{"id":"https://openalex.org/W3203692674","doi":"https://doi.org/10.3390/a14100283","title":"XGB4mcPred: Identification of DNA N4-Methylcytosine Sites in Multiple Species Based on an eXtreme Gradient Boosting Algorithm and DNA Sequence Information","display_name":"XGB4mcPred: Identification of DNA N4-Methylcytosine Sites in Multiple Species Based on an eXtreme Gradient Boosting Algorithm and DNA Sequence Information","publication_year":2021,"publication_date":"2021-09-29","ids":{"openalex":"https://openalex.org/W3203692674","doi":"https://doi.org/10.3390/a14100283","mag":"3203692674"},"language":"en","primary_location":{"id":"doi:10.3390/a14100283","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14100283","pdf_url":"https://www.mdpi.com/1999-4893/14/10/283/pdf?version=1632903809","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/14/10/283/pdf?version=1632903809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100411464","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0002-3113-5149"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":"https://orcid.org/0000-0002-3113-5149","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003528649","display_name":"Xi Lin","orcid":"https://orcid.org/0000-0001-8141-1482"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Lin","raw_affiliation_strings":["School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":"https://orcid.org/0000-0001-8141-1482","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101412171","display_name":"Rong Wang","orcid":"https://orcid.org/0000-0002-5368-1829"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Wang","raw_affiliation_strings":["School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101889672","display_name":"Kaiqi Fan","orcid":"https://orcid.org/0000-0001-7568-8557"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai-Qi Fan","raw_affiliation_strings":["School of Material and Chemical Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":"https://orcid.org/0000-0001-7568-8557","affiliations":[{"raw_affiliation_string":"School of Material and Chemical Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035358660","display_name":"Lijun Han","orcid":"https://orcid.org/0000-0002-1832-3057"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Jun Han","raw_affiliation_strings":["School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":"https://orcid.org/0000-0002-1832-3057","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062164377","display_name":"Zhaoyuan Ding","orcid":"https://orcid.org/0000-0003-0965-2446"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao-Yuan Ding","raw_affiliation_strings":["School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":"https://orcid.org/0000-0003-0965-2446","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100411464"],"corresponding_institution_ids":["https://openalex.org/I23171815"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.222,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49291648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":"10","first_page":"283","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9979000091552734,"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":0.9979000091552734,"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/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9853000044822693,"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":0.984000027179718,"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/computer-science","display_name":"Computer science","score":0.5572929382324219},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.547978401184082},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5461174845695496},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5383058786392212},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5235854387283325},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.45858192443847656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43132779002189636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4312480390071869},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41424453258514404},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.40100041031837463},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2300848662853241},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22420522570610046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1918586790561676},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0803520679473877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5572929382324219},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.547978401184082},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5461174845695496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5383058786392212},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5235854387283325},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.45858192443847656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43132779002189636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4312480390071869},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41424453258514404},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.40100041031837463},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2300848662853241},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22420522570610046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1918586790561676},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0803520679473877},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a14100283","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14100283","pdf_url":"https://www.mdpi.com/1999-4893/14/10/283/pdf?version=1632903809","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5615f0cb47c74781a007ecb08c0869da","is_oa":true,"landing_page_url":"https://doaj.org/article/5615f0cb47c74781a007ecb08c0869da","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":"Algorithms, Vol 14, Iss 10, p 283 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/14/10/283/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a14100283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms; Volume 14; Issue 10; Pages: 283","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a14100283","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14100283","pdf_url":"https://www.mdpi.com/1999-4893/14/10/283/pdf?version=1632903809","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G8240930226","display_name":null,"funder_award_id":"61402422","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3203692674.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1553103276","https://openalex.org/W1984783889","https://openalex.org/W1987735941","https://openalex.org/W2005458309","https://openalex.org/W2006419303","https://openalex.org/W2038636394","https://openalex.org/W2038722690","https://openalex.org/W2059188171","https://openalex.org/W2073199618","https://openalex.org/W2085492504","https://openalex.org/W2123032740","https://openalex.org/W2141818629","https://openalex.org/W2164052908","https://openalex.org/W2187089797","https://openalex.org/W2267357833","https://openalex.org/W2295598076","https://openalex.org/W2537227711","https://openalex.org/W2737592062","https://openalex.org/W2800742848","https://openalex.org/W2883534252","https://openalex.org/W2891420113","https://openalex.org/W2942801317","https://openalex.org/W2946682182","https://openalex.org/W2949348780","https://openalex.org/W2976262693","https://openalex.org/W3034527519","https://openalex.org/W3037668068"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147","https://openalex.org/W2039176012"],"abstract_inverted_index":{"DNA":[0,26,45,76,104],"N4-methylcytosine(4mC)":[1],"plays":[2],"an":[3,97],"important":[4],"role":[5],"in":[6,25,153,157,189],"numerous":[7],"biological":[8],"functions":[9],"and":[10,56,103,115,119,185,195,212,230],"is":[11,28,49,61,175],"a":[12,62,67,83,87,146,154,176],"mechanism":[13],"of":[14,21,75,92,121,134,161,210],"particular":[15],"epigenetic":[16],"importance.":[17],"Therefore,":[18,59],"accurate":[19],"identification":[20,54,91,159],"the":[22,32,73,90,110,122,131,135,140,158,162,196,242,249],"4mC":[23,46,77,93,124,168,183,202],"sites":[24,94,184,203],"sequences":[27,126,181,188],"necessary":[29],"to":[30,43,52,65,70,148,166,233,247],"understand":[31],"functional":[33],"mechanism.":[34],"Although":[35],"some":[36],"effective":[37],"calculation":[38],"tools":[39],"have":[40],"been":[41],"proposed":[42,82,222],"identifying":[44],"sites,":[47],"it":[48],"still":[50],"challenging":[51],"improve":[53],"accuracy":[55,160],"generalization":[57],"ability.":[58],"there":[60,174],"great":[63],"need":[64],"build":[66],"computational":[68],"tool":[69],"accurately":[71],"identify":[72,167],"position":[74],"sites.":[78,169,206],"Hence,":[79],"this":[80],"study":[81],"novel":[84],"predictor":[85,88,165,223,251],"XGB4mcPred,":[86],"for":[89,179],"trained":[95],"using":[96],"extreme":[98],"gradient":[99],"boosting":[100],"algorithm":[101,142],"(XGBoost)":[102],"sequence":[105],"information.":[106],"Firstly,":[107],"we":[108,245],"used":[109,144,246],"One-Hot":[111],"encoding":[112],"on":[113],"adjacent":[114],"spaced":[116],"nucleotides,":[117],"dinucleotides,":[118],"trinucleotides":[120],"original":[123],"site":[125,187],"as":[127,145],"feature":[128,136],"vectors.":[129],"Then,":[130],"importance":[132],"values":[133],"vectors":[137],"pre-trained":[138],"by":[139],"XGBoost":[141],"were":[143],"threshold":[147],"filter":[149],"redundant":[150],"features,":[151],"resulting":[152],"significant":[155],"improvement":[156],"constructed":[163],"XGB4mcPred":[164,224,250],"The":[170,207],"analysis":[171],"shows":[172],"that":[173,220],"clear":[177],"preference":[178],"nucleotide":[180],"between":[182],"non-4mC":[186,205],"six":[190,216],"datasets":[191],"from":[192,204,215],"multiple":[193],"species,":[194],"optimized":[197],"features":[198],"can":[199],"better":[200],"distinguish":[201],"experimental":[208],"results":[209],"cross-validation":[211],"independent":[213],"tests":[214],"different":[217],"species":[218],"show":[219],"our":[221],"significantly":[225],"outperformed":[226],"other":[227,238],"state-of-the-art":[228,239],"predictors":[229],"was":[231,252],"improved":[232],"varying":[234],"degrees":[235],"compared":[236],"with":[237],"predictors.":[240],"Additionally,":[241],"user-friendly":[243],"webserver":[244],"developed":[248],"made":[253],"freely":[254],"accessible.":[255]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2021-10-11T00:00:00"}
