{"id":"W3063921741","doi":"10.1504/ijdmb.2020.10031424","title":"Identification of protein hot regions by combing 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":"Combing; Cluster analysis; Computer science; Sequence (biology); Identification (biology); Data mining; Hot spot (computer programming); Pattern recognition (psychology); Biological system; Artificial intelligence; Materials science; Biology; Genetics","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":[0.0002318686,0.00008990947,0.0001176694,0.0001028412,0.00003269055,0.00005294588,0.00028079,0.00008304633,8.580833e-7],"category_scores_gemma":[0.0002277237,0.00008425197,0.00002065595,0.00008587065,0.00008447725,0.0000635904,0.00005948709,0.00006922462,3.468524e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002392518,"about_ca_system_score_gemma":0.0001897402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001620327,"about_ca_topic_score_gemma":0.00003097333,"domain_scores_codex":[0.9989785,0.00003573866,0.0005866921,0.0001136887,0.0002147413,0.00007064075],"domain_scores_gemma":[0.9988484,0.00002620434,0.0006780842,0.0001468072,0.0002510931,0.00004942916],"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":[0.0006193497,0.00005186885,0.01104988,0.0002046417,0.00007837066,0.000003129971,0.0001986448,0.001500657,0.9588283,0.000244784,0.0005944725,0.02662592],"study_design_scores_gemma":[0.001377673,0.0001933531,0.001483552,0.0001804352,0.00002100767,0.00001497682,0.0002271019,0.9506624,0.04521989,0.0000762175,0.0004210403,0.0001223053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4800052,0.0001537034,0.5178738,0.001468801,0.00005383435,0.00008029372,0.0003551494,0.000003312103,0.000005952072],"genre_scores_gemma":[0.9584793,0.00002210301,0.04000654,0.0004236114,0.00004127007,0.000001643002,0.001018319,0.000005600106,0.00000165552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9491618,"threshold_uncertainty_score":0.3435696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03435348076170269,"score_gpt":0.2755679535106321,"score_spread":0.2412144727489294,"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."}}