{"id":"W4399917261","doi":"10.1002/pro.5076","title":"Structure‐aware deep learning model for peptide toxicity prediction","year":2024,"lang":"en","type":"article","venue":"Protein Science","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Centre for Disease Control; BC Cancer Agency","funders":"Investment Agriculture Foundation; Genome British Columbia; Genome Canada","keywords":"Benchmark (surveying); Computer science; Deep learning; Toxicity; Machine learning; Artificial intelligence; Peptide; Graph; Amino acid; Computational biology; Chemistry; Biology; Biochemistry; Theoretical computer science","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":[0.0003027062,0.0001118663,0.0001109308,0.000103611,0.0005813109,0.0001110372,0.00021905,0.00008999521,0.000092814],"category_scores_gemma":[0.0001036696,0.00009288302,0.00005846559,0.0002027048,0.000508746,0.000437035,0.00008588302,0.0002454452,0.00003952688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005779805,"about_ca_system_score_gemma":0.0001291895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001877491,"about_ca_topic_score_gemma":0.00001408384,"domain_scores_codex":[0.9990708,0.0000217927,0.0001353071,0.0003790554,0.00004793116,0.0003450743],"domain_scores_gemma":[0.9997243,0.00003589261,0.00003660034,0.0001148433,0.0000691298,0.00001920711],"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":[0.00001883837,0.000008448324,0.00003543466,0.00004582679,0.000009404005,5.824218e-7,0.0004097492,0.002484533,0.9851156,0.002611061,0.0001938948,0.009066654],"study_design_scores_gemma":[0.0001654866,0.0001251798,0.0001107095,0.0001031384,0.00001348448,0.00003028492,0.0002142413,0.1710713,0.8217498,0.003954008,0.002293735,0.0001686847],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7743373,0.0006625694,0.2228404,0.0002116432,0.0005211057,0.0005856355,0.0001035637,0.000271289,0.0004665406],"genre_scores_gemma":[0.9919607,0.000008058815,0.001868095,0.00004702622,0.00004751368,0.0000397795,0.00001970727,0.00001098762,0.005998134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2209723,"threshold_uncertainty_score":0.4471032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01426983484856749,"score_gpt":0.2479448806952017,"score_spread":0.2336750458466342,"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."}}