{"id":"https://openalex.org/W7124767786","doi":"https://doi.org/10.1093/gbe/evag211","title":"Identification and Classification of Expressed Orphan Genes, Spurious Orphan Genes, and Conserved Genes in the Human Gut Microbiome","display_name":"Identification and Classification of Expressed Orphan Genes, Spurious Orphan Genes, and Conserved Genes in the Human Gut Microbiome","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7124767786","doi":"https://doi.org/10.1093/gbe/evag211","pmid":"https://pubmed.ncbi.nlm.nih.gov/42635192","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13554803"},"language":"en","primary_location":{"id":"doi:10.1093/gbe/evag211","doi":"https://doi.org/10.1093/gbe/evag211","is_oa":true,"landing_page_url":"https://doi.org/10.1093/gbe/evag211","pdf_url":"https://academic.oup.com/gbe/advance-article-pdf/doi/10.1093/gbe/evag211/70769026/evag211.pdf","source":{"id":"https://openalex.org/S10195028","display_name":"Genome Biology and Evolution","issn_l":"1759-6653","issn":["1759-6653"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","doyens","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Biology and Evolution","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://academic.oup.com/gbe/advance-article-pdf/doi/10.1093/gbe/evag211/70769026/evag211.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123329185","display_name":"Chen Chen","orcid":"https://orcid.org/0009-0002-4152-046X","observed_orcids":["https://orcid.org/0009-0002-4152-046X"]},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Bioinformatics Group, Wageningen University , Wageningen 6700 PB ,"],"raw_orcid":"https://orcid.org/0009-0002-4152-046X","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University , Wageningen 6700 PB ,","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015212248","display_name":"Nikolaos Vakirlis","orcid":"https://orcid.org/0000-0001-7606-6987","observed_orcids":["https://orcid.org/0000-0001-7606-6987"]},"institutions":[{"id":"https://openalex.org/I4210123780","display_name":"Pasteur Hellenic Institute","ror":"https://ror.org/035cy3r13","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210123780"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Vakirlis","raw_affiliation_strings":["Hellenic Pasteur Institute Evolutionary Genomics Group, , Athens 11521 ,"],"raw_orcid":"https://orcid.org/0000-0001-7606-6987","affiliations":[{"raw_affiliation_string":"Hellenic Pasteur Institute Evolutionary Genomics Group, , Athens 11521 ,","institution_ids":["https://openalex.org/I4210123780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044698265","display_name":"Rens Holmer","orcid":"https://orcid.org/0000-0002-1080-1763","observed_orcids":["https://orcid.org/0000-0002-1080-1763"]},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rens Holmer","raw_affiliation_strings":["Bioinformatics Group, Wageningen University , Wageningen 6700 PB ,"],"raw_orcid":"https://orcid.org/0000-0002-1080-1763","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University , Wageningen 6700 PB ,","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080533789","display_name":"Dick de Ridder","orcid":"https://orcid.org/0000-0002-4944-4310","observed_orcids":["https://orcid.org/0000-0002-4944-4310"]},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dick de Ridder","raw_affiliation_strings":["Bioinformatics Group, Wageningen University , Wageningen 6700 PB ,"],"raw_orcid":"https://orcid.org/0000-0002-4944-4310","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University , Wageningen 6700 PB ,","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005612030","display_name":"Anne Kupczok","orcid":"https://orcid.org/0000-0001-5237-1899","observed_orcids":["https://orcid.org/0000-0001-5237-1899"]},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Anne Kupczok","raw_affiliation_strings":["Bioinformatics Group, Wageningen University , Wageningen 6700 PB ,"],"raw_orcid":"https://orcid.org/0000-0001-5237-1899","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University , Wageningen 6700 PB ,","institution_ids":["https://openalex.org/I913481162"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005612030"],"corresponding_institution_ids":["https://openalex.org/I913481162"],"apc_list":{"value":2850,"currency":"USD","value_usd":2850},"apc_paid":{"value":2850,"currency":"USD","value_usd":2850},"fwci":1.3024,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71682836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.0015999999595806003,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/orphan-genes","display_name":"orphan genes","score":0.996999979019165},{"id":"https://openalex.org/keywords/conserved-genes","display_name":"conserved genes","score":0.9369999766349792},{"id":"https://openalex.org/keywords/human-gut-microbiota","display_name":"human gut microbiome","score":0.9750000238418579},{"id":"https://openalex.org/keywords/metatranscriptomics","display_name":"metatranscriptomics","score":0.9430000185966492},{"id":"https://openalex.org/keywords/gene-expression","display_name":"gene expression","score":0.7429999709129333},{"id":"https://openalex.org/keywords/metagenome-assembled-genomes","display_name":"metagenome-assembled genomes","score":0.6679999828338623},{"id":"https://openalex.org/keywords/xgboost-classification","display_name":"XGBoost classification","score":0.8240000009536743},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.925000011920929},{"id":"https://openalex.org/keywords/gene-function-prediction","display_name":"gene function prediction","score":0.4090000092983246}],"concepts":[{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.7506999969482422},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.713699996471405},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6922000050544739},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.5659000277519226},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5551999807357788},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4948999881744385},{"id":"https://openalex.org/C2779161069","wikidata":"https://www.wikidata.org/wiki/Q2496179","display_name":"Orphan receptor","level":4,"score":0.450300008058548},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.3874000012874603},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.33390000462532043},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.3301999866962433},{"id":"https://openalex.org/C75480439","wikidata":"https://www.wikidata.org/wiki/Q1367466","display_name":"Orphan drug","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C190944805","wikidata":"https://www.wikidata.org/wiki/Q3922751","display_name":"Human Microbiome Project","level":4,"score":0.3012000024318695},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2847999930381775},{"id":"https://openalex.org/C69991583","wikidata":"https://www.wikidata.org/wiki/Q1423575","display_name":"Candidate gene","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C23525593","wikidata":"https://www.wikidata.org/wiki/Q15312389","display_name":"Neuron-derived orphan receptor 1","level":5,"score":0.2745000123977661},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.260699987411499},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C130895681","wikidata":"https://www.wikidata.org/wiki/Q5282122","display_name":"Disease gene identification","level":5,"score":0.2556000053882599}],"mesh":[{"descriptor_ui":"D000069196","descriptor_name":"Gastrointestinal Microbiome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/gbe/evag211","doi":"https://doi.org/10.1093/gbe/evag211","is_oa":true,"landing_page_url":"https://doi.org/10.1093/gbe/evag211","pdf_url":"https://academic.oup.com/gbe/advance-article-pdf/doi/10.1093/gbe/evag211/70769026/evag211.pdf","source":{"id":"https://openalex.org/S10195028","display_name":"Genome Biology and Evolution","issn_l":"1759-6653","issn":["1759-6653"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","doyens","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Biology and Evolution","raw_type":"journal-article"},{"id":"doi:10.64898/2026.01.16.699869","doi":"https://doi.org/10.64898/2026.01.16.699869","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.01.16.699869","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/01/17/2026.01.16.699869.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:13554803","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13554803/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13554803/pdf/evag211.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Biol Evol","raw_type":"Text"},{"id":"pmid:42635192","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42635192","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":"Genome biology and evolution","raw_type":"Journal Article"},{"id":"pmh:oai:library.wur.nl:wurpubs/d841c53d-beab-4980-9cd4-ad095bfb8f1d","doi":null,"is_oa":true,"landing_page_url":"https://research.wur.nl/en/publications/identification-and-classification-of-expressed-orphan-genes-spuri","pdf_url":"https://edepot.wur.nl/724172","source":{"id":"https://openalex.org/S4210201231","display_name":"Socio-Environmental Systems Modeling","issn_l":"2663-3027","issn":["2663-3027"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1759-6653","raw_type":"Article/Letter to editor"}],"best_oa_location":{"id":"doi:10.1093/gbe/evag211","doi":"https://doi.org/10.1093/gbe/evag211","is_oa":true,"landing_page_url":"https://doi.org/10.1093/gbe/evag211","pdf_url":"https://academic.oup.com/gbe/advance-article-pdf/doi/10.1093/gbe/evag211/70769026/evag211.pdf","source":{"id":"https://openalex.org/S10195028","display_name":"Genome Biology and Evolution","issn_l":"1759-6653","issn":["1759-6653"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","doyens","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Biology and Evolution","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.428600013256073,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334952","display_name":"Wageningen University and Research","ror":"https://ror.org/04qw24q55"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124767786.pdf","grobid_xml":"https://content.openalex.org/works/W7124767786.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1983377173","https://openalex.org/W1996423252","https://openalex.org/W2004132756","https://openalex.org/W2019377841","https://openalex.org/W2036897871","https://openalex.org/W2046085083","https://openalex.org/W2059223767","https://openalex.org/W2089095343","https://openalex.org/W2096093282","https://openalex.org/W2100002703","https://openalex.org/W2116041602","https://openalex.org/W2118001436","https://openalex.org/W2127509950","https://openalex.org/W2128643990","https://openalex.org/W2140211206","https://openalex.org/W2143485490","https://openalex.org/W2158714788","https://openalex.org/W2277953252","https://openalex.org/W2295598076","https://openalex.org/W2295737414","https://openalex.org/W2588063017","https://openalex.org/W2601961903","https://openalex.org/W2608157918","https://openalex.org/W2618851150","https://openalex.org/W2911964244","https://openalex.org/W2921715902","https://openalex.org/W2945454784","https://openalex.org/W2990682473","https://openalex.org/W3007397157","https://openalex.org/W3042305844","https://openalex.org/W3045244624","https://openalex.org/W3097658527","https://openalex.org/W3122109253","https://openalex.org/W3143063265","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3212023711","https://openalex.org/W3216588755","https://openalex.org/W4205099117","https://openalex.org/W4205192056","https://openalex.org/W4206767430","https://openalex.org/W4294089543","https://openalex.org/W4300861393","https://openalex.org/W4309306270","https://openalex.org/W4324311049","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4380686451","https://openalex.org/W4383198213","https://openalex.org/W4390918238","https://openalex.org/W4400407087","https://openalex.org/W4401881945","https://openalex.org/W4404050697","https://openalex.org/W4404447386","https://openalex.org/W4404474315","https://openalex.org/W4409229284","https://openalex.org/W4412168576","https://openalex.org/W4415223239","https://openalex.org/W4415427338","https://openalex.org/W7117418535"],"related_works":["https://openalex.org/W4412014196","https://openalex.org/W2325038494","https://openalex.org/W7100226289","https://openalex.org/W7135249839","https://openalex.org/W7145829847","https://openalex.org/W191719806","https://openalex.org/W2284776723","https://openalex.org/W4387933901","https://openalex.org/W7135276857","https://openalex.org/W4210606617"],"abstract_inverted_index":{"Abstract":[0],"Orphan":[1],"genes":[2,90],"(OGs)\u2014genes":[3],"lacking":[4,53],"detectable":[5,54,114],"homologs":[6],"outside":[7],"a":[8],"species\u2014are":[9],"widespread":[10],"in":[11,93,157,169,191,221],"microbial":[12],"genomes":[13,193],"and":[14,22,85,116,128,134,164,197,209,218,226],"are":[15,56],"thought":[16],"to":[17,19,59,78],"contribute":[18],"their":[20],"adaptation":[21],"molecular":[23],"innovation.":[24],"However,":[25],"not":[26],"all":[27],"predicted":[28,111],"OGs":[29,52,81,104,112,160,163,172,199,213,220],"may":[30],"represent":[31],"novel":[32],"functional":[33],"coding":[34],"sequences.":[35],"False":[36],"positive":[37],"OGs,":[38,42],"also":[39],"called":[40],"spurious":[41,83,162,195,219],"can":[43],"arise":[44],"from":[45,82,161,173,216],"gene":[46,133],"prediction":[47],"errors.":[48],"We":[49,121],"reason":[50],"that":[51,211],"expression":[55,107,115],"more":[57,192],"likely":[58],"be":[60],"spurious.":[61,120],"To":[62],"test":[63],"this,":[64],"we":[65,101],"combined":[66],"large-scale":[67],"metatranscriptomic":[68],"profiling":[69],"of":[70,155,167],"the":[71,149],"human":[72],"gut":[73],"microbiome":[74],"with":[75,88],"machine":[76],"learning":[77],"distinguish":[79],"expressed":[80,159,171,187,198,212],"ones":[84],"compare":[86],"them":[87],"conserved":[89],"(CGs)":[91],"found":[92],"multiple":[94],"species.":[95],"Using":[96],"nearly":[97],"5,000":[98],"metatranscriptome":[99],"libraries,":[100],"identified":[102],"\u223c218,000":[103],"supported":[105],"by":[106],"evidence,":[108],"while":[109,138],"\u223c330,000":[110],"lacked":[113],"were":[117,189,200],"classified":[118],"as":[119],"extracted":[122],"154":[123],"features":[124],"for":[125,131,140],"sequence,":[126],"structural,":[127],"evolutionary":[129,227],"properties":[130],"each":[132],"trained":[135],"XGBoost":[136],"classifiers":[137],"accounting":[139],"genomic":[141],"representation.":[142],"The":[143],"models":[144],"achieved":[145],"an":[146,165],"area":[147],"under":[148],"receiver":[150],"operating":[151],"characteristic":[152],"curve":[153],"(AUC)":[154],"0.82":[156],"distinguishing":[158,170],"AUC":[166],"0.93":[168],"CGs.":[174,203],"Interpretation":[175],"based":[176],"on":[177],"SHAP":[178],"(SHapley":[179],"Additive":[180],"exPlanations)":[181],"revealed":[182],"clear":[183],"biological":[184],"signals.":[185,228],"Particularly,":[186],"orphans":[188],"present":[190],"than":[194,202],"ones,":[196],"shorter":[201],"This":[204],"work":[205],"improves":[206],"OG":[207],"discovery":[208],"suggests":[210],"differ":[214],"systematically":[215],"CGs":[217],"sequence":[222],"composition,":[223],"structural":[224],"constraints,":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-01-20T00:00:00"}