{"id":"W4285395549","doi":"10.1101/2022.07.13.499967","title":"ProteinSGM: Score-based generative modeling for <i>de novo</i> protein design","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Computer science; Modular design; Generative Design; Protein design; Image (mathematics); Generative model; Consistency (knowledge bases); Image synthesis; Artificial intelligence; Function (biology); Algorithm; Protein structure; Biology; Programming language; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001136805,0.0005939518,0.0004565289,0.0003604782,0.000232499,0.0006094272,0.001196292,0.001020599,0.002378078],"category_scores_gemma":[0.002205,0.0004376249,0.000722646,0.0003644632,0.0007571013,0.0005097965,0.0009110151,0.001273388,0.000552147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009740267,"about_ca_system_score_gemma":0.0007026558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001919778,"about_ca_topic_score_gemma":0.002052189,"domain_scores_codex":[0.9997419,0.00009289619,0.00001045775,0.00004760056,0.00008404886,0.00002312671],"domain_scores_gemma":[0.9992773,0.000401801,0.00008485415,0.00009233301,0.00008487712,0.00005882665],"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":[0.00002775669,0.00002055873,0.000413821,0.00003658617,0.00001525281,0.0000525435,0.00002877417,0.9578128,0.004633005,0.02130503,0.001189649,0.01446415],"study_design_scores_gemma":[0.000003422673,0.000004402777,0.00001851256,0.000001344035,0.000001034225,0.000006314235,8.340313e-7,0.9957652,0.000760865,0.003108275,0.0003282471,0.000001554517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01462057,0.0001076736,0.9828413,0.0002161408,0.00002497484,0.00003084699,0.0001022747,0.0009005314,0.001155764],"genre_scores_gemma":[0.5534758,0.0002793351,0.4396414,0.0002188991,0.00005433811,0.0002063663,0.0004992405,0.0007295801,0.00489495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002378078,"threshold_uncertainty_score":0.007955432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02035408204490387,"score_gpt":0.2319375680692763,"score_spread":0.2115834860243725,"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."}}