{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:42:37Z","timestamp":1770331357238,"version":"3.49.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"DOI":"10.1186\/s13040-025-00517-x","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T14:46:22Z","timestamp":1768833982000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning based prediction of RNA 5hmC modifications using composite feature representations and comparative benchmarking with transformer models"],"prefix":"10.1186","volume":"19","author":[{"given":"Muhammad","family":"Attique","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaser Daanial","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fahad","family":"Alturise","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tamim","family":"Alkhalifah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"517_CR1","doi-asserted-by":"crossref","unstructured":"Zaccara S, Ries RJ, Jaffrey SR. Reading, writing and erasing mRNA methylation. Nat Rev Mol Cell Biol. 2019;20.","DOI":"10.1038\/s41580-019-0168-5"},{"key":"517_CR2","doi-asserted-by":"crossref","unstructured":"Williams GD, Gokhale NS, Horner SM. Regulation of viral infection by the RNA modification N6-methyladenosine. Annu Rev Virol. 2019;6.","DOI":"10.1146\/annurev-virology-092818-015559"},{"key":"517_CR3","doi-asserted-by":"crossref","unstructured":"Wibowo AS, Tayara H, Chong KT. XGB5hmC: identifier based on XGB model for RNA 5-hydroxymethylcytosine detection. Chemom Intell Lab Syst. 2023;238.","DOI":"10.1016\/j.chemolab.2023.104847"},{"key":"517_CR4","doi-asserted-by":"crossref","unstructured":"Miao Z, Xin N, Wei B, et al. 5-hydroxymethylcytosine is detected in RNA from mouse brain tissues. Brain Res. 2016, 1642.","DOI":"10.1016\/j.brainres.2016.04.055"},{"key":"517_CR5","doi-asserted-by":"crossref","unstructured":"Fu L, Guerrero CR, Zhong N, et al. Tet-mediated formation of 5-hydroxymethylcytosine in RNA. J Am Chem Soc. 2014;136.","DOI":"10.1021\/ja505305z"},{"key":"517_CR6","doi-asserted-by":"crossref","unstructured":"Delatte B, Wang F, Ngoc LV, et al. Transcriptome-wide distribution and function of RNA hydroxymethylcytosine. Science. 2016;351.","DOI":"10.1126\/science.aac5253"},{"key":"517_CR7","doi-asserted-by":"crossref","unstructured":"Jonkhout N, Tran J, Smith MA, et al. The RNA modification landscape in human disease. RNA. 2017;23.","DOI":"10.1261\/rna.063503.117"},{"key":"517_CR8","doi-asserted-by":"crossref","unstructured":"Khan SA, Khan YD, Ahmad S, et al. N-MyristoylG-PseAAC: sequence-based prediction of N-myristoyl glycine sites in proteins by integration of PseAAC and statistical moments. Lett Org Chem. 2019;16:226\u201334.","DOI":"10.2174\/1570178616666181217153958"},{"key":"517_CR9","doi-asserted-by":"crossref","unstructured":"Malebary SJ, Khan YD. Identification of antimicrobial peptides using Chou\u2019s 5 step rule. Comput Mater Contin. 2021;67.","DOI":"10.32604\/cmc.2021.015041"},{"key":"517_CR10","doi-asserted-by":"crossref","unstructured":"Liu Y, Chen D, Su R, et al. iRNA5hmc: the first predictor to identify RNA 5-hydroxymethylcytosine modifications using machine learning. Front Bioeng Biotechnol. 2020;8.","DOI":"10.3389\/fbioe.2020.00227"},{"key":"517_CR11","doi-asserted-by":"crossref","unstructured":"Ahmed S, Hossain Z, Uddin M, et al. Accurate prediction of RNA 5-hydroxymethylcytosine modification by utilizing novel position-specific gapped k-mer descriptors. Comput Struct Biotechnol J. 2020;18.","DOI":"10.1016\/j.csbj.2020.10.032"},{"key":"517_CR12","doi-asserted-by":"crossref","unstructured":"Ali SD, Kim JH, Tayara H, et al. Prediction of RNA 5-hydroxymethylcytosine modifications using deep learning. IEEE Access. 2021;9.","DOI":"10.1109\/ACCESS.2021.3049146"},{"key":"517_CR13","doi-asserted-by":"crossref","unstructured":"Liu HY, Du PF. i5hmCVec: identifying 5-hydroxymethylcytosine sites of Drosophila RNA using sequence feature embeddings. Front Genet. 2022;13.","DOI":"10.3389\/fgene.2022.896925"},{"key":"517_CR14","first-page":"1","volume":"14","author":"S Khan","year":"2024","unstructured":"Khan S, Uddin I, Khan M, et al. Sequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modification. Sci Rep. 2024;14:1\u201312.","journal-title":"Sci Rep"},{"key":"517_CR15","doi-asserted-by":"crossref","unstructured":"Zhang S, Shi H. iR5hmcsc: identifying RNA 5-hydroxymethylcytosine with multiple features based on stacking learning. Comput Biol Chem. 2021;95.","DOI":"10.1016\/j.compbiolchem.2021.107583"},{"key":"517_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bib\/bbac341","volume":"23","author":"H Shi","year":"2022","unstructured":"Shi H, Zhang S, Li X. R5hmCFDV: computational identification of RNA 5-hydroxymethylcytosine based on deep feature fusion and deep voting. Brief Bioinform. 2022;23:1\u201313.","journal-title":"Brief Bioinform"},{"key":"517_CR17","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1093\/bioinformatics\/btq003","volume":"26","author":"Y Huang","year":"2010","unstructured":"Huang Y, Niu B, Gao Y, et al. CD-HIT suite: a web server for clustering and comparing biological sequences. Bioinformatics. 2010;26:680\u201382.","journal-title":"Bioinformatics"},{"key":"517_CR18","doi-asserted-by":"crossref","unstructured":"Lan J, Rajan N, Bizet M, et al. Functional role of Tet-mediated RNA hydroxymethylcytosine in mouse ES cells and during differentiation. Nat Commun. 2020;11.","DOI":"10.1038\/s41467-020-18729-6"},{"key":"517_CR19","doi-asserted-by":"crossref","unstructured":"Shahid M, Ilyas M, Hussain W, et al. ORI-Deep: improving the accuracy for predicting origin of replication sites by using a blend of features and long short-term memory network. Brief Bioinform. 2022;23.","DOI":"10.1093\/bib\/bbac001"},{"key":"517_CR20","doi-asserted-by":"crossref","unstructured":"Alghamdi W, Alzahrani E, Ullah MZ, et al. 4mC-RF: improving the prediction of 4mC sites using composition and position relative features and statistical moment. Anal Biochem. 2021;633.","DOI":"10.1016\/j.ab.2021.114385"},{"key":"517_CR21","doi-asserted-by":"publisher","first-page":"68788","DOI":"10.1109\/ACCESS.2021.3076448","volume":"9","author":"SJ Malebary","year":"2021","unstructured":"Malebary SJ, Khan R, Khan YD. ProtoPred: advancing oncological research through identification of proto-oncogene proteins. IEEE Access. 2021;9:68788\u201397.","journal-title":"IEEE Access"},{"key":"517_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-15533-8","volume":"12","author":"AA Shah","year":"2022","unstructured":"Shah AA, Abid H, Malik M, et al. Machine learning techniques for identification of carcinogenic mutations, which cause breast adenocarcinoma. Sci Rep. 2022;12:1\u201315.","journal-title":"Sci Rep"},{"key":"517_CR23","first-page":"215","volume":"71","author":"TI Baig","year":"2022","unstructured":"Baig TI, Khan YD, Alam TM, et al. Ilipo-pseaac: identification of lipoylation sites using statistical moments and general pseaac. Comput Mater Contin. 2022;71:215\u201330.","journal-title":"Comput Mater Contin"},{"key":"517_CR24","doi-asserted-by":"crossref","unstructured":"Attique M, Farooq MS, Khelifi A, et al. Prediction of therapeutic peptides using machine learning: computational models, datasets, and feature encodings. IEEE Access. 2020;8.","DOI":"10.1109\/ACCESS.2020.3015792"},{"key":"517_CR25","doi-asserted-by":"crossref","unstructured":"Alghamdi W, Attique M, Alzahrani E, et al. Lbcepred: a machine learning model to predict linear B-cell epitopes. Brief Bioinform. 2022;bbac035.","DOI":"10.1093\/bib\/bbac035"},{"key":"517_CR26","doi-asserted-by":"crossref","unstructured":"Ahmed S, Arif M, Kabir M, et al. PredAoDP: accurate identification of antioxidant proteins by fusing different descriptors based on evolutionary information with support vector machine. Chemom Intell Lab Syst. 2022;104623.","DOI":"10.1016\/j.chemolab.2022.104623"},{"key":"517_CR27","doi-asserted-by":"publisher","first-page":"536","DOI":"10.2174\/1389202921999200831142629","volume":"21","author":"MK Mahmood","year":"2020","unstructured":"Mahmood MK, Ehsan A, Khan YD, et al. iHyd-LysSite (EPSV): identifying hydroxylysine sites in protein using statistical formulation by extracting enhanced position and sequence variant feature technique. Curr Genomics. 2020;21:536\u201345.","journal-title":"Curr Genomics"},{"key":"517_CR28","doi-asserted-by":"crossref","unstructured":"Hussain W, Rasool N, Khan YD. Insights into machine learning-based approaches for virtual screening in drug discovery: existing strategies and streamlining through FP-CADD. Curr Drug Discov Technol. 2020;17.","DOI":"10.2174\/1570163817666200806165934"},{"key":"517_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/5483115","volume":"2022","author":"O Barukab","year":"2022","unstructured":"Barukab O, Khan YD, Khan SA, et al. Dnapred_Prot: identification of DNA-binding proteins using composition- and position-based features. Appl Bionics Biomech. 2022;2022:1\u201317.","journal-title":"Appl Bionics Biomech"},{"key":"517_CR30","doi-asserted-by":"crossref","unstructured":"Hu MK. Visual pattern recognition by moment invariants. IRE Trans Inf Theory. 1962;8.","DOI":"10.1109\/TIT.1962.1057692"},{"key":"517_CR31","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhao P, Li C, et al. ILearnPlus: a comprehensive and automated machine-learning platform for nucleic acid and protein sequence analysis, prediction and visualization. Nucleic Acids Res. 2021;49.","DOI":"10.1093\/nar\/gkab122"},{"key":"517_CR32","doi-asserted-by":"crossref","unstructured":"Cursons J, Pillman KA, Scheer KG, et al. Combinatorial targeting by MicroRNAs co-ordinates post-transcriptional control of EMT. Cell Syst. 2018;7.","DOI":"10.1016\/j.cels.2018.05.019"},{"key":"517_CR33","doi-asserted-by":"crossref","unstructured":"He W, Jia C, Zou Q. 4mCPred: machine learning methods for DNA N 4 -methylcytosine sites prediction. Bioinformatics. 2019;35.","DOI":"10.1093\/bioinformatics\/bty668"},{"key":"517_CR34","doi-asserted-by":"crossref","unstructured":"Zhang X, Wang S, Xie L, et al. PseU-ST: a new stacked ensemble-learning method for identifying RNA pseudouridine sites. Front Genet. 2023;14.","DOI":"10.3389\/fgene.2023.1121694"},{"key":"517_CR35","doi-asserted-by":"crossref","unstructured":"Attique M, Alkhalifah T, Alturise F, et al. DeepBCE: evaluation of deep learning models for identification of immunogenic B-cell epitopes. Comput Biol Chem. 2023;104.","DOI":"10.1016\/j.compbiolchem.2023.107874"},{"key":"517_CR36","doi-asserted-by":"crossref","unstructured":"Malebary SJ, Khan YD. Evaluating machine learning methodologies for identification of cancer driver genes. Sci Rep. 2021;11.","DOI":"10.1038\/s41598-021-91656-8"},{"key":"517_CR37","doi-asserted-by":"crossref","unstructured":"Almagrabi AO, Khan YD, Khan SA. iPhosD-PseAAC: identification of phosphoaspartate sites in proteins using statistical moments and PseAAC. Biocell. 2021;45.","DOI":"10.32604\/biocell.2021.013770"},{"key":"517_CR38","doi-asserted-by":"crossref","unstructured":"Naseer S, Ali RF, Khan YD, et al. iGluK-Deep: computational identification of lysine glutarylation sites using deep neural networks with general pseudo amino acid compositions. J Biomol Struct Dyn. 2021.","DOI":"10.1080\/07391102.2021.1962738"},{"key":"517_CR39","doi-asserted-by":"publisher","first-page":"700","DOI":"10.2174\/2212392XMTEzpMTE6y","volume":"16","author":"M Awais","year":"2021","unstructured":"Awais M, Hussain W, Rasool N, et al. iTSP-PseAAC: identifying tumor suppressor proteins by using fully connected neural network and PseAAC. Curr Bioinform. 2021;16:700\u201309.","journal-title":"Curr Bioinform"},{"key":"517_CR40","doi-asserted-by":"crossref","unstructured":"Naseer S, Ali RF, Fati SM, et al. Computational identification of 4-carboxyglutamate sites to supplement physiological studies using deep learning. Sci Rep. 2022;12.","DOI":"10.1038\/s41598-021-03895-4"},{"key":"517_CR41","doi-asserted-by":"crossref","unstructured":"Zhao Y, Liu Y. OCLSTM: optimized convolutional and long short-term memory neural network model for protein secondary structure prediction. PLoS One. 2021;16.","DOI":"10.1371\/journal.pone.0245982"},{"key":"517_CR42","doi-asserted-by":"crossref","unstructured":"Shen Z, Bao W, Huang DS. Recurrent neural network for predicting transcription factor binding sites. Sci Rep. 2018;8.","DOI":"10.1038\/s41598-018-33321-1"},{"key":"517_CR43","volume-title":"Proc. SSST, 2014 - 8th work. Syntax. Semant. Struct. Stat. Transl","author":"K Cho","year":"2014","unstructured":"Cho K, van Merri\u00ebnboer B, Bahdanau D, et al. On the properties of neural machine translation: encoder-decoder approaches. In: Proc. SSST, 2014 - 8th Work. Syntax. Semant. Struct. Stat. Transl. 2014."},{"key":"517_CR44","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9:1735\u201380.","journal-title":"Neural Comput"},{"key":"517_CR45","doi-asserted-by":"publisher","first-page":"e12400","DOI":"10.1111\/exsy.12400","volume":"36","author":"A Khamparia","year":"2019","unstructured":"Khamparia A, Singh KM. A systematic review on deep learning architectures and applications. Expert Syst. 2019;36:e12400.","journal-title":"Expert Syst"},{"key":"517_CR46","first-page":"56","volume":"9","author":"B Yue","year":"2018","unstructured":"Yue B, Fu J, Liang J. Residual recurrent neural networks for learning sequential representations. Inf. 2018;9:56.","journal-title":"Inf"},{"key":"517_CR47","doi-asserted-by":"crossref","unstructured":"Reza Rezvan M, Ghanbari Sorkhi A, Pirgazi J, et al. AdvanceSplice: integrating N-gram one-hot encoding and ensemble modeling for enhanced accuracy. Biomed. Signal Process. Control. 2024;92.","DOI":"10.1016\/j.bspc.2024.106017"},{"key":"517_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-025-60872-5","volume":"16","author":"RJ Peni\u0107","year":"2025","unstructured":"Peni\u0107 RJ, Vla\u0161i\u0107 T, Huber RG, et al. RiNALMo: general-purpose RNA language models can generalize well on structure prediction tasks. Nat Commun. 2025;16:1\u201315.","journal-title":"Nat Commun"},{"key":"517_CR49","unstructured":"Zhou Z, Ji Y, Li W, et al. DNABERT-2: efficient foundation model and benchmark for multi-species genome. In: 12th Int. Conf. Learn. Represent. ICLR 2024. 2023."}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13040-025-00517-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-025-00517-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-025-00517-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:02:01Z","timestamp":1770289321000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13040-025-00517-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["517"],"URL":"https:\/\/doi.org\/10.1186\/s13040-025-00517-x","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]},"assertion":[{"value":"7 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"15"}}