{"id":"W3135313273","doi":"10.22541/au.158697112.27465963","title":"A new method for protein characterization and classification using geometrical features for 3D face analysis: an example of tubulin structures","year":2020,"lang":"en","type":"dataset","venue":"Authorea","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"MacEwan University; University of Alberta","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Support vector machine; Classifier (UML); Computer science; Feature extraction; Face (sociological concept); Kernel (algebra); Machine learning; Mathematics","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":[0.0002896891,0.0002272727,0.0003933623,0.0002336274,0.00007022177,0.00005749831,0.0002211255,0.0004754136,0.000005875283],"category_scores_gemma":[0.0005229608,0.0002101269,0.0001254042,0.0003311283,0.00002616115,0.000007671888,0.0000791892,0.0001482273,3.280617e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001209507,"about_ca_system_score_gemma":0.0001112067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002407575,"about_ca_topic_score_gemma":0.00004304025,"domain_scores_codex":[0.9988092,0.00009562706,0.000379274,0.0004147557,0.0001403979,0.0001607939],"domain_scores_gemma":[0.9987989,0.00003853086,0.0005425556,0.0004004622,0.0001147625,0.000104786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007677297,0.00007603236,0.00008456074,0.001797713,0.001664351,4.034283e-7,0.0003352342,0.000818757,0.5662701,0.0002729706,0.3814382,0.046474],"study_design_scores_gemma":[0.0005716803,0.0007054621,0.002412958,0.00002351453,0.001408093,0.000005446943,0.00003955127,0.07606463,0.01056812,0.00007777921,0.9077113,0.0004114195],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.001035855,0.00004079699,0.5867846,0.00003472764,0.00002790044,0.00065142,0.4114183,0.000005803741,5.335814e-7],"genre_scores_gemma":[0.0003886476,0.00001429875,0.3225292,0.00004466443,0.0001656633,0.00003821391,0.6767646,0.00001566941,0.00003904511],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.5557019,"threshold_uncertainty_score":0.8568728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04185039328066677,"score_gpt":0.3479901986833264,"score_spread":0.3061398054026596,"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."}}