo [40].”
MethodEnhancer-promoter interactions are encoded by complex genomic signatures on looping chromatin
Whalen, S., Truty, R. M., & Pollard, K. S. (2016) · Nature Genetics · doi:10.1038/ng.3539 · Cited by 456 · cited 1× · see citing works
“For instance, IM-PET [12], RIPPLE [13], TargetFinder [14] and EpiTensor [15], aim to predict 3D genomic interactions in different cell lines by integrating numerous one-dimensional (1D) local chromatin states including genomic and epigenomic data.”
BackgroundUnsupervised pattern discovery in human chromatin structure through genomic segmentation
Hoffman, M. M., Buske, O. J., Wang, J., Weng, Z., Bilmes, J., & Noble, W. S. (2012) · eScholarship@UMassChan · Cited by 397 · see citing works
Unsupervised pattern discovery in human chromatin structure through genomic segmentation
Hoffman, M. M., Buske, O. J., Wang, J., Weng, Z., Bilmes, J. A., & Noble, W. S. (2013) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/2506583.2506701 · Cited by 288 · see citing works
Global view of enhancer–promoter interactome in human cells
He, B., Chen, C., Teng, L., & Tan, K. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1320308111 · Cited by 258 · cited 1× · see citing works
“For instance, IM-PET [12], RIPPLE [13], TargetFinder [14] and EpiTensor [15], aim to predict 3D genomic interactions in different cell lines by integrating numerous one-dimensional (1D) local chromatin states including genomic and epigenomic data.”
BackgroundModulation of long noncoding RNAs by risk SNPs underlying genetic predispositions to prostate cancer
Guo, H., Ahmed, M., Zhang, F., Yao, C. Q., Li, S., Liang, Y., Hua, J., Soares, F., Sun, Y., Langstein, J., et al. (2016) · Nature Genetics · doi:10.1038/ng.3637 · Cited by 226 · cited 1× · see citing works
“For example, Guo et al. [6] identified mechanism of GWAS risk SNP rs7463708 in promoting prostate transformation.”
BackgroundHOCOMOCO: expansion and enhancement of the collection of transcription factor binding sites models
Kulakovskiy, I. V., Vorontsov, I. E., Yevshin, I., Soboleva, A. V., Kasianov, A. S., Ashoor, H., Ba-Alawi, W., Bajić, V. B., Medvedeva, Y. A., Kolpakov, F., et al. (2015) · Nucleic Acids Research · doi:10.1093/nar/gkv1249 · Cited by 210 · cited 1× · see citing works
“Then we performed motif enrichment analysis using CentriMo [38] to compare these words against known motifs in the HOCOMOCO v9 dataset [39], and drew out top enriched motifs with sequence logo [40].”
MethodRegulatory variation in a TBX5 enhancer leads to isolated congenital heart disease
Smemo, S., Campos, L. C. G., Moskowitz, I. P. G., Krieger, J. E., Pereira, A. C., & Nóbrega, M. A. (2012) · Human Molecular Genetics · doi:10.1093/hmg/dds165 · Cited by 204 · cited 1× · see citing works
“Recent studies have shown that noncoding single nucleotide polymorphisms (SNPs) that are associated with risk for numerous common diseases through genome-wide association studies (GWAS), frequently lie in cell line-specific enhancers [3, 4].”
BackgroundPredicting enhancer‐promoter interaction from genomic sequence with deep neural networks
Singh, S. K., Yang, Y., Póczos, B., & Ma, J. (2019) · Quantitative Biology · doi:10.1007/s40484-019-0154-0 · Cited by 180 · see citing works
Modeling gene regulation from paired expression and chromatin accessibility data
Duren, Z., Chen, X., Jiang, R., Wang, Y., & Wong, W. (2017) · Proceedings of the National Academy of Sciences of the United States of America · doi:10.1073/pnas.1704553114 · Cited by 171 · cited 1× · see citing works
“At the meantime, there are many inspiring methods for 1D chromatin states prediction [17, 18], including gkmSVM for enhancer prediction [19], DeepSEA for epigenomic state prediction [20] and DeepBind for DNA/RNA-binding proteins prediction [21], which extract sequence features and yield high…”
MethodSelf-citationConstructing 3D interaction maps from 1D epigenomes
Zhu, Y., Chen, Z., Zhang, K., Wang, M., Medovoy, D., Whitaker, J. W., Ding, B., Li, N., Zheng, L., & Wang, W. (2016) · Nature Communications · doi:10.1038/ncomms10812 · Cited by 139 · cited 1× · see citing works
“For instance, IM-PET [12], RIPPLE [13], TargetFinder [14] and EpiTensor [15], aim to predict 3D genomic interactions in different cell lines by integrating numerous one-dimensional (1D) local chromatin states including genomic and epigenomic data.”
BackgroundXu, M., Zeng, W., Chen, N., Chen, T., & Jiang, R. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx234 · Cited by 125 · cited 1× · see citing works
“At the meantime, there are many inspiring methods for 1D chromatin states prediction [17, 18], including gkmSVM for enhancer prediction [19], DeepSEA for epigenomic state prediction [20] and DeepBind for DNA/RNA-binding proteins prediction [21], which extract sequence features and yield high…”
MethodSelf-citationA predictive modeling approach for cell line-specific long-range regulatory interactions
Roy, S., Siahpirani, A. F., Chasman, D. A., Knaack, S., Ay, F., Stewart, R. M., Wilson, M. D., & Sridharan, R. (2015) · Nucleic Acids Research · doi:10.1093/nar/gkv865 · Cited by 121 · cited 1× · see citing works
“For instance, IM-PET [12], RIPPLE [13], TargetFinder [14] and EpiTensor [15], aim to predict 3D genomic interactions in different cell lines by integrating numerous one-dimensional (1D) local chromatin states including genomic and epigenomic data.”
BackgroundVirely, C., Moulin, S., Cobaleda, C., Lasgi, C., Alberdi, A., Soulier, J., Sigaux, F., Chan, S. H., Kastner, P., & Ghysdael, J. (2010) · Leukemia · doi:10.1038/leu.2010.63 · Cited by 93 · cited 1× · see citing works
“Overexpression of some dominant-negative isoforms have been associated with B-cell malignancies, such as acute lymphoblastic leukemia [43].”
BackgroundHeimann, P., Housni, H. E., Oğur, G., Weterman, M. A. J., Petty, E. M., & Vassart, G. (2001) · PubMed · Cited by 77 · see citing works
Walking on multiple disease-gene networks to prioritize candidate genes
Jiang, R. (2015) · Journal of Molecular Cell Biology · doi:10.1093/jmcb/mjv008 · Cited by 74 · see citing works
Self-citationfootprintDB: a database of transcription factors with annotated cis elements and binding interfaces
Sebastián, Á., & Contreras‐Moreira, B. (2013) · Bioinformatics · doi:10.1093/bioinformatics/btt663 · Cited by 73 · cited 1× · see citing works
“Then we performed motif enrichment analysis using CentriMo [38] to compare these words against known motifs in the HOCOMOCO v9 dataset [39], and drew out top enriched motifs with sequence logo [40].”
MethodMcLaughlin, J. N., Mazzoni, M. R., Cleator, J. H., Earls, L. R., Perdigoto, A. L., Brooks, J. D., Muldowney, J. A. S., Vaughan, D. E., & Hamm, H. E. (2005) · Journal of Biological Chemistry · doi:10.1074/jbc.m500721200 · Cited by 71 · cited 1× · see citing works
“SOX15_f1 will bind to SOX15, which is involved in the regulation of embryonic development and in the determination of the cell fate [44].”
BackgroundDeKelver, R. C., Lewin, B., Lam, K., Komeno, Y., Yan, M., Rundle, C. W., Lo, M., & Zhang, D. (2013) · PLoS Genetics · doi:10.1371/journal.pgen.1003765 · Cited by 27 · cited 1× · see citing works
“Multiple transcript variants encoding different isoforms have been found for this gene, some of which are implicated in carcinogenesis [45].”
BackgroundXu, M., Zeng, W., Chen, N., Chen, T., & Jiang, R. (2017) · doi:10.7490/f1000research.1114750.1 · Cited by 23 · see citing works
Self-citationMimvec: a deep learning approach for analyzing the human phenome
Gan, M., Li, W., Zeng, W., Wang, X., & Jiang, R. (2017) · BMC Systems Biology · doi:10.1186/s12918-017-0451-z · Cited by 6 · cited 1× · see citing works
“Paragraph Vector [22] successfully solves the problem by mapping texts into a unified vector representation, and generates embedding representation which can be further used for different applications [23], such as machine translation [24], sentiment analysis [22], and information retrieval [25].”
BackgroundSelf-citation
Flagged first, then by citations
3 of the 53 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
A guide to machine learning for biologists
Greener, J. G., Kandathil, S. M., Moffat, L., & Jones, D. T. (2022) · Nature Reviews Molecular Cell Biology · doi:10.1038/s41580-021-00407-0 · Cited by 2,127 · see citing works
“Another class of robust non-linear methods are ensemble-based models like random forests [39] and XGBoost [40,41].”
BackgroundMethodA primer on deep learning in genomics
Zou, J., Huss, M., Abid, A., Mohammadi, P., Torkamani, A., & Telenti, A. (2019) · Nature Genetics · doi:10.1038/s41588-018-0295-5 · Cited by 891 · see citing works
Zou, Q., Xing, P., Wei, L., & Liu, B. (2019) · RNA · doi:10.1261/rna.069112.118 · Cited by 525 · see citing works
Towards a comprehensive catalogue of validated and target-linked human enhancers
Gasperini, M., Tome, J. M., & Shendure, J. (2020) · Nature Reviews Genetics · doi:10.1038/s41576-019-0209-0 · Cited by 396 · see citing works
Applications of transformer-based language models in bioinformatics: a survey
Zhang, S., Fan, R., Liu, Y., Chen, S., Liu, Q., & Zeng, W. (2023) · Bioinformatics Advances · doi:10.1093/bioadv/vbad001 · Cited by 176 · see citing works
Self-citationNicholls, H. L., John, C. R., Watson, D. S., Munroe, P. B., Barnes, M. R., & Cabrera, C. P. (2020) · Frontiers in Genetics · doi:10.3389/fgene.2020.00350 · Cited by 155 · see citing works
“However, whilst deep learning enables the consideration of millions of parameters, its application to date has mostly flourished in image classification and natural language processing (Zeng et al., 2018; Aung et al., 2019; Hampe et al., 2019), requiring an investment in its development and benchmarking with tradition…”
MethodA review of deep learning applications in human genomics using next-generation sequencing data
Alharbi, W., & Rashid, M. (2022) · Human Genomics · doi:10.1186/s40246-022-00396-x · Cited by 161 · see citing works
“Another NLP implementation in the same field was shown by Zeng et al. (2018), who combined NLP with GBRT and introduced the EP2vec model to EPIs.”
MethodLe, N. Q. K., Yapp, E. K. Y., Ho, Q., Nagasundaram, N., Ou, Y., & Yeh, H. (2019) · Analytical Biochemistry · doi:10.1016/j.ab.2019.02.017 · Cited by 152 · see citing works
“quences, NLP has been successfully applied in enhancer-promoter interactions [18,28].”
MethodInterpretation of deep learning in genomics and epigenomics
Talukder, A., Barham, C., Li, X., & Hu, H. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa177 · Cited by 142 · see citing works
“A model named EP2vec was developed to predict EPIs [19].”
BackgroundMethodInfluentialComputational methods for analysing multiscale 3D genome organization
Zhang, Y., Boninsegna, L., Yang, M., Misteli, T., Alber, F., & Ma, J. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-023-00638-1 · Cited by 90 · see citing works
“Alternatively, some methods use the approaches initially developed for natural language processing by encoding DNA sequences into vector representations (also known as embeddings) in a semantic space 65,68,71 .”
Representation learning applications in biological sequence analysis
Iuchi, H., Matsutani, T., Yamada, K., Iwano, N., Sumi, S., Hosoda, S., Zhao, S., Fukunaga, T., & Hamada, M. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.05.039 · Cited by 83 · see citing works
Quantitative prediction of enhancer–promoter interactionsPreprint
Belokopytova, P. S., Mozheiko, E. A., Nuriddinov, M. A., Fishman, D., & Fishman, V. (2019) · Genome Research · doi:10.1101/gr.249367.119 · Cited by 72 · see citing works
“them (Whalen et al. 2016; Zeng et al. 2018) might be overestimated, as discussed above.”
BackgroundXu, J., Zhang, A., Liu, F., & Zhang, X. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad165 · Cited by 64 · see citing works
“…artificial intelligence tasks (Liu et al. 2021) and has been widely adopted in the analysis of DNA sequences, protein sequences, and scRNA-seq data (Zeng et al. 2018; Clauwaert et al. 2021; Jumper et al. 2021; Chu et al. 2022; Shu et al. 2022; Yang et al. 2022; Chen et al. 2023), owing to its…”
MethodSilencerDB: a comprehensive database of silencers
Zeng, W., Chen, S., Cui, X., Chen, X., Gao, Z., & Jiang, R. (2020) · Nucleic Acids Research · doi:10.1093/nar/gkaa839 · Cited by 61 · see citing works
“Among various classes of regulatory elements, the research community has thus far been favoring enhancers over the past few decades (6) for their ability to activate gene expression, encouraging the emergence of various enhancer resources, including validated enhancer databases (7,8), comprehensive enhancer databases…”
BackgroundMethodSelf-citationDeciphering the impact of genetic variation on human polyadenylation using APARENT2
Linder, J., Koplik, S. E., Kundaje, A., & Seelig, G. (2022) · Genome Biology · doi:10.1186/s13059-022-02799-4 · Cited by 49 · see citing works
Deciphering microbial gene function using natural language processing
Miller, D., Stern, A., & Burstein, D. (2022) · Nature Communications · doi:10.1038/s41467-022-33397-4 · Cited by 57 · see citing works
“Other studies applied NLP algorithms to DNA k-mers for taxonomic classi fi cation 23 , predicting enhancer-promoter interactions 24 , and chromatin accessibility 25 .”
MethodAsada, K., Kaneko, S., Takasawa, K., Machino, H., Takahashi, S., Shinkai, N., Shimoyama, R., Komatsu, M., & Hamamoto, R. (2021) · Frontiers in Oncology · doi:10.3389/fonc.2021.666937 · Cited by 54 · see citing works
IChrom-Deep: An Attention-Based Deep Learning Model for Identifying Chromatin Interactions
Zhang, P., & Wu, H. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3292299 · Cited by 53 · see citing works
Xu, H., Zhang, S., Yi, X., Plewczyński, D., & Li, M. J. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.02.013 · Cited by 48 · see citing works
“There were several methods developed based on this approach, including SPEID [129], EPIANN [130], PEP [131], EP2vec [132] and CHINN [133].”
MethodTahir, M., Norouzi, M., Khan, S. S., Davie, J., Yamanaka, S., & Ashraf, A. B. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109302 · Cited by 44 · see citing works
“( ii) Data-driven and statistical approaches that make use of existing EP-pairs and their interactions to predict if an enhancer and a promoter would interact [153, 155, 157].”
Tao, H., Li, H., Xu, K., Hong, H., Jiang, S., Du, G., Wang, J., Sun, Y., Huang, X., Ding, Y., et al. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa405 · Cited by 44 · see citing works
“Semi-supervised methods have been developed to predict chromatin interaction and organization; they enable the extraction of features from unlabeled genomic and epigenomic profiles and training of models that integrate initial and extracted features, which results in much better algorithm performance than achieved wit…”
BackgroundMethodInfluentialKhanal, J., Tayara, H., Zou, Q., & Chong, K. T. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.03.015 · Cited by 44 · see citing works
Jing, F., Zhang, S., & Zhang, S. (2020) · BMC Bioinformatics · doi:10.1186/s12859-020-03844-4 · Cited by 41 · see citing works
Deep‐learning power and perspectives for genomic selection
Montesinos-López, O. A., Montesinos‐López, A., Hernández-Suárez, C., Barrón‐López, J. A., & Crossa, J. L. (2021) · The Plant Genome · doi:10.1002/tpg2.20122 · Cited by 37 · see citing works
scGraph: a graph neural network-based approach to automatically identify cell types
Yin, Q., Liu, Q., Fu, Z., Zeng, W., Zhang, B., Zhang, X., Jiang, R., & Lv, H. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac199 · Cited by 34 · see citing works
Self-citationA survey on algorithms to characterize transcription factor binding sites
Tognon, M., Giugno, R., & Pinello, L. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad156 · Cited by 31 · see citing works
Rozenwald, M., Galitsyna, A. A., Sapunov, G. V., Khrameeva, E. E., & Gelfand, M. S. (2020) · PeerJ Computer Science · doi:10.7717/peerj-cs.307 · Cited by 32 · see citing works
HiChIPdb: a comprehensive database of HiChIP regulatory interactions
Zeng, W., Liu, Q., Yin, Q., Jiang, R., & Wong, W. H. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkac859 · Cited by 31 · see citing works
Self-citationInterpreting neural networks for biological sequences by learning stochastic masks
Linder, J., Fleur, A. L., Chen, Z., Ljubetič, A., Baker, D. A., Kannan, S., & Seelig, G. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-021-00428-6 · Cited by 25 · see citing works
“X̂s = σ ( log B̃ + X/max [ Ṡ(X) − s, ε ]) , lim ε→+0 (18)”
MethodA review on the applications of Transformer-based language models for nucleotide sequence analysis
Ghosh, N., Santoni, D., Saha, I., & Felici, G. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.03.024 · Cited by 31 · see citing works
“Recently, Natural Language Processing (NLP) approaches have shown a significant impact in bioinformatics ranging from DNA/RNA sequence analysis to computational biology [3,4].”
Machine Learning Methods for Exploring Sequence Determinants of 3D Genome Organization
Yang, M., & Ma, J. (2022) · Journal of Molecular Biology · doi:10.1016/j.jmb.2022.167666 · Cited by 26 · see citing works
A deep learning framework for enhancer prediction using word embedding and sequence generation
Geng, Q., Yang, R., & Zhang, L. (2022) · Biophysical Chemistry · doi:10.1016/j.bpc.2022.106822 · Cited by 25 · see citing works
Hassan, J., Saeed, S. M., Deka, L., Uddin, M. J., & Das, D. B. (2024) · Pharmaceutics · doi:10.3390/pharmaceutics16020260 · Cited by 28 · see citing works
Zhou, X., Feng, R., Ding, N., Cao, W., Liu, Y., Zhou, S., & Deng, Y. (2025) · Nucleic Acids Research · doi:10.1093/nar/gkaf863 · Cited by 23 · see citing works
“…training between the generator and the discriminator, GAN extracts promoter sequence features from a library, while WGAN-GP introduces Wasserstein distance and gradient penalty parameters to address instability in traditional GAN training and improve the quality of generated sequences [ 48 ].”
Epigenetics of neural differentiation: Spotlight on enhancers
Giacoman-Lozano, M., Meléndez-Ramírez, C., Martínez-Ledesma, E., Durán, R. C., & Velasco, I. (2022) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2022.1001701 · Cited by 22 · see citing works
EpiGePT: a Pretrained Transformer model for epigenomicsPreprint
Gao, Z., Liu, Q., Zeng, W., Jiang, R., & Wong, W. H. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.07.15.549134 · Cited by 20 · see citing works
Self-citationHow natural language processing derived techniques are used on biological data: a systematic review
Oikonomou, E. D., Karvelis, P. S., Γιαννακέας, Ν., Vrahatis, A. G., Glavas, E., & Tzallas, A. T. (2024) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-024-00458-1 · Cited by 19 · see citing works
“The team of (W. Zeng et al. 2018) used a type of RNN called Gated Recurrent Neural Networks (GRU) (Chung et al., 2014) to predict binding sites, and they were able to do so with predictions of AUC value as high as 0.9649.”
InfluentialMachine and Deep Learning Methods for Predicting 3D Genome Organization
Wall, B. P. G., Nguyen, M., Harrell, J. C., & Dozmorov, M. G. (2024) · Methods in molecular biology · doi:10.1007/978-1-0716-4136-1_22 · Cited by 19 · see citing works
Exploiting XG Boost for Predicting Enhancer-promoter Interactions
Yu, X., Zhou, J., Zhao, M., Yi, C., Duan, Q., Zhou, W., & Li, J. (2020) · Current Bioinformatics · doi:10.2174/1574893615666200120103948 · Cited by 18 · see citing works
Liu, S., Xu, X., Yang, Z., Zhao, X., Liu, S., & Zhang, W. (2021) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2021.3109488 · Cited by 17 · see citing works
Chromatin Hubs: A biological and computational outlook
Mora, A., Huang, X., Jauhari, S., Jiang, Q. L., & Li, X. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.07.002 · Cited by 17 · see citing works
“Sequence-based methods include PEP [117], EP2vec [118], SPEID [119], CNN with TL [120], and SEPT [121].”
MethodZhang, M., Hu, Y., & Zhu, M. (2021) · Genes · doi:10.3390/genes12091385 · Cited by 17 · see citing works
“However, these traditional machine learning methods often require feature engineering, which leads to redundant features, such as GTB [14], GBRT [15], and random forest [16].”
BackgroundSeeing the forest through the trees: prioritising potentially functional interactions from Hi-C
Liu, N., Low, W., Alinejad-Rokny, H., Pederson, S., Sadlon, T. J., Barry, S., & Breen, J. (2021) · Epigenetics & Chromatin · doi:10.1186/s13072-021-00417-4 · Cited by 11 · see citing works
AI in Health Science: A Perspective
Mishra, R., Chaudhary, K., & Mishra, I. (2022) · Current Pharmaceutical Biotechnology · doi:10.2174/1389201023666220929145220 · Cited by 14 · see citing works
Kuang, Z., Zhao, Y., & Yang, X. (2023) · Agriculture Communications · doi:10.1016/j.agrcom.2023.100014 · Cited by 12 · see citing works
A unified framework for integrative study of heterogeneous gene regulatory mechanisms
Cao, Q., Zhang, Z., Fu, X., Wu, Q., Lee, T., Lo, E., Cheng, A. S. L., Cheng, C., Leung, D., & Yip, K. Y.-L. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0205-2 · Cited by 12 · see citing works
DNA Computing: Concepts for Medical Applications
Sakowski, S., Waldmajer, J., Majsterek, I., & Popławski, T. (2022) · Applied Sciences · doi:10.3390/app12146928 · Cited by 9 · see citing works
“[19] Natural language processing Gene sequence Enhancer‐promoter”
BackgroundA neural network model to screen feature genes for pancreatic cancer
Huang, J., Zhou, Y., Zhang, H., & Wu, Y. (2023) · BMC Bioinformatics · doi:10.1186/s12859-023-05322-z · Cited by 9 · see citing works
“On many bioinformatics problems, they have shown better performance than traditional machine learning methods, such as sequence motif discovery [10, 11], chromatin interaction prediction [12], and genetic variation detection [13].”
MethodTahir, M., Tayara, H., Hayat, M., & Chong, K. T. (2021) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2021.104391 · Cited by 8 · see citing works
Dampier, W., Link, R. W., Earl, J. P., Collins, M. L., Souza, D. R. D., Koser, K. L., Nonnemacher, M. R., & Wigdahl, B. L. (2022) · Frontiers in Virology · doi:10.3389/fviro.2022.880618 · Cited by 8 · see citing works
“Of particular interest to this manuscript are advances in arti fi cial intelligence (AI) methods, particularly the Transformer models (40, 41).”
MethodFine-Tuning Transformers For Genomic TasksPreprint
Martinek, V., Čechák, D., Grešová, K., Alexiou, P., & Šimeček, P. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.02.07.479412 · Cited by 7 · see citing works
“…sequence (Georgakilas et al., 2019) and identification of functional elements regulating gene expression, namely gene promoters (Umarov & Solovyev, 2017), enhancers (Liu et al., 2016), enhancer-promoter interactions (Zeng et al., 2018) and transcription factor binding sites (Shen et al., 2018).”
BackgroundLai, C. H.-L., Kwok, A. P. K., & Wong, K.-C. (2024) · Journal of Personalized Medicine · doi:10.3390/jpm14090981 · Cited by 6 · see citing works
“For genomic data, there is a well-established consensus to use the k -mers technique, where k is a multiple of three, aligning with the codon structure of genetic sequences that are read in triplets of bases [78].”
MethodRepresentation Learning of Biological Concepts: A Systematic Review
Yang, Y., Zuo, X., Das, A., Xu, H., & Zheng, W. J. (2023) · Current Bioinformatics · doi:10.2174/1574893618666230612161210 · Cited by 6 · see citing works
GATv2EPI: Predicting Enhancer–Promoter Interactions with a Dynamic Graph Attention Network
Zhang, T., Zhao, X., Sun, H., Gao, B., & Liu, X. (2024) · Genes · doi:10.3390/genes15121511 · Cited by 6 · see citing works
Tahir, M., Khan, S. S., Davie, J., Yamanaka, S., & Ashraf, A. B. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05848-6 · Cited by 6 · see citing works
“(ii ) Data-driven and machine learning approaches that make use of existing EP-pairs and their interaction to predict if an enhancer and promoter will interact [19, 23, 24].”
Annotating regulatory elements by heterogeneous network embedding
Lu, Y., Feng, Z., Zhang, S., & Wang, Y. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac185 · Cited by 5 · see citing works
Sequence-Based Deep Learning Frameworks on Enhancer-Promoter Interactions Prediction
Min, X., Lu, F., & Li, C. (2020) · Current Pharmaceutical Design · doi:10.2174/1381612826666201124112710 · Cited by 6 · see citing works
Deep Learning Applied on Next Generation Sequencing Data Analysis
Danilevsky, A., & Shomron, N. (2021) · Methods in molecular biology · doi:10.1007/978-1-0716-1103-6_9 · Cited by 6 · see citing works
Machine learning for synthetic biology: Methods and applications
Hu, R., Zhang, S., Meng, H., Han, Y., Zhang, J., Luo, X., Si, T., Liu, C., & Qiao, Y. (2020) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/tb-2020-0456 · Cited by 5 · see citing works
Tahir, M., Hayat, M., Khan, R., & Chong, K. T. (2022) · Electronics · doi:10.3390/electronics11121917 · Cited by 5 · see citing works
EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation
Meng, Q., Lyu, Y., Peng, X., Xu, J., Tang, J., & Guo, F. (2024) · Big Data Mining and Analytics · doi:10.26599/bdma.2024.9020018 · Cited by 4 · see citing works
EPI-HAN: Identification of Enhancer Promoter Interaction Using Hierarchical Attention Network
Ahmed, F. S., Aly, S., & Liu, X. (2024) · Current Bioinformatics · doi:10.2174/0115748936294743240524113731 · Cited by 3 · see citing works
EPnet: A general network to predict enhancer-promoter interactions
Wang, Z., Zhou, L., Jiang, S., & Huang, W. (2021) · International Conference on Information Science and Technology · doi:10.1109/icist52614.2021.9440647 · Cited by 3 · see citing works
“EP2vec [17] simply transforms sequences into word vectors followed by a Gradient Boosted Decision Tree which appears to be efficient to work on the task with natural language processing (NLP).”
Exploiting epigenomic and sequence-based features for predicting enhancer-promoter interactions
Zhou, J., Liu, R., Wu, Z., Zhang, J., & Liu, J. (2020) · E3S Web of Conferences · doi:10.1051/e3sconf/202021803046 · Cited by 3 · see citing works
A systematic study of motif pairs that may facilitate enhancer–promoter interactions
Wang, S., Hu, H., & Li, X. (2022) · Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics · doi:10.1515/jib-2021-0038 · Cited by 3 · see citing works
Computational methods for identifying enhancer‐promoter interactions
Gong, H., Chen, Z., Tang, Y.-X., Li, M.-H., Zhang, S., Zhang, X.-T., & Chen, Y. (2023) · Quant. Biol. · doi:10.15302/j-qb-022-0322 · Cited by 3 · see citing works
Deep Learning in Neural Networks and their Application in Genomics
Kanaka, K. K., Sukhija, N., Sivalingam, J., Goli, R. C., Rathi, P., Jaglan, K., & Raj, C. (2023) · Acta Scientific Veterinary Sciences · doi:10.31080/asvs.2023.05.0683 · Cited by 3 · see citing works
Identifying promoter and enhancer sequences by graph convolutional networks
Tenekeci, S., & Tekır, S. (2024) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2024.108040 · Cited by 3 · see citing works
The discovery of wheat-derived anticaries peptides by a ML-based computational strategy
Guo, H., Yu, Y., Zhang, Z., Zhang, C., Fu, Q., Zhang, J., Yan, W., Han, J., & Huang, J. (2025) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2025.118303 · Cited by 2 · see citing works
Yadav, V. K., & Jalmi, S. K. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.146721 · Cited by 2 · see citing works
Assessment of Outcomes by Using Machine Learning
Venugopalan, S. R., Elnagar, M. H., Karhade, D. S., & Allareddy, V. (2021) · Springer eBooks · doi:10.1007/978-3-030-71881-7_11 · Cited by 2 · see citing works
Wu, T., Zhuang, R., Wu, Y., Wang, X., Qu, H., Dong, D.-F., Lü, Y., & Wu, J.-Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-11313-2 · Cited by 1 · see citing works
"An Analysis of Application of Natural Language Processing in Enhancing Education"
Raj, S., & Paliwal, M. (2021) · International Journal of Innovative Research in Computer Science & Technology · doi:10.55524/ijircst.2021.9.6.41 · Cited by 1 · see citing works
CBOEP: Generating negative enhancer-promoter interactions to train classifiers
Koga, T., & Maruyama, O. (2023) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3584371.3612997 · Cited by 1 · see citing works
“Recall that the TargetFinder datasets are used in several studies for EPI prediction, including TargetFinder [17], PEP [19], EPIANN [10], EP2vec [20], SPEID [15], a CNN-based method [22], EPIVAN [7], EPIsHilbert [21], and EPIHC [9].”
Computational methods to predict Enhancer-target Gene Pairs
XiaoQiang, X. U., Ting, C. U. I., Zhang, H., Shang, D., & Li, C. (2023) · Scientia Sinica Vitae · doi:10.1360/ssv-2023-0086 · Cited by 1 · see citing works
“McEnhancer [72] , EP_Bayes [73] , EAGLE [74] , DIRECT-NET [75] 等 是一种基于注意力的神经网络模型 , 可以更加关注有 助于 EPI 的特征 , 更准确地预测 EPI; EP2vec [82] 利用自 然语言处理的无监督深度学习方法将增强子和启动子 序列转化为序列嵌入特征 , 并利用有监督分类器对 EPI 进行预测 .”
Puzzle Hi-C: An accurate scaffolding software
Lin, G., Huang, Z., Yue, T., Chai, J., Li, Y., Yang, H., Qin, W., Yang, G., Murphy, R. W., Zhang, Y., et al. (2024) · PLoS ONE · doi:10.1371/journal.pone.0298564 · Cited by 1 · see citing works
HilbertEPIs: Enhancer-Promoter Interactions Prediction with Hilbert Curve and CNN Model
Hu, Y., Peng, R., Long, C., & Zhu, M. (2021) · International Conference on Bioinformatics and Computational Biology (ICBCB) · doi:10.1109/icbcb52223.2021.9459226 · Cited by 1 · see citing works
“Zeng et al. raised EP2vec [16] which viewed k-mer as words and sequence as text, using doc2vec to learn words as features and pulled all these features into Gradient Boosting Decision Tree [17] to actively learn classification strategy.”
MethodThree-Layer Dynamic Transfer Learning Language Model for E. Coli Promoter Classification
He, Y., Shen, Z., Zhang, Q., Wang, S., Yuan, C., Qin, X., Wu, H., & Zhao, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60802-6_7
Hundreds of motif pairs may facilitate enhancer-promoter interactionsPreprint
Wang, S., Hu, H., & Li, X. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.12.29.424656
K-mer Content Changes with Node Degree in Promoter–Enhancer Network of Mouse ES Cells
Szyman, K., Wilczyński, B., & Dąbrowski, M. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms22158067
Development of digital Hi-C assayPreprint
Mori, A., & Schweikert, G. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.12.31.522397
Categorisation of Post-Sale Automotive Customer Feedback Using Natural Language Processing
Vicente-Estévez, D., Dacal-Nieto, Á., Paradela, A., Alonso-Ramos, V., Areal, J. J., & Riomao, A. (2024) · International Conference on Machine Learning and Human-Computer Interaction (MLHMI) · doi:10.1109/mlhmi63000.2024.00019
“According to [5], NLP techniques were used to predict enhancer-promoter interactions with decent success.”
MethodKamel, A. A. B., Belal, N. A., & El-Sonbaty, Y. (2023) · International Conference on Computer Theory and Applications (ICCTA) · doi:10.1109/iccta60978.2023.10969268
“[13] b) The Atomic Number: Each nucleotide has an atomic number of values C = 58, T = 66, A = 70, G = 78.”
Maruyama, O., & Koga, T. (2025) · BMC Bioinformatics · doi:10.1186/s12859-025-06171-8
“…are positive and negative EP pairs for several cell lines, have been used in many subsequently developed computational models, including PEP [7], EPIANN [8], EP2vec [9], SPEID [10], a convolutional neural network (CNN)-based method [11], EPIsCNN, EPIVAN [12], EPIsHil-bert [13], and EPIHC [14].”
Liu, J., Zhang, P., Xu, S., Srinivasan, S. S., Wu, Y., & Zhang, J. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084625
Additional file 1 of A neural network model to screen feature genes for pancreatic cancer
Huang, J., Zhou, Y., Zhang, H., & Wu, Y. (2023) · Figshare · doi:10.6084/m9.figshare.22807470
Jing, F., Zhang, S., & Zhang, S. (2020) · Figshare · doi:10.6084/m9.figshare.13204601
EPI-CAT: Prediction of enhancer-promoter interactions based on cross-attention transformer
Liu, C., Huang, X., Zhang, Z., Qi, Y., & Liu, L. (2026) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2026.151520
Jia, J., Li, G., & Sun, M. (2026) · Current Genomics · doi:10.2174/0113892029407030251229080710
“First, the dataset utilized in this study is relatively small, which may limit the model’s capacity to learn more complex, high-dimensional representations through deep learning [75, 76].”
Li, W., Zeng, W.-W., & Wong, W.-H. (2026) · Cybernetics and Intelligence · doi:10.26599/cai.2024.9390003
Self-citationDeep learning-driven de novo design of ribosome binding sites in Paracoccus denitrificans
Zheng, Z., Zhou, S., & Deng, Y. (2026) · Synthetic and Systems Biotechnology · doi:10.1016/j.synbio.2026.07.013
“…model not only learns the key sequence features from the original RBS dataset but also — by incorporating Wasserstein distance and gradient penalty parameters — effectively alleviates the training instability common in conventional GANs, thereby enhancing the quality of generated sequences [46].”
EPI-LinkFormer: a pretrained deep learning framework for predicting enhancer-promoter interactions
Liu, C., & Huang, X. (2026) · International Conference on Biomedicine and Bioinformatics Engineering (ICBBE) · doi:10.1145/3822183.3822250
“Subsequent studies began to incorporate representation-learning ideas; for instance, EP2vec [10] treats k-mers as “tokens” and learns contextualized sequence representations via embedding techniques.”
Language-Model-Based Detection of Genetic Editing in BacteriaPreprint
Gabay, E., & Burstein, D. E. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.17.751846
- Authors
- Zeng, W., Wu, M., & Jiang, R.
- Affiliations
- Tsinghua University (CN)
- Corresponding author
- Jiang, Rui
- Venue
- BMC Genomics
- Published
- 2018-05
- Volume
- 19
- Issue
- S2
- Pages
- 84-84
- ISSN
- 1471-2164 (ISSN-L)
- PMC
- PMC5954283
- OpenAlex
- W2800857888
- Cited by
- 96
- References
- 53
- Citations by year
- 2026: 6 · 2025: 7 · 2024: 12 · 2023: 16 · 2022: 17 · 2021: 16 · 2020: 18 · 2019: 2 · 2018: 2
- FWCI
- 3.38
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- BMC Genomics (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, other-oa)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61175002, 61721003, 61573207)
- Tsinghua University (61175002)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
- Keywords
- enhancer-promoter interactions, 3D genome organization, sequence embeddings, DNA sequence representation, attention mechanism, gene expression regulation, long DNA sequences
- MeSH terms
- Unsupervised Machine Learning, HeLa Cells, Humans, Natural Language Processing, Promoter Regions, Genetic, Regulatory Sequences, Nucleic Acid, Sequence Analysis, DNA, Computational Biology, K562 Cells, Databases, Genetic, Cell Line, Tumor, Human Umbilical Vein Endothelial Cells
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
