{"id":"W4388537735","doi":"10.1101/2023.11.06.565922","title":"Sample-efficient Antibody Design through Protein Language Model for Risk-aware Batch Bayesian Optimization","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Benchmark (surveying); Machine learning; Bayesian probability; Generative model; Language model; Artificial intelligence; Naturalness; Process (computing); Bayesian optimization; Data mining; Generative grammar","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":[0.003961297,0.001223441,0.00192291,0.0008992018,0.0004832349,0.001227349,0.001961655,0.001731465,0.002765962],"category_scores_gemma":[0.007819506,0.001133092,0.001439609,0.000760196,0.001596685,0.001638003,0.001737451,0.002191704,0.0006785389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001772238,"about_ca_system_score_gemma":0.00319483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004572987,"about_ca_topic_score_gemma":0.004937086,"domain_scores_codex":[0.9984086,0.0006993015,0.00005394383,0.0002514901,0.0004440023,0.0001428118],"domain_scores_gemma":[0.9954017,0.003462905,0.0003432942,0.0001807321,0.0004518649,0.000159403],"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":[0.00007937913,0.00005642668,0.0004018714,0.00006438023,0.00002981317,0.00003849837,0.00002960371,0.9641182,0.002345825,0.01199426,0.0008383539,0.02000339],"study_design_scores_gemma":[0.000009246654,0.0000146681,0.00001860739,0.000002630806,0.000003562544,0.000005521083,0.000001724177,0.995128,0.0004085993,0.004259045,0.0001447898,0.000003495051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008159886,0.0001944153,0.9900526,0.0002166333,0.00001294615,0.00004454922,0.00004178758,0.0004326582,0.0008445499],"genre_scores_gemma":[0.3885095,0.0003205356,0.6052316,0.0006627899,0.00007232814,0.0004596369,0.0003605535,0.0003836433,0.003999443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004572987,"threshold_uncertainty_score":0.0209496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04990827090442633,"score_gpt":0.3165979333547751,"score_spread":0.2666896624503488,"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."}}