{"id":"W4376872947","doi":"10.1186/s12859-023-05327-8","title":"CysPresso: a classification model utilizing deep learning protein representations to predict recombinant expression of cysteine-dense peptides","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biochemical and Structural Characterization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Critical Systems Labs; Sunnybrook Health Science Centre","funders":"H2020 Marie Skłodowska-Curie Actions; Medical Research Council; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; University of Cambridge; UK Research and Innovation","keywords":"Artificial intelligence; Deep learning; Computer science; Computational biology; Machine learning; Concatenation (mathematics); Convolutional neural network; Chemical space; Support vector machine; Drug discovery; Chemistry; Biology; Biochemistry; Mathematics","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":[0.0001571397,0.000135476,0.0001401946,0.00009060181,0.0001075814,0.00002845344,0.0001629855,0.0001526303,0.000003039272],"category_scores_gemma":[0.0003690694,0.0001173765,0.00007205737,0.0002546639,0.00004032837,0.00002249582,0.0001597939,0.00009292533,0.00001646594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000122921,"about_ca_system_score_gemma":0.00003636718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003489724,"about_ca_topic_score_gemma":0.000003372813,"domain_scores_codex":[0.9989193,0.00003829945,0.0004591816,0.000190191,0.0001917337,0.0002012746],"domain_scores_gemma":[0.9992429,0.00001570276,0.0002225767,0.0002919465,0.0001385119,0.00008834096],"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":[0.00007290941,0.0000130596,0.0008572009,0.000175108,0.000006614187,1.574165e-7,0.0004124908,0.005726896,0.9909638,0.00008025978,0.0002678642,0.001423607],"study_design_scores_gemma":[0.0002482553,0.0001256223,0.003188547,0.00009362662,0.000009239548,0.000002892723,0.0006374916,0.485984,0.5092061,0.00009450119,0.0002674298,0.0001422708],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9324856,0.0000182382,0.06639515,0.0000623853,0.00006013491,0.0004415245,0.00002393594,0.00006674055,0.0004462996],"genre_scores_gemma":[0.9647645,0.00003645456,0.03356804,0.00002559152,0.00004574948,0.00007340527,0.0007725509,0.00001694347,0.0006967229],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4817577,"threshold_uncertainty_score":0.4786474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03017812936265334,"score_gpt":0.2728277365811366,"score_spread":0.2426496072184833,"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."}}