{"id":"W2035431183","doi":"10.1007/s10549-009-0557-0","title":"Learning to predict relapse in invasive ductal carcinomas based on the subcellular localization of junctional proteins","year":2009,"lang":"en","type":"article","venue":"Breast Cancer Research and Treatment","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Athabasca University; University of Saskatchewan; University of Alberta","funders":"","keywords":"Classifier (UML); Breast cancer; Subcellular localization; Decision tree; Machine learning; PTEN; Artificial intelligence; Biology; Decision tree learning; Bioinformatics; Computer science; Cancer; Cytoplasm; Signal transduction; PI3K/AKT/mTOR pathway","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":[0.0002424553,0.00009176647,0.00008268422,0.00009209559,0.0001077181,0.00001640487,0.00006837752,0.00004941247,0.00002616072],"category_scores_gemma":[0.00009206852,0.00006114888,0.00002505579,0.0001672575,0.00006512591,0.000003319614,0.00002775573,0.0001183671,0.000002637169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009567605,"about_ca_system_score_gemma":0.0002030013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004643006,"about_ca_topic_score_gemma":0.000240133,"domain_scores_codex":[0.9991414,0.0001253421,0.000125666,0.0001713832,0.0002469711,0.0001892635],"domain_scores_gemma":[0.9996017,0.00003211666,0.00003464223,0.0001567207,0.0001036007,0.00007117019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005584131,0.001509119,0.7397962,0.0001249198,0.0001512587,0.00004795309,0.001565753,0.1448735,0.07037723,0.0009113488,0.001035944,0.0340227],"study_design_scores_gemma":[0.005399905,0.02347981,0.7776491,0.0004353351,0.00003050758,0.0000693127,0.0008526922,0.04564846,0.1393045,0.0002124469,0.006475254,0.0004426479],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996338,0.0001205263,0.0003063356,0.002064878,0.0000142948,0.0005838047,0.00002713032,0.000004577292,0.0005405198],"genre_scores_gemma":[0.9992342,0.00008707085,0.00009472755,0.00007838695,0.00005916329,0.0001175007,0.00006502631,0.000006902681,0.0002570191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09922501,"threshold_uncertainty_score":0.2493579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01810154030875124,"score_gpt":0.2895833958624085,"score_spread":0.2714818555536573,"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."}}