{"id":"W2908096659","doi":"10.1371/journal.pcbi.1006578","title":"Trajectory-based training enables protein simulations with accurate folding and Boltzmann ensembles in cpu-hours","year":2018,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Chemistry; National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Institute of General Medical Sciences; Directorate for Biological Sciences; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Foundation for the National Institutes of Health; National Science Foundation","keywords":"Force field (fiction); Computer science; Molecular dynamics; Folding (DSP implementation); Protein folding; Divergence (linguistics); Parameterized complexity; Algorithm; Bayesian probability; Protein structure prediction; Energy landscape; Statistical physics; Biological system; Protein structure; Physics; Artificial intelligence; Chemistry; Computational chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0000739231,0.0001402763,0.0001434674,0.0000921162,0.0001036321,0.00001847883,0.00008161709,0.0001264925,0.000008244135],"category_scores_gemma":[0.00006302823,0.0001207153,0.00002127556,0.0001030635,0.0002055036,0.0000062208,0.00003133079,0.00007311474,0.000001199261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001165184,"about_ca_system_score_gemma":0.0001405372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001152259,"about_ca_topic_score_gemma":0.0001811928,"domain_scores_codex":[0.999171,0.00007155982,0.0001655682,0.0003172993,0.00006250788,0.0002121337],"domain_scores_gemma":[0.9996258,0.00005639056,0.00007490332,0.00009542567,0.0001013372,0.00004611651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004871693,0.00009404216,0.03024677,0.00004183775,0.000133484,0.000008128208,0.0003933619,0.07982098,0.8811338,0.003476085,0.00001904055,0.004145319],"study_design_scores_gemma":[0.01051429,0.006496952,0.09496176,0.0004610998,0.000125058,0.0001095474,0.0006813972,0.4995839,0.3268781,0.05509129,0.002670956,0.00242567],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9661198,0.0001337689,0.03314806,0.0001355709,0.00002328798,0.0002644584,0.00004375016,0.00001780111,0.000113504],"genre_scores_gemma":[0.977262,0.00000195064,0.02199503,0.0002340075,0.0001345916,0.00002808215,0.0003191556,0.00001551315,0.000009704364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5542557,"threshold_uncertainty_score":0.4922626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02055285792841822,"score_gpt":0.264118891613088,"score_spread":0.2435660336846698,"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."}}