{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004999769,0.0005627737,0.0004857183,0.001680474,0.0002570954,0.0006239774,0.0005190876,0.0006361994,0.001235378],"category_scores_gemma":[0.001609569,0.0001255006,0.000428007,0.001279306,0.0001972713,0.0008998257,0.0004719086,0.0005633772,0.000830337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003281807,"about_ca_system_score_gemma":0.0006045282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001273273,"about_ca_topic_score_gemma":0.001791028,"domain_scores_codex":[0.9996718,0.00005456611,0.00002377895,0.00009574222,0.0001200208,0.00003406372],"domain_scores_gemma":[0.9994304,0.0001616398,0.0001226023,0.00009131255,0.000158746,0.00003532449],"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":[0.0009661449,0.0007224789,0.03168133,0.0003902462,0.0001426026,0.0003504074,0.0001978186,0.123753,0.1918097,0.006877956,0.011374,0.6317343],"study_design_scores_gemma":[0.00002498219,0.0001445016,0.006190292,0.00002191594,0.00002659325,0.0001902348,0.0000420299,0.9707134,0.01702215,0.002943636,0.002656188,0.00002398293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3987942,0.0008129903,0.5884517,0.0002539732,0.00008950372,0.0001609266,0.003182846,0.004941437,0.003312483],"genre_scores_gemma":[0.7572429,0.0003789198,0.2329514,0.0001005913,0.00004505406,0.000146391,0.007639181,0.0001480024,0.001347636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001680474,"threshold_uncertainty_score":0.004132688,"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."}}