{"id":"W4411328709","doi":"10.1038/s41587-025-02701-0","title":"Identification of non-canonical peptides with moPepGen","year":2025,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute; Canadian Cancer Society Research Institute","keywords":"Proteogenomics; Computational biology; Biology; RNA; Gene; Unobservable; Identification (biology); Proteome; Germline; Genetics; Somatic cell; Transcriptome; Open reading frame; Genome; Genomics; Gene expression; Peptide sequence","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":[0.0001452401,0.0001061313,0.0001447215,0.0001088604,0.00003887133,0.000006420041,0.0003070179,0.001114926,0.00000632041],"category_scores_gemma":[0.0001153548,0.00008579584,0.00004712832,0.0002063163,0.0001427781,0.000001833688,0.00009107864,0.0002124255,0.000004712842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008645989,"about_ca_system_score_gemma":0.0001103189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005201587,"about_ca_topic_score_gemma":0.00001679936,"domain_scores_codex":[0.999276,0.00002264166,0.0001826861,0.0003034986,0.00007465926,0.0001404824],"domain_scores_gemma":[0.9993076,0.000009801317,0.00009559112,0.000494605,0.00007573561,0.00001667464],"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":[0.00008502038,0.00003006505,0.000214957,0.00001980274,0.0000537717,0.000001087595,0.000002327098,0.000003118546,0.9799793,0.008408684,0.0005613093,0.0106405],"study_design_scores_gemma":[0.0002124418,0.0001748895,0.0009670882,0.00002101559,0.0000193156,0.000006361752,0.00002339268,0.00001062825,0.9738024,0.0005900154,0.02408665,0.00008583603],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9636247,0.002320226,0.02864742,0.002481986,0.0002083376,0.0003552183,0.00001477588,0.00004146166,0.002305867],"genre_scores_gemma":[0.9960867,0.0001555184,0.00256572,0.0001662287,0.00003146046,0.00002644091,0.00001506442,0.000009723159,0.0009431869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03246195,"threshold_uncertainty_score":0.8599329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002538917794488438,"score_gpt":0.2391111020031757,"score_spread":0.2365721842086873,"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."}}