{"id":"W2163449716","doi":"10.1002/jcc.20918","title":"Prediction of protein structural class using novel evolutionary collocation‐based sequence representation","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":172,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Representation (politics); Support vector machine; Sequence (biology); Protein methods; Class (philosophy); Pseudo amino acid composition; Data mining; Machine learning; Sequence analysis; Amino acid; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001304066,0.00009524165,0.0001294718,0.0000455291,0.0000890758,0.000006602374,0.0001382106,0.00009564211,0.0000225482],"category_scores_gemma":[0.0002282509,0.0000961184,0.00009179258,0.000132421,0.0001216885,0.00002013929,0.00002733318,0.0001406708,3.239716e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000643354,"about_ca_system_score_gemma":0.0005556899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003638451,"about_ca_topic_score_gemma":9.263479e-8,"domain_scores_codex":[0.998858,0.00002615667,0.0005354511,0.00009598213,0.0003994562,0.00008491505],"domain_scores_gemma":[0.9983259,0.00002567,0.0007394713,0.0001112057,0.0007465539,0.00005122888],"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":[0.00006934657,0.0000256234,0.004334923,0.00004759799,0.00002685028,0.000001021069,0.00002469447,0.5113055,0.4840326,0.000007397284,0.00008821076,0.00003617195],"study_design_scores_gemma":[0.001966701,0.0002246651,0.03373256,0.0001336334,0.00003951598,0.001583673,0.00007727627,0.5301853,0.4306143,0.0007209118,0.0005217151,0.0001997453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9425746,0.00006695339,0.0569228,0.00007067402,0.0000598125,0.00008015293,0.00004336253,0.000004640713,0.0001770175],"genre_scores_gemma":[0.9177994,0.000002402329,0.08170687,0.000028397,0.0001947949,0.000001534123,0.0002012321,0.000008521509,0.00005685396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0534183,"threshold_uncertainty_score":0.3919595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03889561558284672,"score_gpt":0.2932569067144774,"score_spread":0.2543612911316307,"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."}}