{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003682475,0.0003702051,0.0004844408,0.0000370241,0.0002224561,0.00002515799,0.0009297281,0.0003029062,0.000006719264],"category_scores_gemma":[0.0001622706,0.0003238144,0.0002084302,0.0002012656,0.0003785593,0.000001855311,0.004789127,0.000303491,0.000002094148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002385222,"about_ca_system_score_gemma":0.0002921728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001508639,"about_ca_topic_score_gemma":0.00001325408,"domain_scores_codex":[0.9980979,0.0001053717,0.000454448,0.0007277005,0.0002695119,0.0003450576],"domain_scores_gemma":[0.9975699,0.00001914675,0.0005157905,0.001296237,0.0004714193,0.000127503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009461115,0.00009913459,0.03011267,0.0004596765,0.0003743737,0.000003313278,0.0000766337,0.00007446266,0.9685902,0.00002095728,0.00009299054,9.767133e-7],"study_design_scores_gemma":[0.0003700876,0.0001526097,0.2569199,0.0000782125,0.0001112565,9.887877e-9,0.00001724283,0.00003786734,0.7407206,0.000002081375,0.001294828,0.0002952483],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989788,0.00267058,0.001010209,0.0001636484,0.0002185234,0.001121353,0.005005314,0.00001532272,0.000007042093],"genre_scores_gemma":[0.9961647,0.0007947983,0.002509488,0.00008052069,0.0002841206,0.0001080527,0.00000438356,0.00005111172,0.000002828823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2278696,"threshold_uncertainty_score":0.9999214,"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."}}