{"id":"W3204768651","doi":"10.1016/j.sbi.2021.11.008","title":"Deep generative modeling for protein design","year":2021,"lang":"en","type":"preprint","venue":"Current Opinion in Structural Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Institute of Genetics; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Generative grammar; Discriminative model; Generative model; Computer science; Generative Design; Protein design; Artificial intelligence; Function (biology); Machine learning; Protein structure; Biology; Engineering; Genetics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001934774,0.0004836264,0.0005022578,0.0001070828,0.00009539483,0.00005798871,0.0004422579,0.0008609279,0.00001164782],"category_scores_gemma":[0.0001955053,0.0004405629,0.0002380531,0.00008061486,0.0001065957,0.000004920958,0.0007245661,0.0005439352,6.486835e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006633337,"about_ca_system_score_gemma":0.000327603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001905134,"about_ca_topic_score_gemma":0.00001926301,"domain_scores_codex":[0.9975016,0.0002815258,0.0005486627,0.001099082,0.00008889238,0.0004802017],"domain_scores_gemma":[0.9988899,0.00001703289,0.0002323008,0.0005349329,0.0002410054,0.00008487875],"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":[0.001224381,0.00008902259,0.001428694,0.00223915,0.000454428,0.00000214262,0.0006178666,0.4285163,0.466573,0.008253935,0.0003705329,0.09023059],"study_design_scores_gemma":[0.002295183,0.0006289087,0.0001848475,0.000548312,0.00004169097,0.00002976983,0.0001356572,0.8865908,0.03530898,0.06937754,0.003001006,0.00185727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2174427,0.0216228,0.7513863,0.00009389741,0.007206263,0.002053792,0.0001591684,0.0000224937,0.00001258274],"genre_scores_gemma":[0.9225513,0.001118078,0.06336188,0.00004421317,0.002246603,0.001035078,0.00957655,0.00005331908,0.00001301126],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7051085,"threshold_uncertainty_score":0.9998046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05946952344950198,"score_gpt":0.3520063394774142,"score_spread":0.2925368160279122,"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."}}