{"id":"W4296345676","doi":"10.1101/2022.09.17.508377","title":"CysPresso: A classification model utilizing deep learning protein representations to predict recombinant expression of cysteine-dense peptides","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Biochemical and Structural Characterization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Artificial intelligence; Concatenation (mathematics); Deep learning; Computer science; Computational biology; Machine learning; Convolutional neural network; Biology; Mathematics","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":[0.0007058034,0.001014963,0.0006067291,0.000753784,0.0002089582,0.0006714333,0.0006350366,0.0009682683,0.0009711199],"category_scores_gemma":[0.0009341723,0.0002469476,0.0006845611,0.0003094365,0.0002476887,0.0005942567,0.0003961509,0.0009442897,0.0003225174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001083878,"about_ca_system_score_gemma":0.0008315793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0067549,"about_ca_topic_score_gemma":0.004668689,"domain_scores_codex":[0.9998585,0.00002644441,0.000009036322,0.00005100556,0.00002290129,0.00003212594],"domain_scores_gemma":[0.9996167,0.0001834051,0.0000551636,0.00002531899,0.00008618105,0.00003313762],"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":[0.0005900547,0.0004229311,0.01294043,0.00007907178,0.0001573001,0.0001550367,0.00003158737,0.8640357,0.01185027,0.001121787,0.003428197,0.1051876],"study_design_scores_gemma":[0.000002572508,0.0000213831,0.0002031289,0.000001742789,0.000003224221,0.00000499411,0.000001518982,0.9987774,0.0007661018,0.0001590015,0.0000569766,0.000001908684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7179537,0.001295273,0.2720544,0.0007917863,0.0001338492,0.0001315293,0.001651396,0.004115735,0.001872215],"genre_scores_gemma":[0.9616752,0.0002355474,0.03344199,0.000159613,0.00002989672,0.0001148848,0.002158817,0.00006051226,0.002123461],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.0067549,"threshold_uncertainty_score":0.01343119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01744192711003154,"score_gpt":0.2411621154795059,"score_spread":0.2237201883694744,"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."}}