{"id":"https://openalex.org/W7214019972","doi":"https://doi.org/10.64898/2026.09.22.753630","title":"Coevolutionary mining of prokaryotic non-coding elements with a genome language model","display_name":"Coevolutionary mining of prokaryotic non-coding elements with a genome language model","publication_year":2026,"publication_date":"2026-09-23","ids":{"openalex":"https://openalex.org/W7214019972","doi":"https://doi.org/10.64898/2026.09.22.753630"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.22.753630","doi":"https://doi.org/10.64898/2026.09.22.753630","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753630","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.09.22.753630","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152452397","display_name":"David Li","orcid":"https://orcid.org/0000-0002-8921-5168","observed_orcids":["https://orcid.org/0000-0002-8921-5168"]},"institutions":[{"id":"https://openalex.org/I4390039274","display_name":"Arc Research Institute","ror":"https://ror.org/00wra1b14","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4390039274"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David B. Li","raw_affiliation_strings":["Arc Institute, Palo Alto, CA, USA","ChEM-H Institute, Stanford University, Stanford, CA, USA","Department of Bioengineering, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8921-5168","affiliations":[{"raw_affiliation_string":"Arc Institute, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4390039274"]},{"raw_affiliation_string":"ChEM-H Institute, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Bioengineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091078534","display_name":"Garyk Brixi","orcid":"https://orcid.org/0000-0002-1253-0522","observed_orcids":["https://orcid.org/0000-0002-1253-0522"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I4390039274","display_name":"Arc Research Institute","ror":"https://ror.org/00wra1b14","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4390039274"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garyk Brixi","raw_affiliation_strings":["Arc Institute, Palo Alto, CA, USA","ChEM-H Institute, Stanford University, Stanford, CA, USA","Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1253-0522","affiliations":[{"raw_affiliation_string":"Arc Institute, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4390039274"]},{"raw_affiliation_string":"ChEM-H Institute, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152465280","display_name":"Alexandra Kim","orcid":"https://orcid.org/0009-0005-5503-3584","observed_orcids":["https://orcid.org/0009-0005-5503-3584"]},"institutions":[{"id":"https://openalex.org/I4390039274","display_name":"Arc Research Institute","ror":"https://ror.org/00wra1b14","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4390039274"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandra S. Kim","raw_affiliation_strings":["Arc Institute, Palo Alto, CA, USA","Department of Mathematics, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0009-0005-5503-3584","affiliations":[{"raw_affiliation_string":"Arc Institute, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4390039274"]},{"raw_affiliation_string":"Department of Mathematics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073800073","display_name":"Mateus Bernabe Fiamenghi","orcid":"https://orcid.org/0000-0003-4535-8594","observed_orcids":["https://orcid.org/0000-0003-4535-8594"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mateus B. Fiamenghi","raw_affiliation_strings":["DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4535-8594","affiliations":[{"raw_affiliation_string":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065949523","display_name":"Claudia L. Driscoll","orcid":"https://orcid.org/0000-0003-2285-6910","observed_orcids":["https://orcid.org/0000-0003-2285-6910"]},"institutions":[{"id":"https://openalex.org/I4390039274","display_name":"Arc Research Institute","ror":"https://ror.org/00wra1b14","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4390039274"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claudia L. Driscoll","raw_affiliation_strings":["Arc Institute, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2285-6910","affiliations":[{"raw_affiliation_string":"Arc Institute, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4390039274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068703921","display_name":"Simone A. Evans","orcid":"https://orcid.org/0000-0003-4975-8747","observed_orcids":["https://orcid.org/0000-0003-4975-8747"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simone A. Evans","raw_affiliation_strings":["Department of Biochemistry, Stanford University, Stanford, CA, USA","Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA","Department of Microbiology and Immunology, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4975-8747","affiliations":[{"raw_affiliation_string":"Department of Biochemistry, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Microbiology and Immunology, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001705723","display_name":"Linyi Gao","orcid":"https://orcid.org/0000-0002-3579-0327","observed_orcids":["https://orcid.org/0000-0002-3579-0327","https://orcid.org/0009-0002-5068-5709"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Gao","raw_affiliation_strings":["Department of Biochemistry, Stanford University, Stanford, CA, USA","Department of Microbiology and Immunology, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3579-0327","affiliations":[{"raw_affiliation_string":"Department of Biochemistry, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Microbiology and Immunology, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152449928","display_name":"Natalia Ivanova","orcid":"https://orcid.org/0000-0002-5802-9485","observed_orcids":["https://orcid.org/0000-0002-5802-9485"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalia N. Ivanova","raw_affiliation_strings":["DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5802-9485","affiliations":[{"raw_affiliation_string":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023696415","display_name":"Nikos C. Kyrpides","orcid":"https://orcid.org/0000-0002-6131-0462","observed_orcids":["https://orcid.org/0000-0002-6131-0462"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikos C. Kyrpides","raw_affiliation_strings":["DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6131-0462","affiliations":[{"raw_affiliation_string":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014360828","display_name":"Karl A. Deisseroth","orcid":"https://orcid.org/0000-0001-9440-3967","observed_orcids":["https://orcid.org/0000-0001-9440-3967"]},"institutions":[{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karl Deisseroth","raw_affiliation_strings":["Department of Bioengineering, Stanford University, Stanford, CA, USA","Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA","Howard Hughes Medical Institute, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9440-3967","affiliations":[{"raw_affiliation_string":"Department of Bioengineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"raw_affiliation_string":"Howard Hughes Medical Institute, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I1344073410","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035477681","display_name":"Max E. Wilkinson","orcid":"https://orcid.org/0000-0003-4738-9503","observed_orcids":["https://orcid.org/0000-0003-4738-9503"]},"institutions":[{"id":"https://openalex.org/I1334819555","display_name":"Memorial Sloan Kettering Cancer Center","ror":"https://ror.org/02yrq0923","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1334819555"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max E. Wilkinson","raw_affiliation_strings":["Structural Biology Program, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-4738-9503","affiliations":[{"raw_affiliation_string":"Structural Biology Program, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center, New York, NY, USA","institution_ids":["https://openalex.org/I1334819555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050241478","display_name":"Michael Andrew Fischbach","orcid":"https://orcid.org/0000-0003-3079-8247","observed_orcids":["https://orcid.org/0000-0003-3079-8247","https://orcid.org/0000-0002-9203-4026"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael A. Fischbach","raw_affiliation_strings":["ChEM-H Institute, Stanford University, Stanford, CA, USA","Chan Zuckerberg Biohub, Stanford, CA, USA","Department of Bioengineering, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3079-8247","affiliations":[{"raw_affiliation_string":"ChEM-H Institute, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Chan Zuckerberg Biohub, Stanford, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Bioengineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021962955","display_name":"Brian Hie","orcid":"https://orcid.org/0000-0003-3224-8142","observed_orcids":["https://orcid.org/0000-0003-3224-8142"]},"institutions":[{"id":"https://openalex.org/I4390039274","display_name":"Arc Research Institute","ror":"https://ror.org/00wra1b14","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4390039274"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brian L. Hie","raw_affiliation_strings":["Arc Institute, Palo Alto, CA, USA","Department of Chemical Engineering, Stanford University, Stanford, CA, USA","Stanford Data Science, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3224-8142","affiliations":[{"raw_affiliation_string":"Arc Institute, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4390039274"]},{"raw_affiliation_string":"Department of Chemical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford Data Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5021962955"],"corresponding_institution_ids":["https://openalex.org/I4390039274","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.4982999861240387,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.4982999861240387,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.4603999853134155,"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.011800000444054604,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/non-coding-rna","display_name":"non-coding RNA","score":0.8220000267028809},{"id":"https://openalex.org/keywords/minerva","display_name":"Minerva","score":0.6050000190734863},{"id":"https://openalex.org/keywords/rna-secondary-structure-prediction","display_name":"RNA secondary structure prediction","score":0.6079999804496765},{"id":"https://openalex.org/keywords/protein-contact-prediction","display_name":"protein contact prediction","score":0.7210000157356262},{"id":"https://openalex.org/keywords/crispr","display_name":"CRISPR","score":0.9070000052452087},{"id":"https://openalex.org/keywords/proteobacteria","display_name":"Proteobacteria","score":0.859000027179718},{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":0.4909999966621399},{"id":"https://openalex.org/keywords/bacterial-genomes","display_name":"bacterial genomes","score":0.5540000200271606}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.8065000176429749},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7888000011444092},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.7014999985694885},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6011000275611877},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5437999963760376},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.40869998931884766},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.3898000121116638},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.382099986076355},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.36480000615119934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.359499990940094},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C185581394","wikidata":"https://www.wikidata.org/wiki/Q145911","display_name":"Base pair","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3190000057220459},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.31520000100135803},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.28850001096725464},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C19843653","wikidata":"https://www.wikidata.org/wiki/Q213907","display_name":"Model organism","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.22.753630","doi":"https://doi.org/10.64898/2026.09.22.753630","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753630","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"doi:10.5281/zenodo.22903367","doi":"https://doi.org/10.5281/zenodo.22903367","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22903367","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.22903368","doi":"https://doi.org/10.5281/zenodo.22903368","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22903368","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.64898/2026.09.22.753630","doi":"https://doi.org/10.64898/2026.09.22.753630","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753630","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W229090448","https://openalex.org/W1982501766","https://openalex.org/W1982680051","https://openalex.org/W1990487336","https://openalex.org/W1994272924","https://openalex.org/W2005544327","https://openalex.org/W2011271395","https://openalex.org/W2011368877","https://openalex.org/W2025305823","https://openalex.org/W2061042699","https://openalex.org/W2068725534","https://openalex.org/W2096915408","https://openalex.org/W2101291993","https://openalex.org/W2114998496","https://openalex.org/W2118746294","https://openalex.org/W2122679732","https://openalex.org/W2122914162","https://openalex.org/W2131042010","https://openalex.org/W2141152740","https://openalex.org/W2160378127","https://openalex.org/W2169244146","https://openalex.org/W2171546617","https://openalex.org/W2171641243","https://openalex.org/W2179324586","https://openalex.org/W2342307854","https://openalex.org/W2547766908","https://openalex.org/W2605443933","https://openalex.org/W2605897695","https://openalex.org/W2626778328","https://openalex.org/W2803245377","https://openalex.org/W2896457183","https://openalex.org/W2941342985","https://openalex.org/W2950954328","https://openalex.org/W3005389897","https://openalex.org/W3111174583","https://openalex.org/W3158368350","https://openalex.org/W3168867926","https://openalex.org/W3170689505","https://openalex.org/W3203343200","https://openalex.org/W3209528471","https://openalex.org/W3212854871","https://openalex.org/W4205313308","https://openalex.org/W4229443239","https://openalex.org/W4281755820","https://openalex.org/W4284889270","https://openalex.org/W4294782938","https://openalex.org/W4327550249","https://openalex.org/W4367598489","https://openalex.org/W4382394445","https://openalex.org/W4387966979","https://openalex.org/W4388007370","https://openalex.org/W4392346912","https://openalex.org/W4395010528","https://openalex.org/W4396721167","https://openalex.org/W4401415626","https://openalex.org/W4401662181","https://openalex.org/W4401990684","https://openalex.org/W4403824354","https://openalex.org/W4404246274","https://openalex.org/W4404349982","https://openalex.org/W4406799200","https://openalex.org/W4408016794","https://openalex.org/W4408293704","https://openalex.org/W4409781688","https://openalex.org/W4409990698","https://openalex.org/W4411472741","https://openalex.org/W4411886797","https://openalex.org/W4412069926","https://openalex.org/W4413353167","https://openalex.org/W4415024864","https://openalex.org/W4415780211","https://openalex.org/W4416815663","https://openalex.org/W7133227460","https://openalex.org/W7133517058","https://openalex.org/W7154574572","https://openalex.org/W7161952625","https://openalex.org/W7162870193","https://openalex.org/W7163532908","https://openalex.org/W7197051316","https://openalex.org/W7213444707"],"related_works":["https://openalex.org/W7223227346","https://openalex.org/W4415141161","https://openalex.org/W2106144124","https://openalex.org/W3205706603","https://openalex.org/W165354108","https://openalex.org/W7213544987","https://openalex.org/W7098948981","https://openalex.org/W2142215914","https://openalex.org/W7098955073","https://openalex.org/W7169118113"],"abstract_inverted_index":{"Abstract":[0],"Microbial":[1],"genomes":[2,154],"encode":[3,129],"non-coding":[4],"RNAs":[5],"(ncRNAs)":[6],"and":[7,13,22,61,81,111,155],"nucleic-acid-interacting":[8],"proteins":[9],"essential":[10],"to":[11,26,43],"biology":[12],"biotechnology.":[14],"However,":[15],"discovery":[16,151],"of":[17,55,84,132],"these":[18],"systems":[19,68,128],"remains":[20],"protein-centric":[21],"based":[23],"on":[24],"similarity":[25],"known":[27,67],"sequences.":[28],"Here,":[29],"we":[30,98,120],"introduce":[31],"Minerva,":[32],"a":[33],"framework":[34],"for":[35],"coevolutionary":[36],"mining":[37,145],"that":[38,100,122,138],"uses":[39],"genome":[40,89],"language":[41],"models":[42],"predict":[44,82],"pairwise":[45],"interactions":[46],"directly":[47],"from":[48],"sequence.":[49],"Minerva":[50,147],"enables":[51,148],"fast,":[52],"alignment-free":[53],"prediction":[54],"base":[56],"pairing,":[57],"monomeric":[58],"protein":[59],"contacts,":[60],"repetitive":[62,94,116],"sequence":[63],"motifs.":[64,95,117],"We":[65],"recover":[66],"such":[69],"as":[70],"CRISPR,":[71],"detect":[72],"open-reading-frame":[73],"signatures":[74],"at":[75],"the":[76,101],"DNA":[77,141],"level":[78],"without":[79],"supervision,":[80],"hundreds":[83],"unannotated":[85],"regions":[86],"per":[87],"bacterial":[88],"containing":[90],"multiple":[91],"hairpins":[92],"or":[93],"In":[96,118],"Pseudomonadota,":[97],"find":[99],"widespread":[102],"TwoAYGGAY":[103],"structured":[104],"RNA":[105],"family":[106],"carries":[107],"large":[108],"secondary-structure":[109],"extensions":[110],"is":[112],"often":[113],"flanked":[114],"by":[115],"prophages,":[119],"discover":[121],"Unknown":[123],"Group":[124],"27":[125],"reverse":[126],"transcriptase":[127],"variable":[130],"arrays":[131],"structurally":[133],"conserved":[134],"yet":[135],"sequence-diverse":[136],"ncRNAs":[137],"template":[139],"complementary":[140],"hairpin":[142],"products.":[143],"Coevolutionary":[144],"with":[146],"efficient":[149],"biological":[150],"across":[152],"microbial":[153],"metagenomes.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-23T00:00:00"}