{"id":"W2338607938","doi":"10.1109/tnb.2016.2553119","title":"Identifying Individual-Cancer-Related Genes by Rebalancing the Training Samples","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on NanoBioscience","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Fundamental Research Funds for the Central Universities; Northwestern Polytechnical University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Resampling; Logistic regression; Identification (biology); Computer science; Artificial intelligence; Cancer; Regression; Machine learning; Set (abstract data type); Random forest; Gene; Computational biology; Pattern recognition (psychology); Mathematics; Statistics; Biology; Genetics","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":[0.0003430529,0.0001411329,0.00009799809,0.00004048362,0.000444469,0.00006626566,0.0003848803,0.0001105535,0.00003646332],"category_scores_gemma":[0.000005549098,0.00008421248,0.00008505792,0.0001930063,0.000190369,0.00001616743,0.000005572444,0.00009061884,0.00001417062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002400001,"about_ca_system_score_gemma":0.00008610653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001634658,"about_ca_topic_score_gemma":0.00003538996,"domain_scores_codex":[0.9989395,0.00003651174,0.0002380078,0.0002875574,0.0001776775,0.0003207991],"domain_scores_gemma":[0.9994634,0.00004224299,0.00009897424,0.0002946265,0.00003226487,0.00006852318],"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":[0.000008329438,0.00002235436,0.00002573368,0.000004140507,0.00003629336,2.387665e-7,0.0003831546,0.0002025191,0.8697005,0.00002694997,0.0007472752,0.1288425],"study_design_scores_gemma":[0.000626713,0.0001548755,0.0002409304,0.00009916184,0.00004854049,0.00002659107,0.0004014965,0.0003925594,0.9750926,0.000213862,0.02234206,0.0003605344],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3420629,0.0008465965,0.6539898,0.001076841,0.001303391,0.0002502385,0.0001916211,0.00005268803,0.0002259966],"genre_scores_gemma":[0.9971415,0.0009636065,0.0006547523,0.0003850529,0.00004974262,0.00003325835,0.000003594726,0.00001294739,0.0007554829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6550787,"threshold_uncertainty_score":0.3434085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02909360852314391,"score_gpt":0.2582098246154407,"score_spread":0.2291162160922968,"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."}}