{"id":"W2050870676","doi":"10.1186/1471-2105-10-410","title":"Refining gene signatures: a Bayesian approach","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Canada; Douglas Mental Health University Institute; Natural Sciences and Engineering Research Council of Canada","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Bayesian probability; Context (archaeology); Data mining; Machine learning; DNA microarray; Artificial intelligence; Curse of dimensionality; Identification (biology); Microarray analysis techniques; Feature selection; Bayes' theorem; Pattern recognition (psychology); Gene; Biology; Genetics; Gene expression","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":[0.0001257435,0.000126138,0.00009549161,0.00005624192,0.00008195678,0.00003944405,0.0001922154,0.0001676444,0.000008673568],"category_scores_gemma":[0.00004034236,0.0001088141,0.00006817891,0.0001211379,0.00002374522,0.000007016738,0.00003231764,0.00008395725,0.00001388211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000115841,"about_ca_system_score_gemma":0.00007955085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.957588e-7,"about_ca_topic_score_gemma":0.000001117365,"domain_scores_codex":[0.9992537,0.00002004538,0.0002433633,0.0001519064,0.000142667,0.0001883315],"domain_scores_gemma":[0.9993727,0.00000345319,0.000111889,0.0003829913,0.00004542119,0.00008352066],"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":[0.0002647486,0.0003141047,0.001187482,0.0001768879,0.00005582985,0.000001068327,0.0008773373,0.006529954,0.8139915,0.003114043,0.0731401,0.100347],"study_design_scores_gemma":[0.003450321,0.001185267,0.01305551,0.00009271343,0.00007649211,0.00008288142,0.001608612,0.2591736,0.3346588,0.0006161762,0.3842995,0.0017001],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01000826,0.0006747569,0.9250942,0.0001354941,0.0001562974,0.0001769883,0.00001147105,0.00006235069,0.06368016],"genre_scores_gemma":[0.5934507,0.00008490551,0.4023067,0.001801572,0.0002683132,0.00002020283,0.0003905194,0.00001626175,0.001660802],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5834425,"threshold_uncertainty_score":0.4437309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01636014766742929,"score_gpt":0.250817003064846,"score_spread":0.2344568553974167,"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."}}