{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00278554,0.0009525084,0.001364877,0.002563887,0.0007108962,0.0008117898,0.001122159,0.000909389,0.001410529],"category_scores_gemma":[0.00668798,0.0002134756,0.001067186,0.002503031,0.0005072847,0.0009115583,0.000749459,0.0007691269,0.0008722653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000806447,"about_ca_system_score_gemma":0.0008209195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002150842,"about_ca_topic_score_gemma":0.001204261,"domain_scores_codex":[0.9980807,0.0004547854,0.0001188671,0.0003862053,0.0008244867,0.0001349323],"domain_scores_gemma":[0.9973711,0.00112444,0.0003014198,0.0002084411,0.000919109,0.00007553059],"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":[0.0006482264,0.0003353794,0.007027515,0.0002842795,0.0002031054,0.0001992504,0.0001410363,0.13255,0.02202221,0.003159726,0.004931185,0.828498],"study_design_scores_gemma":[0.00004139667,0.0002941201,0.006360077,0.00002847863,0.00004957421,0.0002663735,0.00003875647,0.9688985,0.01573904,0.005861995,0.002379643,0.00004209427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09430326,0.001846324,0.8993361,0.0002656831,0.0001635466,0.0001674908,0.0003972306,0.002513251,0.00100705],"genre_scores_gemma":[0.5571774,0.0004504643,0.439712,0.00008101269,0.0001196143,0.0002716002,0.0009629304,0.0001010219,0.001123933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00278554,"threshold_uncertainty_score":0.01473147,"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."}}