{"id":"W1986913015","doi":"10.1016/j.bbrc.2006.07.141","title":"Classifier ensembles for protein structural class prediction with varying homology","year":2006,"lang":"en","type":"article","venue":"Biochemical and Biophysical Research Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":164,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pattern recognition (psychology); Classifier (UML); Artificial intelligence; Computer science; Support vector machine; Homology (biology); Protein structure prediction; Computational biology; Mathematics; Algorithm; Protein structure; Biology; Genetics; Amino acid","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":[0.000248959,0.00012895,0.000125352,0.00005414265,0.0004147261,0.00006006336,0.0004219607,0.0001687432,0.000003047092],"category_scores_gemma":[0.0002138699,0.00009829617,0.00004961268,0.0001649456,0.0007979778,0.000009172209,0.0003231576,0.0003348048,0.000003260603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002127912,"about_ca_system_score_gemma":0.00007050423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004956383,"about_ca_topic_score_gemma":0.00001434069,"domain_scores_codex":[0.9988781,0.0001255068,0.0002008714,0.000255519,0.0002107322,0.0003292657],"domain_scores_gemma":[0.9987803,0.0001140412,0.00005438899,0.0006901413,0.0002717949,0.00008937984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001449519,0.00007766288,0.0003533615,0.00004800163,0.00002132563,1.753011e-7,0.00001347584,0.000004789148,0.9877272,0.008753992,0.001963578,0.0008914765],"study_design_scores_gemma":[0.001789874,0.001778134,0.004623985,0.00009609344,0.00003976024,0.00003822529,0.00008830089,0.02660493,0.8788835,0.006611099,0.07894578,0.0005002759],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9914896,0.0003271837,0.001732126,0.002616538,0.00001423259,0.0006727686,0.00008907644,0.00003263591,0.003025794],"genre_scores_gemma":[0.983951,0.00004207446,0.0143243,0.00004103422,0.0002036533,0.0002315678,0.0007199577,0.00001677314,0.000469578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1088437,"threshold_uncertainty_score":0.4008401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03527510867903335,"score_gpt":0.3373514513869992,"score_spread":0.3020763427079659,"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."}}