{"id":"W4388163834","doi":"10.1101/2023.10.27.564468","title":"Mining Mass Spectra for Peptide Facts","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Institut de Valorisation des Données","keywords":"Computer science; Identification (biology); Tandem mass spectrometry; Task (project management); Peptide; Pipeline (software); Mass spectrometry; Artificial intelligence; Data mining; Chemistry; Biology; Chromatography; Engineering; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001121391,0.001174762,0.0006869331,0.007826749,0.000642673,0.001547132,0.001809663,0.001456358,0.003285456],"category_scores_gemma":[0.005077151,0.0004144248,0.001063806,0.003441764,0.0005508187,0.003144502,0.001055684,0.001153466,0.001430584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005646403,"about_ca_system_score_gemma":0.0007097096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007686591,"about_ca_topic_score_gemma":0.001638064,"domain_scores_codex":[0.9989894,0.0001176024,0.00009632009,0.0004174091,0.000323779,0.00005547352],"domain_scores_gemma":[0.9957809,0.001893881,0.0009263441,0.0005306904,0.0007121895,0.0001558964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001524619,0.0006639881,0.08386921,0.001508198,0.0004324045,0.004139765,0.0004872242,0.04607216,0.09329943,0.02183321,0.02766761,0.7185023],"study_design_scores_gemma":[0.0001254261,0.0001995188,0.02461594,0.0002601581,0.0002391684,0.003214489,0.0006005952,0.7824008,0.06762376,0.0869199,0.0336944,0.0001058397],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3209799,0.004722312,0.6406852,0.003184375,0.0003132688,0.0003436299,0.01638003,0.007248764,0.00614247],"genre_scores_gemma":[0.5869524,0.001342549,0.3918768,0.000371743,0.0003650326,0.0001100985,0.01680592,0.0002053569,0.001969989],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007826749,"threshold_uncertainty_score":0.01099098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02675642107873135,"score_gpt":0.2625595897281026,"score_spread":0.2358031686493712,"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."}}