{"id":"https://openalex.org/W7225008930","doi":"https://doi.org/10.64898/2026.10.28.762457","title":"Single-cell foundation models transfer across deep evolutionary distances","display_name":"Single-cell foundation models transfer across deep evolutionary distances","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7225008930","doi":"https://doi.org/10.64898/2026.10.28.762457"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.28.762457","doi":"https://doi.org/10.64898/2026.10.28.762457","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762457","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.28.762457.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","license_id":"https://openalex.org/licenses/cc-by","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/2026/10/31/2026.10.28.762457.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117843293","display_name":"Lena Trnovec","orcid":"https://orcid.org/0009-0007-4372-0648","observed_orcids":["https://orcid.org/0009-0007-4372-0648"]},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Lena Trnovec","raw_affiliation_strings":["Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia"],"raw_orcid":"https://orcid.org/0009-0007-4372-0648","affiliations":[{"raw_affiliation_string":"Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077496004","display_name":"Mariko Katoh\u2010Kurasawa","orcid":"https://orcid.org/0000-0002-6404-485X","observed_orcids":["https://orcid.org/0000-0002-6404-485X"]},"institutions":[{"id":"https://openalex.org/I181547552","display_name":"Baylor College of Medicine","ror":"https://ror.org/02pttbw34","country_code":"US","type":"education","lineage":["https://openalex.org/I181547552","https://openalex.org/I2801539370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mariko Katoh-Kurasawa","raw_affiliation_strings":["Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX 77030, USA"],"raw_orcid":"https://orcid.org/0000-0002-6404-485X","affiliations":[{"raw_affiliation_string":"Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX 77030, USA","institution_ids":["https://openalex.org/I181547552"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066683739","display_name":"Rachel N. Arey","orcid":"https://orcid.org/0000-0001-9941-3945","observed_orcids":["https://orcid.org/0000-0001-9941-3945"]},"institutions":[{"id":"https://openalex.org/I181547552","display_name":"Baylor College of Medicine","ror":"https://ror.org/02pttbw34","country_code":"US","type":"education","lineage":["https://openalex.org/I181547552","https://openalex.org/I2801539370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachel N. Arey","raw_affiliation_strings":["Department of Molecular and Cellular Biology, Baylor College of Medicine, Houston, TX 77030, USA"],"raw_orcid":"https://orcid.org/0000-0001-9941-3945","affiliations":[{"raw_affiliation_string":"Department of Molecular and Cellular Biology, Baylor College of Medicine, Houston, TX 77030, USA","institution_ids":["https://openalex.org/I181547552"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055034051","display_name":"Gad Shaulsky","orcid":"https://orcid.org/0000-0002-0532-0551","observed_orcids":["https://orcid.org/0000-0002-0532-0551"]},"institutions":[{"id":"https://openalex.org/I181547552","display_name":"Baylor College of Medicine","ror":"https://ror.org/02pttbw34","country_code":"US","type":"education","lineage":["https://openalex.org/I181547552","https://openalex.org/I2801539370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gad Shaulsky","raw_affiliation_strings":["Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX 77030, USA"],"raw_orcid":"https://orcid.org/0000-0002-0532-0551","affiliations":[{"raw_affiliation_string":"Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX 77030, USA","institution_ids":["https://openalex.org/I181547552"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073792028","display_name":"Bla\u017e Zupan","orcid":"https://orcid.org/0000-0002-5864-7056","observed_orcids":["https://orcid.org/0000-0002-5864-7056"]},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]},{"id":"https://openalex.org/I181547552","display_name":"Baylor College of Medicine","ror":"https://ror.org/02pttbw34","country_code":"US","type":"education","lineage":["https://openalex.org/I181547552","https://openalex.org/I2801539370"]}],"countries":["SI","US"],"is_corresponding":true,"raw_author_name":"Bla\u017e Zupan","raw_affiliation_strings":["Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX 77030, USA","Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia"],"raw_orcid":"https://orcid.org/0000-0002-5864-7056","affiliations":[{"raw_affiliation_string":"Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX 77030, USA","institution_ids":["https://openalex.org/I181547552"]},{"raw_affiliation_string":"Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073792028"],"corresponding_institution_ids":["https://openalex.org/I153976015","https://openalex.org/I181547552"],"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9990000128746033,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9990000128746033,"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/T10268","display_name":"Developmental Biology and Gene Regulation","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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/single-cell-foundation-models","display_name":"single-cell foundation models","score":0.9950000047683716},{"id":"https://openalex.org/keywords/cross-species-transmission","display_name":"interspecies transmission","score":0.9490000009536743},{"id":"https://openalex.org/keywords/dictyostelium-discoideum","display_name":"Dictyostelium discoideum","score":0.8740000128746033},{"id":"https://openalex.org/keywords/caenorhabditis-elegans","display_name":"Caenorhabditis elegans","score":1.0},{"id":"https://openalex.org/keywords/geneformer","display_name":"Geneformer","score":0.800000011920929},{"id":"https://openalex.org/keywords/scgpt","display_name":"scGPT","score":0.996999979019165},{"id":"https://openalex.org/keywords/ultraconserved-elements","display_name":"ultraconserved elements","score":0.8420000076293945},{"id":"https://openalex.org/keywords/ortholog-mapping","display_name":"ortholog mapping","score":0.8960000276565552}],"concepts":[{"id":"https://openalex.org/C2778944004","wikidata":"https://www.wikidata.org/wiki/Q91703","display_name":"Caenorhabditis elegans","level":3,"score":0.6628999710083008},{"id":"https://openalex.org/C2775969001","wikidata":"https://www.wikidata.org/wiki/Q134351","display_name":"Dictyostelium discoideum","level":3,"score":0.6116999983787537},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.507099986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4528000056743622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44339999556541443},{"id":"https://openalex.org/C92938381","wikidata":"https://www.wikidata.org/wiki/Q83185","display_name":"Horizontal gene transfer","level":4,"score":0.438400000333786},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.42640000581741333},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C2778961482","wikidata":"https://www.wikidata.org/wiki/Q25241","display_name":"Vertebrate","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C3018928802","wikidata":"https://www.wikidata.org/wiki/Q83185","display_name":"Gene transfer","level":3,"score":0.33000001311302185},{"id":"https://openalex.org/C2775889303","wikidata":"https://www.wikidata.org/wiki/Q17146891","display_name":"Dictyostelium","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.28.762457","doi":"https://doi.org/10.64898/2026.10.28.762457","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762457","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.28.762457.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.28.762457","doi":"https://doi.org/10.64898/2026.10.28.762457","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762457","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.28.762457.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","license_id":"https://openalex.org/licenses/cc-by","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/W7225008930.pdf","grobid_xml":"https://content.openalex.org/works/W7225008930.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3195577433","https://openalex.org/W7134069825"],"related_works":["https://openalex.org/W4409914987","https://openalex.org/W7160553923","https://openalex.org/W7213289232","https://openalex.org/W7201876171","https://openalex.org/W4387696832","https://openalex.org/W4409566559","https://openalex.org/W7169779003","https://openalex.org/W7081582991","https://openalex.org/W7135136597","https://openalex.org/W6958490392"],"abstract_inverted_index":{"Abstract":[0],"Single-cell":[1],"foundation":[2],"models":[3,65,114,124],"are":[4,14],"trained":[5],"mostly":[6],"on":[7,115],"human":[8],"and":[9,36,40,48,58,69,80,89,139,148],"other":[10],"vertebrate":[11],"cells,":[12],"yet":[13],"proposed":[15],"as":[16],"general-purpose":[17],"models.":[18],"Whether":[19],"they":[20],"transfer":[21],"far":[22],"beyond":[23],"their":[24],"training":[25],"species":[26],"is":[27],"unknown.":[28],"We":[29],"evaluated":[30],"zero-shot":[31],"embeddings":[32,130,145],"from":[33,53],"Geneformer,":[34],"scGPT":[35],"UCE":[37,74,97],"against":[38],"PCA":[39],"scVI":[41],"in":[42],"developmental":[43,67],"atlases":[44],"of":[45,84,117,137],"Dictyostelium":[46],"discoideum":[47],"Caenorhabditis":[49],"elegans":[50],",":[51],"separated":[52],"humans":[54],"by":[55,77],"1.2":[56],"billion":[57,135],"600":[59],"million":[60],"years.":[61],"Without":[62],"retraining,":[63],"the":[64],"recovered":[66],"order":[68],"preserved":[70],"organism-specific":[71],"cell":[72,129],"identities.":[73],"encodes":[75],"genes":[76],"protein":[78],"sequence":[79],"could":[81],"use":[82],"97%":[83],"measured":[85],"genes,":[86,108],"whereas":[87],"Geneformer":[88],"scGPT,":[90],"after":[91],"ortholog":[92],"mapping,":[93],"used":[94],"under":[95],"one-fifth.":[96],"performed":[98],"most":[99],"consistently,":[100],"often":[101,149],"exceeding":[102],"species-native":[103],"baselines.":[104],"Restricted":[105],"to":[106],"ortholog-mappable":[107],"it":[109],"still":[110],"scored":[111],"above":[112],"vocabulary-based":[113],"five":[116],"six":[118],"annotation":[119],"tasks,":[120],"some":[121],"narrowly.":[122],"Foundation":[123],"can":[125],"thus":[126],"yield":[127],"informative":[128],"across":[131],"more":[132,146,150],"than":[133],"a":[134],"years":[136],"evolution,":[138],"protein-sequence":[140],"gene":[141],"representations":[142],"make":[143],"these":[144],"complete":[147],"accurate.":[151]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-01T00:00:00"}
