{"id":"W2082006641","doi":"10.1021/ac0258709","title":"A Method for Assessing the Statistical Significance of Mass Spectrometry-Based Protein Identifications Using General Scoring Schemes","year":2003,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":496,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genome Canada","funders":"","keywords":"Identification (biology); Representation (politics); Data mining; Scoring algorithm; Simple (philosophy); Computer science; Statistical analysis; Machine learning; Statistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003722765,0.0001852794,0.0002591843,0.00002444151,0.0002199083,0.00007709812,0.0002891387,0.0001268708,0.0003142275],"category_scores_gemma":[0.0005139493,0.0001628882,0.0001424189,0.0003082331,0.0001989817,0.00006562825,0.00002398781,0.000281261,9.612477e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001260008,"about_ca_system_score_gemma":0.0002094439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001155468,"about_ca_topic_score_gemma":2.118623e-7,"domain_scores_codex":[0.9985504,0.00002369988,0.0004588713,0.000420626,0.0002231369,0.0003233006],"domain_scores_gemma":[0.9985563,0.0003910143,0.000228124,0.0005577396,0.0001672536,0.00009961639],"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":[0.000006175642,0.00006536319,0.000252394,0.0002296997,0.00002931032,7.749541e-7,0.000002829877,0.0003579229,0.9635376,0.03535752,0.00001955097,0.0001408332],"study_design_scores_gemma":[0.0001736887,0.000003383297,0.000006252836,0.00004862649,0.00008179331,0.000003213743,0.00005050192,0.09960394,0.8816301,0.01722305,0.001005843,0.000169555],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08246279,0.00003635677,0.9144664,0.0001199078,0.000004742973,0.0002536011,0.00008862576,0.00005523769,0.002512366],"genre_scores_gemma":[0.3708462,9.651708e-7,0.6284103,0.00001451958,0.00005211123,0.0002155896,0.00002672281,0.00002294335,0.0004105741],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2883835,"threshold_uncertainty_score":0.6642389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03911847149694674,"score_gpt":0.3819344892939808,"score_spread":0.342816017797034,"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."}}