{"id":"W2111527303","doi":"10.1186/1742-4682-4-47","title":"Measuring the functional sequence complexity of proteins","year":2007,"lang":"en","type":"article","venue":"Theoretical Biology and Medical Modelling","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Computational biology; Measure (data warehouse); Protein sequencing; Computer science; Variable (mathematics); Biology; Bioinformatics; Algorithm; Data mining; Mathematics; Peptide sequence; Genetics; Gene","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":[0.001532175,0.0003819821,0.0003629198,0.002402287,0.0003283873,0.0007964073,0.0004422684,0.0004952463,0.0009278905],"category_scores_gemma":[0.007808231,0.000150292,0.0003438367,0.001232112,0.00136669,0.00146799,0.0006110155,0.0004855676,0.0001604485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000866061,"about_ca_system_score_gemma":0.0003887995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004382262,"about_ca_topic_score_gemma":0.0002998118,"domain_scores_codex":[0.9988762,0.0002972306,0.00009677376,0.0001773635,0.000482593,0.00006978746],"domain_scores_gemma":[0.9914888,0.004947572,0.00153155,0.0006667344,0.001074953,0.0002903179],"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":[0.0007138015,0.0002395078,0.1283419,0.001040343,0.0003363433,0.0003857774,0.0008139199,0.1940912,0.2819235,0.1209759,0.001536381,0.2696013],"study_design_scores_gemma":[0.00003470391,0.0006391587,0.1030114,0.0001086829,0.000116204,0.002646098,0.0003327309,0.5202178,0.2139882,0.1517595,0.006919635,0.0002259292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6342696,0.0009210134,0.3602314,0.0003693993,0.00003083901,0.00005370269,0.0005635768,0.000234668,0.00332583],"genre_scores_gemma":[0.9319187,0.0001816605,0.06717863,0.00003453838,0.00003378399,0.00004356324,0.0003213243,0.00002098428,0.0002668748],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002402287,"threshold_uncertainty_score":0.008103073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05477837189285917,"score_gpt":0.2846450181320267,"score_spread":0.2298666462391675,"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."}}