{"id":"W3040612823","doi":"10.1101/2020.06.30.180687","title":"EukProt: A database of genome-scale predicted proteins across the diversity of eukaryotes","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Science for Life Laboratory; Fundación Bancaria Caixa d'Estalvis i Pensions de Barcelona; Svenska Forskningsrådet Formas; Deutsche Forschungsgemeinschaft; European Commission; Gordon and Betty Moore Foundation; Agence Nationale de la Recherche; Vetenskapsrådet; Generalitat de Catalunya; National Science Foundation","keywords":"Phylogenomics; Phylogenetic tree; Annotation; Identifier; Biology; Genome; Phylogenetics; Database; Diversification (marketing strategy); Computer science; Information retrieval; Data science; Computational biology; Gene; Bioinformatics; Genetics","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":[0.0009847301,0.002218141,0.001316285,0.004754433,0.001468169,0.00270492,0.001440201,0.0008967551,0.01785687],"category_scores_gemma":[0.001901235,0.001237846,0.0007918178,0.005939095,0.000268185,0.002193628,0.002018007,0.001235408,0.02016862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003670772,"about_ca_system_score_gemma":0.00111507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007088546,"about_ca_topic_score_gemma":0.001039268,"domain_scores_codex":[0.9992453,0.00009839315,0.0001178142,0.0002468669,0.0002084261,0.00008319557],"domain_scores_gemma":[0.9993728,0.0001062507,0.000121042,0.0001235973,0.0001472378,0.0001290857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0050338,0.0002961578,0.006770789,0.006836543,0.0004794274,0.001599558,0.000527158,0.002110358,0.22467,0.005936797,0.6192989,0.1264404],"study_design_scores_gemma":[0.0006365629,0.000479033,0.02939926,0.0007791584,0.0003858597,0.004879098,0.0004382457,0.006283809,0.05059079,0.008309569,0.8975303,0.0002882996],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05287901,0.007815568,0.04364831,0.000785607,0.0005787214,0.0001943212,0.8440799,0.03691434,0.01310431],"genre_scores_gemma":[0.01609764,0.001498807,0.03523107,0.00009535912,0.00008457636,0.0001080672,0.9424655,0.00194317,0.002475791],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01785687,"threshold_uncertainty_score":0.05973715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01608637753569252,"score_gpt":0.218223798012238,"score_spread":0.2021374204765454,"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."}}