{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005759498,0.001214106,0.00107775,0.0008984875,0.0005179002,0.0007450262,0.001023729,0.0009056398,0.000653326],"category_scores_gemma":[0.01421147,0.0002675065,0.000823478,0.0005873747,0.0006612782,0.0007924372,0.0006764135,0.0008872088,0.0004778391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003998126,"about_ca_system_score_gemma":0.0006630162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001658094,"about_ca_topic_score_gemma":0.001952034,"domain_scores_codex":[0.998195,0.0006905276,0.0001157871,0.0005848148,0.0002952971,0.0001185151],"domain_scores_gemma":[0.9945238,0.002966194,0.0005495244,0.001146397,0.0006858654,0.0001283275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002022282,0.001255789,0.1437131,0.0003993712,0.0005846068,0.0006558131,0.0004515777,0.1492975,0.1249188,0.001712351,0.005730967,0.5692579],"study_design_scores_gemma":[0.0001832988,0.0008000886,0.04805201,0.00008939621,0.0004340722,0.0007888906,0.0002718419,0.825639,0.1096604,0.00649588,0.007486763,0.00009833658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6400948,0.001845384,0.3524356,0.0006944025,0.0002456743,0.00042967,0.0006332628,0.002040583,0.00158058],"genre_scores_gemma":[0.8833326,0.0002137305,0.1126505,0.0003907166,0.00008556507,0.0002348375,0.001972787,0.0001416305,0.000977627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005759498,"threshold_uncertainty_score":0.03045946,"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."}}