{"id":"https://openalex.org/W7225800285","doi":"https://doi.org/10.64898/2026.11.09.765485","title":"BryoCAD: Extending Plant DNA Foundation Models Beyond Flowering Plants","display_name":"BryoCAD: Extending Plant DNA Foundation Models Beyond Flowering Plants","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225800285","doi":"https://doi.org/10.64898/2026.11.09.765485"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.09.765485","doi":"https://doi.org/10.64898/2026.11.09.765485","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765485","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.11.09.765485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010964993","display_name":"Ming\u2010Ren Yen","orcid":"https://orcid.org/0000-0002-9012-3244","observed_orcids":["https://orcid.org/0000-0002-9012-3244"]},"institutions":[{"id":"https://openalex.org/I4210093852","display_name":"Institute of Plant and Microbial Biology, Academia Sinica","ror":"https://ror.org/00jj3h083","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210093852","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Ren Yen","raw_affiliation_strings":["Institute of Plant and Microbial Biology, Academia Sinica, Taiwan;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Plant and Microbial Biology, Academia Sinica, Taiwan;","institution_ids":["https://openalex.org/I4210093852"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012757323","display_name":"Jingjing Zhai","orcid":"https://orcid.org/0000-0002-1535-3103","observed_orcids":["https://orcid.org/0000-0002-1535-3103"]},"institutions":[{"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":"Jingjing Zhai","raw_affiliation_strings":["Institute for Genomic Diversity, Cornell University, Ithaca, NY, 14853, USA;"],"raw_orcid":"https://orcid.org/0000-0002-1535-3103","affiliations":[{"raw_affiliation_string":"Institute for Genomic Diversity, Cornell University, Ithaca, NY, 14853, USA;","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020994377","display_name":"Sheng\u2010Kai Hsu","orcid":"https://orcid.org/0000-0002-6942-7163","observed_orcids":["https://orcid.org/0000-0002-6942-7163"]},"institutions":[{"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":"Sheng-Kai Hsu","raw_affiliation_strings":["Cornell University"],"raw_orcid":"https://orcid.org/0000-0002-6942-7163","affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101524696","display_name":"Ting\u2010Ying Wu","orcid":"https://orcid.org/0000-0001-6488-5133","observed_orcids":["https://orcid.org/0000-0001-6488-5133"]},"institutions":[{"id":"https://openalex.org/I4210093852","display_name":"Institute of Plant and Microbial Biology, Academia Sinica","ror":"https://ror.org/00jj3h083","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210093852","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ting-Ying Wu","raw_affiliation_strings":["Institute of Plant and Microbial Biology, Academia Sinica, Taiwan;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Plant and Microbial Biology, Academia Sinica, Taiwan;","institution_ids":["https://openalex.org/I4210093852"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101524696"],"corresponding_institution_ids":["https://openalex.org/I4210093852"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9458000063896179,"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":0.9458000063896179,"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/T11836","display_name":"Bryophyte Studies and Records","score":0.012600000016391277,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.009700000286102295,"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":[],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7443000078201294},{"id":"https://openalex.org/C2777975993","wikidata":"https://www.wikidata.org/wiki/Q29993","display_name":"Bryophyte","level":2,"score":0.6948000192642212},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6414999961853027},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5077999830245972},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.48510000109672546},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.43630000948905945},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4302999973297119},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C2777695334","wikidata":"https://www.wikidata.org/wiki/Q992846","display_name":"Marchantia polymorpha","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.37400001287460327},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.3346000015735626},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.31709998846054077},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C19843653","wikidata":"https://www.wikidata.org/wiki/Q213907","display_name":"Model organism","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C70343354","wikidata":"https://www.wikidata.org/wiki/Q3381973","display_name":"Phylogenomics","level":5,"score":0.2685000002384186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.09.765485","doi":"https://doi.org/10.64898/2026.11.09.765485","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765485","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.09.765485","doi":"https://doi.org/10.64898/2026.11.09.765485","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765485","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Bryophytes":[0],"exhibit":[1],"diverse":[2],"genome":[3],"architectures":[4],"and":[5,18,62,69,148,171,191],"gene":[6,153,192],"repertoires,":[7],"yet":[8],"their":[9,29],"functional":[10],"interpretation":[11,190],"remains":[12,35],"constrained":[13],"by":[14],"incomplete":[15],"genomic":[16,188],"annotations":[17],"limited":[19],"experimental":[20],"resources.":[21],"Although":[22],"DNA":[23,43,202],"foundation":[24,203],"models":[25,204],"offer":[26],"promising":[27],"solutions,":[28],"applicability":[30],"to":[31,82,130,141,166,174,205],"evolutionarily":[32,206],"divergent":[33],"bryophytes":[34],"largely":[36],"unexplored.":[37],"Here,":[38],"we":[39],"introduce":[40],"BryoCAD,":[41],"a":[42,84,97,197],"language":[44],"model":[45,54,124],"developed":[46],"through":[47],"continued":[48,185],"pre-training":[49,186],"of":[50,100,109,120],"the":[51,91,114,118],"angiosperm-specific":[52],"PlantCAD2":[53],"on":[55],"17":[56],"bryophyte":[57,67],"genomes":[58,68],"spanning":[59],"hornworts,":[60],"liverworts,":[61],"mosses.":[63],"Across":[64],"three":[65,115],"representative":[66],"four":[70],"gene-boundary":[71],"motif":[72],"recovery":[73],"tasks,":[74],"BryoCAD-Small":[75,104,159],"improved":[76],"mean":[77,98,137],"zero-shot":[78],"accuracy":[79,99,138],"from":[80,139,164,172],"45.7%":[81],"57.0%,":[83],"24.8%":[85],"relative":[86],"increase":[87],"over":[88,92,123],"PlantCAD2-Small,":[89],"while":[90],"200-fold":[93],"larger":[94],"Evo2-20B":[95],"achieved":[96],"only":[101],"39.3%.":[102],"Remarkably,":[103],"outperformed":[105],"PlantCAD2-Large":[106],"in":[107,168,176],"11":[108],"12":[110],"motif-recovery":[111],"comparisons":[112],"across":[113,146,194],"bryophytes,":[116,195],"highlighting":[117],"benefits":[119],"lineage-specific":[121,184],"adaptation":[122],"scaling":[125],"alone.":[126],"These":[127],"improvements":[128],"extended":[129],"all":[131],"six":[132],"tested":[133],"algal":[134],"species,":[135],"increasing":[136],"26.3%":[140],"37.5%,":[142],"although":[143],"performance":[144],"varied":[145],"ferns":[147],"gymnosperms.":[149],"BryoCAD":[150],"also":[151],"enhanced":[152],"structure":[154],"annotation:":[155],"replacing":[156],"PlantCAD2-Small":[157],"with":[158],"increased":[160],"transcript-level":[161],"F1":[162],"scores":[163],"0.578":[165],"0.625":[167],"Marchantia":[169],"polymorpha":[170],"0.485":[173],"0.530":[175],"Physcomitrium":[177],"patens.":[178],"Together,":[179],"our":[180],"findings":[181],"demonstrate":[182],"that":[183],"enhances":[187],"sequence":[189],"annotation":[193],"providing":[196],"transferable":[198],"framework":[199],"for":[200],"extending":[201],"diverse,":[207],"understudied":[208],"plant":[209],"lineages.":[210]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
