{"id":"W4206456346","doi":"10.1101/2021.12.31.474423","title":"NeoRdRp: A comprehensive dataset for identifying RNA-dependent RNA polymerase of various RNA viruses from metatranscriptomic data","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Plant Virus Research Studies","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Medical Science, University of Tokyo; Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo; Japan Agency for Medical Research and Development","keywords":"RNA; Biology; RNA polymerase; Computational biology; RNA-dependent RNA polymerase; Genetics; RNA editing; Gene","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002954346,0.002312743,0.001563251,0.00532374,0.00108614,0.001728086,0.002164781,0.002295099,0.001770043],"category_scores_gemma":[0.006324581,0.000692545,0.002517621,0.004258508,0.0005227555,0.001688082,0.002238353,0.001702349,0.002993074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009290317,"about_ca_system_score_gemma":0.001638461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002280287,"about_ca_topic_score_gemma":0.004439572,"domain_scores_codex":[0.9970144,0.0004962318,0.0004260839,0.001173485,0.0006256772,0.0002641317],"domain_scores_gemma":[0.9971719,0.0009049982,0.0005018651,0.0007624418,0.0003763319,0.0002824249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005795978,0.001342339,0.1806493,0.02404129,0.003861049,0.002901519,0.001083688,0.03927155,0.3810707,0.005094619,0.2060209,0.148867],"study_design_scores_gemma":[0.001305119,0.001430826,0.2301676,0.001770942,0.001659585,0.003122155,0.001105985,0.1543085,0.1490645,0.01053558,0.4447497,0.0007796341],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1110596,0.003147769,0.01615568,0.0002054367,0.0001808182,0.0002774703,0.8576471,0.009719872,0.001606267],"genre_scores_gemma":[0.03256978,0.0004358845,0.02992291,0.0001127358,0.00002284024,0.0003649667,0.9360294,0.000327946,0.0002136169],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.00532374,"threshold_uncertainty_score":0.01562428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1119969760671828,"score_gpt":0.3046719405150173,"score_spread":0.1926749644478345,"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."}}