{"id":"W7117868205","doi":"10.1093/bib/bbaf682","title":"MetImputBERT: a pretrained BERT framework for missing value imputation in NMR metabolomics data","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; Fundamental Research Funds for the Central Universities; Key Research and Development Program of Heilongjiang; National Institutes of Health; H. Lundbeck A/S; Servier; National Natural Science Foundation of China; Eisai; Genentech; IXICO; National Key Research and Development Program of China; Northern California Institute for Research and Education; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Imputation (statistics); Missing data; Python (programming language); Classifier (UML); Pattern recognition (psychology); Metabolomics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005576539,0.001953527,0.001686666,0.001116437,0.001252622,0.002516942,0.005899312,0.002869672,0.01450969],"category_scores_gemma":[0.02031025,0.00176744,0.002629657,0.001573591,0.0008686983,0.002425139,0.003224887,0.005801041,0.008072985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001406997,"about_ca_system_score_gemma":0.004219988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01361316,"about_ca_topic_score_gemma":0.03488847,"domain_scores_codex":[0.9983569,0.0007177318,0.0000995605,0.0003947538,0.0003007204,0.0001302779],"domain_scores_gemma":[0.9957882,0.002484441,0.0002423815,0.0007011534,0.0006081765,0.0001757426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001318807,0.0003395713,0.01187818,0.0008914421,0.001405115,0.0009003297,0.0006155947,0.461852,0.005354024,0.02821873,0.1204029,0.3668232],"study_design_scores_gemma":[0.00008375868,0.00006618613,0.0006783237,0.00007788472,0.00004941475,0.0002208326,0.00003908376,0.9586785,0.002918205,0.02344582,0.01368198,0.0000599308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005895134,0.0005645003,0.9553083,0.0006917715,0.0001794571,0.0001340397,0.004234822,0.03166623,0.001325813],"genre_scores_gemma":[0.08800068,0.0006062124,0.8751603,0.001642026,0.0002074417,0.0007512972,0.01965888,0.006933004,0.007040041],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01450969,"threshold_uncertainty_score":0.04853982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01907477285301544,"score_gpt":0.3095810916491005,"score_spread":0.2905063187960851,"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."}}