{"id":"W2108197782","doi":"10.1016/j.jbi.2004.07.008","title":"Classification and knowledge discovery in protein databases","year":2004,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Imperial Bank of Commerce (Canada)","funders":"U.S. National Library of Medicine; National Institutes of Health; National Science Foundation","keywords":"Artificial intelligence; Computer science; Machine learning; Feature selection; Cluster analysis; Robustness (evolution); Pattern recognition (psychology); Data mining; Ensemble learning","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":[0.0007526706,0.00007805599,0.0001584463,0.0003590948,0.00003080397,0.0001180769,0.0005107183,0.00005232669,0.000001204187],"category_scores_gemma":[0.0002623183,0.0000588455,0.00002491617,0.000451362,0.0001352687,0.003005581,0.0001609707,0.0001976496,0.000005580811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001081285,"about_ca_system_score_gemma":0.0003022451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003447254,"about_ca_topic_score_gemma":0.000002944394,"domain_scores_codex":[0.9986639,0.00002721415,0.0008086095,0.00005910071,0.0003083615,0.000132805],"domain_scores_gemma":[0.9990307,0.00005382214,0.0004556017,0.0002630346,0.00009216738,0.0001046517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004950589,0.001470409,0.001354372,0.0005766972,0.00004552357,0.00005198799,0.008407217,0.00001458902,0.02685905,0.7016554,0.00758636,0.2519289],"study_design_scores_gemma":[0.01683379,0.003627005,0.138703,0.007408,0.00007283501,0.002835118,0.006617858,0.131759,0.0963078,0.124847,0.4685071,0.002481443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05665304,0.00008467102,0.9411774,0.001574064,0.0000997439,0.0001167829,0.000007710745,0.00002797523,0.0002586295],"genre_scores_gemma":[0.6584296,0.0001364349,0.3411868,0.0001598305,0.00005027951,0.000005651224,0.00001062316,0.000003529322,0.00001725477],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6017765,"threshold_uncertainty_score":0.239965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03453498297277332,"score_gpt":0.3070496474201495,"score_spread":0.2725146644473762,"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."}}