{"id":"https://openalex.org/W4417224510","doi":"https://doi.org/10.1021/acs.jcim.5c02216","title":"Prompt-CBP: A Novel Prompt Learning-Based Model for Predicting Cross-Species Promoters","display_name":"Prompt-CBP: A Novel Prompt Learning-Based Model for Predicting Cross-Species Promoters","publication_year":2025,"publication_date":"2025-12-11","ids":{"openalex":"https://openalex.org/W4417224510","doi":"https://doi.org/10.1021/acs.jcim.5c02216","pmid":"https://pubmed.ncbi.nlm.nih.gov/41376239"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c02216","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02216","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1021/acs.jcim.5c02216","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054798085","display_name":"Xiao Liu","orcid":"https://orcid.org/0000-0002-7042-3880"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Liu","raw_affiliation_strings":["Chongqing University","School of Microelectronics and Communication Engineering"],"raw_orcid":"https://orcid.org/0000-0002-7042-3880","affiliations":[{"raw_affiliation_string":"Chongqing University","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"School of Microelectronics and Communication Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084686280","display_name":"Jiale Fu","orcid":"https://orcid.org/0000-0002-9596-5758"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Fu","raw_affiliation_strings":["Chongqing University","School of Microelectronics and Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"School of Microelectronics and Communication Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014432632","display_name":"Yunfeng Pan","orcid":"https://orcid.org/0000-0002-7863-8042"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfeng Pan","raw_affiliation_strings":["Chongqing University","School of Microelectronics and Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"School of Microelectronics and Communication Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054798085"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33950024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"65","issue":"24","first_page":"13435","last_page":"13446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9646000266075134,"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":0.9646000266075134,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.010499999858438969,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.005200000014156103,"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/promoter","display_name":"Promoter","score":0.7730000019073486},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.616100013256073},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5651999711990356},{"id":"https://openalex.org/keywords/conserved-sequence","display_name":"Conserved sequence","score":0.5378999710083008},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.39739999175071716},{"id":"https://openalex.org/keywords/tata-box","display_name":"TATA box","score":0.39100000262260437},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.38600000739097595},{"id":"https://openalex.org/keywords/promoter-activity","display_name":"Promoter activity","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.7730000019073486},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6438999772071838},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5651999711990356},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.5378999710083008},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4472000002861023},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4180000126361847},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C65888428","wikidata":"https://www.wikidata.org/wiki/Q1413955","display_name":"TATA box","level":5,"score":0.39100000262260437},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.38600000739097595},{"id":"https://openalex.org/C2775871807","wikidata":"https://www.wikidata.org/wiki/Q24963883","display_name":"Promoter activity","level":5,"score":0.37599998712539673},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3596000075340271},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3366999924182892},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.33660000562667847},{"id":"https://openalex.org/C54985914","wikidata":"https://www.wikidata.org/wiki/Q1295754","display_name":"Consensus sequence","level":4,"score":0.3294000029563904},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C128040838","wikidata":"https://www.wikidata.org/wiki/Q1810628","display_name":"Pseudorandom binary sequence","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.25110000371932983}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c02216","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02216","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:41376239","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41376239","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.5c02216","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02216","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6244561350","display_name":null,"funder_award_id":"CSTB2024NSCQ-MSX0129","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"}],"funders":[{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1944386267","https://openalex.org/W1991259976","https://openalex.org/W2050550887","https://openalex.org/W2101292724","https://openalex.org/W2111492198","https://openalex.org/W2126939295","https://openalex.org/W2132618831","https://openalex.org/W2148114118","https://openalex.org/W2151658462","https://openalex.org/W2155244199","https://openalex.org/W2169800536","https://openalex.org/W2746992081","https://openalex.org/W2754289562","https://openalex.org/W2896457183","https://openalex.org/W2900007277","https://openalex.org/W2908351833","https://openalex.org/W2963739921","https://openalex.org/W3119438769","https://openalex.org/W3157397027","https://openalex.org/W3185341429","https://openalex.org/W3205270560","https://openalex.org/W4220736664","https://openalex.org/W4221109414","https://openalex.org/W4287019748","https://openalex.org/W4287208373","https://openalex.org/W4287902301","https://openalex.org/W4288099568","https://openalex.org/W4291186635","https://openalex.org/W4297257598","https://openalex.org/W4297795751","https://openalex.org/W4300861907","https://openalex.org/W4382490702","https://openalex.org/W4383497774","https://openalex.org/W4385245566","https://openalex.org/W4389331567","https://openalex.org/W4392874548","https://openalex.org/W4406632986"],"related_works":[],"abstract_inverted_index":{"Promoter":[0],"sequences":[1,13],"across":[2,43,136],"species":[3],"exhibit":[4],"both":[5],"specificity":[6,10],"and":[7,36,131,154,178],"conservation.":[8],"The":[9,145,160],"of":[11,142],"promoter":[12,27,56,71,78,137,148,199],"typically":[14],"leads":[15],"to":[16,22,64,80,89,98,128,165,194],"lower":[17],"cross-species":[18,55],"prediction":[19,190],"performance":[20,191],"compared":[21,164],"within-species":[23],"prediction.":[24,57],"However,":[25],"conserved":[26,70,133],"motifs":[28],"such":[29],"as":[30],"the":[31,77,91,119,126,140,173,179],"TATA":[32],"box,":[33],"Inr,":[34],"BRE,":[35],"DPE":[37],"are":[38],"crucial":[39],"for":[40,54,115,157],"predicting":[41],"promoters":[42],"species.":[44],"This":[45],"study":[46],"introduces":[47],"a":[48,59,82,109],"novel":[49],"prompt":[50,60,168],"learning-based":[51],"model,":[52],"Prompt-CBP,":[53],"First,":[58],"generator":[61],"was":[62,87,96,113,192],"employed":[63],"create":[65],"targeted":[66],"prompts":[67,124],"based":[68],"on":[69,130,197],"features,":[72,102],"which":[73],"were":[74],"combined":[75],"with":[76,185],"sequence":[79,83,92,101],"form":[81],"pair.":[84,93],"Second,":[85],"DNABERT-2":[86],"used":[88],"encode":[90],"Third,":[94],"CNN":[95],"applied":[97],"extract":[99],"local":[100],"while":[103],"BiLSTM":[104],"captured":[105],"global":[106],"features.":[107,144],"Finally,":[108],"fully":[110],"connected":[111],"layer":[112],"utilized":[114,147],"binary":[116],"classification":[117],"at":[118],"output":[120],"stage.":[121],"During":[122],"prediction,":[123],"guide":[125],"model":[127],"focus":[129],"capture":[132],"features":[134],"shared":[135],"sequences,":[138],"minimizing":[139],"influence":[141],"species-specific":[143],"experiment":[146],"data":[149,200],"sets":[150],"from":[151],"two":[152],"prokaryotes":[153],"three":[155],"eukaryotes":[156],"\u2033leave-one-species-out":[158],"cross-validation\u2033.":[159],"results":[161],"demonstrated":[162],"that,":[163],"methods":[166],"without":[167],"learning,":[169],"our":[170],"approach":[171],"improved":[172],"average":[174,180],"ACC":[175],"by":[176,182],"0.3213":[177],"AUC":[181],"0.4137.":[183],"Additionally,":[184],"smaller":[186],"sample":[187],"sizes,":[188],"its":[189],"comparable":[193],"models":[195],"trained":[196],"extensive":[198],"sets.":[201]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-12-11T00:00:00"}