{"id":"W2190667587","doi":"10.6339/jds.2003.01(2).131","title":"Analysis of Unbalanced Microarray Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Microarray analysis techniques; China; Data science; Microarray databases; Library science; Data analysis; Data mining; Computer science; Statistics; Political science; Mathematics; Biology; Gene","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":[0.0007697123,0.00003915673,0.0001172237,0.0001133444,0.00003708763,0.00002697405,0.001807787,0.00002374832,0.0000299597],"category_scores_gemma":[0.0003418654,0.00003143483,0.00003203641,0.0009511275,0.0001705375,0.0000445537,0.0006426651,0.00004400253,5.381578e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006355207,"about_ca_system_score_gemma":0.0005758295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001681202,"about_ca_topic_score_gemma":0.000008907719,"domain_scores_codex":[0.9991241,0.00002735226,0.0002364811,0.0002639579,0.0002661177,0.00008195655],"domain_scores_gemma":[0.9977617,0.000006508385,0.0002849042,0.001552304,0.0003350336,0.00005953806],"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":[0.00001074889,0.00002962798,0.003065082,0.000002265711,0.00006434225,0.000001389255,0.000009616234,0.00004051481,0.9890066,0.00001020381,0.004068903,0.003690704],"study_design_scores_gemma":[0.000244956,0.00004722432,0.03026665,0.00001615716,0.0002196599,0.00002564854,0.0002274451,0.001329423,0.8843977,0.000007971822,0.08314189,0.00007526024],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9524938,0.002871392,0.04204399,0.0008689092,0.0004376131,0.00003563118,0.0005520707,0.000001656097,0.0006949537],"genre_scores_gemma":[0.9922895,0.0006030778,0.006496013,0.0001086106,0.00006910665,1.015907e-7,0.0003422801,0.000002000958,0.00008928684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1046089,"threshold_uncertainty_score":0.3359348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06929950204773849,"score_gpt":0.3692050382421703,"score_spread":0.2999055361944318,"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."}}