{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T01:13:19Z","timestamp":1780449199777,"version":"3.54.1"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"vor","delay-in-days":11,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31671373"],"award-info":[{"award-number":["31671373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"XJTLU Key Program Special Fund","award":["KSF-T-01"],"award-info":[{"award-number":["KSF-T-01"]}]},{"name":"AI University Research Centre"},{"name":"XJTLU Key Programme Special Fund","award":["KSF-P-02"],"award-info":[{"award-number":["KSF-P-02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Increasing evidence suggests that post-transcriptional ribonucleic acid (RNA) modifications regulate essential biomolecular functions and are related to the pathogenesis of various diseases. Precise identification of RNA modification sites is essential for understanding the regulatory mechanisms of RNAs. To date, many computational approaches for predicting RNA modifications have been developed, most of which were based on strong supervision enabled by base-resolution epitranscriptome data. However, high-resolution data may not be available.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We propose WeakRM, the first weakly supervised learning framework for predicting RNA modifications from low-resolution epitranscriptome datasets, such as those generated from acRIP-seq and hMeRIP-seq. Evaluations on three independent datasets (corresponding to three different RNA modification types and their respective sequencing technologies) demonstrated the effectiveness of our approach in predicting RNA modifications from low-resolution data. WeakRM outperformed state-of-the-art multi-instance learning methods for genomic sequences, such as WSCNN, which was originally designed for transcription factor binding site prediction. Additionally, our approach captured motifs that are consistent with existing knowledge, and visualization of the predicted modification-containing regions unveiled the potentials of detecting RNA modifications with improved resolution.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability implementation<\/jats:title><jats:p>The source code for the WeakRM algorithm, along with the datasets used, are freely accessible at: https:\/\/github.com\/daiyun02211\/WeakRM<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab278","type":"journal-article","created":{"date-parts":[[2021,4,23]],"date-time":"2021-04-23T20:20:16Z","timestamp":1619209216000},"page":"i222-i230","source":"Crossref","is-referenced-by-count":36,"title":["Weakly supervised learning of RNA modifications from low-resolution epitranscriptome data"],"prefix":"10.1093","volume":"37","author":[{"given":"Daiyun","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Biological Sciences, Xi\u2019an Jiaotong-Liverpool University , Suzhou, Jiangsu 215123, China"},{"name":"Department of Computer Science, University of Liverpool , Liverpool L69 7ZB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, Xi\u2019an Jiaotong-Liverpool University , Suzhou, Jiangsu 215123, China"},{"name":"Institute of Systems, Molecular and Integrative Biology, University of Liverpool , Liverpool L69 7ZB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjue","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, Xi\u2019an Jiaotong-Liverpool University , Suzhou, Jiangsu 215123, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jionglong","family":"Su","sequence":"additional","affiliation":[{"name":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University , Suzhou, Jiangsu 215123, China"},{"name":"AI University Research Centre, Xi\u2019an Jiaotong-Liverpool University , Suzhou, Jiangsu 215123, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frans","family":"Coenen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Liverpool , Liverpool L69 7ZB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3455-205X","authenticated-orcid":false,"given":"Jia","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Xi\u2019an Jiaotong-Liverpool University , Suzhou, Jiangsu 215123, China"},{"name":"Institute of Systems, Molecular and Integrative Biology, University of Liverpool , Liverpool L69 7ZB, UK"},{"name":"AI University Research Centre, Xi\u2019an Jiaotong-Liverpool University , Suzhou, Jiangsu 215123, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,7,12]]},"reference":[{"key":"2023062410173984500_btab278-B1","doi-asserted-by":"crossref","first-page":"3528","DOI":"10.1016\/j.csbj.2020.10.032","article-title":"Accurate prediction of RNA 5-hydroxymethylcytosine modification by utilizing novel position-specific gapped k-mer descriptors","volume":"18","author":"Ahmed","year":"2020","journal-title":"Comput. Struct. Biotechnol. J"},{"key":"2023062410173984500_btab278-B2","doi-asserted-by":"crossref","first-page":"20942","DOI":"10.1038\/s41598-020-77824-2","article-title":"XG-ac4C: identification of N4-acetylcytidine (ac4C) in mRNA using eXtreme gradient boosting with electron-ion interaction pseudopotentials","volume":"10","author":"Alam","year":"2020","journal-title":"Sci. Rep"},{"key":"2023062410173984500_btab278-B3","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning","volume":"33","author":"Alipanahi","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023062410173984500_btab278-B4","doi-asserted-by":"crossref","first-page":"e20059","DOI":"10.1371\/journal.pone.0020059","article-title":"A linear model for transcription factor binding affinity prediction in protein binding microarrays","volume":"6","author":"Annala","year":"2011","journal-title":"PLoS One"},{"key":"2023062410173984500_btab278-B5","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.tibtech.2020.06.002","article-title":"New twists in detecting mRNA modification dynamics","volume":"39","author":"Anreiter","year":"2021","journal-title":"Trends Biotechnol"},{"key":"2023062410173984500_btab278-B6","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1016\/j.cell.2018.10.030","article-title":"Acetylation of cytidine in mRNA promotes translation efficiency","volume":"175","author":"Arango","year":"2018","journal-title":"Cell"},{"key":"2023062410173984500_btab278-B7","doi-asserted-by":"crossref","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","article-title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","volume":"10","author":"Bach","year":"2015","journal-title":"PLoS One"},{"key":"2023062410173984500_btab278-B8","doi-asserted-by":"crossref","first-page":"8004","DOI":"10.1038\/srep08004","article-title":"MBSTAR: multiple instance learning for predicting specific functional binding sites in microRNA targets","volume":"5","author":"Bandyopadhyay","year":"2015","journal-title":"Sci. Rep"},{"key":"2023062410173984500_btab278-B9","doi-asserted-by":"crossref","first-page":"D303","DOI":"10.1093\/nar\/gkx1030","article-title":"MODOMICS: a database of RNA modification pathways. 2017 update","volume":"46","author":"Boccaletto","year":"2018","journal-title":"Nucleic Acids Research"},{"key":"2023062410173984500_btab278-B10","doi-asserted-by":"crossref","first-page":"e41","DOI":"10.1093\/nar\/gkz074","article-title":"WHISTLE: a high-accuracy map of the human N6-methyladenosine (m6A) epitranscriptome predicted using a machine learning approach","volume":"47","author":"Chen","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023062410173984500_btab278-B11","doi-asserted-by":"crossref","first-page":"1676","DOI":"10.1093\/bib\/bbz112","article-title":"Comprehensive review and assessment of computational methods for predicting RNA post-transcriptional modification sites from RNA sequences","volume":"21","author":"Chen","year":"2020","journal-title":"Brief. Bioinform"},{"key":"2023062410173984500_btab278-B12","first-page":"1551","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Dauphin","year":"2017"},{"key":"2023062410173984500_btab278-B13","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1126\/science.aac5253","article-title":"RNA biochemistry. Transcriptome-wide distribution and function of RNA hydroxymethylcytosine","volume":"351","author":"Delatte","year":"2016","journal-title":"Science"},{"key":"2023062410173984500_btab278-B14","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1038\/nprot.2012.148","article-title":"Transcriptome-wide mapping of N6-methyladenosine by m6A-seq based on immunocapturing and massively parallel sequencing","volume":"8","author":"Dominissini","year":"2013","journal-title":"Nat. Protoc"},{"key":"2023062410173984500_btab278-B15","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1016\/j.bbrc.2016.05.124","article-title":"tRNA modification profiles of the fast-proliferating cancer cells","volume":"476","author":"Dong","year":"2016","journal-title":"Biochem. Biophys. Res. Commun"},{"key":"2023062410173984500_btab278-B16","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.canlet.2020.01.021","article-title":"Writers, readers and erasers of RNA modifications in cancer","volume":"474","author":"Esteve-Puig","year":"2020","journal-title":"Cancer Lett"},{"key":"2023062410173984500_btab278-B17","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2164-16-S4-S3","article-title":"A structure-based multiple-instance learning approach to predicting in vitro transcription factor-DNA interaction","volume":"16","author":"Gao","year":"2015","journal-title":"BMC Genomics"},{"key":"2023062410173984500_btab278-B18","doi-asserted-by":"crossref","first-page":"2097","DOI":"10.1093\/bioinformatics\/btx115","article-title":"Computational modeling of in vivo and in vitro protein-DNA interactions by multiple instance learning","volume":"33","author":"Gao","year":"2017","journal-title":"Bioinformatics"},{"key":"2023062410173984500_btab278-B19","doi-asserted-by":"crossref","first-page":"842","DOI":"10.3389\/fcell.2020.00842","article-title":"Epitranscriptomic N4-acetylcytidine profiling in CD4+ T cells of systemic lupus erythematosus","volume":"8","author":"Guo","year":"2020","journal-title":"Front. Cell Dev. Biol"},{"key":"2023062410173984500_btab278-B20","first-page":"3376","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018","author":"Ilse","year":"2018"},{"key":"2023062410173984500_btab278-B21","article-title":"Decoding the epitranscriptional landscape from native RNA sequences","author":"Jenjaroenpun","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023062410173984500_btab278-B22","doi-asserted-by":"crossref","first-page":"e1586","DOI":"10.1002\/wrna.1586","article-title":"A molecular-level perspective on the frequency, distribution, and consequences of messenger RNA modifications","volume":"11","author":"Jones","year":"2020","journal-title":"Wiley Interdiscip. Rev. RNA"},{"key":"2023062410173984500_btab278-B23","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1101\/gr.200535.115","article-title":"Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks","volume":"26","author":"Kelley","year":"2016","journal-title":"Genome Res"},{"key":"2023062410173984500_btab278-B24","volume-title":"Explainable AI: Interpreting, Explaining and Visualizing Deep Learning","author":"Kindermans","year":"2019"},{"key":"2023062410173984500_btab278-B25","doi-asserted-by":"crossref","first-page":"i52","DOI":"10.1093\/bioinformatics\/btw252","article-title":"Classifying and segmenting microscopy images with deep multiple instance learning","volume":"32","author":"Kraus","year":"2016","journal-title":"Bioinformatics"},{"key":"2023062410173984500_btab278-B26","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1038\/nmeth.4110","article-title":"Epitranscriptome sequencing technologies: decoding RNA modifications","volume":"14","author":"Li","year":"2017","journal-title":"Nat. Methods"},{"key":"2023062410173984500_btab278-B27","article-title":"Accurate detection of m6A RNA modifications in native RNA sequences","volume":"10","author":"Liu","year":"2019","journal-title":"Nat. Commun"},{"key":"2023062410173984500_btab278-B28","doi-asserted-by":"crossref","first-page":"1587","DOI":"10.1016\/j.csbj.2020.06.010","article-title":"Bioinformatics approaches for deciphering the epitranscriptome: recent progress and emerging topics","volume":"18","author":"Liu","year":"2020","journal-title":"Comput. Struct. Biotechnol. J"},{"key":"2023062410173984500_btab278-B29","doi-asserted-by":"crossref","first-page":"227","DOI":"10.3389\/fbioe.2020.00227","article-title":"iRNA5hmC: the first predictor to identify RNA 5-hydroxymethylcytosine modifications using machine learning","volume":"8","author":"Liu","year":"2020","journal-title":"Front. Bioeng. Biotechnol"},{"key":"2023062410173984500_btab278-B30","first-page":"570","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Maron","year":"1997"},{"key":"2023062410173984500_btab278-B31","doi-asserted-by":"crossref","first-page":"e1595","DOI":"10.1002\/wrna.1595","article-title":"Naturally occurring modified ribonucleosides","volume":"11","author":"McCown","year":"2020","journal-title":"Wiley Interdiscip. Rev. RNA"},{"key":"2023062410173984500_btab278-B32","doi-asserted-by":"crossref","first-page":"e110488","DOI":"10.1371\/journal.pone.0110488","article-title":"AdaBoost based multi-instance transfer learning for predicting proteome-wide interactions between Salmonella and human proteins","volume":"9","author":"Mei","year":"2014","journal-title":"PLoS One"},{"key":"2023062410173984500_btab278-B33","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1093\/bioinformatics\/btt171","article-title":"Exome-based analysis for RNA epigenome sequencing data","volume":"29","author":"Meng","year":"2013","journal-title":"Bioinformatics"},{"key":"2023062410173984500_btab278-B34","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1016\/j.brainres.2016.04.055","article-title":"5-hydroxymethylcytosine is detected in RNA from mouse brain tissues","volume":"1642","author":"Miao","year":"2016","journal-title":"Brain Res"},{"key":"2023062410173984500_btab278-B35","doi-asserted-by":"crossref","first-page":"1747","DOI":"10.1021\/acs.jproteome.5b00883","article-title":"Genome-wide functional annotation of human protein-coding splice variants using multiple instance learning","volume":"15","author":"Panwar","year":"2016","journal-title":"J. Proteome Res"},{"key":"2023062410173984500_btab278-B36","first-page":"53","volume-title":"ICML-2000 Workshop on Attribute-Value and Relational Learning","author":"Ram\u00f3n","year":"2000"},{"key":"2023062410173984500_btab278-B37","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1038\/s41586-020-2418-2","article-title":"Dynamic RNA acetylation revealed by quantitative cross-evolutionary mapping","volume":"583","author":"Sas-Chen","year":"2020","journal-title":"Nature"},{"key":"2023062410173984500_btab278-B38","first-page":"3145","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Shrikumar","year":"2017"},{"key":"2023062410173984500_btab278-B39","article-title":"Technical note on transcription factor motif discovery from importance scores (TF-MoDISco) version 0.5.6.5","author":"Shrikumar","year":"2018","journal-title":"ArXiv"},{"key":"2023062410173984500_btab278-B40","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1038\/s41590-020-0650-4","article-title":"The RNA modification N6-methyladenosine as a novel regulator of the immune system","volume":"21","author":"Shulman","year":"2020","journal-title":"Nat. Immunol"},{"key":"2023062410173984500_btab278-B41","article-title":"Deep inside convolutional networks: visualising image classification models and saliency maps","author":"Simonyan","year":"2014","journal-title":"CoRR"},{"key":"2023062410173984500_btab278-B42","doi-asserted-by":"crossref","first-page":"3528","DOI":"10.1093\/bioinformatics\/btaa178","article-title":"m7GHub: deciphering the location, regulation and pathogenesis of internal mRNA N7-methylguanosine (m7G) sites in human","volume":"36","author":"Song","year":"2020","journal-title":"Bioinformatics"},{"key":"2023062410173984500_btab278-B43","volume-title":"Proc. of Advances in Neural Information Processing Systems","author":"Sotoudeh","year":"2019"},{"key":"2023062410173984500_btab278-B44","first-page":"5109","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Sundararajan","year":"2017"},{"key":"2023062410173984500_btab278-B45","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1109\/TCBB.2014.2323058","article-title":"Genome-Wide protein function prediction through multi-instance multi-label learning","volume":"11","author":"Wu","year":"2014","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"2023062410173984500_btab278-B46","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1038\/s41580-019-0168-5","article-title":"Reading, writing and erasing mRNA methylation","volume":"20","author":"Zaccara","year":"2019","journal-title":"Nat. Rev. Mol. Cell Biol"},{"key":"2023062410173984500_btab278-B47","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1016\/j.molcel.2019.03.036","article-title":"Transcriptome-wide mapping of internal N7-methylguanosine methylome in mammalian mRNA","volume":"74","author":"Zhang","year":"2019","journal-title":"Mol. Cell"},{"key":"2023062410173984500_btab278-B48","doi-asserted-by":"crossref","first-page":"8484","DOI":"10.1038\/s41598-019-44966-x","article-title":"Modeling in-vivo protein-DNA binding by combining multiple-instance learning with a hybrid deep neural network","volume":"9","author":"Zhang","year":"2019","journal-title":"Sci. Rep"},{"key":"2023062410173984500_btab278-B49","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TCBB.2018.2864203","article-title":"Weakly-supervised convolutional neural network architecture for predicting protein-DNA binding","volume":"17","author":"Zhang","year":"2020","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"2023062410173984500_btab278-B50","doi-asserted-by":"crossref","first-page":"11112","DOI":"10.1038\/s41598-019-47594-7","article-title":"PACES: prediction of N4-acetylcytidine (ac4C) modification sites in mRNA","volume":"9","author":"Zhao","year":"2019","journal-title":"Sci. Rep"},{"key":"2023062410173984500_btab278-B51","doi-asserted-by":"crossref","first-page":"e91","DOI":"10.1093\/nar\/gkw104","article-title":"SRAMP: prediction of mammalian N6-methyladenosine (m6A) sites based on sequence-derived features","volume":"44","author":"Zhou","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023062410173984500_btab278-B52","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1093\/nsr\/nwx106","article-title":"A brief introduction to weakly supervised learning","volume":"5","author":"Zhou","year":"2018","journal-title":"Natl. Sci. Rev"},{"key":"2023062410173984500_btab278-B53","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1261\/rna.069112.118","article-title":"Gene2vec: gene subsequence embedding for prediction of mammalian N6-methyladenosine sites from mRNA","volume":"25","author":"Zou","year":"2019","journal-title":"RNA"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/Supplement_1\/i222\/50694180\/btab278.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/Supplement_1\/i222\/50694180\/btab278.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T07:21:00Z","timestamp":1724916060000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/Supplement_1\/i222\/6319681"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,1]]},"references-count":53,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2021,8,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab278","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,7,1]]},"published":{"date-parts":[[2021,7,1]]}}}