{"id":"W4300594491","doi":"10.1073/pnas.2122676119","title":"Dissecting the stability determinants of a challenging de novo protein fold using massively parallel design and experimentation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Structural Genomics Consortium; Princess Margaret Cancer Centre; University of Toronto","funders":"National Institute of General Medical Sciences; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Ontario Genomics; Ontario Institute for Cancer Research","keywords":"Protein design; Fold (higher-order function); Protein folding; Protein stability; Protein engineering; Stability (learning theory); Computer science; Protein structure; Computational biology; Chemistry; Crystallography; Biology; Biochemistry; Enzyme; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009758596,0.00005033542,0.00006633905,0.00002756854,0.0002725266,0.00000729039,0.0002707792,0.00002969188,0.000001426021],"category_scores_gemma":[0.0002233295,0.00003319281,0.00002830767,0.0001376929,0.0002738974,0.00001490556,0.0001870966,0.00006428693,3.163985e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000174639,"about_ca_system_score_gemma":0.00003306014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006296518,"about_ca_topic_score_gemma":7.516297e-8,"domain_scores_codex":[0.9992897,0.00001497083,0.0001602472,0.0001367764,0.0003138899,0.00008444495],"domain_scores_gemma":[0.9995992,0.00002455313,0.0002692117,0.000007873788,0.00008808088,0.00001103238],"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":[0.00002862399,0.00001256245,0.005742773,0.00002654552,0.000005565703,3.110013e-9,0.0003000206,0.001181937,0.991342,0.00122643,7.111017e-7,0.0001328194],"study_design_scores_gemma":[0.0001058309,0.00007478541,0.007066419,0.00001701058,0.000005105725,0.00001143724,0.001264707,0.01510242,0.9667832,0.009524185,0.000002651063,0.00004231456],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9991354,0.0001917841,0.0002224337,0.0001321498,0.00000613296,0.0002524601,0.000004798864,0.000001243591,0.00005353997],"genre_scores_gemma":[0.9930188,0.000005451249,0.006894615,0.00002755344,0.00001870121,0.0000265841,7.7059e-8,0.000002401493,0.000005817956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02455887,"threshold_uncertainty_score":0.2096082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05579076981344424,"score_gpt":0.3245581322165691,"score_spread":0.2687673624031249,"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."}}