{"id":"https://openalex.org/W4393870943","doi":"https://doi.org/10.1038/s41467-024-46947-9","title":"Genomic language model predicts protein co-regulation and function","display_name":"Genomic language model predicts protein co-regulation and function","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W4393870943","doi":"https://doi.org/10.1038/s41467-024-46947-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/38570504","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10991518"},"language":"en","primary_location":{"id":"doi:10.1038/s41467-024-46947-9","doi":"https://doi.org/10.1038/s41467-024-46947-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41467-024-46947-9","pdf_url":"https://www.nature.com/articles/s41467-024-46947-9.pdf","source":{"id":"https://openalex.org/S64187185","display_name":"Nature Communications","issn_l":"2041-1723","issn":["2041-1723"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Communications","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41467-024-46947-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070231595","display_name":"Yunha Hwang","orcid":"https://orcid.org/0000-0003-0554-5598","observed_orcids":["https://orcid.org/0000-0003-0554-5598"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunha Hwang","raw_affiliation_strings":["Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, USA. yhwang@g.harvard.edu","Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0554-5598","affiliations":[{"raw_affiliation_string":"Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, USA. yhwang@g.harvard.edu","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080713048","display_name":"Andre Cornman","orcid":"https://orcid.org/0009-0001-9252-6063","observed_orcids":["https://orcid.org/0009-0001-9252-6063"]},"institutions":[{"id":"https://openalex.org/I4405258057","display_name":"Tatta Bio","ror":"https://ror.org/001dv4j44","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405258057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andre L. Cornman","raw_affiliation_strings":["Tatta Bio, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tatta Bio, Baltimore, MD, USA","institution_ids":["https://openalex.org/I4405258057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052338661","display_name":"Elizabeth H. Kellogg","orcid":"https://orcid.org/0000-0002-9664-3179","observed_orcids":["https://orcid.org/0000-0002-9664-3179"]},"institutions":[{"id":"https://openalex.org/I1313298211","display_name":"St. Jude Children's Research Hospital","ror":"https://ror.org/02r3e0967","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1313298211","https://openalex.org/I2802152183"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth H. Kellogg","raw_affiliation_strings":["Department of Molecular Biology and Genetics, Cornell University, Ithaca, NY, USA","Department of Structural Biology, St. Jude Children's Research Hospital, Memphis, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular Biology and Genetics, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Structural Biology, St. Jude Children's Research Hospital, Memphis, TN, USA","institution_ids":["https://openalex.org/I1313298211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084204507","display_name":"Sergey Ovchinnikov","orcid":"https://orcid.org/0000-0003-2774-2744","observed_orcids":["https://orcid.org/0000-0003-2774-2744"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sergey Ovchinnikov","raw_affiliation_strings":["Department of Biology, Massachusetts Institute of Technology, Cambridge, MA, USA. so3@mit.edu","John Harvard Distinguished Science Fellowship Program, Harvard University, Cambridge, MA, USA. so3@mit.edu","John Harvard Distinguished Science Fellowship Program, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2774-2744","affiliations":[{"raw_affiliation_string":"Department of Biology, Massachusetts Institute of Technology, Cambridge, MA, USA. so3@mit.edu","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"John Harvard Distinguished Science Fellowship Program, Harvard University, Cambridge, MA, USA. so3@mit.edu","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"John Harvard Distinguished Science Fellowship Program, Harvard University, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048349346","display_name":"Peter R. Girguis","orcid":"https://orcid.org/0000-0002-3599-8160","observed_orcids":["https://orcid.org/0000-0002-3599-8160","https://orcid.org/0000-0001-9006-5411"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peter R. Girguis","raw_affiliation_strings":["Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, USA. pgirguis@oeb.harvard.edu","Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3599-8160","affiliations":[{"raw_affiliation_string":"Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, USA. pgirguis@oeb.harvard.edu","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048349346","https://openalex.org/A5070231595","https://openalex.org/A5084204507"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I63966007"],"apc_list":{"value":6790,"currency":"USD","value_usd":6790},"apc_paid":{"value":6790,"currency":"USD","value_usd":6790},"fwci":12.4551,"has_fulltext":true,"cited_by_count":112,"citation_normalized_percentile":{"value":0.99547064,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"2880","last_page":"2880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8955000042915344,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8955000042915344,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.05790000036358833,"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":0.01850000023841858,"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/genomic-language-models","display_name":"genomic language models","score":0.9890000224113464},{"id":"https://openalex.org/keywords/operon","display_name":"operon","score":0.7049999833106995},{"id":"https://openalex.org/keywords/protein-embeddings","display_name":"protein embeddings","score":0.8050000071525574},{"id":"https://openalex.org/keywords/gene-function-prediction","display_name":"gene function prediction","score":0.6899999976158142},{"id":"https://openalex.org/keywords/gene-expression-regulation","display_name":"gene expression regulation","score":0.7699999809265137},{"id":"https://openalex.org/keywords/attention-patterns","display_name":"attention patterns","score":0.6269999742507935},{"id":"https://openalex.org/keywords/phylogenetic-context","display_name":"phylogenetic context","score":0.6209999918937683},{"id":"https://openalex.org/keywords/functional-modules","display_name":"functional modules","score":0.4880000054836273},{"id":"https://openalex.org/keywords/enzyme-function","display_name":"enzyme function","score":0.5120000243186951}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6396887898445129},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6018531918525696},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5282741189002991},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5237138867378235},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.45867854356765747},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4512655735015869},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.43201589584350586},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4236019253730774},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.31799954175949097},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009876","descriptor_name":"Operon","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1038/s41467-024-46947-9","doi":"https://doi.org/10.1038/s41467-024-46947-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41467-024-46947-9","pdf_url":"https://www.nature.com/articles/s41467-024-46947-9.pdf","source":{"id":"https://openalex.org/S64187185","display_name":"Nature Communications","issn_l":"2041-1723","issn":["2041-1723"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Communications","raw_type":"journal-article"},{"id":"doi:10.1101/2023.04.07.536042","doi":"https://doi.org/10.1101/2023.04.07.536042","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.04.07.536042","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/05/25/2023.04.07.536042.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:10991518","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10991518","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10991518/pdf/41467_2024_Article_46947.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nat Commun","raw_type":"Text"},{"id":"pmid:38570504","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38570504","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,"listed_in":[],"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":"Nature communications","raw_type":"Journal Article"},{"id":"pmh:oai:RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-46947-9","doi":null,"is_oa":false,"landing_page_url":"https://www.nature.com/articles/s41467-024-46947-9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:e89d2e92e119410faf6ff04cf3e744c7","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/e89d2e92e119410faf6ff04cf3e744c7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nature Communications, Vol 15, Iss 1, Pp 1-13 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1038/s41467-024-46947-9","doi":"https://doi.org/10.1038/s41467-024-46947-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41467-024-46947-9","pdf_url":"https://www.nature.com/articles/s41467-024-46947-9.pdf","source":{"id":"https://openalex.org/S64187185","display_name":"Nature Communications","issn_l":"2041-1723","issn":["2041-1723"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Communications","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3632377348","display_name":"Collaborative Research: A multidimensional approach to understanding  microbial carbon cycling beneath the seafloor during cool hydrothermal  circulation","funder_award_id":"1635365","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G388578259","display_name":"Towards Life with a Reduced Protein Alphabet","funder_award_id":"2032259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4768352037","display_name":null,"funder_award_id":"80NSSC18K1140","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5304168789","display_name":null,"funder_award_id":"80NSSC19K1427","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G7237959246","display_name":"Exploring the unknown protein universe using evolutionary information","funder_award_id":"DP5OD026389","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7742316701","display_name":"HOW DO WE CONTEND WITH THE TRULY ALIEN? MOST STRATEGIES FOR BIOSIGNATURE DETECTION RELY UPON FINDING FEATURES KNOWN TO BE ASSOCIATED WITH TERRESTRIAL LIFE  SUCH AS PARTICULAR CLASSES OF MOLECULES  BUT LIFE MAY BE VASTLY DIFFERENT ON OTHER WORLDS. THIS WORK WILL FURTHER DEVELOP SEVERAL TRULY  AGNOSTIC  APPROACHES  NONE OF WHICH PRESUPPOSE A PARTICULAR MOLECULAR FRAMEWORK. SOME OF THESE AREAS WILL INVOLVE NEW LINES OF INQUIRY THAT CAN BE ACCOMPLISHED USING INSTRUMENTATION THAT IS EITHER HIGH HERITAGE OR ON A PATH TOWARD HIGH TRL. OTHERS WILL NECESSITATE THE DESIGN OF COMPLETELY NEW ANALYTICAL TECHNIQUES. OUR NAI WILL NOT ONLY ADVANCE EACH OF THESE  AGNOSTIC  DETECTION CONCEPTS SEPARATELY BUT ALSO JOIN THESE TRADITIONALLY FRAGMENTED EFFORTS IN A UNIFIED RESEARCH PROGRAM  ONE THAT DRAWS LESSONS FROM OUR OPERATIONAL EXPERIENCES IN PLANETARY EXPLORATION THUS FAR. WE WILL BRING TOGETHER THEORETICIANS AND EXPERIMENTALISTS AS AN INCUBATOR FOR NEW AGNOSTIC LIFE DETECTION APPROACHES  CREATE A COMMON TRAINING SET OF BIOTIC AND ABIOTIC TEST SUBSTRATES  ESTABLISH LIKELIHOODS AND THRESHOLDS WITH PROBABILISTIC MODELS  AND DEVELOP A BROADER FORMULATION OF THE  LADDER OF LIFE.  IN THE PROCESS  WE WILL MERGE THE BROAD AND NARROW ENDS OF THE LIFE DETECTION SPECTRUM INTO A COLLECTIVE DIALOGUE ONE THAT WILL HELP US SYNTHESIZE  PRIORITIZE  EVALUATE  AND STRENGTHEN THE SEARCH FOR LIFE ON FUTURE SPACE MISSIONS.","funder_award_id":"80NSSC18K1140","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320309622","display_name":"Harvard University","ror":"https://ror.org/03vek6s52"},{"id":"https://openalex.org/F4320322037","display_name":"Nuclear Safety and Security Commission","ror":"https://ror.org/05qk3ge34"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338027","display_name":"FAS Division of Science, Harvard University","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393870943.pdf","grobid_xml":"https://content.openalex.org/works/W4393870943.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1914471426","https://openalex.org/W1969230095","https://openalex.org/W1988714210","https://openalex.org/W2019531132","https://openalex.org/W2022927779","https://openalex.org/W2041579725","https://openalex.org/W2045204781","https://openalex.org/W2064675550","https://openalex.org/W2064971934","https://openalex.org/W2072561431","https://openalex.org/W2076048958","https://openalex.org/W2107867854","https://openalex.org/W2108211735","https://openalex.org/W2127464112","https://openalex.org/W2127597332","https://openalex.org/W2131550794","https://openalex.org/W2134153749","https://openalex.org/W2322975763","https://openalex.org/W2564167865","https://openalex.org/W2626778328","https://openalex.org/W2740705661","https://openalex.org/W2775529910","https://openalex.org/W2797911275","https://openalex.org/W2949904390","https://openalex.org/W2950954328","https://openalex.org/W2963341956","https://openalex.org/W2970727289","https://openalex.org/W2972697066","https://openalex.org/W3006881356","https://openalex.org/W3037620288","https://openalex.org/W3040739508","https://openalex.org/W3106210592","https://openalex.org/W3127238141","https://openalex.org/W3127656915","https://openalex.org/W3146944767","https://openalex.org/W3164078851","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3203588026","https://openalex.org/W3215907690","https://openalex.org/W4213112325","https://openalex.org/W4225434086","https://openalex.org/W4225879163","https://openalex.org/W4280626237","https://openalex.org/W4298006192","https://openalex.org/W4306878720","https://openalex.org/W4310155672","https://openalex.org/W4310957810","https://openalex.org/W4315631495","https://openalex.org/W4318071656","https://openalex.org/W4327550249","https://openalex.org/W4362471278","https://openalex.org/W4375858802","https://openalex.org/W4382603228","https://openalex.org/W4387994442","https://openalex.org/W4392095606","https://openalex.org/W4399940408","https://openalex.org/W4404821554","https://openalex.org/W6763527631"],"related_works":["https://openalex.org/W4402100089","https://openalex.org/W7028714238","https://openalex.org/W6908397939","https://openalex.org/W7170056316","https://openalex.org/W7154726423","https://openalex.org/W4403507140","https://openalex.org/W7161489096","https://openalex.org/W4406259803","https://openalex.org/W4416252969","https://openalex.org/W2107717979"],"abstract_inverted_index":{"Deciphering":[0],"the":[1,28,58,102,117,123,142,164],"relationship":[2],"between":[3,84,108,190],"a":[4,65,90,193],"gene":[5,66,85],"and":[6,14,72,105,127,131,170,177,186],"its":[7],"genomic":[8,52,61,75,91,118,184,194],"context":[9,53,119],"is":[10,67,148,167],"fundamental":[11],"to":[12,37,48,80,100,173],"understanding":[13],"engineering":[15],"biological":[16],"systems.":[17],"Machine":[18],"learning":[19,24,149,162],"has":[20],"shown":[21],"promise":[22],"in":[23,44,63,182,192],"latent":[25,103],"relationships":[26,83,107,189],"underlying":[27],"sequence-structure-function":[29],"paradigm":[30],"from":[31],"massive":[32],"protein":[33,113,124],"sequence":[34,125],"datasets.":[35],"However,":[36],"date,":[38],"limited":[39],"attempts":[40],"have":[41],"been":[42],"made":[43],"extending":[45],"this":[46],"continuum":[47],"include":[49],"higher":[50],"order":[51],"information.":[54],"Evolutionary":[55],"processes":[56],"dictate":[57],"specificity":[59],"of":[60,97,141,163,180],"contexts":[62,185],"which":[64],"found":[68],"across":[69],"phylogenetic":[70],"distances,":[71],"these":[73],"emergent":[74],"patterns":[76,144],"can":[77],"be":[78],"leveraged":[79],"uncover":[81,187],"functional":[82,104,151,175],"products.":[86],"Here,":[87],"we":[88],"train":[89],"language":[92],"model":[93],"(gLM)":[94],"on":[95],"millions":[96],"metagenomic":[98,165],"scaffolds":[99],"learn":[101],"regulatory":[106,178],"genes.":[109],"gLM":[110,147],"learns":[111],"contextualized":[112],"embeddings":[114],"that":[115,146,158],"capture":[116],"as":[120,122],"well":[121],"itself,":[126],"encode":[128,174],"biologically":[129],"meaningful":[130],"functionally":[132],"relevant":[133],"information":[134],"(e.g.":[135],"enzymatic":[136],"function,":[137],"taxonomy).":[138],"Our":[139,155],"analysis":[140],"attention":[143],"demonstrates":[145],"co-regulated":[150],"modules":[152],"(i.e.":[153],"operons).":[154],"findings":[156],"illustrate":[157],"gLM's":[159],"unsupervised":[160],"deep":[161],"corpus":[166],"an":[168],"effective":[169],"promising":[171],"approach":[172],"semantics":[176],"syntax":[179],"genes":[181,191],"their":[183],"complex":[188],"region.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":41},{"year":2025,"cited_by_count":51},{"year":2024,"cited_by_count":20}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-04-04T00:00:00"}