{"id":"https://openalex.org/W7214199980","doi":"https://doi.org/10.64898/2026.09.23.753901","title":"ProFinder: Candidate constitutive promoter prediction across the bacterial tree for genetic tool development in non-model species","display_name":"ProFinder: Candidate constitutive promoter prediction across the bacterial tree for genetic tool development in non-model species","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214199980","doi":"https://doi.org/10.64898/2026.09.23.753901"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.23.753901","doi":"https://doi.org/10.64898/2026.09.23.753901","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.23.753901","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.23.753901.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.23.753901.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030112517","display_name":"Anupam Gautam","orcid":"https://orcid.org/0000-0002-6460-6525","observed_orcids":["https://orcid.org/0000-0002-6460-6525"]},"institutions":[{"id":"https://openalex.org/I4210165766","display_name":"Max Planck Institute for Biology","ror":"https://ror.org/0243gzr89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210165766"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anupam Gautam","raw_affiliation_strings":["Institute for Bioinformatics and Medical Informatics, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany","Max Planck Institute for Biology, Max-Planck-Ring 5, 72076 Tuebingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Bioinformatics and Medical Informatics, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"Max Planck Institute for Biology, Max-Planck-Ring 5, 72076 Tuebingen, Germany","institution_ids":["https://openalex.org/I4210165766"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003320997","display_name":"J. Wallis Marsh","orcid":"https://orcid.org/0000-0003-4681-1012","observed_orcids":["https://orcid.org/0000-0003-4681-1012"]},"institutions":[{"id":"https://openalex.org/I4210165766","display_name":"Max Planck Institute for Biology","ror":"https://ror.org/0243gzr89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210165766"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"James W. Marsh","raw_affiliation_strings":["Max Planck Institute for Biology, Max-Planck-Ring 5, 72076 Tuebingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Biology, Max-Planck-Ring 5, 72076 Tuebingen, Germany","institution_ids":["https://openalex.org/I4210165766"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003320997"],"corresponding_institution_ids":["https://openalex.org/I4210165766"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.8148999810218811,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.8148999810218811,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.12229999899864197,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.03889999911189079,"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/bacterial-promoters","display_name":"bacterial promoters","score":0.6949999928474426},{"id":"https://openalex.org/keywords/synthetic-biology","display_name":"synthetic biology","score":0.5130000114440918},{"id":"https://openalex.org/keywords/bacterial-phylogeny","display_name":"bacterial phylogeny","score":0.5040000081062317}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7107999920845032},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.635699987411499},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6209999918937683},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5529999732971191},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5396999716758728},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.4629000127315521},{"id":"https://openalex.org/C2776989901","wikidata":"https://www.wikidata.org/wiki/Q134668","display_name":"Gammaproteobacteria","level":4,"score":0.46059998869895935},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3249000012874603},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C195139083","wikidata":"https://www.wikidata.org/wiki/Q3463539","display_name":"Intergenic region","level":4,"score":0.2806999981403351},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.23.753901","doi":"https://doi.org/10.64898/2026.09.23.753901","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.23.753901","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.23.753901.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.23.753901","doi":"https://doi.org/10.64898/2026.09.23.753901","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.23.753901","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.23.753901.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214199980.pdf","grobid_xml":"https://content.openalex.org/works/W7214199980.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7212319807"],"related_works":["https://openalex.org/W2787044201","https://openalex.org/W3214710775","https://openalex.org/W3157128375","https://openalex.org/W4391994538","https://openalex.org/W4388302327","https://openalex.org/W2526784604","https://openalex.org/W4415163946","https://openalex.org/W2166516473","https://openalex.org/W3081166989","https://openalex.org/W7128692883"],"abstract_inverted_index":{"Abstract":[0],"Reliable":[1],"constitutive":[2,54,86,122],"promoters":[3,113],"for":[4,13,48,114],"non-model":[5],"bacteria":[6],"are":[7,21],"lacking,":[8],"resulting":[9],"in":[10],"a":[11,39,51,64,81,117],"bottleneck":[12],"genetic":[14],"tool":[15],"development.":[16],"Existing":[17],"computational":[18,40],"promoter":[19,49,123],"predictors":[20],"trained":[22],"on":[23,28],"model":[24],"Gammaproteobacteria":[25],"and":[26,63,95],"degrade":[27],"phylogenetically":[29],"distant":[30],"or":[31],"compositionally":[32],"atypical":[33],"genomes.":[34],"Here":[35],"we":[36],"present":[37],"ProFinder,":[38],"method":[41],"that":[42],"integrates":[43],"three":[44],"biologically":[45],"informed":[46],"criteria":[47],"prediction:":[50],"conserved":[52],"98-gene":[53],"marker":[55],"panel,":[56],"an":[57,75],"empirically":[58],"derived":[59],"intergenic":[60],"search":[61],"window,":[62],"72-motif":[65],"\u03c3":[66],"70":[67],"motif":[68],"catalogue":[69,119],"built":[70],"from":[71],"diverse":[72],"lineages.":[73],"From":[74],"input":[76],"bacterial":[77,105,131],"assembly,":[78],"ProFinder":[79,110,133],"returns":[80],"ranked":[82],"shortlist":[83],"of":[84,92,120],"putative":[85],"promoters.":[87],"It":[88],"matches":[89],"the":[90,130],"precision":[91],"full-genome":[93],"classifiers":[94],"is":[96],"more":[97],"robust":[98],"to":[99,103,125],"GC":[100],"extremes.":[101],"Applied":[102],"56,742":[104],"genomes":[106],"spanning":[107],"149":[108],"phyla,":[109],"returned":[111],"candidate":[112],"99.76%,":[115],"delivering":[116],"pan-bacterial":[118],"pre-computed":[121],"parts":[124],"accelerate":[126],"chassis":[127],"development":[128],"across":[129],"tree.":[132],"can":[134],"be":[135],"accessed":[136],"at:":[137],"https://plabase.cs.uni-tuebingen.de/profinder/":[138],".":[139]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-25T00:00:00"}
