{"id":"W2924375708","doi":"10.3390/molecules24061181","title":"Deep Learning for Validating and Estimating Resolution of Cryo-Electron Microscopy Density Maps †","year":2019,"lang":"en","type":"article","venue":"Molecules","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; University of Washington Bothell; University of Washington; Nvidia","keywords":"Convolutional neural network; Artificial intelligence; Cryo-electron microscopy; Resolution (logic); Computer science; Pattern recognition (psychology); Deep learning; Artificial neural network; Voxel; Physics; Nuclear magnetic resonance","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001017851,0.00009516565,0.0001095871,0.00002228964,0.00009626464,0.00001196027,0.00006793083,0.00007518266,0.000001491132],"category_scores_gemma":[0.00005215579,0.0001030402,0.00003988096,0.00004477804,0.00003524058,0.000003600223,0.00005479134,0.00007075958,8.521168e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001109024,"about_ca_system_score_gemma":0.00001523767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007898128,"about_ca_topic_score_gemma":0.000005191916,"domain_scores_codex":[0.9993617,0.00002012883,0.0001436809,0.0002460383,0.00004120836,0.0001872781],"domain_scores_gemma":[0.9996396,0.00001500581,0.0001128588,0.0001448588,0.00006382885,0.00002390427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003058174,0.00001117038,0.0007618212,0.00003915449,0.000008313,6.033272e-8,0.00001850343,0.001102118,0.9956554,0.0004656551,0.00005457658,0.001852689],"study_design_scores_gemma":[0.0001935001,0.0002883061,0.0001716738,0.00001883151,0.00001040705,0.000006518855,0.00002682348,0.006801696,0.9894777,0.000724604,0.002169786,0.0001101504],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5588239,0.0003404963,0.440546,0.00001763566,0.000009564803,0.0001864143,0.000002468953,0.00001281092,0.00006069298],"genre_scores_gemma":[0.7544014,0.00004794685,0.2451998,0.00003705502,0.00002880227,0.00003069191,0.0001170397,0.00001766214,0.0001196411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1955774,"threshold_uncertainty_score":0.4201859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005348238324346345,"score_gpt":0.3051904720690905,"score_spread":0.2998422337447442,"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."}}