M6A-BERT-Stacking: a tissue-specific predictor for identifying RNA N6-methyladenosine sites based on bert and stacking strategy
Open accessAbstract
As the most abundant RNA methylation modification, N6-methyladenosine (m6A) could regulate asymmetric and symmetric division of hematopoietic stem cells and play an important role in various diseases. Therefore, the precise identification of m6A sites around the genomes of different species is a critical step to further revealing their biological functions and influence on these diseases. However, the traditional wet-lab experimental methods for identifying m6A sites are often laborious and expensive. In this study, we proposed an ensemble deep learning model called m6A-BERT-Stacking, a powerful predictor for the detection of m6A sites in various tissues of three species. First, we utilized two encoding methods, i.e., di ribonucleotide index of RNA (DiNUCindex_RNA) and k-mer word segmentation, to extract RNA sequence features. Second, two encoding matrices together with the original sequences were respectively input into three different deep learning models in parallel to train three sub-models, namely residual networks with convolutional block attention module (Resnet-CBAM), bidirectional long short-term memory with attention (BiLSTM-Attention), and pre-trained bidirectional encoder representations from transformers model for DNA-language (DNABERT). Finally, the outputs of all sub-models were ensembled based on the stacking strategy to obtain the final prediction of m6A sites through the fully connected layer. The experimental results demonstrated that m6A-BERT-Stacking outperformed most of the existing methods based on the same independent datasets.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Transformers are well-suited to learn sequence data of biology, including DNA, RNA, and protein sequence learning, genomic regulatory prediction, protein function annotation, protein design, and further adaptation into medical image and gene expression analysis.
“It makes it well-suited to learn the sequence data of biology [76], including the DNA [6], RNA [77], and protein [7] sequence learning, genomic regulatory prediction [78], protein function annotation [79], protein design [80], and further adaptation into medical image [81] and gene expression analysis [13].”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [77]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
CBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853 · see citing works
Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences
Li, W.-Z., & Godzik, A. (2006) · Bioinform. · doi:10.1093/bioinformatics/btl158 · Cited by 10,990 · see citing works
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · see citing works
Topology of the human and mouse m6A RNA methylomes revealed by m6A-seq
Dominissini, D., Moshitch-Moshkovitz, S., Schwartz, S., Salmon-Divon, M., Ungar, L., Osenberg, S., Cesarkas, K., Jacob-Hirsch, J., Amariglio, N., Kupiec, M., et al. (2012) · Nature · doi:10.1038/nature11112 · Cited by 4,884 · see citing works
Comprehensive Analysis of mRNA Methylation Reveals Enrichment in 3′ UTRs and near Stop Codons
Meyer, K. D., Saletore, Y., Zumbo, P., Elemento, O., Mason, C. E., & Jaffrey, S. R. (2012) · Cell · doi:10.1016/j.cell.2012.05.003 · Cited by 4,223 · see citing works
Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification
Zhou, P., Shi, W. Y., Tian, J., Qi, Z., Li, B., Hao, H., & Xu, B. (2016) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p16-2034 · Cited by 2,108 · see citing works
A review on the long short-term memory model
Houdt, G. V., Mosquera, C., & Nápoles, G. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09838-1 · Cited by 2,066 · see citing works
Single-nucleotide-resolution mapping of m6A and m6Am throughout the transcriptome
Linder, B., Grozhik, A. V., Olarerin-George, A. O., Meydan, C., Mason, C. E., & Jaffrey, S. R. (2015) · Nature Methods · doi:10.1038/nmeth.3453 · Cited by 1,569 · see citing works
A primer in BERTology: What we know about how BERT works
Rogers, A., Kovaleva, O., & Rumshisky, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00349 · Cited by 1,552 · see citing works
Functions of N6-methyladenosine and its role in cancer
He, L., Li, H., Wu, A., Peng, Y., Shu, G., & Yin, G. (2019) · Molecular Cancer · doi:10.1186/s12943-019-1109-9 · Cited by 1,403 · see citing works
Ji, Y., Zhou, Z., Liu, H., & Davuluri, R. V. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab083 · Cited by 1,303 · see citing works
SRAMP: prediction of mammalian N 6 -methyladenosine (m 6 A) sites based on sequence-derived features
Zhou, Y., Zeng, P., Li, Y., Zhang, Z., & Cui, Q. (2016) · Nucleic Acids Research · doi:10.1093/nar/gkw104 · Cited by 1,104 · see citing works
MODOMICS: a database of RNA modification pathways. 2021 update
Boccaletto, P., Stefaniak, F., Ray, A., Cappannini, A., Mukherjee, S., Purta, E., Kurkowska, M., Shirvanizadeh, N., Destefanis, E., Groza, P., et al. (2021) · Nucleic Acids Research · doi:10.1093/nar/gkab1083 · Cited by 811 · see citing works
m6A RNA methylation: from mechanisms to therapeutic potential
He, P. C., & He, C. (2021) · The EMBO Journal · doi:10.15252/embj.2020105977 · Cited by 794 · see citing works
Transformer models for text-based emotion detection: a review of BERT-based approaches
Acheampong, F. A., Nunoo‐Mensah, H., & Chen, W. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-021-09958-2 · Cited by 686 · see citing works
The emerging role of RNA modifications in the regulation of mRNA stability
Boo, S. H., & Kim, Y. K. (2020) · Experimental & Molecular Medicine · doi:10.1038/s12276-020-0407-z · Cited by 588 · see citing works
Vacic, V., Iakoucheva, L. M., & Radivojac, P. (2006) · Bioinformatics · doi:10.1093/bioinformatics/btl151 · Cited by 539 · 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
High‐Resolution N6‐Methyladenosine (m6A) Map Using Photo‐Crosslinking‐Assisted m6A Sequencing
Chen, K., Lu, Z., Wang, X., Fu, Y., Luo, G., Liu, N., Han, D., Dominissini, D., Dai, Q., Pan, T., et al. (2014) · Angewandte Chemie International Edition · doi:10.1002/anie.201410647 · Cited by 404 · see citing works
iRNA-Methyl: Identifying N6-methyladenosine sites using pseudo nucleotide composition
Chen, W., Feng, P., Ding, H., Lin, H., & Chou, K. (2015) · Analytical Biochemistry · doi:10.1016/j.ab.2015.08.021 · Cited by 350 · see citing works
Chen, K., Wei, Z. C., Zhang, Q., Wu, X., Rong, R., Lu, Z.-L., Su, J., de Magalhães, J. P., Rigden, D. J., & Meng, J. (2019) · Nucleic Acids Research · doi:10.1093/nar/gkz074 · Cited by 227 · see citing works
Wei, L., Chen, H., & Su, R. (2018) · Molecular Therapy Nucleic Acids · doi:10.1016/j.omtn.2018.07.004 · Cited by 179 · see citing works
m6A RNA Methylation Maintains Hematopoietic Stem Cell Identity and Symmetric Commitment
Cheng, Y., Luo, H., Izzo, F., Pickering, B. F., Nguyen, D. T. T., Myers, R. M., Schurer, A., Gourkanti, S., Brüning, J. C., Vu, L., et al. (2019) · Cell Reports · doi:10.1016/j.celrep.2019.07.032 · Cited by 171 · see citing works
Jin, J., Yu, Y., Wang, R., Zeng, X., Pang, C., Jiang, Y., Li, Z., Dai, Y., Su, R., Zou, Q., et al. (2022) · Genome biology · doi:10.1186/s13059-022-02780-1 · Cited by 158 · see citing works
Chen, Z., Zhao, P., Li, F., Wang, Y., Smith, A. I., Webb, G. I., Akutsu, T., Baggag, A., Bensmail, H., & Song, J. (2019) · Briefings in Bioinformatics · doi:10.1093/bib/bbz112 · Cited by 142 · see citing works
DiProDB: a database for dinucleotide properties
Friedel, M., Nikolajewa, S., Sühnel, J., & Wilhelm, T. E. (2008) · Nucleic Acids Research · doi:10.1093/nar/gkn597 · Cited by 129 · see citing works
Detecting N6-methyladenosine sites from RNA transcriptomes using ensemble Support Vector Machines
Chen, W., Xing, P., & Zou, Q. (2017) · Scientific Reports · doi:10.1038/srep40242 · Cited by 122 · see citing works
Qiang, X., Chen, H., Ye, X., Su, R., & Wei, L. (2018) · Frontiers in Genetics · doi:10.3389/fgene.2018.00495 · Cited by 115 · see citing works
Nazari, I., Tahir, M., Tayara, H., & Chong, K. T. (2019) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2019.103811 · Cited by 100 · see citing works
Computational identification of N6-methyladenosine sites in multiple tissues of mammals
Dao, F., Lv, H., Yang, Y. R., Zulfiqar, H., Gao, H., & Lin, H. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.04.015 · Cited by 100 · see citing works
Huang, Y., He, N., Chen, Y., Chen, Z., & Li, L. (2018) · International Journal of Biological Sciences · doi:10.7150/ijbs.27819 · Cited by 99 · see citing works
Li, G.-Q., Liu, Z., Shen, H., & Yu, D. (2016) · IEEE Transactions on NanoBioscience · doi:10.1109/tnb.2016.2599115 · Cited by 82 · see citing works
RFAthM6A: a new tool for predicting m6A sites in Arabidopsis thaliana
Wang, X., & Yan, R. (2018) · Plant Molecular Biology · doi:10.1007/s11103-018-0698-9 · Cited by 69 · see citing works
Prediction of RNA–protein interactions using a nucleotide language model
Yamada, K., & Hamada, M. (2022) · Bioinformatics Advances · doi:10.1093/bioadv/vbac023 · Cited by 69 · see citing works
Liu, K., Cao, L., Du, P.-F., & Chen, W. (2020) · Molecular Therapy — Nucleic Acids · doi:10.1016/j.omtn.2020.07.034 · Cited by 54 · see citing works
Abbas, Z., Tayara, H., Zou, Q., & Chong, K. T. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.08.014 · Cited by 45 · see citing works
Tahir, M., Hayat, M., & Chong, K. T. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.05.027 · Cited by 37 · see citing works
Rehman, M. U., Kim, J., Tayara, H., & Chong, K. T. (2021) · IEEE Access · doi:10.1109/access.2021.3054361 · Cited by 36 · see citing works
Zhang, L., Qin, X., Liu, M., Xu, Z., & Liu, G. (2021) · Genes · doi:10.3390/genes12030354 · Cited by 27 · see citing works
Extremely-randomized-tree-based Prediction of N6-methyladenosine Sites in Saccharomyces cerevisiae
Govindaraj, R. G., Subramaniyam, S., & Manavalan, B. (2020) · Current Genomics · doi:10.2174/1389202921666200219125625 · Cited by 26 · see citing works
A brief review of machine learning methods for RNA methylation sites prediction
Wang, H., Wang, S., Zhang, Y., Bi, S., & Zhu, X. (2022) · Methods · doi:10.1016/j.ymeth.2022.03.001 · Cited by 24 · see citing works
Zhao, X., Zhang, Y., Qiao, N., Zhang, H., Ji, J., & Yin, M. (2019) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2019.01.035 · Cited by 24 · see citing works
A tool for feature extraction from biological sequences
Amerifar, S., Norouzi, M., & Ghandi, M. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac108 · Cited by 17 · see citing works
6mA-Pred: identifying DNA N6-methyladenine sites based on deep learning
Huang, Q., Zhou, W., Guo, F., Xu, L., & Zhang, L. (2021) · PeerJ · doi:10.7717/peerj.10813 · Cited by 17 · see citing works
Predicting N6-Methyladenosine Sites in Multiple Tissues of Mammals through Ensemble Deep Learning
Luo, Z., Lou, L., Qiu, W., Xu, Z., & Xiao, X. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms232415490 · Cited by 15 · see citing works
KNIndex: a comprehensive database of physicochemical properties fork-tuple nucleotides
Zhang, W., Xu, J., Wang, J., Zhou, Y.-K., Chen, W., & Du, P.-F. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa284 · Cited by 13 · see citing works
Wang, Y., Hou, Z., Yang, Y., Wong, K., & Li, X. (2022) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010779 · Cited by 11 · see citing works
Jia, C., JIN, D., Wang, X., & Zhao, Q. (2021) · Biocell · doi:10.32604/biocell.2022.016655 · Cited by 7 · see citing works
Zhang, Y., Yu, Z., Yu, B., Wang, X., Gao, H., Sun, J., & Li, S. (2022) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2022.104495 · Cited by 6 · see citing works
Wang, H., Zhao, S., Cheng, Y., Bi, S., & Zhu, X. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2022.999506 · Cited by 6 · see citing works
Zhang, Z., & Wang, L. (2020) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2020.1821778 · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Transformer Architecture and Attention Mechanisms in Genome Data Analysis: A Comprehensive Review
Choi, S. R., & Lee, M. (2023) · Biology · doi:10.3390/biology12071033 · Cited by 265 · see citing works
“[36] proposed an ensemble deep learning model called m6A-BERT-Stacking to detect m6A sites in various tissues of three species.”
BackgroundChallenges in AI-driven Biomedical Multimodal Data Fusion and Analysis
Liu, J., Cen, X., Yi, C., Wang, F.-A., Ding, J., Cheng, J., Wu, Q., Gai, B., Zhou, Y., He, R., et al. (2025) · Genomics, Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzaf011 · Cited by 75 · see citing works
Li, G., Zhao, B.-W., Su, X., Yang, Y., Hu, P., Zhou, X., & Hu, L. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3357979 · Cited by 69 · see citing works
“Divergent strategies, such as M6A-bert-stacking [11], TS-m6A-DL [12], im6A-TS-CNN [13], and m6A-neural-network [14], endeavor to introduce more encoding methods, including one-hot encoding, k-mer encoding, and Nucleotide Chemical Property, to extract deep representations of RNA sequences.”
Li, C., Wang, H., Wen, Y., Yin, R., Zeng, X., & Li, K. (2024) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2024.3459870 · Cited by 45 · see citing works
“Numerous studies have demonstrated that features learned from DNA base sequences can be easily applied to RNA tasks [28], [39], [40], [41].”
iDNA-OpenPrompt: OpenPrompt learning model for identifying DNA methylation
Yu, X., Ren, J.-L., Long, H., Zeng, R., Zhang, G., Bilal, A., & Cui, Y.-N. (2024) · Frontiers in Genetics · doi:10.3389/fgene.2024.1377285 · Cited by 22 · see citing works
Asim, M. N., Ibrahim, M. A., Asif, T., & Dengel, A. R. (2025) · Heliyon · doi:10.1016/j.heliyon.2024.e41488 · Cited by 16 · see citing works
Li, G., Yang, Y., Li, D., Su, X., Zeng, Z., Hu, P., & Hu, L. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111541 · Cited by 12 · see citing works
Jin, R., Zou, Q., & Luo, X. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26146701 · Cited by 11 · see citing works
“In m6A modification prediction, the M6A-BERT-Stacking tool integrates BERT and stacking strategies to predict tissue-specific m6A modification sites [61].”
Tissue-specific RNA methylation prediction from gene expression data using sparse regression models
Jiang, J., Song, B., Meng, J., & Zhou, J. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107892 · Cited by 9 · see citing works
Li, G., Su, X., Yang, Y., Li, D., Cui, Z., Deng, X., Hu, P., & Hu, L. (2025) · Communications Biology · doi:10.1038/s42003-025-08265-8 · Cited by 9 · see citing works
“Inspired by natural language processing, models such as iN6-Methyl 30 , m 6 A-word2vec 31 , m 6 A-bert-stacking 32 , and DeepPromise 33 treat RNA sequences as textual data, capturing complex patterns and contextual dependencies.”
Multimodal zero-shot learning of previously unseen epitranscriptomes from RNA-seq data
Song, Y., Song, B., Huang, D., Nguyen, A., Hu, L., Meng, J., & Wang, Y. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf332 · Cited by 4 · see citing works
“…prediction methods, including im 6 A-TS-CNN [73] and TS-m 6 A-DL [74], both based on convolutional neural networks, im 6 APred that utilizes ensemble deep leaning strategies [75], and m 6 A-BERT-Stacking that leverages multiple modules including convolutional blocks and BiLSTM with attention [78].”
A robust stacked neural network approach for early and accurate breast cancer diagnosis
Li, X., Gao, M., Zhang, C., Ma, G., Zhang, Q., Meng, W., Yuan, T., Wang, Y., & Li, Z. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1644857 · Cited by 3 · see citing works
RPCP-PURI: A robust and precise computational predictor for Phishing Uniform Resource Identification
Asif, T., Mehmood, F., Gillani, S. A. M., Asim, M. N., Khan, M. U. G., Mahmood, W., & Dengel, A. (2024) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103953 · Cited by 3 · see citing works
iDNA-ITLM: An interpretable and transferable learning model for identifying DNA methylation
Yu, X., Yani, C., Wang, Z., Long, H., Zeng, R., Liu, X., Anas, B., & Ren, J. (2024) · PLoS ONE · doi:10.1371/journal.pone.0301791 · Cited by 3 · see citing works
“In addition, we also compare the method of this paper with other models on the RNA methylation dataset, such as iDNA-LTLM (no fine-tuning), m6A-BERT BiLSTM [33], m6A-BERT ResNet-50 [33].”
BackgroundMethodInfluentialLi, G., Zhao, B.-W., Su, X., Yang, Y., Zeng, Z., Hu, P., & Hu, L. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109625 · Cited by 2 · see citing works
Teng, Z., Li, Z., Liu, D., Wang, C., & Wang, G. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf651 · Cited by 1 · see citing works
“Then, CD-HIT [23] was utilized to measure sequence similarities, and sequences that sharing over 80% similarity with others were removed following previous studies [24–27].”
Learning RNA sequence patterns to interpretably identify m6A modification sites
Li, G., Zhao, B.-W., Su, X., Yang, Y., Hu, P., & Hu, L. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10386062
“Furthermore, we compare M6AInter with five state-of-the-art methods focusing on the m6A modification site identification on benchmark datasets, including M6A-bert-stacking [6], TS-m6A-DL [7], iRNA-m6A [14], im6A-TS-CNN [7] and m6A-neural-network [9].”
MethodTowards Pathogenicity Prediction of BRCA Variants Using BERT-Based Genomic Language ModelsPreprint
Marco, A. D., Masci, L. U., & Nguyen, P. T. (2025) · doi:10.36227/techrxiv.175393273.34898231/v1
Prediction of RNA m6A Methylation Sites in Multiple Tissues Based on Dual-branch Residual Network
Xiao-Tian, G. U. O., Gao, W., Chen, D., Hui-Min, L. I., & Xue-Wen, T. A. N. (2025) · PROGRESS IN BIOCHEMISTRY AND BIOPHYSICS · doi:10.3724/j.pibb.2025.0167
AI-Driven Insights into RNA Sequence Analysis Landscape
Asim, M. N., Ahmed, S., & Dengel, A. (2025) · Springer eBooks · doi:10.1007/978-3-031-90454-7_4
- Authors
- Li, Q., Cheng, X., Song, C., & Liu, T.
- Affiliations
- Shanghai Ocean University (CN)
- Corresponding author
- Liu, Taigang
- Venue
- Symmetry
- Publisher
- MDPI AG
- Published
- 2023-03-15
- Volume
- 15
- Issue
- 3
- Pages
- 731
- ISSN
- 2073-8994 (ISSN-L)
- OpenAlex
- W4324385651
- Cited by
- 20
- References
- 52
- Citations by year
- 2025: 12 · 2024: 5 · 2023: 3
- FWCI
- 1.78
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Symmetry (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- National Natural Science Foundation of China (11601324)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA modifications and cancer
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA regulation and disease
- Keywords
- N6-methyladenosine, RNA methylation, m6A site prediction, ensemble learning, stacking, BERT, DNABERT, k-mer features, BiLSTM-Attention, hematopoietic stem 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
