{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000608415,0.0001424039,0.0001125982,0.00003372025,0.0001647607,0.00001599666,0.0001741447,0.0001271339,0.00001466154],"category_scores_gemma":[0.0000455694,0.0001214925,0.00006621549,0.00006621029,0.00007368912,0.000009653985,0.00008642616,0.00007185483,0.00002379036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001076475,"about_ca_system_score_gemma":0.00007021765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005304288,"about_ca_topic_score_gemma":0.00000532144,"domain_scores_codex":[0.9992879,0.00001227327,0.0002263466,0.0001079689,0.0001307505,0.0002347556],"domain_scores_gemma":[0.9995012,0.000005675827,0.00008596051,0.0002768956,0.0000519408,0.00007837287],"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":[0.0006025727,0.00009872367,0.1018993,0.0005419242,0.0007075971,0.0001387253,0.004950825,0.002889012,0.7147737,0.003131523,0.05338092,0.1168852],"study_design_scores_gemma":[0.004164941,0.001383792,0.05090787,0.00006155149,0.00008888978,0.00268414,0.000839115,0.03694924,0.8311077,0.001419231,0.06796985,0.002423652],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9543168,0.0002926808,0.04023724,0.00002799721,0.0002143829,0.000185191,0.00001783192,0.00003858354,0.004669298],"genre_scores_gemma":[0.9310005,0.00006529943,0.06796081,0.0003504669,0.0001641042,0.000004981928,0.0001321114,0.00001401392,0.0003076669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.116334,"threshold_uncertainty_score":0.495432,"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."}}