{"id":"W4409202039","doi":"10.1101/2025.04.01.646650","title":"SnoBIRD: A tool to identify C/D box snoRNAs and refine their annotation across all eukaryotes","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Small nucleolar RNA; Annotation; Computational biology; Biology; Data science; Computer science; Evolutionary biology; Bioinformatics; Genetics; Long non-coding RNA; Gene","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001119527,0.002411161,0.0009491362,0.002658561,0.0007023729,0.001245533,0.001240433,0.0007792339,0.01967594],"category_scores_gemma":[0.002351149,0.0008919024,0.001269873,0.001361919,0.0003173378,0.0009422635,0.001421687,0.001407242,0.008931051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003981751,"about_ca_system_score_gemma":0.000846773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001477061,"about_ca_topic_score_gemma":0.003098049,"domain_scores_codex":[0.9995535,0.00007197439,0.00003200702,0.0001793016,0.0001161568,0.00004692521],"domain_scores_gemma":[0.9995064,0.0002151245,0.00006359728,0.00007359193,0.00008724351,0.0000540869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003693698,0.000323617,0.02266237,0.004031812,0.0008554736,0.001313397,0.0006530044,0.04101253,0.113082,0.01012645,0.4893518,0.3128939],"study_design_scores_gemma":[0.0008768465,0.000352144,0.01250932,0.0004787048,0.0003935191,0.001312871,0.0002635717,0.4807607,0.1712696,0.02517995,0.3062945,0.0003084831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.05212544,0.001507248,0.4263841,0.0006468329,0.0004730102,0.0003054494,0.09516496,0.4164772,0.006915779],"genre_scores_gemma":[0.1549236,0.0009899809,0.6421795,0.0005361839,0.0001178644,0.0005173839,0.1634504,0.028366,0.008919073],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01967594,"threshold_uncertainty_score":0.0658226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01569409607926278,"score_gpt":0.2824807300036805,"score_spread":0.2667866339244178,"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."}}