{"id":"W4280544582","doi":"10.1101/2022.04.21.489108","title":"METAbolomics data Balancing with Over-sampling Algorithms (META-BOA): an online resource for addressing class imbalance","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"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; Class (philosophy); Sampling (signal processing); Data mining; Machine learning; Random forest; Visualization; Sample (material); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006338549,0.002929831,0.00226871,0.004691246,0.001358205,0.00322779,0.004485509,0.002128727,0.1210262],"category_scores_gemma":[0.02283343,0.001704058,0.003182547,0.003814898,0.0005893723,0.003351761,0.004946943,0.002762865,0.05857976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001142788,"about_ca_system_score_gemma":0.002966851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003311116,"about_ca_topic_score_gemma":0.00705853,"domain_scores_codex":[0.9971482,0.0004955341,0.0002455703,0.0007487624,0.001170537,0.0001914107],"domain_scores_gemma":[0.9894267,0.005931268,0.0006996,0.001832338,0.001537951,0.0005721544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001334992,0.0003258884,0.006386515,0.002690279,0.0005017266,0.0004308522,0.0003155343,0.005898525,0.00959308,0.005223479,0.8390835,0.1282155],"study_design_scores_gemma":[0.001594522,0.0003156943,0.0171805,0.001503086,0.0003649887,0.0009844635,0.0002456888,0.1861301,0.05175783,0.0714467,0.6677997,0.0006768229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.006220025,0.001241464,0.2099197,0.001397608,0.0006495442,0.0006559479,0.2223993,0.5489669,0.008549534],"genre_scores_gemma":[0.04516304,0.001107761,0.508626,0.002663824,0.0004010091,0.004087969,0.3005131,0.127042,0.0103953],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1210262,"threshold_uncertainty_score":0.404873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1269588896736987,"score_gpt":0.3143546181974931,"score_spread":0.1873957285237944,"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."}}