{"id":"https://openalex.org/W4406260263","doi":"https://doi.org/10.1109/bibm62325.2024.10821845","title":"Prediction of single-stranded DNA binding proteins with protein language model","display_name":"Prediction of single-stranded DNA binding proteins with protein language model","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406260263","doi":"https://doi.org/10.1109/bibm62325.2024.10821845"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10821845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049405110","display_name":"Siwen Wu","orcid":"https://orcid.org/0000-0003-2393-4650"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siwen Wu","raw_affiliation_strings":["University of North Carolina at Charlotte,Department of Bioinformatics and Genomics,Charlotte,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Department of Bioinformatics and Genomics,Charlotte,USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019398608","display_name":"Jinbo Xu","orcid":"https://orcid.org/0000-0001-7111-4839"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinbo Xu","raw_affiliation_strings":["Toyota Technological Institute at Chicago,Chicago,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago,Chicago,USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103170888","display_name":"Jun\u2010tao Guo","orcid":"https://orcid.org/0000-0001-5949-8948"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-tao Guo","raw_affiliation_strings":["University of North Carolina at Charlotte,Department of Bioinformatics and Genomics,Charlotte,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Department of Bioinformatics and Genomics,Charlotte,USA","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9124,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88905443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"258","last_page":"263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9905999898910522,"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":0.9905999898910522,"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":0.9502000212669373,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9271000027656555,"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":0.5656729936599731},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.5247485637664795},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4052181839942932},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3016504645347595},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15796557068824768},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.14405789971351624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5656729936599731},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.5247485637664795},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4052181839942932},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3016504645347595},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15796557068824768},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.14405789971351624}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10821845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338440","display_name":"HORIZON EUROPE Health","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1876902280","https://openalex.org/W1892469892","https://openalex.org/W1986347357","https://openalex.org/W2001998124","https://openalex.org/W2010688088","https://openalex.org/W2011204918","https://openalex.org/W2016789453","https://openalex.org/W2058918675","https://openalex.org/W2079916408","https://openalex.org/W2103148772","https://openalex.org/W2103601429","https://openalex.org/W2130479394","https://openalex.org/W2156125289","https://openalex.org/W2166517610","https://openalex.org/W2167974691","https://openalex.org/W2561871078","https://openalex.org/W2625898396","https://openalex.org/W2883467144","https://openalex.org/W2946492269","https://openalex.org/W2963457143","https://openalex.org/W2984633739","https://openalex.org/W2988542995","https://openalex.org/W2996926654","https://openalex.org/W3087136401","https://openalex.org/W3129587589","https://openalex.org/W3146944767","https://openalex.org/W3177500196","https://openalex.org/W4205773061","https://openalex.org/W4229449348","https://openalex.org/W4293413552","https://openalex.org/W4309506674","https://openalex.org/W4309728499","https://openalex.org/W4315621825","https://openalex.org/W4327550249","https://openalex.org/W4364353366","https://openalex.org/W4391280974","https://openalex.org/W4392983286","https://openalex.org/W4399498119","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2078814861","https://openalex.org/W2527526854","https://openalex.org/W1976181487"],"abstract_inverted_index":{"Single-stranded":[0],"DNA":[1,23,74,85],"binding":[2,12,40,75,86,104,112],"proteins":[3,13,76,87,105,134],"(SSBs)":[4],"represent":[5],"one":[6],"important":[7,127],"type":[8],"of":[9,37,51,98],"nucleic":[10,38,110],"acid":[11,39,111],"and":[14,27,31,54,122,173,185,203],"are":[15,43,83,100],"crucial":[16],"for":[17,107,183,199,205],"many":[18],"cellular":[19],"functions,":[20],"such":[21],"as":[22,102],"replication,":[24],"transcriptional":[25],"regulation,":[26],"maintaining":[28],"genome":[29],"stability":[30],"integrity.":[32],"Compared":[33],"to":[34,46,69,143,197],"other":[35],"types":[36],"proteins,":[41,113],"SSBs":[42,53,71,99,132],"underexplored":[44],"due":[45],"a":[47,60,95,144,170,174,178,211],"relatively":[48],"small":[49],"number":[50,97],"annotated":[52],"experimentally":[55],"solved":[56],"SSB":[57],"structures.":[58],"Only":[59],"few":[61],"computational":[62],"approaches":[63],"have":[64],"been":[65],"developed":[66,150],"so":[67],"far":[68],"classify":[70],"from":[72,133,177],"double-stranded":[73],"(DSBs),":[77],"which":[78],"typically":[79],"assume":[80],"the":[81,151,160,200,206],"inputs":[82],"known":[84],"(DBPs).":[88],"However,":[89],"our":[90],"recent":[91],"study":[92],"reveals":[93],"that":[94,115,190],"large":[96],"predicted":[101],"RNA":[103],"(RBPs)":[106],"any":[108],"given":[109],"suggesting":[114],"SSB/DSB":[116,147,201],"classification":[117,124],"alone":[118],"is":[119,125],"not":[120],"enough":[121],"SSB/RBP":[123,153,207],"equally":[126],"in":[128,141],"accurately":[129],"predicting":[130],"novel":[131],"with":[135,155,210],"unknown":[136],"functions.":[137],"In":[138],"this":[139],"study,":[140],"addition":[142],"much":[145],"improved":[146],"classifier,":[148],"we":[149,168],"first":[152],"classifier":[154,202,208],"machine":[156,214],"learning":[157],"models.":[158],"Besides":[159],"widely":[161],"used":[162],"PSSM":[163],"(position":[164],"specific":[165],"scoring":[166],"matrix),":[167],"tested":[169],"structural":[171],"feature":[172,175],"extracted":[176],"protein":[179],"language":[180],"model":[181],"ESM2":[182,191],"training":[184],"testing.":[186],"Our":[187],"results":[188],"show":[189],"improves":[192],"prediction":[193],"accuracy":[194],"dramatically,":[195],"up":[196],"95%":[198],"92%":[204],"respectively":[209],"support":[212],"vector":[213],"(SVM)":[215],"approach.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}