{"id":"W4407950139","doi":"10.1073/pnas.2419140122","title":"Cryo-EM heterogeneity analysis using regularized covariance estimation and kernel regression","year":2025,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Air Force Office of Scientific Research; National Institute of General Medical Sciences; Simons Foundation; Air Force Research Laboratory; National Institutes of Health; National Science Foundation","keywords":"Interpretability; Computer science; Kernel (algebra); Principal component analysis; Covariance; Algorithm; Regularization (linguistics); Embedding; Artificial intelligence; Pattern recognition (psychology); Covariance matrix; Canonical correlation; Kernel density estimation; Estimator; Mathematics; Statistics","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":[0.0003363171,0.00005500953,0.00009205368,0.00008094569,0.0001588349,0.00001270288,0.0002250543,0.00006551802,6.610853e-7],"category_scores_gemma":[0.0001002218,0.00003949329,0.00004762482,0.0006348916,0.0002689019,0.00001475983,0.0001029678,0.00004709894,2.111207e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000116932,"about_ca_system_score_gemma":0.00002019016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001927316,"about_ca_topic_score_gemma":1.012061e-7,"domain_scores_codex":[0.9994066,0.000003874647,0.0001560888,0.0001923252,0.0001714709,0.00006959728],"domain_scores_gemma":[0.9996288,0.00000927905,0.0002124136,0.00001097192,0.0001273011,0.00001121008],"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":[0.000009925169,0.00001058217,0.001796685,0.00001483689,0.00001993334,2.486245e-10,0.00000583776,0.0006698636,0.9896022,0.007425859,0.00005510653,0.0003891544],"study_design_scores_gemma":[0.00006887138,0.0000139308,0.008699732,0.00002846979,0.00004170816,0.00000108148,0.00001410913,0.01134033,0.9654809,0.01419934,0.00007255182,0.00003894519],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911397,0.0002306905,0.007975195,0.0003677185,0.000002691479,0.0001083962,0.000007320759,0.00000438329,0.0001639797],"genre_scores_gemma":[0.9381589,0.00005990545,0.06157955,0.0001099971,0.000008774546,0.00000659491,6.646372e-7,0.000001437824,0.00007414761],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05360436,"threshold_uncertainty_score":0.1610489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02152098910276154,"score_gpt":0.3775156360137789,"score_spread":0.3559946469110174,"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."}}