{"id":"W2148271643","doi":"10.1093/bioinformatics/btv060","title":"Computational identification of MoRFs in protein sequences","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Support vector machine; Identification (biology); Sequence (biology); Artificial intelligence; Computational biology; Data mining; Set (abstract data type); Machine learning; Pattern recognition (psychology); Biology; Genetics","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":[0.0004737129,0.000086075,0.0001024604,0.00008365383,0.00001751453,0.00001888121,0.0001736436,0.00008186047,0.000003584063],"category_scores_gemma":[0.0002872231,0.00008087633,0.00002956849,0.0001362354,0.00007196372,0.00001601997,0.00006361571,0.00006566528,0.00002574515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001874208,"about_ca_system_score_gemma":0.0001395814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001288071,"about_ca_topic_score_gemma":0.000006545612,"domain_scores_codex":[0.999001,0.00002613475,0.0005689557,0.00006508335,0.000221576,0.0001172963],"domain_scores_gemma":[0.9993374,0.00000732813,0.0002807088,0.000187045,0.000136938,0.00005058802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004679011,0.0006981196,0.1108896,0.002189263,0.0002140829,0.000005934539,0.01616872,0.696732,0.1019054,0.02120921,0.01320169,0.03631808],"study_design_scores_gemma":[0.002056672,0.0005929616,0.01131818,0.0001079043,0.00001498385,0.00003948985,0.002382481,0.8965242,0.07379486,0.002792018,0.009825882,0.0005503698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578253,0.00006279942,0.03634404,0.000106439,0.000088507,0.0003332973,0.00002278456,0.00001603884,0.005200814],"genre_scores_gemma":[0.950223,0.000004140103,0.04926631,0.00005918998,0.0000266297,0.00001176775,0.0001979176,0.000006428236,0.0002046421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1997922,"threshold_uncertainty_score":0.3298041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01588503249904103,"score_gpt":0.2752276049529452,"score_spread":0.2593425724539041,"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."}}