{"id":"W2116063068","doi":"10.1093/bioinformatics/btl379","title":"General framework for developing and evaluating database scoring algorithms using the TANDEM search engine","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":218,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; U.S. Public Health Service","keywords":"Computer science; Database search engine; Database; Function (biology); Software; Suite; Information retrieval; Matching (statistics); Source code; Data mining; Open source; Search engine; Programming language; 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":[0.000277617,0.0001089688,0.0000978251,0.00002408837,0.0003705354,0.00007627043,0.0001400074,0.00006903677,0.000005506267],"category_scores_gemma":[0.0000598904,0.00008663064,0.00002682869,0.0001006174,0.00004232832,0.0001430983,0.0001148467,0.0001599326,7.135791e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006909124,"about_ca_system_score_gemma":0.00005504313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002099189,"about_ca_topic_score_gemma":0.000001079511,"domain_scores_codex":[0.9992484,0.000003494271,0.0002873154,0.0001003156,0.0001360381,0.0002244382],"domain_scores_gemma":[0.9994182,0.000137392,0.0001055515,0.0002413774,0.00007110093,0.00002635084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003817833,0.00008434854,0.003082473,0.002311271,0.0001124112,0.00000225908,0.001579218,0.02044969,0.2140604,0.4731644,0.0004128336,0.2847025],"study_design_scores_gemma":[0.0001568166,0.000006284015,0.00001351753,0.0001345444,0.00001606894,0.00001175187,0.0002505266,0.86234,0.1263282,0.009746153,0.0008386869,0.0001574153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.122488,0.00009035329,0.8767444,0.00008967546,0.00001370183,0.0002394128,0.00004401849,0.00007001711,0.0002203973],"genre_scores_gemma":[0.01625015,0.00003700366,0.9832056,0.00005811847,0.0002453756,0.00007579681,0.00006565972,0.0000169882,0.00004535196],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8418903,"threshold_uncertainty_score":0.3532695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07749868424509176,"score_gpt":0.3742599619674528,"score_spread":0.296761277722361,"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."}}