{"id":"W1571001643","doi":"10.1007/11424918_17","title":"Fast Protein Superfamily Classification Using Principal Component Null Space Analysis","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Principal component analysis; Artificial intelligence; Curse of dimensionality; Classifier (UML); Artificial neural network; Machine learning; Pattern recognition (psychology); Support vector machine; Data mining","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004949397,0.0003884081,0.0003684638,0.000487639,0.0001674261,0.0001459955,0.0008159721,0.0003841558,0.00002672173],"category_scores_gemma":[0.00006955085,0.000367608,0.0001705513,0.000350045,0.0004360372,0.00001387959,0.0004966639,0.0005103731,0.00001529656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001737808,"about_ca_system_score_gemma":0.0002703375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002685301,"about_ca_topic_score_gemma":0.0001068395,"domain_scores_codex":[0.9977877,0.00003601176,0.000455898,0.0007803018,0.0005426943,0.0003974569],"domain_scores_gemma":[0.9984723,0.00002679632,0.000319725,0.00089704,0.0001741083,0.0001100326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004015373,0.00006265678,0.002045959,0.00009375644,0.0001942843,0.000009097038,0.000402724,0.7862272,0.1201002,0.001224005,0.00001164471,0.08958835],"study_design_scores_gemma":[0.0002148512,0.000142754,0.001520126,0.0001109531,0.00009030869,0.00002173436,6.688008e-7,0.9817289,0.009773835,0.0002771039,0.00551341,0.0006053334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04310849,0.0001730011,0.9536386,0.0001899804,0.000185169,0.0003997642,0.00001199249,0.00002661438,0.002266455],"genre_scores_gemma":[0.6937714,0.00002384622,0.3043906,0.0003468335,0.0005825539,0.000006496915,0.0001435078,0.00003774806,0.000697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6506629,"threshold_uncertainty_score":0.9998776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01715153564647308,"score_gpt":0.2630029553141384,"score_spread":0.2458514196676653,"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."}}