{"id":"W4405711459","doi":"10.1101/2024.12.19.629475","title":"Scoring information integration with statistical quality control enhanced cross-run analysis of data-independent acquisition proteomics data","year":2024,"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":"University of Toronto","funders":"","keywords":"False positive paradox; Computer science; Benchmark (surveying); Data mining; False discovery rate; Identifier; Identification (biology); Quantitative proteomics; Data quality; Proteomics; Machine learning; Chemistry; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02167944,0.002628618,0.001723855,0.003682684,0.0008139675,0.003579488,0.00283588,0.001175263,0.002913752],"category_scores_gemma":[0.0384099,0.0008808908,0.001715197,0.002654964,0.00107863,0.002330178,0.003597978,0.002591911,0.00229152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001070371,"about_ca_system_score_gemma":0.003090071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002099815,"about_ca_topic_score_gemma":0.003711722,"domain_scores_codex":[0.9879465,0.002807222,0.001515575,0.003117129,0.004067014,0.0005465068],"domain_scores_gemma":[0.9729626,0.008198636,0.00274182,0.007075327,0.008491615,0.0005301036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003019624,0.000795853,0.03965478,0.001692758,0.002036948,0.0006178539,0.0007672278,0.04091322,0.185152,0.009502005,0.03088729,0.6849605],"study_design_scores_gemma":[0.000264355,0.0004957707,0.018961,0.00009745955,0.0003938321,0.0005927916,0.0001026757,0.6327733,0.308783,0.01538461,0.02181458,0.0003365964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.040135,0.0005316348,0.9115835,0.0002427502,0.0001564231,0.0002286511,0.002040032,0.04417636,0.0009055695],"genre_scores_gemma":[0.2060524,0.0001963534,0.773562,0.0004196442,0.0001092769,0.0006077865,0.01021907,0.006950119,0.001883356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02167944,"threshold_uncertainty_score":0.1146532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02737988234716809,"score_gpt":0.3187752830986281,"score_spread":0.29139540075146,"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."}}