{"id":"https://openalex.org/W4389314672","doi":"https://doi.org/10.1145/3627377.3627415","title":"PB_DBP: Identifying DNA-binding proteins using ProBert_BiLSTM model","display_name":"PB_DBP: Identifying DNA-binding proteins using ProBert_BiLSTM model","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4389314672","doi":"https://doi.org/10.1145/3627377.3627415"},"language":"en","primary_location":{"id":"doi:10.1145/3627377.3627415","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627377.3627415","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627377.3627415","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 6th International Conference on Big Data Technologies","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3627377.3627415","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056042882","display_name":"Jinfeng Li","orcid":"https://orcid.org/0009-0003-2271-7803"},"institutions":[{"id":"https://openalex.org/I130541836","display_name":"Beijing Institute of Petrochemical Technology","ror":"https://ror.org/025s55q11","country_code":"CN","type":"education","lineage":["https://openalex.org/I130541836"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfeng Li","raw_affiliation_strings":["Beijing Institute of Petrochemical Technology, China"],"raw_orcid":"https://orcid.org/0009-0003-2271-7803","affiliations":[{"raw_affiliation_string":"Beijing Institute of Petrochemical Technology, China","institution_ids":["https://openalex.org/I130541836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735898","display_name":"Shun Zhang","orcid":"https://orcid.org/0009-0006-1967-4445"},"institutions":[{"id":"https://openalex.org/I130541836","display_name":"Beijing Institute of Petrochemical Technology","ror":"https://ror.org/025s55q11","country_code":"CN","type":"education","lineage":["https://openalex.org/I130541836"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Zhang","raw_affiliation_strings":["Beijing Institute of Petrochemical Technology, China"],"raw_orcid":"https://orcid.org/0009-0006-1967-4445","affiliations":[{"raw_affiliation_string":"Beijing Institute of Petrochemical Technology, China","institution_ids":["https://openalex.org/I130541836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004026597","display_name":"Chun Fang","orcid":"https://orcid.org/0000-0002-0161-0412"},"institutions":[{"id":"https://openalex.org/I130541836","display_name":"Beijing Institute of Petrochemical Technology","ror":"https://ror.org/025s55q11","country_code":"CN","type":"education","lineage":["https://openalex.org/I130541836"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Fang","raw_affiliation_strings":["Beijing Institute of Petrochemical Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-0161-0412","affiliations":[{"raw_affiliation_string":"Beijing Institute of Petrochemical Technology, China","institution_ids":["https://openalex.org/I130541836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130541836"],"apc_list":null,"apc_paid":null,"fwci":4.0243,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93876294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"242","last_page":"246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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":0.9970999956130981,"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":0.569972813129425},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.5319865942001343},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5290840268135071},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5254339575767517},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.49855494499206543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4902244210243225},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4742771089076996},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.460561603307724},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.45279842615127563},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44645795226097107},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4211553931236267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3982519507408142},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3596746623516083},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.35957539081573486},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3219798505306244},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24770337343215942},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.18226882815361023},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14379048347473145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.569972813129425},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.5319865942001343},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5290840268135071},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5254339575767517},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.49855494499206543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4902244210243225},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4742771089076996},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.460561603307724},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.45279842615127563},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44645795226097107},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4211553931236267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3982519507408142},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3596746623516083},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.35957539081573486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3219798505306244},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24770337343215942},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.18226882815361023},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14379048347473145},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627377.3627415","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627377.3627415","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627377.3627415","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 6th International Conference on Big Data Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627377.3627415","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627377.3627415","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627377.3627415","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 6th International Conference on Big Data Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.49000000953674316,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G6113355497","display_name":null,"funder_award_id":"BIPTCSF-21","funder_id":"https://openalex.org/F4320330914","funder_display_name":"Beijing Institute of Petrochemical Technology"},{"id":"https://openalex.org/G7177796324","display_name":null,"funder_award_id":"61602280","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"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320330914","display_name":"Beijing Institute of Petrochemical Technology","ror":"https://ror.org/025s55q11"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389314672.pdf","grobid_xml":"https://content.openalex.org/works/W4389314672.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2055043387","https://openalex.org/W2060259273","https://openalex.org/W2064675550","https://openalex.org/W2139086914","https://openalex.org/W2150381702","https://openalex.org/W2777094228","https://openalex.org/W2896457183","https://openalex.org/W3177500196","https://openalex.org/W4205773061","https://openalex.org/W4400064739","https://openalex.org/W6959643953"],"related_works":["https://openalex.org/W2053028024","https://openalex.org/W2011602722","https://openalex.org/W2024383575","https://openalex.org/W1965617697","https://openalex.org/W2072002764","https://openalex.org/W2012033675","https://openalex.org/W4237340100","https://openalex.org/W2073512219","https://openalex.org/W2033162017","https://openalex.org/W1986026327"],"abstract_inverted_index":{"DNA-binding":[0],"proteins":[1,6,53],"are":[2,80],"a":[3,96,111,120],"class":[4],"of":[5,29,34,52,77,88,123,140,153],"that":[7],"can":[8],"bind":[9],"to":[10,102,136],"specific":[11],"nucleotide":[12],"sequences":[13,63],"in":[14,23,38,60,128],"the":[15,25,32,39,49,57,65,73,78,83,89,104,138,145],"DNA":[16],"sequence,":[17],"and":[18,27,36,64,75,86,142],"they":[19],"play":[20],"essential":[21],"roles":[22],"maintaining":[24],"structure":[26],"function":[28],"DNA,":[30],"regulating":[31],"expression":[33],"genes,":[35],"participating":[37],"cell":[40],"cycle.":[41],"Traditional":[42],"prediction":[43,79,98],"methods":[44],"usually":[45],"focus":[46],"on":[47,144],"extracting":[48],"physicochemical":[50],"characteristics":[51],"from":[54],"sequences,":[55,117],"ignoring":[56],"information":[58,67],"inherent":[59],"amino":[61,69],"acid":[62,70],"positional":[66],"between":[68],"sequences.":[71],"Moreover,":[72],"accuracy":[74],"reliability":[76],"limited":[81],"by":[82],"small":[84],"size":[85],"noise":[87],"training":[90],"data":[91,147],"sets.":[92],"This":[93],"study":[94],"introduces":[95],"new":[97],"method":[99,132],"called":[100],"PB_DBP":[101,108],"tackle":[103],"issues":[105],"mentioned":[106],"above.":[107],"combines":[109],"ProtBert,":[110],"pre-training":[112],"model":[113,121],"designed":[114],"for":[115],"protein":[116],"with":[118],"BiLSTM,":[119],"capable":[122],"effectively":[124],"capturing":[125],"long-term":[126],"dependencies":[127],"sequence":[129],"data.":[130],"Our":[131],"has":[133],"been":[134],"demonstrated":[135],"outperform":[137],"combination":[139],"CNN":[141],"LSTM":[143],"public":[146],"sets,":[148],"achieving":[149],"an":[150],"AUC":[151],"value":[152],"0.988.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}