{"id":"W2165474022","doi":"10.1093/bioinformatics/btn165","title":"Designing succinct structural alphabets","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Chinese Government Scholarship; Natural Sciences and Engineering Research Council of Canada; Mitacs; National Natural Science Foundation of China","keywords":"Sequence (biology); Computer science; Construct (python library); State (computer science); Algorithm; Programming language; Chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001508624,0.0006391061,0.001126547,0.001709296,0.0008817313,0.001663821,0.001798504,0.0009680557,0.005865538],"category_scores_gemma":[0.008761628,0.000830665,0.0007287915,0.001910405,0.001077111,0.003654516,0.001865612,0.001449361,0.002036327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008476707,"about_ca_system_score_gemma":0.00144199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005936821,"about_ca_topic_score_gemma":0.00134494,"domain_scores_codex":[0.9984395,0.0004133487,0.0002183424,0.0002991391,0.0004521719,0.0001776133],"domain_scores_gemma":[0.9941936,0.002974597,0.0004921298,0.001228871,0.0008385448,0.0002723398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001010758,0.0005224044,0.006478334,0.001569749,0.00007944206,0.0009499985,0.0009338503,0.2465489,0.05146978,0.2404348,0.02059115,0.4294108],"study_design_scores_gemma":[0.0001302148,0.0003078111,0.0006114985,0.0002332532,0.00006351975,0.0005030055,0.0003104713,0.7170136,0.0484871,0.1978965,0.03437093,0.00007205134],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08898649,0.0006348155,0.8904444,0.0005548652,0.0002066906,0.0002777886,0.002175443,0.004917451,0.0118021],"genre_scores_gemma":[0.3568824,0.0007284094,0.6314175,0.0004149535,0.0001060307,0.0005940822,0.004669406,0.0009735629,0.004213717],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005865538,"threshold_uncertainty_score":0.01962221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009531432337122883,"score_gpt":0.2269266545942755,"score_spread":0.2173952222571526,"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."}}