{"id":"W1819658147","doi":"10.1186/1471-2105-6-68","title":"Feature selection and nearest centroid classification for protein mass spectrometry","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":171,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Feature selection; Computer science; Dimensionality reduction; Artificial intelligence; Principal component analysis; Pattern recognition (psychology); Linear discriminant analysis; Data mining; k-nearest neighbors algorithm; Curse of dimensionality; Centroid; Machine learning; Classifier (UML); Boosting (machine learning); Support vector machine","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":[0.0001640006,0.0001458005,0.0001396599,0.00007830958,0.0001432844,0.00005785413,0.00008546784,0.0001368196,0.000005320635],"category_scores_gemma":[0.0001195159,0.0001304962,0.00006119344,0.0001266482,0.00003524697,0.00001316242,0.0000397501,0.00007779924,0.00000675411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002670808,"about_ca_system_score_gemma":0.00004249934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.299107e-7,"about_ca_topic_score_gemma":0.00003307706,"domain_scores_codex":[0.9993008,0.00001310881,0.0001828907,0.0001668036,0.00009607821,0.00024031],"domain_scores_gemma":[0.9995511,0.000008606517,0.0001314685,0.0001654074,0.00008129534,0.00006208385],"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":[0.0001720785,0.00006468454,0.003452421,0.0002565165,0.0001015825,6.201436e-8,0.00007543756,0.00008260139,0.9704976,0.007034984,0.01122585,0.007036148],"study_design_scores_gemma":[0.002428524,0.0008555139,0.0158313,0.00002667948,0.00009409094,0.00003054866,0.0006510934,0.1349262,0.2685142,0.0004237349,0.5755057,0.0007123827],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3545909,0.001726755,0.6369594,0.001959745,0.0001748881,0.001575685,0.0001048868,0.00006168092,0.002846152],"genre_scores_gemma":[0.2325186,0.0003765782,0.7641679,0.0001760599,0.0005523437,0.00008952177,0.0001904386,0.00002265034,0.001905947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7019835,"threshold_uncertainty_score":0.5321482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01365895679510542,"score_gpt":0.2436644381373854,"score_spread":0.23000548134228,"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."}}