{"id":"https://openalex.org/W7124834579","doi":"https://doi.org/10.1186/s13040-025-00517-x","title":"Deep learning based prediction of RNA 5hmC modifications using composite feature representations and comparative benchmarking with transformer models","display_name":"Deep learning based prediction of RNA 5hmC modifications using composite feature representations and comparative benchmarking with transformer models","publication_year":2026,"publication_date":"2026-01-19","ids":{"openalex":"https://openalex.org/W7124834579","doi":"https://doi.org/10.1186/s13040-025-00517-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/41555424"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-025-00517-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00517-x","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13040-025-00517-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019971091","display_name":"Muhammad Attique","orcid":"https://orcid.org/0000-0001-8973-2993"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]},{"id":"https://openalex.org/I87482320","display_name":"University of Management and Technology","ror":"https://ror.org/0095xcq10","country_code":"PK","type":"education","lineage":["https://openalex.org/I87482320"]},{"id":"https://openalex.org/I99165933","display_name":"University of Gujrat","ror":"https://ror.org/01xe5fb92","country_code":"PK","type":"education","lineage":["https://openalex.org/I99165933"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Attique","raw_affiliation_strings":["Department of Computer Science, University of Management and Technology, Lahore, 54000, Pakistan","Department of Information Technology, University of Gujrat, Gujrat, 50700, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Management and Technology, Lahore, 54000, Pakistan","institution_ids":["https://openalex.org/I87482320"]},{"raw_affiliation_string":"Department of Information Technology, University of Gujrat, Gujrat, 50700, Pakistan","institution_ids":["https://openalex.org/I1323252656","https://openalex.org/I99165933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075858344","display_name":"Yaser Daanial Khan","orcid":"https://orcid.org/0000-0002-2482-275X"},"institutions":[{"id":"https://openalex.org/I87482320","display_name":"University of Management and Technology","ror":"https://ror.org/0095xcq10","country_code":"PK","type":"education","lineage":["https://openalex.org/I87482320"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Yaser Daanial Khan","raw_affiliation_strings":["Department of Computer Science, University of Management and Technology, Lahore, 54000, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Management and Technology, Lahore, 54000, Pakistan","institution_ids":["https://openalex.org/I87482320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088232762","display_name":"Fahad Alturise","orcid":"https://orcid.org/0000-0001-9176-7984"},"institutions":[{"id":"https://openalex.org/I156216236","display_name":"Qassim University","ror":"https://ror.org/01wsfe280","country_code":"SA","type":"education","lineage":["https://openalex.org/I156216236"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Fahad Alturise","raw_affiliation_strings":["Department of Cybersecurity, College of Computer, Qassim University, Buraydah, 51452, Saudi Arabia. falturise@qu.edu.sa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybersecurity, College of Computer, Qassim University, Buraydah, 51452, Saudi Arabia. falturise@qu.edu.sa","institution_ids":["https://openalex.org/I156216236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016603327","display_name":"Tamim Alkhalifah","orcid":"https://orcid.org/0000-0001-8407-2068"},"institutions":[{"id":"https://openalex.org/I156216236","display_name":"Qassim University","ror":"https://ror.org/01wsfe280","country_code":"SA","type":"education","lineage":["https://openalex.org/I156216236"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Tamim Alkhalifah","raw_affiliation_strings":["Department of Computer Engineering, College of Computer, Qassim University, Buraydah, 51452, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, College of Computer, Qassim University, Buraydah, 51452, Saudi Arabia","institution_ids":["https://openalex.org/I156216236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088232762"],"corresponding_institution_ids":["https://openalex.org/I156216236"],"apc_list":{"value":2490,"currency":"USD","value_usd":2490},"apc_paid":{"value":2490,"currency":"USD","value_usd":2490},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05037806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"1","first_page":"15","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.01119999960064888,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11482","display_name":"RNA modifications and cancer","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.70660001039505},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6301000118255615},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6223000288009644},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5418000221252441},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5285999774932861},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.4587000012397766},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4133000075817108}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.70660001039505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406999826431274},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6301000118255615},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5418000221252441},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4438999891281128},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.32600000500679016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13040-025-00517-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00517-x","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:41555424","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41555424","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData mining","raw_type":null},{"id":"pmh:oai:europepmc.org:11682285","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12874776","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:bf95ecfcc7ca40b4a101304d3c68f939","is_oa":true,"landing_page_url":"https://doaj.org/article/bf95ecfcc7ca40b4a101304d3c68f939","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Mining, Vol 19, Iss 1, Pp 1-25 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12874776","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12874776/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Min","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13040-025-00517-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00517-x","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1982704134","https://openalex.org/W2064675550","https://openalex.org/W2097606916","https://openalex.org/W2159498975","https://openalex.org/W2271549028","https://openalex.org/W2345143513","https://openalex.org/W2753767186","https://openalex.org/W2868772566","https://openalex.org/W2883534252","https://openalex.org/W2896262061","https://openalex.org/W2906411860","https://openalex.org/W2928389720","https://openalex.org/W2959403793","https://openalex.org/W2972933339","https://openalex.org/W3014996649","https://openalex.org/W3048350608","https://openalex.org/W3048439402","https://openalex.org/W3082441088","https://openalex.org/W3089695391","https://openalex.org/W3098699793","https://openalex.org/W3119855908","https://openalex.org/W3127336123","https://openalex.org/W3134163647","https://openalex.org/W3134539395","https://openalex.org/W3159663509","https://openalex.org/W3169622143","https://openalex.org/W3193542455","https://openalex.org/W3200048961","https://openalex.org/W3203395656","https://openalex.org/W4205765055","https://openalex.org/W4206110562","https://openalex.org/W4206129384","https://openalex.org/W4210459809","https://openalex.org/W4224130789","https://openalex.org/W4225315146","https://openalex.org/W4240121760","https://openalex.org/W4285807029","https://openalex.org/W4312881411","https://openalex.org/W4317388440","https://openalex.org/W4366753183","https://openalex.org/W4368363773","https://openalex.org/W4390506881","https://openalex.org/W4391906315","https://openalex.org/W4411886797"],"related_works":[],"abstract_inverted_index":{"RNA":[0,87,201],"5-hydroxymethylcytosine":[1],"(5hmC)":[2],"post-transcriptional":[3],"modification":[4],"plays":[5],"an":[6,184],"important":[7],"role":[8],"in":[9,35],"the":[10,39,151,172],"regulation":[11],"of":[12,21,42,86,121,153,157,200],"gene":[13],"expression,":[14],"its":[15,105],"stability":[16],"and":[17,50,60,83,119,135,155,170,186],"evolution.":[18],"These":[19],"kinds":[20],"modifications":[22],"emphasizes":[23],"to":[24,56,166,178,193],"understand":[25],"their":[26],"further":[27],"biological":[28],"impacts.":[29],"Although":[30],"several":[31],"sequencing":[32],"technologies":[33],"supports":[34],"biochemical":[36],"experiments":[37],"for":[38,197],"precise":[40],"determination":[41],"5hmC":[43,202],"modifications,":[44],"these":[45],"experimental":[46],"identifications":[47],"are":[48],"laborious":[49],"costly;":[51],"therefore,":[52],"it":[53],"is":[54,71,96],"obvious":[55],"prioritise":[57],"some":[58],"proper":[59],"effective":[61,185],"computational":[62,188],"support.":[63],"In":[64],"this":[65],"work,":[66],"we":[67],"introduce":[68],"hm5C-DeepPred,":[69],"which":[70],"a":[72,99],"deep":[73],"learning-based":[74],"model":[75,95,179],"that":[76,142,175,190],"incorporates":[77],"composite":[78],"features":[79],"including":[80],"positional,":[81],"relational":[82],"configurational":[84],"properties":[85],"sequences":[88],"using":[89],"moment":[90],"based":[91],"characteristic":[92],"features.":[93],"The":[94,117],"predicated":[97],"on":[98,147],"highly-tuned":[100],"convolution":[101],"neural":[102],"network":[103],"as":[104,113],"core":[106],"predictor,":[107],"complemented":[108],"by":[109,125],"fine-tuned":[110],"transformer":[111],"models":[112],"stronger":[114],"comparative":[115],"baselines.":[116],"generalizability":[118],"robustness":[120],"hm5C-DeepPred":[122,143,182],"were":[123],"verified":[124],"10-fold":[126],"cross-validation,":[127],"statistical":[128],"significance":[129],"test,":[130],"internal":[131],"independent":[132],"validation":[133],"set":[134],"cross-species":[136],"external":[137],"testing.":[138],"Our":[139],"results":[140],"showed":[141],"outperformed":[144],"other":[145],"predictors":[146],"those":[148],"benchmarks,":[149],"having":[150],"accuracy":[152],"93.34%":[154],"MCC":[156],"0.8942,":[158],"respectively.":[159],"We":[160],"also":[161],"used":[162],"explainable":[163],"AI":[164],"techniques":[165],"interpret":[167],"feature":[168],"contributions":[169],"pinpoint":[171],"sequence":[173],"elements":[174],"contributed":[176],"most":[177],"decisions.":[180],"Hence,":[181],"presents":[183],"reliable":[187],"tool":[189],"has":[191],"potential":[192],"be":[194],"highly":[195],"reproducible":[196],"large-scale":[198],"analysis":[199],"modifications.":[203]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2026-01-20T00:00:00"}