{"id":"W4233884501","doi":"10.1504/ijdmb.2020.109503","title":"Identification of protein hot regions by combining structure-based classification, energy-based clustering and sequence-based conservation in evolution","year":2020,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Sequence (biology); Computer science; Identification (biology); Energy conservation; Data mining; Energy (signal processing); Pattern recognition (psychology); Artificial intelligence; Biological system; Algorithm; Mathematics; Statistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002448791,0.00009366263,0.000123817,0.0001070536,0.00003366682,0.00005366961,0.000289892,0.00008662946,9.428106e-7],"category_scores_gemma":[0.0002461259,0.00008796852,0.00002106173,0.00008977208,0.00008932973,0.00006500236,0.00006213231,0.0000732582,3.744728e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002318556,"about_ca_system_score_gemma":0.0002025958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000151137,"about_ca_topic_score_gemma":0.00002873328,"domain_scores_codex":[0.9989393,0.00003755877,0.0006094277,0.0001185127,0.0002216893,0.00007350722],"domain_scores_gemma":[0.9987971,0.00002863224,0.0007142378,0.0001503373,0.0002578814,0.00005184026],"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":[0.0007323047,0.00005630344,0.01187854,0.0002107375,0.00008961819,0.000003613546,0.0002520698,0.001695811,0.9562538,0.0002809136,0.0006986716,0.02784757],"study_design_scores_gemma":[0.001473776,0.0002223151,0.001423726,0.0001878389,0.00002195888,0.00001573126,0.0002715325,0.9562758,0.03944264,0.00007298899,0.0004636608,0.0001280118],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4792041,0.0001618532,0.5186263,0.001479471,0.00005821608,0.00008255887,0.0003765732,0.000003669791,0.000007238965],"genre_scores_gemma":[0.9545542,0.00002166054,0.04385667,0.0004393874,0.00004230827,0.000001773845,0.001076342,0.000005918739,0.000001741271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.95458,"threshold_uncertainty_score":0.3587252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0338256636374612,"score_gpt":0.276483070015979,"score_spread":0.2426574063785178,"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."}}