{"id":"W4413298485","doi":"10.1101/2025.08.13.670088","title":"Eukan: a fully automated nuclear genome annotation pipeline for less studied and divergent eukaryotes","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Pipeline (software); Annotation; Computational biology; Genome; Biology; Computer science; Genetics; Gene; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002715307,0.001279132,0.0007628174,0.00179173,0.001058932,0.002008906,0.001555974,0.0008409674,0.004644102],"category_scores_gemma":[0.006121716,0.0006434522,0.001039972,0.001360596,0.0004802224,0.001992415,0.002480447,0.001008904,0.002780272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000826262,"about_ca_system_score_gemma":0.002006833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003168773,"about_ca_topic_score_gemma":0.007281574,"domain_scores_codex":[0.998558,0.0003568444,0.0001057629,0.0004939638,0.0004087248,0.00007676241],"domain_scores_gemma":[0.9974526,0.0009146694,0.0002014569,0.0008057753,0.0005214587,0.0001041611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002038078,0.000284722,0.02183279,0.001721223,0.0004727551,0.0006283658,0.001052168,0.06797781,0.286659,0.02725544,0.07532643,0.5147512],"study_design_scores_gemma":[0.0002392159,0.0002053247,0.02090441,0.0002916505,0.0001629878,0.0007015113,0.0004337415,0.5586281,0.1706234,0.06188793,0.1856264,0.0002953928],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07522695,0.000664749,0.8410124,0.0004573754,0.0001732632,0.0001333592,0.01789676,0.05998021,0.004455011],"genre_scores_gemma":[0.1613719,0.0002761094,0.7742884,0.0002347378,0.00003981037,0.0001846094,0.05413502,0.004977345,0.004492112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004644102,"threshold_uncertainty_score":0.01553607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01508443514389704,"score_gpt":0.2118253714775181,"score_spread":0.196740936333621,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}