{"id":"W2737578470","doi":"10.1186/s12859-017-1758-x","title":"Exploring general-purpose protein features for distinguishing enzymes and non-enzymes within the twilight zone","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"European Regional Development Fund; Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; Fundação para a Ciência e a Tecnologia; Universitat de València","keywords":"Benchmark (surveying); Proteome; Computational biology; Computer science; Protein function prediction; Structural bioinformatics; Protein structure database; Sequence alignment; Similarity (geometry); Structural alignment; Protein methods; Protein sequencing; Annotation; Protein family; Protein function; Function (biology); Structural similarity; Sequence (biology); Protein structure; Multiple sequence alignment; Artificial intelligence; Biology; Bioinformatics; Peptide sequence; Sequence database; Genetics; Gene; Biochemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0007272277,0.0003138484,0.0002539942,0.00005027936,0.001199945,0.0006652902,0.0007303707,0.0001618574,0.000002233124],"category_scores_gemma":[0.001657845,0.0002178216,0.0001164157,0.00004089962,0.0002507883,0.00008699785,0.0005213114,0.0002485281,0.000006173324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001485477,"about_ca_system_score_gemma":0.00008894926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003576477,"about_ca_topic_score_gemma":0.0001230455,"domain_scores_codex":[0.9986149,0.0000311293,0.000530568,0.0002095208,0.0002302536,0.0003835988],"domain_scores_gemma":[0.9980114,0.00005781711,0.0006577478,0.001033474,0.0001258393,0.0001137579],"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":[0.004161162,0.001000932,0.1530337,0.02945936,0.002911128,0.00003422503,0.0914553,0.02147482,0.1561883,0.1734074,0.12971,0.2371637],"study_design_scores_gemma":[0.004762426,0.001201215,0.03192105,0.0007190706,0.0002364242,0.0001851484,0.004703246,0.4180893,0.4009705,0.0006073932,0.1342692,0.00233496],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8258196,0.001007068,0.1599899,0.0009590725,0.001032785,0.003098677,0.0001287657,0.0001220504,0.007842014],"genre_scores_gemma":[0.5534595,0.0001063282,0.4406567,0.0004447858,0.001027292,0.0004098212,0.0001902801,0.00007245178,0.00363281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3966145,"threshold_uncertainty_score":0.922913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04100894492899753,"score_gpt":0.2774749193984699,"score_spread":0.2364659744694724,"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."}}