{"id":"W4410056385","doi":"10.1016/j.csbj.2025.04.041","title":"Optimizing imputation strategies for mass spectrometry-based proteomics considering intensity and missing value rates","year":2025,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Life Sciences Institute; University of British Columbia; Mitacs; Genome British Columbia","keywords":"Imputation (statistics); Missing data; Mass spectrometry; Proteomics; Computer science; Data mining; Environmental science; Statistics; Chemistry; Mathematics; Chromatography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008692977,0.000145959,0.0001865061,0.0001649923,0.0005566045,0.0001711816,0.00009048255,0.0001869346,0.000005370085],"category_scores_gemma":[0.00005867398,0.0001349632,0.0000407774,0.0001158621,0.0002379752,0.0001246175,0.00004482028,0.000367075,7.233093e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006303635,"about_ca_system_score_gemma":0.0001213409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002375622,"about_ca_topic_score_gemma":4.154974e-7,"domain_scores_codex":[0.9992706,0.000007228449,0.000263294,0.0002280096,0.00005755735,0.0001733045],"domain_scores_gemma":[0.999456,0.0001308233,0.0001652715,0.00006753379,0.0001382895,0.0000420806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001022904,0.000006559259,0.0005483155,0.0001254503,0.00006582936,0.00000424675,0.00004969528,0.02900631,0.8111255,0.1499854,0.00001736032,0.008963134],"study_design_scores_gemma":[0.0004015323,0.00002120807,0.0001882051,0.00005804266,0.00001715546,0.0001465031,0.0001986952,0.2014394,0.1716603,0.625735,0.00002542769,0.000108451],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3378388,0.0002221422,0.6583351,0.003360099,0.00002172376,0.0001102475,0.0000113873,0.00007338985,0.00002701227],"genre_scores_gemma":[0.4879792,0.00001855085,0.5118697,0.00008442676,0.00001868321,0.000009485925,0.00001138921,0.000004747272,0.000003779214],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6394652,"threshold_uncertainty_score":0.550364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0121422024579362,"score_gpt":0.2879088774001399,"score_spread":0.2757666749422037,"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."}}