{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000317122,0.0003952875,0.0003830845,0.0001560863,0.0002242517,0.00007201117,0.000490597,0.0004508147,0.00002228336],"category_scores_gemma":[0.0004806808,0.0004154971,0.0001667916,0.0002728803,0.00007363232,0.000017783,0.0009408696,0.0005573872,0.000002986788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009037273,"about_ca_system_score_gemma":0.0001892406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002019372,"about_ca_topic_score_gemma":0.000001031354,"domain_scores_codex":[0.9973547,0.0002191135,0.0006458071,0.001055666,0.0003757097,0.0003490339],"domain_scores_gemma":[0.9978064,0.00001612102,0.0005931695,0.0009730048,0.0004144127,0.0001969473],"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":[0.0001504363,0.0000716459,0.001690523,0.0002972471,0.00004140741,0.000002692004,0.00002561971,0.002700693,0.9948605,0.00008498782,0.00006814192,0.000006151449],"study_design_scores_gemma":[0.0003024221,0.0001593447,0.01529604,0.0002538526,0.00004240916,3.446035e-8,0.00002126136,0.007617456,0.9750423,0.000005498351,0.0008009922,0.0004584122],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909644,0.0002830175,0.007056956,0.0001155349,0.000264656,0.001021326,0.0001760087,0.0001007069,0.00001739042],"genre_scores_gemma":[0.9915915,0.0001201016,0.007244932,0.00004204452,0.0001785066,0.0006407723,0.00002890056,0.00009047567,0.00006282215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01981818,"threshold_uncertainty_score":0.9998297,"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."}}