{"id":"W3004509766","doi":"10.1109/bibm47256.2019.8983020","title":"Ontology-based transporter substrate annotation for benchmark datasets","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Benchmark (surveying); Computer science; Annotation; Class (philosophy); Ontology; Process (computing); Automation; Artificial intelligence; Gene ontology; Substrate (aquarium); Data mining; Machine learning; Information retrieval; Programming language; Chemistry; Engineering; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001394967,0.0001003083,0.00008962493,0.00002488287,0.00002974541,0.00001346844,0.0001206705,0.0001094893,0.000184766],"category_scores_gemma":[0.00001973655,0.00008851437,0.00005701604,0.00002973602,0.00002159077,0.00000414231,0.000008298057,0.00005002434,0.00003696247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004096194,"about_ca_system_score_gemma":0.00004140352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008381439,"about_ca_topic_score_gemma":0.00005725887,"domain_scores_codex":[0.9994134,0.00001420019,0.0001753017,0.0001717067,0.00006306625,0.0001623157],"domain_scores_gemma":[0.9995624,0.00001441283,0.00006544698,0.0002829548,0.00003816537,0.00003657333],"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":[0.001489015,0.0003436673,0.2639856,0.0009477728,0.0002691037,0.000003862146,0.0002568326,0.01051668,0.6022837,0.004205581,0.1051067,0.01059155],"study_design_scores_gemma":[0.005757905,0.001942622,0.09053542,0.0000311359,0.00008010171,0.00001526289,0.0001198709,0.06458143,0.2200582,0.0002479147,0.615667,0.0009631084],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9493818,0.00003091421,0.04284123,0.0003123908,0.0001812058,0.0005014437,0.0003213301,0.00002361184,0.006406046],"genre_scores_gemma":[0.9678769,0.000002694283,0.01794508,0.00109757,0.00004520085,0.000021533,0.01228287,0.00001194287,0.0007162132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5105603,"threshold_uncertainty_score":0.3609511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005737852420947691,"score_gpt":0.2537707827519128,"score_spread":0.2480329303309652,"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."}}