{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008313884,0.0002203542,0.0003699684,0.0002644394,0.00008982979,0.00007857798,0.0004781795,0.0002552139,0.000002432164],"category_scores_gemma":[0.002036172,0.0002214398,0.00007418114,0.0004774986,0.000068066,0.00002655238,0.0004317375,0.0001739815,0.000001109547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003942884,"about_ca_system_score_gemma":0.0001576647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006921695,"about_ca_topic_score_gemma":0.00007215273,"domain_scores_codex":[0.9984365,0.00003246893,0.0006831592,0.0003408912,0.0001197951,0.0003871915],"domain_scores_gemma":[0.9989374,0.0001467032,0.0001954214,0.0006097616,0.00006884555,0.00004182838],"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":[0.001664939,0.001158362,0.01558499,0.003317563,0.001881488,0.00001072581,0.005357504,0.005872344,0.05259687,0.4680312,0.05183413,0.3926899],"study_design_scores_gemma":[0.007318738,0.0004384001,0.01706891,0.0006967523,0.0003539142,0.00002227652,0.001261843,0.4980591,0.0378891,0.1422025,0.292954,0.00173447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07386462,0.004340141,0.9132717,0.003988689,0.0004490875,0.001218339,0.0002155891,0.00003417589,0.002617662],"genre_scores_gemma":[0.1322153,0.001143225,0.8612467,0.0041907,0.0001121251,0.00007344817,0.0007908136,0.00003288507,0.0001947733],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4921867,"threshold_uncertainty_score":0.9030052,"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."}}