{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005477826,0.0004541102,0.0006869494,0.002614077,0.0005804534,0.0005574376,0.0006472425,0.0005387908,0.0005255626],"category_scores_gemma":[0.00100513,0.0002378334,0.0006602096,0.001662751,0.0003106964,0.0008196099,0.0004839362,0.0003747474,0.0002612259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003567995,"about_ca_system_score_gemma":0.0004441472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003160438,"about_ca_topic_score_gemma":0.004128963,"domain_scores_codex":[0.9995149,0.00006771438,0.0000432937,0.0001733525,0.000143362,0.00005740661],"domain_scores_gemma":[0.9994596,0.000134015,0.0001322444,0.00005030949,0.0001734801,0.0000504341],"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":[0.000742592,0.0005444423,0.1570938,0.000520024,0.0005593566,0.0006260275,0.0005832225,0.07115608,0.1732711,0.004213929,0.003501982,0.5871875],"study_design_scores_gemma":[0.00003632972,0.0001793636,0.07088397,0.00004226799,0.0001750209,0.0007813202,0.0002251376,0.884883,0.03587299,0.004417936,0.002430466,0.00007220475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6492838,0.001416913,0.3453829,0.0001941526,0.00004179118,0.0001584295,0.000377749,0.001134735,0.002009477],"genre_scores_gemma":[0.8523328,0.0003076407,0.145195,0.0000622935,0.00002410924,0.00006695327,0.0008520629,0.00007917672,0.001080009],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.003160438,"threshold_uncertainty_score":0.006284118,"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."}}