{"id":"W4226042892","doi":"10.1073/pnas.2116097119","title":"Massively parallel, computationally guided design of a proenzyme","year":2022,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Peptidase Inhibition and Analysis","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Biological and Environmental Research; National Institute of General Medical Sciences; National Science Foundation; Canadian Institutes of Health Research; Office of Advanced Research Computing, Rutgers, The State University of New Jersey; Masonic Cancer Center, University of Minnesota; National Cancer Institute; National Institutes of Health; Government of Canada; Rutgers, The State University of New Jersey; University of Minnesota; U.S. Department of Energy","keywords":"Proteolysis; Enzyme; Proteases; Massively parallel; Chemistry; Exopeptidase; Biochemistry; Computational biology; Protein engineering; Combinatorial chemistry; Computer science; Biology","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":[0.001145427,0.00006295972,0.0001805487,0.0002456786,0.000184615,0.000005780577,0.0003290314,0.00002472155,0.0001290784],"category_scores_gemma":[0.0003616943,0.00004424942,0.0001074803,0.0009972692,0.0004785454,0.000132335,0.000117098,0.00012679,6.034645e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004237251,"about_ca_system_score_gemma":0.0001126269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002037916,"about_ca_topic_score_gemma":4.037192e-9,"domain_scores_codex":[0.9976941,0.00001261977,0.0003884647,0.0001601892,0.001653082,0.00009153412],"domain_scores_gemma":[0.998879,0.00008606054,0.0005495853,0.000005665996,0.0004485685,0.00003113507],"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":[0.0001467493,0.0004021809,0.006422443,0.0001878328,0.000113865,7.091037e-8,0.0004285559,0.02476981,0.8593239,0.08099977,0.02708831,0.0001164918],"study_design_scores_gemma":[0.003402619,0.001008869,0.1631798,0.0008601481,0.0002286137,0.0002427559,0.001713506,0.1266824,0.5455039,0.1550344,0.001751039,0.0003919023],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9371159,0.00009341538,0.0001952189,0.05105587,0.00001110845,0.0006974409,0.0000859379,0.00002745015,0.01071763],"genre_scores_gemma":[0.9873131,0.000003327275,0.01074267,0.001517434,0.00002567977,0.00002172338,6.268717e-7,0.000002754296,0.0003726971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.31382,"threshold_uncertainty_score":0.1804439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09258248319441771,"score_gpt":0.3380805762363824,"score_spread":0.2454980930419647,"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."}}