{"id":"W2096586490","doi":"10.1186/1756-0500-4-267","title":"GO Trimming: Systematically reducing redundancy in large Gene Ontology datasets","year":2011,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Trimming; Computer science; Redundancy (engineering); Gene ontology; Data mining; Information retrieval; Machine learning; Gene; 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":[0.00258498,0.0001475069,0.0002430491,0.0001484858,0.0001250471,0.00003922393,0.0004651331,0.0002430796,0.00006969261],"category_scores_gemma":[0.0008783535,0.0001181485,0.00006563088,0.0001965892,0.0001338735,0.000008713687,0.0003977522,0.000300891,0.0001133133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003257733,"about_ca_system_score_gemma":0.0002232913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002053459,"about_ca_topic_score_gemma":0.0007498704,"domain_scores_codex":[0.9978487,0.0003180624,0.0004856211,0.0003702235,0.0002385336,0.0007388277],"domain_scores_gemma":[0.9988106,0.0001245906,0.00007945472,0.0007322118,0.0001062045,0.0001468838],"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":[0.003903392,0.00342801,0.0999054,0.005590834,0.0006897215,0.0003889168,0.0087206,0.0003027628,0.7368981,0.03418073,0.07447766,0.03151385],"study_design_scores_gemma":[0.01648102,0.00602109,0.1111948,0.002485139,0.000141587,0.000768988,0.005773187,0.02518403,0.6938501,0.02113364,0.1125542,0.004412137],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9453215,0.003650791,0.03046153,0.0002622993,0.0004968034,0.001776782,0.0003346714,0.00003744471,0.01765817],"genre_scores_gemma":[0.9868029,0.0001320503,0.01198116,0.00005581859,0.0001997001,0.00006155091,0.0004063785,0.00002278064,0.0003376962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.043048,"threshold_uncertainty_score":0.4817955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1295681124709397,"score_gpt":0.369263634827619,"score_spread":0.2396955223566794,"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."}}