{"id":"W4368374143","doi":"10.1038/s43588-023-00440-3","title":"Score-based generative modeling for de novo protein design","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":79,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Generative grammar; Generative model; Computer science; Protein design; Generative Design; Modular design; Image (mathematics); Protein engineering; Artificial intelligence; Protein structure; Algorithm; Biology; Programming language; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002270863,0.0008536567,0.001518379,0.001254465,0.0007543302,0.001273261,0.00275988,0.00176447,0.004795552],"category_scores_gemma":[0.008116674,0.001162079,0.001595234,0.001330251,0.0009879129,0.001443704,0.001856212,0.001939578,0.001264113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00146834,"about_ca_system_score_gemma":0.001576071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006057267,"about_ca_topic_score_gemma":0.01141342,"domain_scores_codex":[0.9991639,0.0003912988,0.00004294821,0.0001197225,0.000210715,0.0000713844],"domain_scores_gemma":[0.995141,0.003745962,0.0001606109,0.0004051589,0.0003846716,0.0001624988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007203164,0.00003542589,0.0004372435,0.00004718416,0.00005169722,0.00005960952,0.00004041133,0.9376966,0.0008200247,0.02492326,0.001215715,0.03460074],"study_design_scores_gemma":[0.000005174795,0.000004427693,0.00001956338,0.000002429542,0.000003692469,0.000005614857,0.000001554204,0.9888825,0.0001511202,0.01074344,0.0001782351,0.000002227263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01304788,0.0002952709,0.9829472,0.0002807359,0.00003975383,0.00005109378,0.0002166937,0.001427519,0.001693928],"genre_scores_gemma":[0.6673269,0.000481879,0.3233476,0.0003058848,0.0001359338,0.0003386138,0.001336191,0.0009836812,0.005743291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006057267,"threshold_uncertainty_score":0.01604271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02197950252939696,"score_gpt":0.3049594280013972,"score_spread":0.2829799254720003,"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."}}