{"id":"W4393019167","doi":"10.1101/2024.03.18.585544","title":"Towards Interpretable Cryo-EM: Disentangling Latent Spaces of Molecular Conformations","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"SLAC National Accelerator Laboratory; National Institutes of Health; U.S. Department of Energy; Laboratory Directed Research and Development; Flatiron Health; Canadian Institute for Advanced Research","keywords":"Leverage (statistics); Identifiability; Computer science; Latent variable; Artificial intelligence; Machine learning; Data science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007397995,0.0004516174,0.000535288,0.0005445705,0.000079646,0.0009223042,0.001450395,0.0003632992,0.0000157971],"category_scores_gemma":[0.0001083072,0.0004681932,0.0002525259,0.0007441916,0.00008589434,0.0004201422,0.002273247,0.000803283,0.00005573543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001850148,"about_ca_system_score_gemma":0.0007574927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000412132,"about_ca_topic_score_gemma":0.000001715375,"domain_scores_codex":[0.9974112,0.0001341537,0.0007441478,0.0007580909,0.0005640193,0.0003884189],"domain_scores_gemma":[0.9971564,0.0000409325,0.0004711811,0.001589288,0.0005580768,0.00018413],"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":[0.00001713928,0.0003110814,0.0005523713,0.002072727,0.0006418636,0.0001367393,0.001108883,0.002285841,0.5901163,0.401418,0.001288809,0.00005016493],"study_design_scores_gemma":[0.0001818431,0.00006235756,0.001000777,0.001104387,0.000108293,4.224056e-8,0.00001158869,0.04220709,0.9526065,0.0004593678,0.001473569,0.000784207],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4513401,0.002000524,0.5408058,0.001092105,0.001486705,0.0009383257,0.0001413792,0.001969422,0.0002256716],"genre_scores_gemma":[0.9411235,0.0001075873,0.05824039,0.0002595443,0.00006099754,0.0001408471,3.505906e-7,0.00006010921,0.000006674156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4897834,"threshold_uncertainty_score":0.999777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01177241956725078,"score_gpt":0.2378397439688889,"score_spread":0.2260673244016381,"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."}}