{"id":"W3121998295","doi":"10.1093/ve/veaa106","title":"Tuning intrinsic disorder predictors for virus proteins","year":2020,"lang":"en","type":"article","venue":"Virus Evolution","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Random forest; Computational biology; Biology; Matthews correlation coefficient; Context (archaeology); Virus; Intrinsically disordered proteins; Genome; Protein structure; Ensemble learning; Viral replication; Viral protein; Computer science; Gene; Artificial intelligence; Genetics; Support vector machine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001288176,0.0001396908,0.0001179067,0.00002656289,0.0001301955,0.00001887688,0.000143935,0.0001506678,0.00003305448],"category_scores_gemma":[0.0002358663,0.0001362078,0.00009603767,0.00008597251,0.00003162528,0.000006455973,0.00006441915,0.00005554259,0.00003007132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001994876,"about_ca_system_score_gemma":0.00005653057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005685809,"about_ca_topic_score_gemma":0.00004521927,"domain_scores_codex":[0.9991043,0.00005063753,0.0001860296,0.0003279714,0.0001088626,0.0002222482],"domain_scores_gemma":[0.9995733,0.000008585695,0.00008271907,0.0001833942,0.00005335002,0.00009866193],"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":[0.0002030181,0.00002919511,0.0003744134,0.00002627198,0.00002951269,3.899929e-7,0.00005101156,0.00004394591,0.9907535,0.0005434543,0.0008790409,0.007066218],"study_design_scores_gemma":[0.0005604393,0.0007261869,0.0008795639,0.00001393057,0.00002677721,0.00000177654,0.00004336158,0.0005413378,0.8579022,0.000470427,0.1386001,0.0002338599],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5378675,0.001105931,0.4590247,0.0004584507,0.0001811677,0.0009357898,0.0000857973,0.00006081882,0.0002798043],"genre_scores_gemma":[0.9952554,0.0000722823,0.003179641,0.000296738,0.0006774597,0.0002425306,0.00008737494,0.00003222433,0.0001563493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4573879,"threshold_uncertainty_score":0.5554395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0141627357878958,"score_gpt":0.2284862620149615,"score_spread":0.2143235262270657,"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."}}