{"id":"W2956732318","doi":"10.1021/acs.jproteome.9b00205","title":"PTMProphet: Fast and Accurate Mass Modification Localization for the Trans-Proteomic Pipeline","year":2019,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":160,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Allergy and Infectious Diseases; National Institute on Aging; National Heart, Lung, and Blood Institute; Medical Research Council; National Institute of General Medical Sciences; Cancer Research UK","keywords":"Pipeline (software); Computer science; False discovery rate; Set (abstract data type); Proteome; Sequence database; Proteomics; Database search engine; Ground truth; Sequence (biology); Computational biology; Data mining; Data set; Function (biology); False positive paradox; Algorithm; Bioinformatics; Chemistry; Biology; Search engine; Artificial intelligence; Information retrieval; Biochemistry; Genetics","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":[0.001542387,0.0001121786,0.0001819608,0.0001154225,0.0002576103,0.00009454237,0.0003996132,0.0001192964,0.0001198836],"category_scores_gemma":[0.0001454792,0.00007646505,0.00008080618,0.0002421471,0.000116413,0.0002019982,0.00003891045,0.0005849386,0.00000816537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001048204,"about_ca_system_score_gemma":0.0001199662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009101535,"about_ca_topic_score_gemma":7.355159e-7,"domain_scores_codex":[0.9986022,0.00004445139,0.0004512437,0.0001995395,0.000429153,0.0002734385],"domain_scores_gemma":[0.9982919,0.0002114819,0.000286234,0.0003340374,0.0007919625,0.00008442532],"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":[0.0002180201,0.00004030248,0.0001497768,0.0002196861,0.00001877897,4.823528e-7,0.0001050448,0.001194383,0.9864521,0.001170392,0.000184353,0.01024667],"study_design_scores_gemma":[0.001152281,0.0001976637,0.00005995225,0.00015589,0.00002218725,0.00003331455,0.0003354548,0.110998,0.8544498,0.01896062,0.01347084,0.0001639467],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08107106,0.0002740971,0.91349,0.002991501,0.00002297145,0.001752057,0.00002502895,0.00001997641,0.0003533238],"genre_scores_gemma":[0.9545878,0.0008216178,0.04182337,0.00002247309,0.0002985783,0.0006270997,0.000009017678,0.00004133948,0.001768754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8735167,"threshold_uncertainty_score":0.3118154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06656372185227585,"score_gpt":0.3885289544544264,"score_spread":0.3219652326021505,"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."}}