{"id":"W4317212859","doi":"10.1093/bioinformatics/btad036","title":"HelixGAN a deep-learning methodology for conditional <i>de novo</i> design of α-helix structures","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computational biology; Peptide; Synthetic biology; Peptidomimetic; Computer science; Protein design; Helix (gastropod); Deep learning; Protein structure; Chemistry; Biology; Artificial intelligence; Biochemistry","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":[0.0004424563,0.00009735578,0.0001777789,0.00005421438,0.00006232379,0.00001125521,0.000131275,0.000131994,0.00002975808],"category_scores_gemma":[0.0006726711,0.00008559872,0.0001340364,0.0001235694,0.00006180673,0.000003380834,0.0000547754,0.00004960418,0.000007112125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007902569,"about_ca_system_score_gemma":0.00003841406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002046684,"about_ca_topic_score_gemma":0.000001132674,"domain_scores_codex":[0.9992717,0.0000517979,0.0002799975,0.00009935618,0.00009172919,0.0002054458],"domain_scores_gemma":[0.9994188,0.0001895806,0.0001356613,0.0001254033,0.00007841326,0.00005211876],"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":[0.00007485781,0.00001643224,0.0002542062,0.00013427,0.0001559127,5.058255e-7,0.000182757,0.008365991,0.9796643,0.000665658,0.002416204,0.008068956],"study_design_scores_gemma":[0.0005237915,0.0002031101,0.0003052718,0.00001020704,0.00008422652,0.00001522549,0.000513343,0.04901465,0.9273154,0.002783649,0.01901569,0.0002155073],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1320293,0.0001306608,0.8672278,0.0001009341,0.00003800277,0.0001684748,0.00008227474,0.0000292757,0.0001933455],"genre_scores_gemma":[0.6583569,0.0002733668,0.3392228,0.0003467546,0.0002064631,0.00004748732,0.001209104,0.00002547443,0.0003116011],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5280049,"threshold_uncertainty_score":0.3490615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04493095210565193,"score_gpt":0.3029639355541699,"score_spread":0.2580329834485179,"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."}}