{"id":"W4401918526","doi":"10.1021/acs.jcim.4c00711","title":"Antibody-SGM, a Score-Based Generative Model for Antibody Heavy-Chain Design","year":2024,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Sequence (biology); Computational biology; Protein design; Generative model; Protein engineering; Artificial intelligence; Protein structure; Generative grammar; Biology; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005863303,0.0001355977,0.0002917826,0.0002433407,0.00006371512,0.0001145187,0.00006636317,0.00009724608,0.00001061506],"category_scores_gemma":[0.0001245893,0.0000947983,0.0001769251,0.000112468,0.00004741321,0.000536355,0.00002234685,0.0003110847,0.000003591047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005180618,"about_ca_system_score_gemma":0.0004095631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004053933,"about_ca_topic_score_gemma":9.864043e-8,"domain_scores_codex":[0.9986943,0.00001594431,0.0006242741,0.00008727716,0.000367989,0.0002101947],"domain_scores_gemma":[0.9990557,0.0001238629,0.00009828054,0.00006230984,0.0004448354,0.0002150399],"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":[0.004906054,0.0001350372,0.00007180015,0.001759861,0.0002651035,0.00003107699,0.002082325,0.3191905,0.6475842,0.003115887,0.001912955,0.01894519],"study_design_scores_gemma":[0.000915022,0.0002065775,0.000001327596,0.0004418275,0.00005383936,0.0001387765,0.00005329577,0.9576347,0.03857404,0.001101845,0.0007782291,0.0001004548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2143451,0.0007099829,0.7823235,0.002176364,0.00006414462,0.0002109426,0.00001557826,0.00001624185,0.0001381723],"genre_scores_gemma":[0.939376,0.0003459117,0.05855731,0.001254849,0.0002529206,0.000006575465,0.0001160568,0.00001220327,0.00007815285],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7250309,"threshold_uncertainty_score":0.3865762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09378072613206233,"score_gpt":0.3829621185818545,"score_spread":0.2891813924497921,"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."}}