{"id":"W4304014526","doi":"10.21203/rs.3.rs-1855828/v1","title":"ProteinSGM: Score-based generative modeling for de novo protein design","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Computer science; Generative model; Generative Design; Artificial intelligence; Engineering; Operations management","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002208571,0.0003657071,0.0003178097,0.0002200694,0.0005299607,0.0001482264,0.0008119032,0.000597244,0.00005305931],"category_scores_gemma":[0.0007444088,0.0003654961,0.0002697637,0.000186809,0.0001279324,0.000003515873,0.001215539,0.001194363,0.000002286654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003030815,"about_ca_system_score_gemma":0.003101194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001055003,"about_ca_topic_score_gemma":0.00005845885,"domain_scores_codex":[0.9961534,0.0008741464,0.00032622,0.001052758,0.0006981961,0.0008953204],"domain_scores_gemma":[0.9979069,0.00005053244,0.0001090737,0.001015022,0.0007218466,0.0001965962],"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":[0.001547063,0.0001534556,0.0001087145,0.001447213,0.0001469886,0.00003257607,0.0001149571,0.5706925,0.4221979,0.000797691,0.0004765853,0.002284319],"study_design_scores_gemma":[0.001526767,0.002189105,0.0000166183,0.0003881117,0.00002820468,0.000008533659,0.0001530511,0.5320038,0.4349074,0.0233774,0.004518718,0.0008823458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1848432,0.00121642,0.8040671,0.0003414894,0.00008152238,0.00877178,0.0004555581,0.0000379783,0.0001848805],"genre_scores_gemma":[0.8440409,0.00006547663,0.1343417,0.0001292373,0.0007945319,0.01772013,0.001969658,0.0001434945,0.0007948467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6697255,"threshold_uncertainty_score":0.9998797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1003423149493608,"score_gpt":0.3912936060681858,"score_spread":0.2909512911188249,"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."}}