{"id":"W2153925032","doi":"10.5539/ijb.v7n1p100","title":"Optimal Algorithm for Metabolomics Classification and Feature Selection varies by Dataset","year":2014,"lang":"en","type":"article","venue":"International Journal of Biology","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Feature selection; Random forest; Computer science; Metabolomics; Linear discriminant analysis; Artificial intelligence; Robustness (evolution); Data mining; Machine learning; Identification (biology); Partial least squares regression; Support vector machine; Pattern recognition (psychology); Algorithm; Bioinformatics; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003109088,0.00008632064,0.0001518699,0.00007048197,0.00004512129,0.0000252877,0.0001663388,0.0001058581,0.000004684718],"category_scores_gemma":[0.0001857425,0.00007097064,0.0000505872,0.00002660897,0.00007043169,0.00000755366,0.00005229649,0.00007584627,4.055536e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001047069,"about_ca_system_score_gemma":0.00002385916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003201806,"about_ca_topic_score_gemma":0.000003251479,"domain_scores_codex":[0.9994549,0.00004535664,0.0001919481,0.0001464908,0.00006271381,0.00009860414],"domain_scores_gemma":[0.9993464,0.00003732846,0.0002391359,0.00005808756,0.0002838812,0.00003518223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002316618,0.00006105859,0.001417663,0.00000323821,0.0005661022,2.841083e-7,0.00001379827,0.00001114287,0.8617592,0.003964675,0.0659253,0.06604588],"study_design_scores_gemma":[0.000924726,0.000656763,0.001287507,0.000002449836,0.0000494715,0.0001067907,0.00003279485,0.00179455,0.04510648,0.0007363278,0.9491959,0.0001062647],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2429129,0.003243638,0.7471054,0.003372495,0.00141128,0.0001333779,0.001731078,0.000004705618,0.00008504862],"genre_scores_gemma":[0.8423447,0.004174875,0.1464973,0.0009651752,0.002120787,0.00001551851,0.003577315,0.00002168221,0.0002826971],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8832706,"threshold_uncertainty_score":0.2894098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01014521852864316,"score_gpt":0.2854282672040444,"score_spread":0.2752830486754012,"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."}}