{"id":"W4391175562","doi":"10.1038/s42256-023-00787-2","title":"Variational autoencoder for design of synthetic viral vector serotypes","year":2024,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Virus-based gene therapy research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"CIHR Skin Research Training Centre","keywords":"Autoencoder; Computer science; Capsid; Computational biology; Vector (molecular biology); Epitope; Virology; Artificial intelligence; Deep learning; Biology; Virus; Gene; Antibody; Immunology; 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":[0.0004260462,0.0001412826,0.0001206509,0.00008020383,0.00004347691,0.00002722111,0.0002994546,0.0002461113,0.0001327464],"category_scores_gemma":[0.0002392585,0.0001188926,0.0001075592,0.0001394453,0.0000683646,0.000004319499,0.00005262342,0.0002685112,0.00001686363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001942581,"about_ca_system_score_gemma":0.0001965177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006490877,"about_ca_topic_score_gemma":0.0000153062,"domain_scores_codex":[0.9989788,0.00007678176,0.0001893893,0.0003463097,0.0002074904,0.0002012261],"domain_scores_gemma":[0.9993871,0.0001358179,0.0000332739,0.0002538525,0.0001437818,0.00004620764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00279371,0.0001220158,0.00007208524,0.0002118208,0.0002901794,0.000005968313,0.0001071487,0.02512657,0.9210616,0.008929905,0.002127906,0.03915111],"study_design_scores_gemma":[0.00008206268,0.001591007,0.00004425033,0.00003733768,0.00002018542,0.00001096523,0.000005224937,0.1348855,0.8533846,0.004982847,0.004792576,0.0001634881],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009952759,0.01266762,0.9753595,0.0006807084,0.0004446568,0.0005379859,0.0001463027,0.00003491488,0.0001755808],"genre_scores_gemma":[0.9853212,0.0001573802,0.01330367,0.0001620115,0.0002672345,0.00006434794,0.00008687591,0.0000338926,0.0006033577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9753685,"threshold_uncertainty_score":0.4848298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01527205586092815,"score_gpt":0.3296407372049388,"score_spread":0.3143686813440106,"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."}}