{"id":"W4210287589","doi":"10.1016/j.cmpb.2022.106673","title":"Hierarchical autoclassification of cryo-EM samples and macromolecular energy landscape determination","year":2022,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Ministerio de Ciencia e Innovación","keywords":"Computer science; Inference; Cluster analysis; Data mining; Bayesian probability; Homogeneous; Hierarchical clustering; Bayesian inference; Artificial intelligence; Machine learning; Pattern recognition (psychology); 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":[0.000359382,0.00008442241,0.0001317188,0.00007971856,0.000067307,0.000008516498,0.0000875727,0.00004693749,0.000003598963],"category_scores_gemma":[0.000007194635,0.00007888823,0.00001983886,0.0001758885,0.0001099094,0.000002313856,0.0001613363,0.0000761987,1.212771e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007178252,"about_ca_system_score_gemma":0.00001458052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008491155,"about_ca_topic_score_gemma":0.000002449979,"domain_scores_codex":[0.9992388,0.0001346452,0.0001865676,0.0002584963,0.00006302024,0.0001185046],"domain_scores_gemma":[0.999688,0.00002233624,0.00007383323,0.0001537896,0.00002370879,0.00003827738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001563224,0.00004393976,0.0005349319,0.00001310078,0.000004822864,7.155688e-7,0.00005065324,0.000002058942,0.3590418,0.0008172459,0.00003169944,0.6394434],"study_design_scores_gemma":[0.002710714,0.006949697,0.01474351,0.00008037697,0.00006899811,0.0003408599,0.0003345037,0.04401525,0.3865922,0.02250111,0.5209292,0.0007336062],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1549187,0.001430825,0.8432843,0.0001607243,0.00002612506,0.0001481192,0.000005686299,0.00001194384,0.00001362982],"genre_scores_gemma":[0.4299591,0.0003276632,0.5692024,0.0001196585,0.00004694989,0.000116771,0.0002012825,0.00000880999,0.00001746316],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6387098,"threshold_uncertainty_score":0.3216969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02516973112527951,"score_gpt":0.3660861459133418,"score_spread":0.3409164147880623,"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."}}