{"id":"https://openalex.org/W7126070138","doi":"https://doi.org/10.1109/bibm66473.2025.11356243","title":"An Efficient and Accurate Method for DNA-Binding Protein Identification via Protein Language Models and Local Sparse Representation","display_name":"An Efficient and Accurate Method for DNA-Binding Protein Identification via Protein Language Models and Local Sparse Representation","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126070138","doi":"https://doi.org/10.1109/bibm66473.2025.11356243"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124151139","display_name":"Yifei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I74525822","display_name":"Hubei University of Technology","ror":"https://ror.org/02d3fj342","country_code":"CN","type":"education","lineage":["https://openalex.org/I74525822"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifei Wang","raw_affiliation_strings":["School of Computer Science, Hubei University of Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University of Technology,Wuhan,China","institution_ids":["https://openalex.org/I74525822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124236120","display_name":"Chengtong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I74525822","display_name":"Hubei University of Technology","ror":"https://ror.org/02d3fj342","country_code":"CN","type":"education","lineage":["https://openalex.org/I74525822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengtong Wang","raw_affiliation_strings":["School of Computer Science, Hubei University of Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University of Technology,Wuhan,China","institution_ids":["https://openalex.org/I74525822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124233770","display_name":"Ziheng Mei","orcid":null},"institutions":[{"id":"https://openalex.org/I74525822","display_name":"Hubei University of Technology","ror":"https://ror.org/02d3fj342","country_code":"CN","type":"education","lineage":["https://openalex.org/I74525822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziheng Mei","raw_affiliation_strings":["School of Computer Science, Hubei University of Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University of Technology,Wuhan,China","institution_ids":["https://openalex.org/I74525822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062162392","display_name":"Ting Cai","orcid":"https://orcid.org/0000-0003-0245-333X"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Cai","raw_affiliation_strings":["Hubei Provincial Key Laboratory of Green Intelligent Computing Power Network,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Hubei Provincial Key Laboratory of Green Intelligent Computing Power Network,Wuhan,China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124265033","display_name":"Yan Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100789","display_name":"Wuhan College","ror":"https://ror.org/01dashf18","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210100789"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yuan","raw_affiliation_strings":["School of Computer Science, Wenhua College,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wenhua College,Wuhan,China","institution_ids":["https://openalex.org/I4210100789"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017995706","display_name":"Chao Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I74525822","display_name":"Hubei University of Technology","ror":"https://ror.org/02d3fj342","country_code":"CN","type":"education","lineage":["https://openalex.org/I74525822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wei","raw_affiliation_strings":["School of Computer Science, Hubei University of Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University of Technology,Wuhan,China","institution_ids":["https://openalex.org/I74525822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124151139"],"corresponding_institution_ids":["https://openalex.org/I74525822"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65182579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7287","last_page":"7292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9929999709129333,"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":0.9929999709129333,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0010000000474974513,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.0008999999845400453,"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/classifier","display_name":"Classifier (UML)","score":0.6599000096321106},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5498999953269958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5336999893188477},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4860000014305115},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.420199990272522},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4196000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7131999731063843},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4519999921321869},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4002000093460083},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2770000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1268797520","display_name":null,"funder_award_id":"62302154","funder_id":"https://openalex.org/F4320320885","funder_display_name":"European Research Consortium for Informatics and Mathematics"},{"id":"https://openalex.org/G5870332028","display_name":null,"funder_award_id":"2024AFB882","funder_id":"https://openalex.org/F4320322186","funder_display_name":"Natural Science Foundation of Hubei Province"}],"funders":[{"id":"https://openalex.org/F4320320885","display_name":"European Research Consortium for Informatics and Mathematics","ror":"https://ror.org/055zrhj18"},{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1821507858","https://openalex.org/W2038163496","https://openalex.org/W2042714852","https://openalex.org/W2096223584","https://openalex.org/W2102945860","https://openalex.org/W2107340752","https://openalex.org/W2129812935","https://openalex.org/W2132109309","https://openalex.org/W2145957695","https://openalex.org/W2156125289","https://openalex.org/W2158714788","https://openalex.org/W2909686100","https://openalex.org/W3119371646","https://openalex.org/W3146944767","https://openalex.org/W3177828909","https://openalex.org/W4237331446","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"identification":[1],"of":[2],"DNA-binding":[3],"proteins":[4],"(DBPs)":[5],"is":[6],"crucial":[7],"for":[8,39,57,64,108],"understanding":[9],"various":[10],"biological":[11],"processes.":[12],"While":[13],"deep":[14],"learning":[15],"has":[16],"advanced":[17],"this":[18,30],"field,":[19],"many":[20],"methods":[21,146],"still":[22],"rely":[23],"on":[24,81,125],"complex,":[25],"hand-crafted":[26],"feature":[27,66,100],"engineering.":[28],"In":[29],"paper,":[31],"we":[32,70],"propose":[33],"a":[34,45,72,85,90,104,130],"novel":[35],"and":[36,117,129,150],"efficient":[37],"framework":[38,124],"DBP":[40],"prediction.":[41],"We":[42,121],"first":[43],"leverage":[44],"state-of-the-art":[46,142],"protein":[47,58],"language":[48],"model,":[49],"ESM-1b,":[50],"to":[51],"generate":[52],"fixed-length,":[53],"information-rich":[54],"vector":[55],"representations":[56],"sequences,":[59],"completely":[60],"bypassing":[61],"the":[62,82,99],"need":[63],"manual":[65],"design.":[67],"For":[68],"classification,":[69],"introduce":[71],"Local":[73],"Sparse":[74],"Representation-based":[75],"Classifier":[76],"(LSRC).":[77],"This":[78],"classifier":[79],"operates":[80],"assumption":[83],"that":[84,137],"protein's":[86],"representation":[87],"lies":[88],"in":[89,98,147],"low-dimensional":[91],"subspace":[92],"spanned":[93],"by":[94],"its":[95],"local":[96],"neighbors":[97],"space.":[101],"By":[102],"constructing":[103],"small,":[105],"adaptive":[106],"dictionary":[107],"each":[109],"test":[110],"sample,":[111],"LSRC":[112],"achieves":[113,140],"both":[114],"high":[115],"accuracy":[116],"re-markable":[118],"computational":[119],"efficiency.":[120],"evaluated":[122],"our":[123,138],"two":[126],"benchmark":[127],"datasets":[128],"newly":[131],"constructed":[132],"dataset.":[133],"The":[134],"results":[135],"demonstrate":[136],"method":[139],"new":[141],"performance,":[143],"outperforming":[144],"existing":[145],"accuracy,":[148],"MCC.":[149],"other":[151],"metrics.":[152]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-30T00:00:00"}