{"id":"W4304757181","doi":"10.1093/bioinformatics/btac649","title":"METAbolomics data Balancing with Over-sampling Algorithms (META-BOA): an online resource for addressing class imbalance","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Overfitting; Sampling (signal processing); Class (philosophy); Data mining; Machine learning; Sample (material); Visualization; Random forest; Resource (disambiguation); Artificial intelligence; Algorithm; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001454121,0.0003091791,0.000490038,0.000211203,0.0007263645,0.0004573208,0.004167087,0.00007237141,0.00001253931],"category_scores_gemma":[0.0001466383,0.0002683201,0.00007885307,0.0006764086,0.00008076401,0.002818072,0.001919796,0.0003851502,0.000002482076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001533735,"about_ca_system_score_gemma":0.000238388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001459642,"about_ca_topic_score_gemma":0.00001095774,"domain_scores_codex":[0.9973288,0.00009205921,0.0007538872,0.0005830904,0.0007032741,0.0005389275],"domain_scores_gemma":[0.9954299,0.0002528678,0.0006969867,0.003343134,0.000134509,0.0001426208],"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":[0.0005054178,0.0023869,0.001446655,0.001511132,0.002756357,0.00004090119,0.01017051,0.03113213,0.006405273,0.1016455,0.1388214,0.7031779],"study_design_scores_gemma":[0.0004314793,0.0001592931,0.0001766973,0.0000156123,0.0001121292,0.00003973514,0.0004443669,0.8010129,0.0004976821,0.0002128208,0.1965528,0.0003444335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008626782,0.0001821222,0.9944239,0.0004959893,0.0001504671,0.0006319564,0.002376019,0.000699202,0.0001776545],"genre_scores_gemma":[0.006013474,0.0000212582,0.9879093,0.001881383,0.0001137959,0.0001606834,0.003788806,0.00003872508,0.0000726264],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7698808,"threshold_uncertainty_score":0.9999769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1940735828464191,"score_gpt":0.3426043390083074,"score_spread":0.1485307561618883,"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."}}