{"id":"W1601201751","doi":"10.1007/11510888_33","title":"Prediction of Secondary Protein Structure Content from Primary Sequence Alone – A Feature Selection Based Approach","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":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Feature selection; Computer science; Representation (politics); Artificial intelligence; Set (abstract data type); Pattern recognition (psychology); Feature (linguistics); Protein function prediction; Selection (genetic algorithm); Sequence (biology); Protein secondary structure; Function (biology); Data mining; Machine learning; Protein function; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002777971,0.000406683,0.0003917378,0.0002300502,0.0001036275,0.00006383024,0.0006413812,0.0006870988,0.00003408279],"category_scores_gemma":[0.0000764837,0.000366065,0.0001081334,0.0001661749,0.0004472192,0.00002229803,0.0002547196,0.0009492933,0.000001300769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001565262,"about_ca_system_score_gemma":0.0006386416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002997749,"about_ca_topic_score_gemma":0.00005092739,"domain_scores_codex":[0.9979292,0.00004080034,0.0004181961,0.0007664165,0.0005447901,0.000300566],"domain_scores_gemma":[0.9986219,0.00003189823,0.0004360088,0.0005891179,0.0002393054,0.00008175698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001713167,0.00006628522,0.000772308,0.0004173822,0.00007856189,0.000004674757,0.0002532162,0.1277357,0.6681151,0.0001077476,0.0001731215,0.2021046],"study_design_scores_gemma":[0.001981096,0.001305297,0.003158818,0.000893404,0.00007661898,0.0001320415,0.000001108027,0.6636983,0.3147973,0.002406863,0.0102352,0.001313912],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0126917,0.0004062344,0.9834636,0.0001462628,0.0002867316,0.0007633991,0.0003560078,0.00004007898,0.00184599],"genre_scores_gemma":[0.4505595,0.00001665175,0.5455235,0.0009627001,0.0008264689,0.00001442025,0.001488694,0.00004950928,0.0005585557],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5359626,"threshold_uncertainty_score":0.9998791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01556352488451747,"score_gpt":0.2160696792375443,"score_spread":0.2005061543530268,"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."}}